Game: Ocarina Of Time #1064
Labels
No labels
area/accessibility
area/audio
area/input
area/install
area/menu
area/renderer
area/saves
area/tooling
area/upscaling
beanstalk: approved
beanstalk: failed
beanstalk: needs approval
beanstalk: running
beanstalk: tested
ci: approved
good first issue
gpu/amd
gpu/igpu
gpu/intel
gpu/nvidia
help wanted
kind
bug
kind
chore
kind
docs
kind
feature
kind
performance
kind
question
needs measurements
platform/linux
platform/macos
platform/steam-deck
platform/windows
preview
priority
critical
priority
high
priority
low
regression
risk
high
risk
low
risk
medium
status
blocked
status
confirmed
status
duplicate
status
invalid
status
needs-info
status
wontfix
ci: approved
No milestone
No project
No assignees
3 participants
Notifications
Due date
No due date set.
Dependencies
No dependencies set
Reference
MagicBeanDev/Longshot#1064
Loading…
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Longshot version
v3.0.0-rc.5 (source 013b1d3a)
Channel
Release candidate
What kind of problem
Something else
What happened
Since rc.4, the time of day is locked at 8:00 PM (20:00). Sun's Song changes it for a moment, then it snaps straight back to night. It loads at night every time.
What I've checked:
When it started: around the Zelda-escape cutscene (I was inside the Market when the gate closed, and the cutscene still played). I had also used Debug tools > Set time once around then.
It looks like something is overriding the world clock for every save, possibly around the time-of-day counter (f_803edf70) or a fixed-time state in the world manager.
Where in the game
HyruleField_Adult (adult). Stuck at night everywhere; tested in Hyrule Field with Sun's Song.
How often
Every time
Graphics card and driver version
NVIDIA GeForce RTX 4080, NVIDIA 617.14
CPU, RAM and operating system
AMD Ryzen 9 7900X3D 12-Core Processor (24 threads), 31 GB, Windows 11 (build 26300)
Changes from the defaults
Fullscreen: On (default: Off)
Text speed: 2x (default: Normal)
Button prompts: Xbox (default: Auto)
Menu shortcut: F1 only (default: Insert, F1 or Esc)
Autosave:: Off (default: On)
Depends on this PC (the values now, not counted as changes):
Quality preset: Custom (default depends on this PC)
Output resolution: 2560x1440 (native) (default depends on this PC)
Profile: Docked (default depends on this PC)
Upscaler: NVIDIA DLSS (default depends on this PC)
Render resolution: Quality 67% (1707x960) (default depends on this PC)
Sharpness: 50% (default depends on this PC)
Frame pacing: On (default depends on this PC)
Window scaling filter: Not needed (window = output) (default depends on this PC)
Game speed: Real time (default depends on this PC)
Switches set (their values are in the attached report.txt): LONGSHOT_NO_UPDATE_CHECK.
longshot_log.txt
[a64] unimplemented import ZN2nn2ro12ProtectRelroEPKvS2_S2_S2_S2 (lr 0x81237908)
[a64] unimplemented import _ZN2nn2vi36SetDisplay120HzRefreshRateCapabilityEPNS0_7DisplayEb (lr 0x8348bf64)
[a64] unimplemented import _ZN2nn3aoc17CountAddOnContentEv (lr 0x83392a38)
[hos host] longshot v3.0.0-rc.5 (source 013b1d3a)
[hos host] run_id: 35b31f104f69fbdb2d7c5ec39c9b26fb
[hos host] crash window: watching this run (HOS_CRASH_WATCH=0: off)
[hos host] options: the settings file is %USERPROFILE%\AppData\Roaming\Longshot\longshot_options.ini
[hos host] oe: output resolution 2560x1440
[hos host] boot: widescreen: a 1.7778 screen is 16:9: the game's own picture
[hos host] boot: image 96 MB at 0x80000000, 9809 MB of memory for the game
[hos host] boot: 31967 MB of memory, 16384 MB of swap
[hos host] vk: reserved core selection: 12 cores, 24 logical, best class=0, fast cores=12, selected=0xc00000
[hos host] vk: core 0: mask=0x3, class=0, popcount=2
[hos host] vk: core 1: mask=0xc, class=0, popcount=2
[hos host] vk: core 2: mask=0x30, class=0, popcount=2
[hos host] vk: core 3: mask=0xc0, class=0, popcount=2
[hos host] vk: core 4: mask=0x300, class=0, popcount=2
[hos host] vk: core 5: mask=0xc00, class=0, popcount=2
[hos host] vk: core 6: mask=0x3000, class=0, popcount=2
[hos host] vk: core 7: mask=0xc000, class=0, popcount=2
[hos host] vk: core 8: mask=0x30000, class=0, popcount=2
[hos host] vk: core 9: mask=0xc0000, class=0, popcount=2
[hos host] vk: core 10: mask=0x300000, class=0, popcount=2
[hos host] vk: core 11: mask=0xc00000, class=0, popcount=2
[hos host] vk: reserved core mask (enhanced): 0xc00000 (12 cores)
[hos MainThread] boot: _init_libc0 (0x85717e50)
[hos MainThread] boot: nnosInitialize (0x8510f720)
[hos MainThread] boot: _init_libc1 (0x85717e60)
[hos MainThread] boot: nninitStartup (0x8262bb10)
[hos MainThread] heap: 6894 MB at 0x1000000000
[hos MainThread] mem: 0x1000000040 committed on first touch (nothing handed it out)
[hos MainThread] mem: 0x1000012a3f committed on first touch (nothing handed it out)
[hos MainThread] boot: _init_libc2 (0x85717e80)
[hos MainThread] boot: main DT_INIT (0x812377e0)
[hos MainThread] boot: subsdk0 DT_INIT (0x84ec0040)
[hos MainThread] boot: sdk DT_INIT (0x84fa0060)
[hos MainThread] boot: nnMain (0x81222cd0)
[hos MainThread] mem: 0x1002400010 committed on first touch (nothing handed it out)
[hos sead::MainThread] mem: 0x10024109c0 committed on first touch (nothing handed it out)
[hos sead::MainThread] fs: mounted content: -> D:\Games\Longshot\romfs
[hos sead::MainThread] mem: 0x11aecffff2 committed on first touch (nothing handed it out)
[hos sead::MainThread] mem: 0x11aed00010 committed on first touch (nothing handed it out)
[hos sead::MainThread] mem: 0x11aed27998 committed on first touch (nothing handed it out)
[hos sead::MainThread] mem: 0x1003f01a88 committed on first touch (nothing handed it out)
[hos sead::MainThread] mem: 0x11aedfff52 committed on first touch (nothing handed it out)
[hos sead::MainThread] oe: language en-US (language.txt)
[hos sead::MainThread] oe: GetCurrentGraphicsScale -> 1.00
[hos sead::MainThread] gs: BootGraphicsSystem(0, 0): no graphics server yet (headless)
[hos host] sleep: at most 6 of the game's threads yield through a short sleep at a time, the others wait on the timer (24 logical processors; HOS_SHORT_SLEEP_POLLERS=0: all yield)
[hos sead::MainThread] nvn: native NVN layer: 427 procs
[hos sead::MainThread] nvn: native NVN device (flags 0): no Switch GPU emulation
[hos sead::MainThread] nvn: window origin upper left
[hos sead::MainThread] nvn: depth mode near = -w (GL)
[hos sead::MainThread] mem: 0x1004032000 committed on first touch (nothing handed it out)
[hos sead::MainThread] nvn: texture pool of 33068 descriptors
[hos sead::MainThread] vi: GetNativeWindow -> 0x1102400
[hos sead::MainThread] mem: 0x1004133000 committed on first touch (nothing handed it out)
[hos sead::MainThread] mem: 0x1006e37000 committed on first touch (nothing handed it out)
[hos sead::MainThread] nvn: window of 3 textures (3 active), 2560x1440 format 0x25
[hos sead::MainThread] mem: 0x1006f3b000 committed on first touch (nothing handed it out)
[hos sead::MainThread] mem: 0x10072b8020 committed on first touch (nothing handed it out)
[hos sead::MainThread] mem: 0x10073b9000 committed on first touch (nothing handed it out)
[hos sead::MainThread] mem: 0x10073ca000 committed on first touch (nothing handed it out)
[hos sead::MainThread] applet: render target pool 512 MB (the game's 305 MB)
[hos Resource Memory] mem: the game's mapped pages 360 MB (peak 360); heap 6894 MB; the console's total 9809 MB
[hos Resource Memory] mem: the game's mapped pages 512 MB (peak 512); heap 6894 MB; the console's total 9809 MB
[hos host] vk: Intel XeSS: no libxess.dll in D:\Games\Longshot\bin, D:\Games\Longshot (the readme says where Intel's file comes from)
[hos ARes Loading 1] texts: mals/usen.product.110.sarc.zs <- D:\Games\Longshot\texts/usen.product.110.sarc.zs (the console's wording made the PC's)
[hos host] discord: connected (application 1570559772111933578)
[hos host] discord: status set
[hos host] vk: the Output resolution's sizes: 35 (the screen's modes, with the common sizes of their shapes, and the game's own); shapes 5:4, 4:3, 3:2, 25:16, 16:10, 5:3, 16:9
[hos host] vk: device 0: NVIDIA GeForce RTX 4080, Vulkan 1.4, driver 0x9a438000, type 2, id 10de:2704
[hos host] vk: DLSS Frame Gen (NGX): device extensions: VK_NVX_binary_import, VK_NVX_image_view_handle, VK_KHR_buffer_device_address, VK_KHR_push_descriptor
[hos host] vk: float atomic add on storage buffers: native (VK_EXT_shader_atomic_float), NVIDIA's driver
[hos host] vk: vendor fixes for NVIDIA (617.14): out-of-bounds texel fetches 0 0, NaN tests by bits 0, gather offset 0
[hos host] vk: subgroups: default 32 lanes, 32-32, pinned to 32 on stages 0x3fff; RADV on GCN 1-4: no
[hos host] vk: mesh shaders: Automatic, from the default: native
[hos host] vk: robust buffer access on
[hos host] vk: programs are loaded when the game makes them (create): the default where the GPU has mesh shaders (RX_VK_LOAD=create or start says which)
[hos host] vk: colour outputs NaN-guarded
[hos host] vk: cooperative matrix A: the console's elements are the device's 0 1 4 5 2 3 6 7
[hos host] vk: cooperative matrix B: the console's elements are the device's 0 1 2 3
[hos host] vk: cooperative matrix C: the console's elements are the device's 0 1 2 3
[hos host] vk: native matrix multiplies on (cooperative matrices, the console's fragment layout checked)
[hos host] vk: NVIDIA Reflex: available (VK_NV_low_latency2)
[hos host] vk: NVIDIA GeForce RTX 4080, Vulkan 1.4, driver 0x9a438000; mesh shaders yes, host memory import yes, pipeline libraries yes
[hos host] vk: driver: NVIDIA 617.14
[hos host] vk: Auto (this PC) would be: 16048 MB of video memory: tier 5; NVIDIA RTX: DLSS Quality (NVIDIA GeForce RTX 4080, 16048 MB of video memory, dedicated, screen 2560x1440 at 180 Hz, 31967 MB of RAM, 24 threads)
[hos host] vk: surface caps images 2..8 extent 1600x900..1600x900 usage 0x9f alpha 0x3 transform 0x1
[hos host] vk: swapchain 1600x900, 4 images, mailbox (V-Sync Auto)
[hos host] vk: guest memory imported in place (alignment 4096)
[hos host] vk: replay ready (window; push descriptors yes (32), extended dynamic state 3 yes, custom border colours yes)
[hos host] vk: driver shader cache at the start: 1458 MB (%USERPROFILE%\AppData\Local\NVIDIA\GLCache 1458 MB)
[hos host] vk: handle tables as descriptor arrays: on
[hos host] hid: 51 controls from longshot_options.ini
[hos host] display: fullscreen (F11 for a window)
[hos host] vk: VRAM mirror of buffer pools on
[hos host] vk: Threaded rendering: Auto: on, the render thread and the recorder thread (24 logical processors)
[hos host] vk: RX_VK_RECORDER=thread: vkCmd* packed on the replay thread and run in order by a recorder thread; the replay waits for it at each command buffer begin, end and reset, submit, wait, readback, destruction and replay lock release (serial replay only); ring 8192 KB, spin adaptive 20-200 us
[hos host] vk: ui: the game's own menu font, from its files
[hos host] vk: ui: Dear ImGui 1.92.9b on the window's images (format 37)
[hos host] vk: fsr3: AMD FSR 3.1 can run on this GPU
[hos host] vk: images from a pool of 128 MB blocks (memory type 1), 0 made at the start
[hos host] vk: presenter thread: off (RX_VK_PRESENT_THREAD=1: on)
[hos host] vk: surface caps images 2..8 extent 2560x1440..2560x1440 usage 0x9f alpha 0x3 transform 0x1
[hos host] vk: swapchain 2560x1440, 4 images, mailbox (V-Sync Auto)
[hos host] vk: surface caps images 2..8 extent 2560x1440..2560x1440 usage 0x9f alpha 0x3 transform 0x1
[hos host] vk: swapchain 2560x1440, 4 images, mailbox (V-Sync Auto)
[hos host] vk: NVIDIA DLSS: NGX started (DLSS's runtime: the newest nvngx_dlss.dll in D:\Games\Longshot\ngx, %USERPROFILE%\AppData\Local\Longshot\ngx)
[hos host] menu: the upscalers asked in the background while the start-up screen shows (679 ms)
[hos host] vk: pipeline cache D:\Games\Longshot\cache/longshot_vk_pipelines.bin (1493098 KB)
[hos host] vk: pipeline cache: 6 play files merged (13908 KB)
[hos host] vk: program cache D:\Games\Longshot\cache/longshot_programs.bin: 47867 program keys kept, 7617817 KB
[hos host] vk: programs: load at create: 33716 notes of 21330 programs indexed, 4 type signatures, 2470 compute programs listed, in 5.7 ms (47867 kept program keys); 2 workers in play, 2 while the game loads; pipelines from: pipeline caches
[hos host] vk: precompile: load at create (RX_VK_LOAD=create): 33716 noted pipelines found, none built; 2470 compute programs named (2199 in the shipped list, 1153 dispatched in play here); 0 mesh fallback programs kept ready, 0 of their noted pipelines with them (0 in no cache); in 1022 ms. No other program is kept ready by a list: each is loaded when the game makes it
[hos host] vk: start-up: the shaders took 1.0 s
[hos host] vk: pipeline cache: what play makes goes into play files (RX_VK_PLAY_CACHE=0: into the one cache)
[hos host] rx: renderer: Vulkan (longshot_vk.dll)
[hos host] vk: the replay runs on a thread of its own, the render thread (RX_VK_ASYNC=0: on the submitting thread)
[hos host] vk: the replay thread runs on logical processors 0xc00000, kept from the game's threads (its ideal processor there; free to go to the other fastest cores when another program takes it)
[hos host] vk: the replay thread may run on logical processors 0xffffff
[hos host] rx: 123 texture and sampler calls made before the renderer started (33 texel writes), given to it
[hos sead::MainThread] nvn: QueueSubmitCommands #1: queue 00001000010FBF90 (its #1), 1 handles (lr 0x812c3cf4)
[hos sead::MainThread] vk: submit-time capture of written pages on
[hos sead::MainThread] vk: capture buffer prewarm (32, 64, 128 MB spares made on a worker) on (RX_VK_CAP_PREWARM)
[hos host] [debug] vk: 78 pools mapped
[hos host] vk: texture storage in the submit-time capture on
[hos host] vk: a 32 MB capture buffer made ahead in 1.8 ms, off the game's thread (RX_VK_CAP_PREWARM)
[hos host] vk: a 64 MB capture buffer made ahead in 3.0 ms, off the game's thread (RX_VK_CAP_PREWARM)
[hos host] vk: a 128 MB capture buffer made ahead in 5.5 ms, off the game's thread (RX_VK_CAP_PREWARM)
[hos host] vk: sparse VRAM mirrors (RX_VK_MIRROR_SPARSE): on
[hos host] vk: occlusion queries on (RX_VK_OCC_QUERIES): the game's samples-passed reports get the GPU's counts; read from the pool
[hos host] vk: render target pool: up to 768 MB (RX_VK_TARGET_POOL_MB)
[hos host] vk: render targets' images from blocks of their own (128 MB, memory type 1)
[hos host] vk: texture 0x103d650000 32x32x32 x1 levels 1 NVN 0x26 -> vk 38 (1 textures, 0 MB)
[hos host] vk: staging arenas: 1 (64 MB in this one)
[hos host] vk: 1 pools imported
[hos host] vk: pool 0x103d800000 (4 MB): mirror made at its first binding (1 so)
[hos host] vk: batched submits off (RX_VK_BATCH)
[a64] unimplemented import _ZN2nn5audio34GetAudioRendererVoiceDropParameterENS0_19AudioRendererHandleE (lr 0x81044370)
[a64] unimplemented import _ZN2nn5audio39IsDeviceOutputVolumeAutoTuneModeEnabledEv (lr 0x81043560)
[a64] unimplemented import _ZN2nn5audio36AcquireAudioOutputDeviceNotificationEPNS_2os11SystemEventE (lr 0x80f72978)
[a64] unimplemented import _ZN2nn5audio40SetDeviceOutputVolumeAutoTuneModeEnabledEb (lr 0x80f729e0)
[a64] unimplemented import _ZN2nn5audio26GetAudioDeviceOutputVolumeEPKNS0_15AudioDeviceNameE (lr 0x80f72e00)
[hos ARes Loading 0] prompts: xbox icons, 16 buttons on these pad's controls
[hos sead::MainThread] audio: renderer opened
[hos host] audio: 5.1 for the game (the selected/default output has 8 channels)
[hos sead::MainThread] audio: device sink on mix 0, 6 channels (0 1 2 3 4 5)
[hos host] audio: output on the default device (10 devices), 5.1
[a64] unimplemented import _ZN2nn5prepo30GetOverSaveFrequencyLimitEventEv (lr 0x80e5ec00)
[hos sead::MainThread] fs: mounted save: -> %USERPROFILE%\AppData\Roaming\Longshot\save\5a3c9e1f0b7d24680000000000000001
[hos BootupBackgroundWorkThread] fs: mounted savt: -> %USERPROFILE%\AppData\Roaming\Longshot\temp
[hos host] vk: vertex format NVN 0x2e -> vk 109
[hos host] vk: vertex format NVN 0x22 -> vk 106
[hos host] vk: vertex format NVN 0x16 -> vk 103
[hos host] vk: module identifiers: 882 known (longshot_module_ids.bin): a learned compute variant's pipeline is made at its program's create call without its code (RX_VK_MODULE_IDS=0: off)
[a64] unimplemented import _ZN2nn5audio34SetAudioRendererVoiceDropParameterENS0_19AudioRendererHandleEf (lr 0x836f755c)
[a64] unimplemented import _ZN2nn4nifm10InitializeEv (lr 0x8119aea8)
[hos host] vk: vertex format NVN 0x29 -> vk 97
[hos host] vk: vertex format NVN 0x69 -> vk 65
[hos sead::MainThread] audio in: stream 0 opened: format 2, 1 channel, 48000 Hz, 4800 frames
[hos sead::MainThread] audio in: stream 1 opened (raw): format 2, 1 channel, 48000 Hz, 4800 frames
[a64] unimplemented import _ZN2nn2vi30QueryDisplayCurrentRefreshRateEPNS0_11RefreshRateEPbPKNS0_7DisplayE (lr 0x83b6eab8)
[a64] unimplemented import _ZN2nn3hid25SetGyroscopeZeroDriftModeERKNS0_19SixAxisSensorHandleERKNS0_22GyroscopeZeroDriftModeE (lr 0x834898d0)
[a64] unimplemented import _ZN2nn6socket10InitializeERKNS0_6ConfigE (lr 0x83c55b24)
[a64] unimplemented import _ZN2nn3ssl10InitializeEv (lr 0x83c55b30)
[a64] unimplemented import _ZN2nn6socket13IsInitializedEv (lr 0x824d92f8)
[a64] unimplemented import _ZN2nn6socket7EventFdEmNS0_12EventFdFlagsE (lr 0x82213be4)
[a64] unimplemented import _ZN2nn6socket5CloseEi (lr 0x82213bf4)
[a64] unimplemented import _ZN2nn4nifm22GetCurrentProxySettingEPNS0_12ProxySettingE (lr 0x82378f6c)
[a64] unimplemented import _ZN2nn4nifm27SubmitNetworkRequestAndWaitEv (lr 0x8120873c)
[a64] unimplemented import _ZN2nn4nifm18IsNetworkAvailableEv (lr 0x82145cec)
[a64] unimplemented import _ZN2nn5audio15AddBiquadFilterEPNS0_19AudioRendererConfigEPNS0_16BiquadFilterTypeEPNS0_10SubMixTypeE (lr 0x80dc7494)
[a64] unimplemented import _ZN2nn5audio26SetBiquadFilterInputOutputEPNS0_16BiquadFilterTypeEPKaS4_i (lr 0x80dc740c)
[a64] unimplemented import _ZN2nn5audio22SetBiquadFilterEnabledEPNS0_16BiquadFilterTypeEb (lr 0x80de9464)
[a64] unimplemented import _ZN2nn5audio24SetBiquadFilterParameterEPNS0_16BiquadFilterTypeERKNS0_22TBiquadFilterParameterIfEE (lr 0x836fcdb4)
[a64] unimplemented import _ZN2nn5audio8AddDelayEPNS0_19AudioRendererConfigEPNS0_9DelayTypeEPvmPNS0_10SubMixTypeENS_8TimeSpanEi (lr 0x80dd53b8)
[a64] unimplemented import _ZN2nn5audio19SetDelayInputOutputEPNS0_9DelayTypeEPKaS4_i (lr 0x80dd531c)
[a64] unimplemented import _ZN2nn5audio15SetDelayEnabledEPNS0_9DelayTypeEb (lr 0x80de9464)
[a64] unimplemented import _ZN2nn5audio14IsDelayEnabledEPKNS0_9DelayTypeE (lr 0x8119f138)
[a64] unimplemented import _ZN2nn5audio12GetDelayTimeEPKNS0_9DelayTypeE (lr 0x8119f164)
[a64] unimplemented import _ZN2nn5audio12SetDelayTimeEPNS0_9DelayTypeENS_8TimeSpanE (lr 0x8119f178)
[a64] unimplemented import _ZN2nn5audio15SetDelayDryGainEPNS0_9DelayTypeEf (lr 0x8119f184)
[a64] unimplemented import _ZN2nn5audio20SetDelayFeedbackGainEPNS0_9DelayTypeEf (lr 0x8119f190)
[a64] unimplemented import _ZN2nn5audio14SetDelayInGainEPNS0_9DelayTypeEf (lr 0x8119f19c)
[a64] unimplemented import _ZN2nn5audio21SetDelayChannelSpreadEPNS0_9DelayTypeEf (lr 0x8119f1a8)
[a64] unimplemented import _ZN2nn5audio21SetDelayLowPassAmountEPNS0_9DelayTypeEf (lr 0x8119f1b4)
[a64] unimplemented import _ZN2nn5audio9AddReverbEPNS0_19AudioRendererConfigEPNS0_10ReverbTypeEPvmPNS0_10SubMixTypeEi (lr 0x80de96ec)
[a64] unimplemented import _ZN2nn5audio20SetReverbInputOutputEPNS0_10ReverbTypeEPKaS4_i (lr 0x80de965c)
[a64] unimplemented import _ZN2nn5audio16SetReverbEnabledEPNS0_10ReverbTypeEb (lr 0x80de9464)
[a64] unimplemented import _ZN2nn5audio15IsReverbEnabledEPKNS0_10ReverbTypeE (lr 0x80de91a0)
[a64] unimplemented import _ZN2nn5audio18SetReverbEarlyModeEPNS0_10ReverbTypeENS1_9EarlyModeE (lr 0x80de91c4)
[a64] unimplemented import _ZN2nn5audio18SetReverbEarlyGainEPNS0_10ReverbTypeEf (lr 0x80de91d0)
[a64] unimplemented import _ZN2nn5audio21SetReverbPredelayTimeEPNS0_10ReverbTypeENS_8TimeSpanE (lr 0x80de91e4)
[a64] unimplemented import _ZN2nn5audio17SetReverbLateModeEPNS0_10ReverbTypeENS1_8LateModeE (lr 0x80de91f0)
[a64] unimplemented import _ZN2nn5audio17SetReverbLateGainEPNS0_10ReverbTypeEf (lr 0x80de91fc)
[a64] unimplemented import _ZN2nn5audio18SetReverbDecayTimeEPNS0_10ReverbTypeENS_8TimeSpanE (lr 0x80de9208)
[a64] unimplemented import _ZN2nn5audio32SetReverbHighFrequencyDecayRatioEPNS0_10ReverbTypeEf (lr 0x80de9214)
[a64] unimplemented import _ZN2nn5audio19SetReverbColorationEPNS0_10ReverbTypeEf (lr 0x80de9220)
[a64] unimplemented import _ZN2nn5audio19SetReverbReverbGainEPNS0_10ReverbTypeEf (lr 0x80de922c)
[a64] unimplemented import _ZN2nn5audio16SetReverbOutGainEPNS0_10ReverbTypeEf (lr 0x80de9238)
[a64] unimplemented import _ZN2nn5audio16SetReverbDryGainEPNS0_10ReverbTypeEf (lr 0x80de9244)
[a64] unimplemented import _ZN2nn5audio20GetReverbInputOutputEPKNS0_10ReverbTypeEPaS4_Pii (lr 0x80de9260)
[a64] unimplemented import ZN2nn5prepo27AddInternetConnectionStatusEPNS0_10PlayReportEPKcS4_S4 (lr 0x80e5bd60)
[a64] unimplemented import _ZN2nn5prepo28RequestImmediateTransmissionEv (lr 0x80df26c0)
[a64] unimplemented import _ZN2nn3nfp10InitializeEv (lr 0x80ed8f34)
[a64] unimplemented import _ZN2nn3nfp29AttachAvailabilityChangeEventEPNS_2os15SystemEventTypeE (lr 0x80ed8f40)
[hos sead::MainThread] vi: QueryDisplayHdrStatus -> SDR
[hos sead::MainThread] hid: the game reads npad 0 (No.1, lr 0x83489670)
[hos sead::MainThread] sdl: SDL3
[hos sead::MainThread] hid: controller 0 connected
[hos sead::MainThread] hid: six-axis handles: 2 asked for, 3 reported
[hos sead::MainThread] nvn: the game reports counter type 16 (lr 0x8074b278)
[hos sead::MainThread] nvn: the game reports counter type 0 (lr 0x8074b290)
[hos Porter] fs: mounted _npln: -> D:\Games\Longshot\romfs
[hos Porter] fiber 0x100ac54230: function 0x8504b440 arg 0x100ac541f8 stack 0x100acc1000+0x10000 flags 1
[hos sead::MainThread] nvn: window crop 0,0 2560x1440
[hos Porter] fiber 0x100acd1090: function 0x8504b440 arg 0x100acd1058 stack 0x100acd4000+0x10000 flags 1
[hos sead::MainThread] nvn: EventSignal (CPU) #1: event 0x1006e38000 mode 0 value 0 (lr 0x802eb420)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #1: event 0x1006e38000 mode 0 value 1 (now 0) (lr 0x802eb444)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #1: event 0x100d6c8000 mode 0 value 0 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #2: event 0x100d6c8000 mode 0 value 0 (now 0) (lr 0x806661f8)
[hos Porter] fiber 0x100ace4090: function 0x8504b440 arg 0x100ace4058 stack 0x100ace7000+0x10000 flags 1
[hos sead::MainThread] nvn: CommandBufferWaitEvent #3: event 0x100d6c8000 mode 0 value 0 (now 0) (lr 0x806661f8)
[hos nn.npln.Worker] fiber 0x100ac3c5d0: function 0x8504b440 arg 0x100ac3c598 stack 0x100acf9000+0x10000 flags 1
[hos sead::MainThread] nvn: QueueSubmitCommands #2: queue 000010100D695020 (its #1), 1 handles (lr 0x80666be0)
[hos nn.npln.Worker] fiber 0x100ac543d0: function 0x8504b440 arg 0x100ac54398 stack 0x100ad09000+0x10000 flags 1
[hos sead::MainThread] nvn: CommandBufferWaitEvent #4: event 0x100d6c8000 mode 0 value 0 (now 0) (lr 0x806661f8)
[hos sead::MainThread] nvn: QueueSubmitCommands #3: queue 000010100D6BF020 (its #1), 1 handles (lr 0x80666be0)
[hos sead::MainThread] nvn: EventSignal (CPU) #2: event 0x1006e38000 mode 0 value 1 (lr 0x8348c78c)
[hos Presentation Thread] nvn: QueueSubmitCommands #4: queue 000010100D5EB020 (its #1), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #5: queue 000010100D640020 (its #1), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #6: queue 000010100D6AA020 (its #1), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #7: queue 0000101004133020 (its #1), 1 handles (lr 0x80590358)
[hos host] [debug] vk: 1235 pools mapped
[hos host] vk: 2 pools imported
[hos host] vk: texture 0x1001f0ffe00 2560x1440x1 x1 levels 1 NVN 0x3f -> vk 122 (2 textures, 15 MB)
[hos host] vk: texture 0x1004137000 2560x1440x1 x1 levels 1 NVN 0x25 -> vk 37 (3 textures, 30 MB)
[hos host] vk: descriptor slotgen ready: draws keep their descriptors through the registrations of slots they do not sample (menu: Descriptor reuse)
[hos host] vk: sampler anisotropy: the game asks for 1 (min filter 5, mip filter linear, LOD bias 0; made with 16)
[hos host] vk: 3 pools imported
[hos host] vk: 4 pools imported
[hos host] vk: write-back diff on (RX_VK_WB_DIFF=0: off)
[hos host] vk: present texture 0x1004137000 2560x1440 format 0x25: rendered
[hos host] vk: present: 2560x1440, format 37 (its image's 37); the Insert menu's HDR 0, HDR10 swapchain no: SDR
[hos host] wide ui: picture 0.0000: the HUD at 100% of its 16:9 size, its sides moved 0 and its top and bottom 0 canvas units; the menus at 100%
[hos host] vk: GPU hang watch: work that finishes nothing for 30 s ends the game (RX_VK_GPU_HANG_SEC)
[hos sead::MainThread] nvn: EventSignal (CPU) #3: event 0x1006e38004 mode 0 value 0 (lr 0x802eb420)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #5: event 0x1006e38004 mode 0 value 1 (now 0) (lr 0x802eb444)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #2: event 0x100d6c8000 mode 0 value 1 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #6: event 0x100d6c8000 mode 0 value 1 (now 0) (lr 0x806661f8)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #7: event 0x100d6c8000 mode 0 value 1 (now 0) (lr 0x806661f8)
[hos sead::MainThread] nvn: QueueSubmitCommands #8: queue 000010100D695020 (its #2), 1 handles (lr 0x80666be0)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #8: event 0x100d6c8000 mode 0 value 1 (now 0) (lr 0x806661f8)
[hos sead::MainThread] nvn: QueueSubmitCommands #9: queue 000010100D6BF020 (its #2), 1 handles (lr 0x80666be0)
[hos Presentation Thread] nvn: QueueSubmitCommands #10: queue 000010100D5EB020 (its #2), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #11: queue 000010100D640020 (its #2), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #12: queue 000010100D6AA020 (its #2), 1 handles (lr 0x805282f4)
[hos sead::MainThread] nvn: EventSignal (CPU) #4: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos Presentation Thread] nvn: QueueSubmitCommands #13: queue 0000101004133020 (its #2), 1 handles (lr 0x80590358)
[hos Presentation Thread] vi: real-time step on: ratio 1.282, game's frame rate 47
[hos host] [debug] vk: 1243 pools mapped
[hos sead::MainThread] nvn: EventSignal (CPU) #5: event 0x1006e38000 mode 0 value 0 (lr 0x802eb420)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #9: event 0x1006e38000 mode 0 value 1 (now 0) (lr 0x802eb444)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #3: event 0x100d6c8000 mode 0 value 2 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #10: event 0x100d6c8000 mode 0 value 2 (now 0) (lr 0x806661f8)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #11: event 0x100d6c8000 mode 0 value 2 (now 0) (lr 0x806661f8)
[hos sead::MainThread] nvn: QueueSubmitCommands #14: queue 000010100D695020 (its #3), 1 handles (lr 0x80666be0)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #12: event 0x100d6c8000 mode 0 value 2 (now 0) (lr 0x806661f8)
[hos sead::MainThread] nvn: QueueSubmitCommands #15: queue 000010100D6BF020 (its #3), 1 handles (lr 0x80666be0)
[hos Presentation Thread] nvn: QueueSubmitCommands #16: queue 000010100D5EB020 (its #3), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #17: queue 000010100D640020 (its #3), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #18: queue 000010100D6AA020 (its #3), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #19: queue 0000101004133020 (its #3), 1 handles (lr 0x80590358)
[hos host] [debug] vk: 1269 pools mapped
[hos host] vk: submission 11 (queue 0x10100d5eb020) stopped at command buffer 0's wait for event 0x100d6c8000 == 1 (has 0)
[hos host] vk: submission 12 (queue 0x10100d640020) stopped at command buffer 0's wait for event 0x100d6c8000 == 1 (has 0)
[hos host] vk: submission 13 (queue 0x10100d6aa020) stopped at command buffer 0's wait for event 0x100d6c8000 == 1 (has 0)
[hos host] vk: texture 0x1005037000 2560x1440x1 x1 levels 1 NVN 0x25 -> vk 37 (4 textures, 45 MB)
[hos host] vk: present texture 0x1005037000 2560x1440 format 0x25: rendered
[hos host] vk: imports given back past 85% of a 4500 MB cap (15215 MB system heap budget): on
[hos host] vk: submission 18 (queue 0x10100d5eb020) stopped at command buffer 0's wait for event 0x100d6c8000 == 2 (has 1)
[hos host] vk: submission 19 (queue 0x10100d640020) stopped at command buffer 0's wait for event 0x100d6c8000 == 2 (has 1)
[hos host] vk: submission 20 (queue 0x10100d6aa020) stopped at command buffer 0's wait for event 0x100d6c8000 == 2 (has 1)
[hos host] vk: submission 21 (queue 0x101004133020) stopped at command buffer 0's wait for event 0x1006e38000 == 1 (has 0)
[hos sead::MainThread] nvn: EventSignal (CPU) #6: event 0x1006e38000 mode 0 value 1 (lr 0x8348c78c)
[hos sead::MainThread] nvn: EventSignal (CPU) #7: event 0x1006e38004 mode 0 value 0 (lr 0x802eb420)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #13: event 0x1006e38004 mode 0 value 1 (now 0) (lr 0x802eb444)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #4: event 0x100d6c8000 mode 0 value 3 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #14: event 0x100d6c8000 mode 0 value 3 (now 1) (lr 0x806661f8)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #15: event 0x100d6c8000 mode 0 value 3 (now 1) (lr 0x806661f8)
[hos sead::MainThread] nvn: QueueSubmitCommands #20: queue 000010100D695020 (its #4), 1 handles (lr 0x80666be0)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #16: event 0x100d6c8000 mode 0 value 3 (now 1) (lr 0x806661f8)
[hos sead::MainThread] nvn: QueueSubmitCommands #21: queue 000010100D6BF020 (its #4), 1 handles (lr 0x80666be0)
[hos host] vk: texture 0x1005f37000 2560x1440x1 x1 levels 1 NVN 0x25 -> vk 37 (5 textures, 60 MB)
[hos Presentation Thread] nvn: QueueSubmitCommands #22: queue 000010100D5EB020 (its #4), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #23: queue 000010100D640020 (its #4), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #24: queue 000010100D6AA020 (its #4), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #25: queue 0000101004133020 (its #4), 1 handles (lr 0x80590358)
[hos sead::MainThread] nvn: EventSignal (CPU) #8: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos host] vk: present texture 0x1005f37000 2560x1440 format 0x25: rendered
[hos host] [debug] vk: 1405 pools mapped
[hos host] [debug] vk: 1469 pools mapped
[hos host] [debug] vk: 1547 pools mapped
[hos host] vk: late pages' fix on (RX_VK_LATE_FIX=0: the wait, as before)
[hos host] vk: submission 25 (queue 0x10100d5eb020) stopped at command buffer 0's wait for event 0x100d6c8000 == 3 (has 2)
[hos host] [debug] vk: 1625 pools mapped
[hos host] vk: submission 26 (queue 0x10100d640020) stopped at command buffer 0's wait for event 0x100d6c8000 == 3 (has 2)
[hos host] vk: submission 27 (queue 0x10100d6aa020) stopped at command buffer 0's wait for event 0x100d6c8000 == 3 (has 2)
[hos host] vk: submission 28 (queue 0x101004133020) stopped at command buffer 0's wait for event 0x1006e38004 == 1 (has 0)
[hos sead::MainThread] nvn: EventSignal (CPU) #9: event 0x1006e38000 mode 0 value 0 (lr 0x802eb420)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #17: event 0x1006e38000 mode 0 value 1 (now 0) (lr 0x802eb444)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #5: event 0x100d6c8000 mode 0 value 4 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #18: event 0x100d6c8000 mode 0 value 4 (now 2) (lr 0x806661f8)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #19: event 0x100d6c8000 mode 0 value 4 (now 2) (lr 0x806661f8)
[hos sead::MainThread] nvn: QueueSubmitCommands #26: queue 000010100D695020 (its #5), 1 handles (lr 0x80666be0)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #20: event 0x100d6c8000 mode 0 value 4 (now 2) (lr 0x806661f8)
[hos sead::MainThread] nvn: QueueSubmitCommands #27: queue 000010100D6BF020 (its #5), 1 handles (lr 0x80666be0)
[hos Presentation Thread] nvn: QueueSubmitCommands #28: queue 000010100D5EB020 (its #5), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #29: queue 000010100D640020 (its #5), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #30: queue 000010100D6AA020 (its #5), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #31: queue 0000101004133020 (its #5), 1 handles (lr 0x80590358)
[hos sead::MainThread] nvn: EventSignal (CPU) #10: event 0x1006e38000 mode 0 value 1 (lr 0x8348c78c)
[hos host] vk: present texture 0x1004137000 2560x1440 format 0x25: rendered
[hos sead::MainThread] nvn: EventSignal (CPU) #11: event 0x1006e38004 mode 0 value 0 (lr 0x802eb420)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #21: event 0x1006e38004 mode 0 value 1 (now 0) (lr 0x802eb444)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #6: event 0x100d6c8000 mode 0 value 5 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #22: event 0x100d6c8000 mode 0 value 5 (now 3) (lr 0x806661f8)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #23: event 0x100d6c8000 mode 0 value 5 (now 3) (lr 0x806661f8)
[hos sead::MainThread] nvn: QueueSubmitCommands #32: queue 000010100D695020 (its #6), 1 handles (lr 0x80666be0)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #24: event 0x100d6c8000 mode 0 value 5 (now 3) (lr 0x806661f8)
[hos sead::MainThread] nvn: QueueSubmitCommands #33: queue 000010100D6BF020 (its #6), 1 handles (lr 0x80666be0)
[hos Presentation Thread] nvn: QueueSubmitCommands #34: queue 000010100D5EB020 (its #6), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #35: queue 000010100D640020 (its #6), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #36: queue 000010100D6AA020 (its #6), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #37: queue 0000101004133020 (its #6), 1 handles (lr 0x80590358)
[hos host] vk: submission 32 (queue 0x10100d5eb020) stopped at command buffer 0's wait for event 0x100d6c8000 == 4 (has 3)
[hos sead::MainThread] nvn: EventSignal (CPU) #12: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos sead::MainThread] nvn: EventSignal (CPU) #13: event 0x1006e38000 mode 0 value 0 (lr 0x802eb420)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #25: event 0x1006e38000 mode 0 value 1 (now 0) (lr 0x802eb444)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #7: event 0x100d6c8000 mode 0 value 6 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #26: event 0x100d6c8000 mode 0 value 6 (now 4) (lr 0x806661f8)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #27: event 0x100d6c8000 mode 0 value 6 (now 4) (lr 0x806661f8)
[hos sead::MainThread] nvn: QueueSubmitCommands #38: queue 000010100D695020 (its #7), 1 handles (lr 0x80666be0)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #28: event 0x100d6c8000 mode 0 value 6 (now 4) (lr 0x806661f8)
[hos sead::MainThread] nvn: QueueSubmitCommands #39: queue 000010100D6BF020 (its #7), 1 handles (lr 0x80666be0)
[hos Presentation Thread] nvn: QueueSubmitCommands #40: queue 000010100D5EB020 (its #7), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #41: queue 000010100D640020 (its #7), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #42: queue 000010100D6AA020 (its #7), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #43: queue 0000101004133020 (its #7), 1 handles (lr 0x80590358)
[hos sead::MainThread] nvn: EventSignal (CPU) #14: event 0x1006e38000 mode 0 value 1 (lr 0x8348c78c)
[hos sead::MainThread] nvn: EventSignal (CPU) #15: event 0x1006e38004 mode 0 value 0 (lr 0x802eb420)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #29: event 0x1006e38004 mode 0 value 1 (now 0) (lr 0x802eb444)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #8: event 0x100d6c8000 mode 0 value 7 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #30: event 0x100d6c8000 mode 0 value 7 (now 5) (lr 0x806661f8)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #31: event 0x100d6c8000 mode 0 value 7 (now 5) (lr 0x806661f8)
[hos sead::MainThread] nvn: QueueSubmitCommands #44: queue 000010100D695020 (its #8), 1 handles (lr 0x80666be0)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #32: event 0x100d6c8000 mode 0 value 7 (now 5) (lr 0x806661f8)
[hos sead::MainThread] nvn: QueueSubmitCommands #45: queue 000010100D6BF020 (its #8), 1 handles (lr 0x80666be0)
[hos Presentation Thread] nvn: QueueSubmitCommands #46: queue 000010100D5EB020 (its #8), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #47: queue 000010100D640020 (its #8), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #48: queue 000010100D6AA020 (its #8), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #49: queue 0000101004133020 (its #8), 1 handles (lr 0x80590358)
[hos sead::MainThread] nvn: EventSignal (CPU) #16: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos sead::MainThread] nvn: EventSignal (CPU) #17: event 0x1006e38000 mode 0 value 0 (lr 0x802eb420)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #33: event 0x1006e38000 mode 0 value 1 (now 0) (lr 0x802eb444)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #9: event 0x100d6c8000 mode 0 value 8 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #34: event 0x100d6c8000 mode 0 value 8 (now 7) (lr 0x806661f8)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #35: event 0x100d6c8000 mode 0 value 8 (now 7) (lr 0x806661f8)
[hos sead::MainThread] nvn: QueueSubmitCommands #50: queue 000010100D695020 (its #9), 1 handles (lr 0x80666be0)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #36: event 0x100d6c8000 mode 0 value 8 (now 7) (lr 0x806661f8)
[hos sead::MainThread] nvn: QueueSubmitCommands #51: queue 000010100D6BF020 (its #9), 1 handles (lr 0x80666be0)
[hos Presentation Thread] nvn: QueueSubmitCommands #52: queue 000010100D5EB020 (its #9), 1 handles (lr 0x805282f4)
[hos sead::MainThread] nvn: EventSignal (CPU) #18: event 0x1006e38000 mode 0 value 1 (lr 0x8348c78c)
[hos Presentation Thread] nvn: QueueSubmitCommands #53: queue 000010100D640020 (its #9), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #54: queue 000010100D6AA020 (its #9), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #55: queue 0000101004133020 (its #9), 1 handles (lr 0x80590358)
[hos host] vk: texture budget: 10928 MB (driver allows 15280 MB, the card has 16048 MB, RAM 31967 MB)
[hos sead::MainThread] nvn: EventSignal (CPU) #19: event 0x1006e38004 mode 0 value 0 (lr 0x802eb420)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #37: event 0x1006e38004 mode 0 value 1 (now 0) (lr 0x802eb444)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #10: event 0x100d6c8000 mode 0 value 9 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #38: event 0x100d6c8000 mode 0 value 9 (now 8) (lr 0x806661f8)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #39: event 0x100d6c8000 mode 0 value 9 (now 8) (lr 0x806661f8)
[hos sead::MainThread] nvn: QueueSubmitCommands #56: queue 000010100D695020 (its #10), 1 handles (lr 0x80666be0)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #40: event 0x100d6c8000 mode 0 value 9 (now 8) (lr 0x806661f8)
[hos sead::MainThread] nvn: QueueSubmitCommands #57: queue 000010100D6BF020 (its #10), 1 handles (lr 0x80666be0)
[hos Presentation Thread] nvn: QueueSubmitCommands #58: queue 000010100D5EB020 (its #10), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #59: queue 000010100D640020 (its #10), 1 handles (lr 0x805282f4)
[hos Presentation Thread] nvn: QueueSubmitCommands #60: queue 000010100D6AA020 (its #10), 1 handles (lr 0x805282f4)
[hos sead::MainThread] nvn: EventSignal (CPU) #20: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos sead::MainThread] nvn: EventSignal (CPU) #21: event 0x1006e38000 mode 0 value 0 (lr 0x802eb420)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #11: event 0x100d6c8000 mode 0 value 10 (lr 0x80666598)
[hos sead::MainThread] nvn: EventSignal (CPU) #22: event 0x1006e38000 mode 0 value 1 (lr 0x8348c78c)
[hos Resource Memory] vcores: 34592 takes, 11726 waits (mean 168 us, longest 611.4 ms), 5373 kicks, 4650 yields, 0 starved grants, 0 escapes in 5 s
[hos sead::MainThread] nvn: EventSignal (CPU) #23: event 0x1006e38004 mode 0 value 0 (lr 0x802eb420)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #12: event 0x100d6c8000 mode 0 value 11 (lr 0x80666598)
[hos sead::MainThread] nvn: EventSignal (CPU) #24: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos sead::MainThread] nvn: EventSignal (CPU) #25: event 0x1006e38000 mode 0 value 0 (lr 0x802eb420)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #13: event 0x100d6c8000 mode 0 value 12 (lr 0x80666598)
[hos sead::MainThread] nvn: EventSignal (CPU) #26: event 0x1006e38000 mode 0 value 1 (lr 0x8348c78c)
[hos sead::MainThread] nvn: EventSignal (CPU) #27: event 0x1006e38004 mode 0 value 0 (lr 0x802eb420)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #14: event 0x100d6c8000 mode 0 value 13 (lr 0x80666598)
[hos sead::MainThread] nvn: EventSignal (CPU) #28: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos sead::MainThread] nvn: EventSignal (CPU) #29: event 0x1006e38000 mode 0 value 0 (lr 0x802eb420)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #15: event 0x100d6c8000 mode 0 value 14 (lr 0x80666598)
[hos sead::MainThread] nvn: EventSignal (CPU) #30: event 0x1006e38000 mode 0 value 1 (lr 0x8348c78c)
[hos sead::MainThread] nvn: EventSignal (CPU) #31: event 0x1006e38004 mode 0 value 0 (lr 0x802eb420)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #16: event 0x100d6c8000 mode 0 value 15 (lr 0x80666598)
[hos sead::MainThread] nvn: EventSignal (CPU) #32: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos sead::MainThread] nvn: EventSignal (CPU) #33: event 0x1006e38000 mode 0 value 0 (lr 0x802eb420)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #17: event 0x100d6c8000 mode 0 value 16 (lr 0x80666598)
[hos sead::MainThread] nvn: EventSignal (CPU) #34: event 0x1006e38000 mode 0 value 1 (lr 0x8348c78c)
[hos sead::MainThread] nvn: EventSignal (CPU) #35: event 0x1006e38004 mode 0 value 0 (lr 0x802eb420)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #18: event 0x100d6c8000 mode 0 value 17 (lr 0x80666598)
[hos sead::MainThread] nvn: EventSignal (CPU) #36: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos sead::MainThread] nvn: EventSignal (CPU) #37: event 0x1006e38000 mode 0 value 0 (lr 0x802eb420)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #19: event 0x100d6c8000 mode 0 value 18 (lr 0x80666598)
[hos sead::MainThread] nvn: EventSignal (CPU) #38: event 0x1006e38000 mode 0 value 1 (lr 0x8348c78c)
[hos sead::MainThread] nvn: EventSignal (CPU) #39: event 0x1006e38004 mode 0 value 0 (lr 0x802eb420)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #20: event 0x100d6c8000 mode 0 value 19 (lr 0x80666598)
[hos sead::MainThread] nvn: EventSignal (CPU) #40: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #21: event 0x100d6c8000 mode 0 value 20 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #22: event 0x100d6c8000 mode 0 value 21 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #23: event 0x100d6c8000 mode 0 value 22 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #24: event 0x100d6c8000 mode 0 value 23 (lr 0x80666598)
[hos host] vk: vertex format NVN 0x3 -> vk 13
[hos host] vk: vertex format NVN 0x8 -> vk 74
[hos sead::MainThread] nvn: CommandBufferSignalEvent #25: event 0x100d6c8000 mode 0 value 24 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #26: event 0x100d6c8000 mode 0 value 25 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #27: event 0x100d6c8000 mode 0 value 26 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #28: event 0x100d6c8000 mode 0 value 27 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #29: event 0x100d6c8000 mode 0 value 28 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #30: event 0x100d6c8000 mode 0 value 29 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #31: event 0x100d6c8000 mode 0 value 30 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #32: event 0x100d6c8000 mode 0 value 31 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #33: event 0x100d6c8000 mode 0 value 32 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #34: event 0x100d6c8000 mode 0 value 33 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #35: event 0x100d6c8000 mode 0 value 34 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #36: event 0x100d6c8000 mode 0 value 35 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #37: event 0x100d6c8000 mode 0 value 36 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #38: event 0x100d6c8000 mode 0 value 37 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #39: event 0x100d6c8000 mode 0 value 38 (lr 0x80666598)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #40: event 0x100d6c8000 mode 0 value 39 (lr 0x80666598)
[hos host] vk: vertex format NVN 0x12 -> vk 77
[hos host] vk: vertex format NVN 0x13 -> vk 78
[hos host] vk: vertex format NVN 0xd -> vk 16
[hos host] vk: vertex format NVN 0xf -> vk 20
[hos host] vk: vertex format NVN 0x11 -> vk 83
[hos host] vk: mirror syncs (600 submits): 58 dirty pages from their submits' captures, 2254 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: read live, by pool:
[hos Resource Memory] mem: the game's mapped pages 951 MB (peak 951); heap 6894 MB; the console's total 9809 MB
[hos ARes Loading 0] prompts: the Talk ring's A B X Y at places 0 1 2 3, the ocarina hint spread
[hos ARes Loading 1] prompts: xbox textures, 2201 runs for this pad's controls
[hos sead::MainThread] prompts: the textures' pool at 0x7fc3075000 (+0xe86c000): a new face or new controls show at once
[hos sead::MainThread] prompts: the layouts at 0x7fe1a31000: the Talk ring and the ocarina hint follow at once
[hos host] vk: 5 pools imported
[hos host] vk: 6 pools imported
[hos sead::MainThread] vk: capture: a submit 0.06 ms (lock 0.01, scan 0.02 over 1200 ranges, 758 MB), 134 pages written, 134 copied (0.5 MB)
[hos host] vk: a capture taken (ms): all 0.005; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 24 kept (248 MB), 12 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.04
[a64] unimplemented import _ZN2nn5movie10InitializeEv (lr 0x83b7d25c)
[a64] unimplemented import _ZN2nn5movie13IsInitializedEv (lr 0x85467d74)
[hos ModuleSystemWorker1] oe: startup logo finished
[hos Resource Memory] mem: the game's mapped pages 1025 MB (peak 1025); heap 6894 MB; the console's total 9809 MB
[hos OptimizeChangeBanc] nvn: DrawMeshTasks: 1 so far (x1 0 x2 0x3 x3 0x400000 x4 0x83b70de0)
[hos OptimizeChangeBanc] nvn: DrawMeshTasks: 2 so far (x1 0 x2 0x3 x3 0x400000 x4 0x83b70de0)
[hos OptimizeChangeBanc] nvn: DrawMeshTasks: 3 so far (x1 0 x2 0x3 x3 0x400000 x4 0x83b70de0)
[hos Resource Memory] mem: the game's mapped pages 1282 MB (peak 1282); heap 6894 MB; the console's total 9809 MB
[hos host] vk: vertex format NVN 0x25 -> vk 37
[hos host] vk: vertex format NVN 0x26 -> vk 38
[hos host] vk: vertex format NVN 0x27 -> vk 41
[hos host] vk: vertex format NVN 0x2c -> vk 95
[hos OptimizeChangeBanc] [debug] nvn: 1 copies of recordings whose control memory was reused let go (366 live)
[hos MovieOperateThread] video: nn::codec::video on libavcodec
[hos MovieOperateThread] video: AV1 on dav1d 1.5.4 (a thread per logical core)
[hos MovieOperateThread] video: AV1 decoder ready on dav1d (1920x1080)
[hos AudioFrameworkThread] audio: voice 0: 48000 Hz, 1 channels, format 2, parameter 0 (0 bytes) at 6677.5 s
[hos AudioFrameworkThread] audio: voice 1: 48000 Hz, 1 channels, format 2, parameter 0 (0 bytes) at 6677.5 s
[hos AudioFrameworkThread] audio: voice 2: 48000 Hz, 1 channels, format 2, parameter 0 (0 bytes) at 6677.5 s
[hos AudioFrameworkThread] audio: voice 3: 48000 Hz, 1 channels, format 2, parameter 0 (0 bytes) at 6677.5 s
[hos AudioFrameworkThread] audio: voice 4: 48000 Hz, 1 channels, format 2, parameter 0 (0 bytes) at 6677.5 s
[hos AudioFrameworkThread] audio: voice 5: 48000 Hz, 1 channels, format 2, parameter 0 (0 bytes) at 6677.5 s
[hos AudioFrameworkThread] audio: wave buffer 0x108acecd50: data 0x108964d000 size 4096 samples 0..2048 loop 0 context 0 (voice format 2)
[hos AudioFrameworkThread] audio: wave buffer 0x108acecd50: data 0x1089655000 size 4096 samples 0..2048 loop 0 context 0 (voice format 2)
[hos AudioFrameworkThread] audio: wave buffer 0x108acecd50: data 0x108965d000 size 4096 samples 0..2048 loop 0 context 0 (voice format 2)
[hos AudioFrameworkThread] audio: wave buffer 0x108acecd50: data 0x1089665000 size 4096 samples 0..2048 loop 0 context 0 (voice format 2)
[hos AudioFrameworkThread] audio: wave buffer 0x108acecd50: data 0x108966d000 size 4096 samples 0..2048 loop 0 context 0 (voice format 2)
[hos AudioFrameworkThread] audio: wave buffer 0x108acecd50: data 0x1089675000 size 4096 samples 0..2048 loop 0 context 0 (voice format 2)
[hos AudioFrameworkThread] audio: wave buffer 0x108acecd50: data 0x108964e000 size 4096 samples 0..2048 loop 0 context 0 (voice format 2)
[hos AudioFrameworkThread] audio: wave buffer 0x108acecd50: data 0x1089656000 size 4096 samples 0..2048 loop 0 context 0 (voice format 2)
[hos AudioUserTaskThread] [debug] codec: Opus decoder 0: 48000 Hz, 1 channels
[hos AudioUserTaskThread] [debug] codec: Opus decoder 1: 48000 Hz, 1 channels
[hos AudioUserTaskThread] [debug] codec: Opus decoder 2: 48000 Hz, 1 channels
[hos AudioUserTaskThread] [debug] codec: Opus decoder 3: 48000 Hz, 1 channels
[hos AudioUserTaskThread] [debug] codec: Opus decoder 4: 48000 Hz, 1 channels
[hos AudioUserTaskThread] [debug] codec: Opus decoder 5: 48000 Hz, 1 channels
[hos AudioUserTaskThread] [trace] codec: GetOpusPacketSize(0x108acfe000, 49152): header 000000ae 07bf4b00 -> 182
[hos AudioUserTaskThread] [trace] codec: GetOpusPacketSize(0x108acfe0b6, 48970): header 00000094 036ed700 -> 156
[hos AudioUserTaskThread] [trace] codec: GetOpusPacketSize(0x108acfe152, 48814): header 000000a1 129a5e00 -> 169
[hos AudioUserTaskThread] [trace] codec: GetOpusPacketSize(0x108acfe1fb, 48645): header 000000a1 03898c00 -> 169
[hos AudioUserTaskThread] [trace] codec: GetOpusPacketSize(0x108acfe2a4, 48476): header 000000a1 66171600 -> 169
[hos AudioUserTaskThread] [trace] codec: GetOpusPacketSize(0x108acfe34d, 48307): header 000000a1 0322bb00 -> 169
[hos OpusDecoder] codec: decode 161 bytes (of 169) -> 960 samples (room for 960)
[hos OpusDecoder] codec: decode 161 bytes (of 169) -> 960 samples (room for 960)
[hos OpusDecoder] codec: decode 161 bytes (of 169) -> 960 samples (room for 960)
[hos OpusDecoder] codec: decode 161 bytes (of 169) -> 960 samples (room for 960)
[hos OpusDecoder] codec: decode 161 bytes (of 169) -> 960 samples (room for 960)
[hos OpusDecoder] codec: decode 161 bytes (of 169) -> 960 samples (room for 960)
[hos OptimizeChangeBanc] [debug] nvn: 4 copies of recordings whose control memory was reused let go (655 live)
[hos host] vk: vertex format NVN 0x14 -> vk 81
[hos MovieOperateThread] video: the first buffer went out before the first picture was decoded (shown black)
[hos host] vk: 1772 programs from the program cache
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.25, present 0.13, draw 0.02, descriptors 0.00, texture lookups 0.03, uploads 0.00, pipelines 0.00, programs 0.00, commands 0.01, dispatch 0.00, memory sync 0.30, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 6 (15 MB): 0.21 MB synced in 14.1 copies, 0.00 MB written back
[hos host] vk: 120 presents, 17.5 fps; a frame: 1 draws (0 skipped), 0 dispatches, 2 passes, 1 barriers, 6 submits, 0.0 uploads (0.0 MB), 1 ub updates (1 overlays), GPU-bound wait 0.0 ms (recording slots only); 2805 pipelines (399 ms), 0 programs (0 failed), 5 textures (60 MB)
[hos host] vk: host time in GPU resource waits: 0.32 ms a frame (fences 0.01, timelines 0.31, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 19.0 full barriers recorded, 13.7 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 0.0; 0x12: 1.0; 0x78: 0.0;
[hos host] vk: GPU time 0.2 ms a frame (the longest submission 0.4 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vi: a movie is playing: the frame rate goes to 240 for it (HOS_MOVIE_PACE=0 leaves it)
[hos host] vk: texture 0x10000000000 1920x1080x1 x1 levels 1 NVN 0x1 -> vk 9 (6 textures, 62 MB)
[hos host] vk: 7 pools imported
[hos host] vk: texture 0x1000021c200 960x540x1 x1 levels 1 NVN 0xd -> vk 16 (7 textures, 63 MB)
[hos host] vk: sampler 268 is nearest: min filter 4, mag filter 1, wrap 7/7/7, lod -1000..1000 bias 0, aniso 1, compare 0
[hos host] vk: sampler anisotropy: the game asks for 1 (min filter 4, mip filter linear, LOD bias 0; made with 16)
[hos host] vk: textures from a pool of their own, 128 MB blocks (RX_VK_COMPACT), 18 made at the start
[hos host] vk: texture 0x10755b4000 1920x1080x1 x1 levels 1 NVN 0x25 -> vk 37 (8 textures, 71 MB)
[hos host] vk: big block-linear textures are unswizzled on the GPU from their pools (RX_VK_GPU_UNSWIZZLE=0: the CPU)
[hos host] vk: import 3.2 ms: commit+properties 0.1, buffer 0.0, allocate 3.1, bind+address 0.0
[hos host] vk: pool 0x10755b4000+0x870000 imported in 3.2 ms as 0x1072c00000..0x1077000000 (8 imports, 7 ms in all)
[hos host] vk: pool 0x1075c00000 remade larger (1 retired)
[hos host] vk: 7 pools imported
[hos host] vk: pool 0x1072c00000..0x1077000000: mirror made with the GPU's contents of 1 retired pool(s)
[hos host] vk: network e409733c45530d75: dispatch 900x1x1, 1 textures 0 images: 1920x1080x1/37
[hos host] vk: page table of guest memory at 0x11d8e00000 (7 pools)
[hos host] vk: network 8306877b7dc8784b: dispatch 720x1x1, 0 textures 0 images:
[hos host] vk: network de3c10dba4ff39d3: dispatch 97x1x1, 0 textures 0 images:
[hos host] vk: network a41c78faa56ccf7d: dispatch 120x1x1, 0 textures 0 images:
[hos host] vk: network e959b9b1451491c0: dispatch 70x1x1, 0 textures 0 images:
[hos host] vk: network 5a4d7378db437fed: dispatch 60x1x1, 0 textures 0 images:
[hos host] vk: network 8b73eaee02efc5e4: dispatch 85x1x1, 0 textures 0 images:
[hos host] vk: network 14140d4c1dbe754f: dispatch 8100x1x1, 0 textures 0 images:
[hos host] vk: texture 0x1075e31000 1920x1080x1 x1 levels 1 NVN 0x3d -> vk 64 (9 textures, 80 MB)
[hos host] vk: network 4c2c129fe950b041: dispatch 5400x1x1, 1 textures 1 images: 1920x1080x1/37 1920x1080x1/64
[hos host] vk: texture 0x1072ca0200 512x512x1 x1 levels 1 NVN 0x3d -> vk 64 (10 textures, 81 MB)
[hos host] vk: sampler anisotropy: the game asks for 0 (min filter 1, mip filter nearest, LOD bias 0; made with 16)
[hos host] vk: texture 0x10000348400 2560x1440x1 x1 levels 1 NVN 0x38 -> vk 37 (11 textures, 96 MB)
[hos host] vk: network 3f6f2b1d671badcd: dispatch 80x180x1, 2 textures 1 images: 1920x1080x1/64 2560x1440x1/37
[hos host] vk: write-back diff: a shadow for pool 0x1072c00000 (68 MB; 68 MB of shadows)
[hos host] vk: mirror of pool 0x1075c00000 (20 MB) given back: retired, 11 submissions since its sync
[hos OptimizeChangeBanc] [debug] nvn: 3 copies of recordings whose control memory was reused let go (2166 live)
[hos host] vk: vertex format NVN 0x1 -> vk 9
[hos host] vk: sparse mirrors: 7, 79 MB with memory of 104 MB (25 MB spared); blocks given memory later 37, given back 0; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 9 binds (1.1 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 4876 dirty pages from their submits' captures, 20873 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 33 runs, 1305.2 MB compared; 10126 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 21265 in captures, 959 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 8 live (124 MB), 0 retired still imported (0 MB), 1 retired given back (20 MB)
[hos OptimizeChangeBanc] [debug] nvn: 6 copies of recordings whose control memory was reused let go (2975 live)
[hos Resource Memory] mem: the game's mapped pages 1536 MB (peak 1536); heap 6894 MB; the console's total 9809 MB
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.02, scan 0.02 over 1341 ranges, 934 MB), 183 pages written, 183 copied (0.7 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (66 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.05
[hos OptimizeChangeBanc] [debug] nvn: 3 copies of recordings whose control memory was reused let go (4311 live)
[hos host] vk: mirror syncs (600 submits): 851 dirty pages from their submits' captures, 26325 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 79 runs, 3124.5 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 22115 in captures, 1499 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: 2539 programs from the program cache
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.14, present 0.04, draw 0.02, descriptors 0.00, texture lookups 0.16, uploads 0.05, pipelines 0.00, programs 0.00, commands 0.02, dispatch 0.64, memory sync 0.30, queue submit 0.20, slot wait 0.02
[hos host] vk: a frame: mirrors 8 (78 MB): 2.40 MB synced in 21.3 copies, 38.89 MB written back
[hos host] vk: 240 presents, 170.9 fps; a frame: 2 draws (0 skipped), 14 dispatches, 3 passes, 14 barriers, 6 submits, 0.1 uploads (0.3 MB), 1 ub updates (1 overlays), GPU-bound wait 0.0 ms (recording slots only); 4762 pipelines (818 ms), 0 programs (0 failed), 11 textures (96 MB)
[hos host] vk: host time in GPU resource waits: 1.45 ms a frame (fences 0.01, timelines 1.44, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 35.4 full barriers recorded, 28.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 12.8; 0x12: 1.0;
[hos host] vk: GPU time 2.3 ms a frame (the longest submission 11.4 ms); 0.1 textures made a frame
[hos host] vk: a frame: 0.03 MB unswizzled on the CPU in 0.01 ms
[hos OptimizeChangeBanc] [debug] nvn: 3 copies of recordings whose control memory was reused let go (4863 live)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.03, scan 0.03 over 1429 ranges, 990 MB), 153 pages written, 153 copied (0.6 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (70 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos OptimizeChangeBanc] [debug] nvn: 4 copies of recordings whose control memory was reused let go (5876 live)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.05
[hos host] vk: sparse mirrors: 7, 78 MB with memory of 104 MB (25 MB spared); blocks given memory later 37, given back 2; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 10 binds (1.1 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 110 dirty pages from their submits' captures, 25620 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 81 runs, 3203.6 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 20464 in captures, 5160 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 8 live (124 MB), 0 retired still imported (0 MB), 1 retired given back (20 MB)
[hos sead::MainThread] nvn: GPU waits in 5 s: 33 sync waits (214 ms), 0 polls timed out (0 ms), 1 queue finishes (34 ms)
[hos Resource Memory] mem: the game's mapped pages 1792 MB (peak 1792); heap 6894 MB; the console's total 9809 MB
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 0.61, present 0.04, draw 0.02, descriptors 0.00, texture lookups 0.00, uploads 0.00, pipelines 0.00, programs 0.00, commands 0.01, dispatch 0.05, memory sync 0.43, queue submit 0.18, slot wait 0.01
[hos host] vk: a frame: mirrors 8 (78 MB): 1.26 MB synced in 21.8 copies, 39.55 MB written back
[hos host] vk: 360 presents, 240.2 fps; a frame: 2 draws (0 skipped), 14 dispatches, 3 passes, 14 barriers, 6 submits, 0.0 uploads (0.0 MB), 1 ub updates (1 overlays), GPU-bound wait 0.0 ms (recording slots only); 5589 pipelines (935 ms), 0 programs (0 failed), 11 textures (96 MB)
[hos host] vk: host time in GPU resource waits: 0.08 ms a frame (fences 0.01, timelines 0.07, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 35.4 full barriers recorded, 28.4 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 13.0; 0x12: 1.0;
[hos host] vk: GPU time 1.7 ms a frame (the longest submission 2.4 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.03, scan 0.03 over 1536 ranges, 1058 MB), 168 pages written, 168 copied (0.7 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (90 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 3 KB; 0 made on demand (0 MB kept now); c1 stages: at most 0 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 102 dirty pages from their submits' captures, 25595 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 81 runs, 3203.6 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 21825 in captures, 2274 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.06
[hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.03, scan 0.03 over 1648 ranges, 1117 MB), 164 pages written, 164 copied (0.6 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (94 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 7, 78 MB with memory of 104 MB (25 MB spared); blocks given memory later 37, given back 2; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 10 binds (1.1 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 94 dirty pages from their submits' captures, 25581 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 80 runs, 3164.1 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 23412 in captures, 675 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 8 live (124 MB), 0 retired still imported (0 MB), 1 retired given back (20 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: 3109 programs from the program cache
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 0.55, present 0.03, draw 0.02, descriptors 0.00, texture lookups 0.00, uploads 0.00, pipelines 0.00, programs 0.00, commands 0.01, dispatch 0.05, memory sync 0.37, queue submit 0.17, slot wait 0.01
[hos host] vk: a frame: mirrors 8 (78 MB): 1.25 MB synced in 21.1 copies, 39.55 MB written back
[hos host] vk: 480 presents, 240.1 fps; a frame: 2 draws (0 skipped), 14 dispatches, 3 passes, 14 barriers, 6 submits, 0.0 uploads (0.0 MB), 1 ub updates (1 overlays), GPU-bound wait 0.0 ms (recording slots only); 6047 pipelines (1013 ms), 0 programs (0 failed), 11 textures (96 MB)
[hos host] vk: host time in GPU resource waits: 0.03 ms a frame (fences 0.01, timelines 0.02, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 35.5 full barriers recorded, 28.5 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 13.0; 0x12: 1.0;
[hos host] vk: GPU time 1.7 ms a frame (the longest submission 2.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.05
[hos Resource Memory] mem: the game's mapped pages 2049 MB (peak 2049); heap 6894 MB; the console's total 9809 MB
[hos OptimizeChangeBanc] [debug] nvn: 2 copies of recordings whose control memory was reused let go (12999 live)
[hos OptimizeChangeBanc] nvn: 50000 recordings made, 13255 live copies (1.2 MB), 7 texture copies; 2 command buffers' segments (0.1 MB)
[hos sead::MainThread] vk: capture: a submit 0.09 ms (lock 0.03, scan 0.03 over 1724 ranges, 1147 MB), 149 pages written, 149 copied (0.6 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 24 kept (82 MB), 12 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 121 dirty pages from their submits' captures, 26432 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 80 runs, 3164.1 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 21881 in captures, 2965 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: memory: working set 8436 MB (peak 8436), private 12123 MB, staging 64 MB in 1 arenas
[hos host] vk: memory heaps: heap 0 (device): 77 blocks 2956 MB, 1391 allocations 466 MB; used 3283 of 15280 MB; heap 1 (system): 9 blocks 384 MB, 36 allocations 342 MB; used 566 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 2 images 31 MB; 2 free ranges, the largest 96 MB
[hos host] vk: image blocks (render targets): 1 blocks 128 MB, 7 images 63 MB; 1 free ranges, the largest 64 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 4 images 32 MB; 18 free ranges, the largest 128 MB
[hos host] vk: render target images: 0 reused from the pool, 7 made new, 0 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 3283 MB used of 15280 MB allowed (2489 MB of it free in the blocks); textures 96 MB (budget 10928 MB), 11 textures
[hos host] vk: textures: decoded ASTC 0 MB, rendered 89 MB (1 drawn in one frame, kept: 128 KB), other 1 MB; used in the last 8 presents 90 MB
[hos host] vk: 14 MB: 0x1004137000 2560x1440x1 x1 levels 1 NVN 0x25 rendered, last used 2 presents ago
[hos host] vk: 14 MB: 0x1005f37000 2560x1440x1 x1 levels 1 NVN 0x25 rendered, last used 3 presents ago
[hos host] vk: 14 MB: 0x1001f0ffe00 2560x1440x1 x1 levels 1 NVN 0x3f rendered, last used 1 presents ago
[hos host] vk: 14 MB: 0x10000348400 2560x1440x1 x1 levels 1 NVN 0x38 rendered, last used 1 presents ago
[hos host] vk: 14 MB: 0x1005037000 2560x1440x1 x1 levels 1 NVN 0x25 rendered, last used 1 presents ago
[hos host] vk: 7 MB: 0x1075e31000 1920x1080x1 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk: 7 MB: 0x10755b4000 1920x1080x1 x1 levels 1 NVN 0x25 rendered, last used 1 presents ago
[hos host] vk: 1 MB: 0x10000000000 1920x1080x1 x1 levels 1 NVN 0x1 rendered, last used 1 presents ago
[hos Presentation Thread] vk: presents after the CPU's signal (600): 243 waited for it, 1.13 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.07
[hos host] vk: status: 600 frames, the slowest 92.0 ms; VRAM 3.2 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 0 program records loaded (0.0 ms), 0 new graphics pipelines, pipelines from the driver's cache 0, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 3063 queued, 3063 loaded (median 0.46 ms, 99th percentile 3.10 ms, worst 45.66 ms, 2240 ms and 689.9 MB read in all); 3850 programs (623 of them compute variants without their code, 0 graphics programs no note names), 6141 graphics pipelines (0 not in a cache), 408 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 3 pipelines made at create taken by draws; 1638 create calls with nothing kept for their stages, 0 before the index; units 4701 (3063 ready, 0 loading), 8528 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 408 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 0.59, present 0.03, draw 0.01, descriptors 0.00, texture lookups 0.00, uploads 0.00, pipelines 0.00, programs 0.00, commands 0.01, dispatch 0.05, memory sync 0.41, queue submit 0.15, slot wait 0.01
[hos host] vk: a frame: mirrors 8 (78 MB): 1.30 MB synced in 21.5 copies, 39.55 MB written back
[hos host] vk: 600 presents, 238.9 fps; a frame: 2 draws (0 skipped), 14 dispatches, 3 passes, 14 barriers, 6 submits, 0.0 uploads (0.0 MB), 1 ub updates (1 overlays), GPU-bound wait 0.0 ms (recording slots only); 6237 pipelines (1056 ms), 0 programs (0 failed), 11 textures (96 MB)
[hos host] vk: host time in GPU resource waits: 0.11 ms a frame (fences 0.01, timelines 0.10, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 35.5 full barriers recorded, 28.5 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 13.0; 0x12: 1.0;
[hos host] vk: GPU time 1.9 ms a frame (the longest submission 3.1 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 48 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 0.00 ms a frame): its jobs 1.45 ms a frame (submits 0.87, presents 0.32, others 0.26), idle -1.45; the game waited for room at 4 presents, 0.99 ms each (0.01 a frame; 24.78 jobs queued at a present); 48 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 1.28 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 320 captures at a CPU signal; the submits' waits read in 0.001 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 1.39 ms after its hand-over (76.66 at most)
[hos host] vk: sparse mirrors: 7, 78 MB with memory of 104 MB (25 MB spared); blocks given memory later 37, given back 2; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 10 binds (1.1 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 135 dirty pages from their submits' captures, 25601 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 81 runs, 3203.6 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 21290 in captures, 2906 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 8 live (124 MB), 0 retired still imported (0 MB), 1 retired given back (20 MB)
[hos Presentation Thread] vk: capture: a submit 0.11 ms (lock 0.04, scan 0.03 over 1896 ranges, 1236 MB), 178 pages written, 178 copied (0.7 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (72 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.06
[hos host] vk: mirror syncs (600 submits): 72 dirty pages from their submits' captures, 25432 from earlier ones', 0 from guest memory as it was at the replay; 24 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 78 runs, 3085.0 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 22971 in captures, 1115 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 0.54, present 0.04, draw 0.02, descriptors 0.00, texture lookups 0.00, uploads 0.00, pipelines 0.00, programs 0.00, commands 0.01, dispatch 0.05, memory sync 0.37, queue submit 0.16, slot wait 0.01
[hos host] vk: a frame: mirrors 8 (78 MB): 1.25 MB synced in 20.5 copies, 39.55 MB written back
[hos host] vk: 720 presents, 241.0 fps; a frame: 2 draws (0 skipped), 14 dispatches, 3 passes, 14 barriers, 6 submits, 0.0 uploads (0.0 MB), 1 ub updates (1 overlays), GPU-bound wait 0.0 ms (recording slots only); 6449 pipelines (1092 ms), 0 programs (0 failed), 11 textures (96 MB)
[hos host] vk: host time in GPU resource waits: 0.10 ms a frame (fences 0.01, timelines 0.09, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 35.6 full barriers recorded, 28.6 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 13.0; 0x12: 1.0;
[hos host] vk: GPU time 1.9 ms a frame (the longest submission 3.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.02, scan 0.04 over 1937 ranges, 1247 MB), 136 pages written, 136 copied (0.5 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (66 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 3 KB; 0 made on demand (0 MB kept now); c1 stages: at most 0 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 7, 78 MB with memory of 104 MB (25 MB spared); blocks given memory later 37, given back 2; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 10 binds (1.1 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 69 dirty pages from their submits' captures, 25366 from earlier ones', 0 from guest memory as it was at the replay; 24 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 79 runs, 3124.5 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 24098 in captures, 0 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 8 live (124 MB), 0 retired still imported (0 MB), 1 retired given back (20 MB)
[hos host] vk: mirror of pool 0x103d800000 (4 MB) given back: idle, 6015 submissions since its sync
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos Presentation Thread] vi: 802 frames presented (160.4 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 682, 15.5-17.8 114, 17.8-22 4, 22-30 0, 30-40 0, over 40 1
[hos Presentation Thread] vk: capture: a submit 0.07 ms (lock 0.01, scan 0.04 over 1937 ranges, 1247 MB), 137 pages written, 137 copied (0.5 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (66 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos BaseProcExecutor1] vcores: 280334 takes, 124129 waits (mean 36 us, longest 140.1 ms), 60768 kicks, 59334 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 0.29, present 0.03, draw 0.02, descriptors 0.00, texture lookups 0.00, uploads 0.00, pipelines 0.00, programs 0.00, commands 0.01, dispatch 0.04, memory sync 0.12, queue submit 0.15, slot wait 0.01
[hos host] vk: a frame: mirrors 8 (76 MB): 1.24 MB synced in 18.5 copies, 39.55 MB written back
[hos host] vk: 840 presents, 239.9 fps; a frame: 2 draws (0 skipped), 14 dispatches, 3 passes, 14 barriers, 6 submits, 0.0 uploads (0.0 MB), 1 ub updates (1 overlays), GPU-bound wait 0.0 ms (recording slots only); 6449 pipelines (1092 ms), 0 programs (0 failed), 11 textures (96 MB)
[hos host] vk: host time in GPU resource waits: 0.05 ms a frame (fences 0.01, timelines 0.04, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 35.5 full barriers recorded, 28.5 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 13.0; 0x12: 1.0;
[hos host] vk: GPU time 1.9 ms a frame (the longest submission 3.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: mirror syncs (600 submits): 191 dirty pages from their submits' captures, 25237 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 81 runs, 3203.6 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 24027 in captures, 74 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos host] vk: mirror of pool 0x107cc00000 (12 MB) given back: idle, 6061 submissions since its sync
[hos host] vk: mirror of pool 0x107d800000 (8 MB) given back: idle, 6061 submissions since its sync
[hos sead::MainThread] vk: capture: a submit 0.07 ms (lock 0.01, scan 0.04 over 1937 ranges, 1247 MB), 137 pages written, 137 copied (0.5 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (94 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 4, 64 MB with memory of 80 MB (15 MB spared); blocks given memory later 37, given back 2; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 10 binds (1.1 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 52 dirty pages from their submits' captures, 25361 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 78 runs, 3085.0 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 24094 in captures, 0 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 8 live (124 MB), 0 retired still imported (0 MB), 1 retired given back (20 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 0.28, present 0.03, draw 0.01, descriptors 0.00, texture lookups 0.00, uploads 0.00, pipelines 0.00, programs 0.00, commands 0.01, dispatch 0.04, memory sync 0.11, queue submit 0.14, slot wait 0.01
[hos host] vk: a frame: mirrors 8 (64 MB): 1.27 MB synced in 18.5 copies, 39.55 MB written back
[hos host] vk: 960 presents, 239.9 fps; a frame: 2 draws (0 skipped), 14 dispatches, 3 passes, 14 barriers, 6 submits, 0.0 uploads (0.0 MB), 1 ub updates (1 overlays), GPU-bound wait 0.0 ms (recording slots only); 6449 pipelines (1092 ms), 0 programs (0 failed), 11 textures (96 MB)
[hos host] vk: host time in GPU resource waits: 0.02 ms a frame (fences 0.01, timelines 0.01, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 35.6 full barriers recorded, 28.6 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 13.0; 0x12: 1.0;
[hos host] vk: GPU time 1.9 ms a frame (the longest submission 3.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos sead::MainThread] [debug] nvn: 1 copies of recordings whose control memory was reused let go (18640 live)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos Presentation Thread] vk: capture: a submit 0.06 ms (lock 0.01, scan 0.03 over 1937 ranges, 1247 MB), 132 pages written, 132 copied (0.5 MB)
[hos host] vk: a capture taken (ms): all 0.001; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (66 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 813 dirty pages from their submits' captures, 24583 from earlier ones', 0 from guest memory as it was at the replay; 24 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 78 runs, 3085.0 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 24096 in captures, 0 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos AudioFrameworkThread] audio: voice 6: 48000 Hz, 1 channels, format 6, parameter 0x1089637500 (32 bytes) at 6681.6 s
[hos AudioFrameworkThread] audio: voice 7: 48000 Hz, 1 channels, format 6, parameter 0x1089637740 (32 bytes) at 6681.6 s
[hos host] vk: ASTC not sampled by this GPU: blocks are decoded on upload
[hos host] vk: texture 0x7fcd59d200 1664x1280x1 x1 levels 1 NVN 0x87 -> vk 37 (ASTC decoded) (12 textures, 104 MB)
[hos host] vk: ASTC is decoded on the GPU (Eden's decoder, Switch 2 tiling)
[hos host] vk: sampler anisotropy: the game asks for 1 (min filter 3, mip filter nearest, LOD bias -0.5; made with 16)
[hos host] vk: texture 0x7fcd1bd200 1464x640x1 x1 levels 1 NVN 0x87 -> vk 37 (ASTC decoded) (13 textures, 108 MB)
[hos host] vk: texture 0x7fcbedb200 683x683x1 x1 levels 1 NVN 0x49 -> vk 139 (14 textures, 108 MB)
[hos host] vk: texture 0x7fdc8a7000 832x640x1 x1 levels 1 NVN 0x87 -> vk 37 (ASTC decoded) (15 textures, 110 MB)
[hos host] vk: texture 0x7fdccb7000 832x640x1 x1 levels 1 NVN 0x87 -> vk 37 (ASTC decoded) (16 textures, 112 MB)
[hos host] vk: texture 0x1001f0e1c00 240x94x1 x1 levels 1 NVN 0x25 -> vk 37 (17 textures, 112 MB)
[hos host] vk: texture 0x1001f0d4a00 198x40x1 x1 levels 1 NVN 0x25 -> vk 37 (18 textures, 112 MB)
[hos host] vk: texture 0x100c922a00 4x4x1 x1 levels 1 NVN 0x25 -> vk 37 (19 textures, 112 MB)
[hos host] vk: texture 0x107cd71600 256x46x1 x1 levels 1 NVN 0x1 -> vk 9 (20 textures, 112 MB)
[hos host] vk: texture #21 at 0x10000000000 beside #6: 262x104x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1, the other 1920x1080x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1 (rendered)
[hos host] vk: texture 0x10000000000 262x104x1 x1 levels 1 NVN 0x1 -> vk 9 (21 textures, 112 MB)
[hos host] vk: texture 0x1001f0ca800 262x104x1 x1 levels 1 NVN 0x1 -> vk 9 (22 textures, 112 MB)
[hos host] vk: texture 0x1001f0bd600 198x40x1 x1 levels 1 NVN 0x25 -> vk 37 (23 textures, 112 MB)
[hos host] vk: texture 0x107cd74600 256x46x1 x1 levels 1 NVN 0x1 -> vk 9 (24 textures, 112 MB)
[hos host] vk: texture 0x1001f0b3400 262x104x1 x1 levels 1 NVN 0x1 -> vk 9 (25 textures, 112 MB)
[hos host] vk: texture 0x1001f0a6200 198x40x1 x1 levels 1 NVN 0x25 -> vk 37 (26 textures, 112 MB)
[hos host] vk: texture 0x107cd77600 256x46x1 x1 levels 1 NVN 0x1 -> vk 9 (27 textures, 112 MB)
[hos host] vk: texture 0x1001f09c000 262x104x1 x1 levels 1 NVN 0x1 -> vk 9 (28 textures, 112 MB)
[hos host] vk: texture 0x1001f077e00 285x94x1 x1 levels 1 NVN 0x25 -> vk 37 (29 textures, 113 MB)
[hos host] vk: texture 0x1001f067c00 242x40x1 x1 levels 1 NVN 0x25 -> vk 37 (30 textures, 113 MB)
[hos host] vk: texture 0x107cd7d600 256x46x1 x1 levels 1 NVN 0x1 -> vk 9 (31 textures, 113 MB)
[hos host] vk: texture #32 at 0x10000000000 beside #6: 306x104x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1, the other 1920x1080x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1 (rendered)
[hos host] vk: texture #32 at 0x10000000000 beside #21: 306x104x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1, the other 262x104x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1 (rendered)
[hos host] vk: texture 0x10000000000 306x104x1 x1 levels 1 NVN 0x1 -> vk 9 (32 textures, 113 MB)
[hos host] vk: texture 0x1001f05da00 306x104x1 x1 levels 1 NVN 0x1 -> vk 9 (33 textures, 113 MB)
[hos host] vk: texture 0x1001f04d800 242x40x1 x1 levels 1 NVN 0x25 -> vk 37 (34 textures, 113 MB)
[hos host] vk: texture 0x107cd80600 256x46x1 x1 levels 1 NVN 0x1 -> vk 9 (35 textures, 113 MB)
[hos host] vk: texture 0x1001f043600 306x104x1 x1 levels 1 NVN 0x1 -> vk 9 (36 textures, 113 MB)
[hos host] vk: texture 0x1001f033400 242x40x1 x1 levels 1 NVN 0x25 -> vk 37 (37 textures, 113 MB)
[hos host] vk: texture 0x107cd83600 256x46x1 x1 levels 1 NVN 0x1 -> vk 9 (38 textures, 113 MB)
[hos host] vk: texture 0x1001f029200 306x104x1 x1 levels 1 NVN 0x1 -> vk 9 (39 textures, 113 MB)
[hos host] vk: texture 0x1001efd9000 631x94x1 x1 levels 1 NVN 0x25 -> vk 37 (40 textures, 113 MB)
[hos host] vk: texture #43 at 0x10000000000 beside #6: 656x113x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1, the other 1920x1080x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1 (rendered)
[hos host] vk: texture #43 at 0x10000000000 beside #21: 656x113x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1, the other 262x104x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1 (rendered)
[hos host] vk: texture #43 at 0x10000000000 beside #32: 656x113x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1, the other 306x104x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1 (rendered)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 0.33, present 0.03, draw 0.12, descriptors 0.10, texture lookups 0.04, uploads 0.04, pipelines 0.00, programs 0.01, commands 0.01, dispatch 0.04, memory sync 0.11, queue submit 0.14, slot wait 0.01
[hos host] vk: a frame: mirrors 10 (76 MB): 1.37 MB synced in 19.8 copies, 39.55 MB written back
[hos host] vk: 1080 presents, 240.1 fps; a frame: 10 draws (0 skipped), 14 dispatches, 3 passes, 15 barriers, 6 submits, 0.4 uploads (0.1 MB), 1 ub updates (1 overlays), GPU-bound wait 0.0 ms (recording slots only); 6449 pipelines (1092 ms), 0 programs (0 failed), 61 textures (115 MB)
[hos host] vk: host time in GPU resource waits: 0.17 ms a frame (fences 0.01, timelines 0.16, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 36.6 full barriers recorded, 29.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 13.3; 0x10: 0.3; 0x12: 1.0;
[hos host] vk: GPU time 1.9 ms a frame (the longest submission 3.5 ms); 0.4 textures made a frame
[hos host] vk: a frame: 0.02 MB unswizzled on the CPU in 0.01 ms
[hos sead::MainThread] vk: capture: a submit 0.07 ms (lock 0.01, scan 0.04 over 1938 ranges, 1479 MB), 133 pages written, 133 copied (0.5 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 24 kept (62 MB), 12 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos host] vk: sparse mirrors: 6, 76 MB with memory of 100 MB (23 MB spared); blocks given memory later 37, given back 2; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 12 binds (1.3 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 967 dirty pages from their submits' captures, 25968 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 79 runs, 3124.5 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 24096 in captures, 0 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 8 live (124 MB), 0 retired still imported (0 MB), 1 retired given back (20 MB)
[hos host] vk: 3 textures retired (58 left, 115 MB): budget 0, drawn over 3, dead targets 0
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos sead::MainThread] vk: capture: a submit 0.07 ms (lock 0.01, scan 0.04 over 1938 ranges, 1479 MB), 137 pages written, 137 copied (0.5 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (96 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos Resource Memory] mem: the game's mapped pages 2304 MB (peak 2304); heap 6894 MB; the console's total 9809 MB
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 21 KB; 0 made on demand (0 MB kept now); c1 stages: at most 1 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 63 dirty pages from their submits' captures, 26888 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 78 runs, 3085.0 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 23222 in captures, 760 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: memory: working set 8716 MB (peak 8716), private 12669 MB, staging 64 MB in 1 arenas
[hos host] vk: memory heaps: heap 0 (device): 77 blocks 2956 MB, 1401 allocations 486 MB; used 3363 of 15280 MB; heap 1 (system): 9 blocks 384 MB, 36 allocations 342 MB; used 566 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 2 images 31 MB; 2 free ranges, the largest 96 MB
[hos host] vk: image blocks (render targets): 1 blocks 128 MB, 7 images 63 MB; 1 free ranges, the largest 64 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 51 images 51 MB; 22 free ranges, the largest 128 MB
[hos host] vk: render target images: 0 reused from the pool, 7 made new, 0 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 3363 MB used of 15280 MB allowed (2469 MB of it free in the blocks); textures 115 MB (budget 10928 MB), 58 textures
[hos host] vk: textures: decoded ASTC 15 MB, rendered 90 MB (21 drawn in one frame, kept: 1121 KB), other 1 MB; used in the last 8 presents 107 MB
[hos host] vk: 14 MB: 0x1005f37000 2560x1440x1 x1 levels 1 NVN 0x25 rendered, last used 3 presents ago
[hos host] vk: 14 MB: 0x10000348400 2560x1440x1 x1 levels 1 NVN 0x38 rendered, last used 1 presents ago
[hos host] vk: 14 MB: 0x1001f0ffe00 2560x1440x1 x1 levels 1 NVN 0x3f rendered, last used 1 presents ago
[hos host] vk: 14 MB: 0x1005037000 2560x1440x1 x1 levels 1 NVN 0x25 rendered, last used 1 presents ago
[hos host] vk: 14 MB: 0x1004137000 2560x1440x1 x1 levels 1 NVN 0x25 rendered, last used 2 presents ago
[hos host] vk: 8 MB: 0x7fcd59d200 1664x1280x1 x1 levels 1 NVN 0x87 ASTC, last used 1 presents ago
[hos host] vk: 7 MB: 0x1075e31000 1920x1080x1 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk: 7 MB: 0x10755b4000 1920x1080x1 x1 levels 1 NVN 0x25 rendered, last used 1 presents ago
[hos Presentation Thread] vk: presents after the CPU's signal (600): 348 waited for it, 0.18 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos host] vk: status: 600 frames, the slowest 10.4 ms; VRAM 3.3 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 0 program records loaded (0.0 ms), 0 new graphics pipelines, pipelines from the driver's cache 0, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 3175 queued, 3175 loaded (median 0.48 ms, 99th percentile 3.10 ms, worst 45.66 ms, 2371 ms and 731.0 MB read in all); 4008 programs (623 of them compute variants without their code, 0 graphics programs no note names), 6402 graphics pipelines (0 not in a cache), 408 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 14 pipelines made at create taken by draws; 1731 create calls with nothing kept for their stages, 0 before the index; units 4906 (3175 ready, 0 loading), 8906 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 408 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 0.34, present 0.03, draw 0.05, descriptors 0.02, texture lookups 0.00, uploads 0.00, pipelines 0.00, programs 0.00, commands 0.02, dispatch 0.04, memory sync 0.15, queue submit 0.14, slot wait 0.01
[hos host] vk: a frame: mirrors 10 (76 MB): 1.32 MB synced in 22.1 copies, 39.55 MB written back
[hos host] vk: 1200 presents, 239.0 fps; a frame: 22 draws (0 skipped), 14 dispatches, 3 passes, 14 barriers, 6 submits, 0.0 uploads (0.0 MB), 1 ub updates (1 overlays), GPU-bound wait 0.0 ms (recording slots only); 6510 pipelines (1113 ms), 0 programs (0 failed), 58 textures (115 MB)
[hos host] vk: host time in GPU resource waits: 0.07 ms a frame (fences 0.01, timelines 0.06, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 35.6 full barriers recorded, 28.6 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 13.0; 0x12: 1.0;
[hos host] vk: GPU time 2.1 ms a frame (the longest submission 3.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 4.17 ms a frame): its jobs 0.84 ms a frame (submits 0.46, presents 0.25, others 0.13), idle 3.33; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 12.21 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 362 captures at a CPU signal; the submits' waits read in 0.001 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 0.85 ms after its hand-over (7.03 at most)
[hos AudioFrameworkThread] audio: voice 8: 48000 Hz, 1 channels, format 6, parameter 0x1089637980 (32 bytes) at 6682.5 s
[hos AudioFrameworkThread] audio: voice 9: 48000 Hz, 1 channels, format 6, parameter 0x1089637bc0 (32 bytes) at 6682.5 s
[hos sead::MainThread] nvn: CommandBufferWaitEvent #5000: event 0x100d6c8000 mode 0 value 1249 (now 1248) (lr 0x806661f8)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: sparse mirrors: 6, 76 MB with memory of 100 MB (23 MB spared); blocks given memory later 37, given back 2; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 12 binds (1.3 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 118 dirty pages from their submits' captures, 27207 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 80 runs, 3164.1 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 19140 in captures, 5061 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 8 live (124 MB), 0 retired still imported (0 MB), 1 retired given back (20 MB)
[hos Presentation Thread] vk: capture: a submit 0.10 ms (lock 0.02, scan 0.04 over 1993 ranges, 1534 MB), 164 pages written, 164 copied (0.6 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (90 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos sead::MainThread] prompts: the font at 0x7fd37800e8: the icons in texts follow at once
[hos host] vk: texture storage read as submitted (1 times; 2 pages from the copies, 0 of them rewritten in guest memory since their submit; 6 pages kept, 8 spans, 327 MB)
[hos host] vk: texture #67 at 0x10000000000 beside #6: 154x98x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1, the other 1920x1080x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1 (rendered)
[hos host] vk: texture #71 at 0x10000000000 beside #6: 138x96x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1, the other 1920x1080x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1 (rendered)
[hos host] vk: texture #71 at 0x10000000000 beside #67: 138x96x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1, the other 154x98x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1 (rendered)
[hos host] vk: texture #75 at 0x10000000000 beside #6: 106x105x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1, the other 1920x1080x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1 (rendered)
[hos host] vk: texture #75 at 0x10000000000 beside #67: 106x105x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1, the other 154x98x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1 (rendered)
[hos host] vk: texture #75 at 0x10000000000 beside #71: 106x105x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1, the other 138x96x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1 (rendered)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.06
[hos host] vk: texture #77 at 0x10000000000 beside #6: 1280x720x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1, the other 1920x1080x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1 (rendered)
[hos host] vk: texture #77 at 0x10000000000 beside #67: 1280x720x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1, the other 154x98x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1 (rendered)
[hos host] vk: texture #77 at 0x10000000000 beside #71: 1280x720x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1, the other 138x96x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1 (rendered)
[hos host] vk: texture #77 at 0x10000000000 beside #75: 1280x720x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1, the other 106x105x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1 (rendered)
[hos host] vk: staging arenas: 2 (64 MB in this one)
[hos host] vk: sampler anisotropy: the game asks for 1 (min filter 3, mip filter nearest, LOD bias 0; made with 16)
[hos Resource Memory] mem: the game's mapped pages 2560 MB (peak 2560); heap 6894 MB; the console's total 9809 MB
[hos host] vk: sampler 318 is nearest: min filter 2, mag filter 0, wrap 7/7/7, lod -1000..1000 bias -0.5, aniso 1, compare 0
[hos host] vk: sampler anisotropy: the game asks for 1 (min filter 2, mip filter nearest, LOD bias -0.5; made with 16)
[hos host] vk: slow submit: 19.6 ms: draw 1.6 texture lookups 6.7 uploads 6.5
[hos host] vk: a frame: 2 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 0.81, present 0.04, draw 0.11, descriptors 0.05, texture lookups 0.07, uploads 0.06, pipelines 0.00, programs 0.02, commands 0.03, dispatch 0.05, memory sync 0.35, queue submit 0.17, slot wait 0.01
[hos host] vk: a frame: mirrors 11 (94 MB): 1.61 MB synced in 25.4 copies, 39.55 MB written back
[hos host] vk: 1320 presents, 232.3 fps; a frame: 43 draws (0 skipped), 14 dispatches, 6 passes, 17 barriers, 6 submits, 0.6 uploads (0.2 MB), 5 ub updates (3 overlays), GPU-bound wait 0.0 ms (recording slots only); 6932 pipelines (1216 ms), 0 programs (0 failed), 129 textures (164 MB)
[hos host] vk: host time in GPU resource waits: 0.64 ms a frame (fences 0.01, timelines 0.63, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 43.1 full barriers recorded, 32.5 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 13.5; 0x10: 0.7; 0x12: 3.1;
[hos host] vk: GPU time 2.1 ms a frame (the longest submission 3.7 ms); 0.6 textures made a frame
[hos host] vk: a frame: 0.14 MB unswizzled on the CPU in 0.06 ms
[hos OptimizeChangeBanc] [debug] nvn: 1 copies of recordings whose control memory was reused let go (21593 live)
[hos host] vk: mirror syncs (600 submits): 1302 dirty pages from their submits' captures, 28691 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 73 runs, 2887.2 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 22420 in captures, 1656 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 56 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos Presentation Thread] vk: capture: a submit 0.10 ms (lock 0.03, scan 0.04 over 2068 ranges, 1584 MB), 167 pages written, 167 copied (0.7 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (90 MB), 10 spare buffers, 56 texture pages copied (0 MB)
[hos AudioFrameworkThread] audio: voice 10: 48000 Hz, 1 channels, format 6, parameter 0x1089637e00 (32 bytes) at 6683.1 s
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.05
[hos host] vk: sparse mirrors: 7, 94 MB with memory of 120 MB (25 MB spared); blocks given memory later 37, given back 2; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 13 binds (1.5 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 296 dirty pages from their submits' captures, 28864 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 69 runs, 2729.0 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 20999 in captures, 679 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 9 live (144 MB), 0 retired still imported (0 MB), 1 retired given back (20 MB)
[hos host] vk: 3 textures retired (130 left, 164 MB): budget 0, drawn over 3, dead targets 0
[hos OptimizeChangeBanc] [debug] nvn: 1 copies of recordings whose control memory was reused let go (24387 live)
[hos AudioFrameworkThread] audio: voice 11: 48000 Hz, 1 channels, format 6, parameter 0x1089638040 (32 bytes) at 6683.3 s
[hos OptimizeChangeBanc] nvn: 100000 recordings made, 24957 live copies (2.6 MB), 53 texture copies; 2 command buffers' segments (0.3 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: 3752 programs from the program cache
[hos host] vk: a frame: 9 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.04, present 0.03, draw 0.23, descriptors 0.08, texture lookups 0.01, uploads 0.00, pipelines 0.01, programs 0.02, commands 0.09, dispatch 0.05, memory sync 0.47, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 11 (94 MB): 1.68 MB synced in 31.4 copies, 39.55 MB written back
[hos host] vk: 1440 presents, 233.4 fps; a frame: 138 draws (0 skipped), 14 dispatches, 17 passes, 31 barriers, 6 submits, 0.0 uploads (0.0 MB), 21 ub updates (11 overlays), GPU-bound wait 0.0 ms (recording slots only); 7183 pipelines (1291 ms), 0 programs (0 failed), 130 textures (164 MB)
[hos host] vk: host time in GPU resource waits: 0.92 ms a frame (fences 0.01, timelines 0.91, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 75.8 full barriers recorded, 49.8 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 15.0; 0x10: 3.0; 0x12: 13.0;
[hos host] vk: GPU time 2.4 ms a frame (the longest submission 3.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.01 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.04, scan 0.04 over 2212 ranges, 1643 MB), 170 pages written, 170 copied (0.7 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (66 MB), 9 spare buffers, 56 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 3675 dirty pages from their submits' captures, 25466 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 68 runs, 2689.5 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 21239 in captures, 427 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.06
[hos host] vk: recorder: 437442 packets run in 10.0 s (busy 0.13 s, spun idle 1.21 s, slept 6564 times, 1595 of them under 200 us), 0 calls made directly (no room); the replay waited for it 34827 times, 45.32 ms in all, the longest 0.21 ms; vkResetDescriptorPool 11645/18.07 ms (max 0.07), replay_mu unlock 11477/17.68 ms (max 0.21), vkEndCommandBuffer 11695/9.50 ms (max 0.05), vkQueueBindSparse 8/0.06 ms (max 0.01), vkDestroyShaderModule 2/0.01 ms (max 0.01)
[hos sead::MainThread] nvn: GPU waits in 5 s: 288 sync waits (302 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.04 over 2212 ranges, 1643 MB), 152 pages written, 152 copied (0.6 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (72 MB), 6 spare buffers, 56 texture pages copied (0 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 58 KB; 0 made on demand (0 MB kept now); c1 stages: at most 3 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 7, 94 MB with memory of 120 MB (25 MB spared); blocks given memory later 37, given back 2; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 13 binds (1.5 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 93 dirty pages from their submits' captures, 29278 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 71 runs, 2808.1 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 21688 in captures, 0 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 9 live (144 MB), 0 retired still imported (0 MB), 1 retired given back (20 MB)
[hos host] vk: a frame: 9 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 0.64, present 0.03, draw 0.19, descriptors 0.07, texture lookups 0.01, uploads 0.00, pipelines 0.01, programs 0.02, commands 0.07, dispatch 0.04, memory sync 0.17, queue submit 0.16, slot wait 0.02
[hos host] vk: a frame: mirrors 11 (94 MB): 1.63 MB synced in 30.8 copies, 39.55 MB written back
[hos host] vk: 1560 presents, 243.0 fps; a frame: 138 draws (0 skipped), 14 dispatches, 17 passes, 31 barriers, 6 submits, 0.0 uploads (0.0 MB), 21 ub updates (11 overlays), GPU-bound wait 0.0 ms (recording slots only); 7203 pipelines (1295 ms), 0 programs (0 failed), 130 textures (164 MB)
[hos host] vk: host time in GPU resource waits: 0.52 ms a frame (fences 0.01, timelines 0.51, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 75.5 full barriers recorded, 49.5 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 15.0; 0x10: 3.0; 0x12: 13.0;
[hos host] vk: GPU time 2.5 ms a frame (the longest submission 3.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos host] vk: mirror syncs (600 submits): 881 dirty pages from their submits' captures, 28478 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 71 runs, 2808.1 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 21688 in captures, 0 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.04 over 2212 ranges, 1643 MB), 152 pages written, 152 copied (0.6 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (66 MB), 9 spare buffers, 56 texture pages copied (0 MB)
[hos host] audio: 986 blocks played in the first 10 s, loudest sample 7631 of 32767
[hos host] vk: a frame: 9 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 0.59, present 0.03, draw 0.19, descriptors 0.07, texture lookups 0.01, uploads 0.00, pipelines 0.01, programs 0.02, commands 0.08, dispatch 0.04, memory sync 0.13, queue submit 0.16, slot wait 0.02
[hos host] vk: a frame: mirrors 11 (94 MB): 1.62 MB synced in 30.5 copies, 39.55 MB written back
[hos host] vk: 1680 presents, 239.9 fps; a frame: 139 draws (0 skipped), 14 dispatches, 17 passes, 31 barriers, 6 submits, 0.0 uploads (0.0 MB), 21 ub updates (11 overlays), GPU-bound wait 0.0 ms (recording slots only); 7203 pipelines (1295 ms), 0 programs (0 failed), 130 textures (164 MB)
[hos host] vk: host time in GPU resource waits: 0.23 ms a frame (fences 0.01, timelines 0.22, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 75.4 full barriers recorded, 49.4 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 15.0; 0x10: 3.0; 0x12: 13.0;
[hos host] vk: GPU time 2.4 ms a frame (the longest submission 3.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: queues ordered by their events: 6000 submissions stopped at a wait, 5999 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 6724, not met 0; captures at a CPU event's wait 959, 0 of them at a wait met on arrival
[hos host] vk: sparse mirrors: 7, 94 MB with memory of 120 MB (25 MB spared); blocks given memory later 37, given back 2; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 13 binds (1.5 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 846 dirty pages from their submits' captures, 28526 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 71 runs, 2808.1 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 21688 in captures, 0 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 9 live (144 MB), 0 retired still imported (0 MB), 1 retired given back (20 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.04 over 2212 ranges, 1643 MB), 151 pages written, 151 copied (0.6 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (90 MB), 8 spare buffers, 56 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 241 dirty pages from their submits' captures, 29089 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 71 runs, 2808.1 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 21592 in captures, 96 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: memory: working set 9153 MB (peak 9576), private 13661 MB, staging 128 MB in 2 arenas
[hos host] vk: memory heaps: heap 0 (device): 78 blocks 3020 MB, 1756 allocations 620 MB; used 3555 of 15280 MB; heap 1 (system): 9 blocks 384 MB, 36 allocations 342 MB; used 588 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 2 images 31 MB; 2 free ranges, the largest 96 MB
[hos host] vk: image blocks (render targets): 1 blocks 128 MB, 11 images 74 MB; 1 free ranges, the largest 53 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 120 images 92 MB; 25 free ranges, the largest 128 MB
[hos host] vk: render target images: 0 reused from the pool, 11 made new, 0 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 3555 MB used of 15280 MB allowed (2399 MB of it free in the blocks); textures 167 MB (budget 10928 MB), 131 textures
[hos host] vk: textures: decoded ASTC 30 MB, rendered 114 MB (34 drawn in one frame, kept: 10879 KB), other 6 MB; used in the last 8 presents 130 MB
[hos host] vk: 14 MB: 0x1005f37000 2560x1440x1 x1 levels 1 NVN 0x25 rendered, last used 3 presents ago
[hos host] vk: 14 MB: 0x1005037000 2560x1440x1 x1 levels 1 NVN 0x25 rendered, last used 1 presents ago
[hos host] vk: 14 MB: 0x1004137000 2560x1440x1 x1 levels 1 NVN 0x25 rendered, last used 2 presents ago
[hos host] vk: 14 MB: 0x1001f0ffe00 2560x1440x1 x1 levels 1 NVN 0x3f rendered, last used 1 presents ago
[hos host] vk: 14 MB: 0x10000348400 2560x1440x1 x1 levels 1 NVN 0x38 rendered, last used 1 presents ago
[hos host] vk: 8 MB: 0x7fcd59d200 1664x1280x1 x1 levels 1 NVN 0x87 ASTC, last used 503 presents ago
[hos host] vk: 7 MB: 0x1075e31000 1920x1080x1 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk: 7 MB: 0x7fc9d18400 1440x1440x1 x1 levels 1 NVN 0x87 ASTC, last used 1 presents ago
[hos Presentation Thread] vk: presents after the CPU's signal (600): 324 waited for it, 1.00 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos host] vk: status: 600 frames, the slowest 27.8 ms; VRAM 3.5 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 0 program records loaded (0.0 ms), 0 new graphics pipelines, pipelines from the driver's cache 0, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 3441 queued, 3441 loaded (median 0.51 ms, 99th percentile 3.27 ms, worst 45.66 ms, 2750 ms and 845.0 MB read in all); 4391 programs (623 of them compute variants without their code, 0 graphics programs no note names), 7088 graphics pipelines (0 not in a cache), 408 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 36 pipelines made at create taken by draws; 1951 create calls with nothing kept for their stages, 0 before the index; units 5392 (3441 ready, 0 loading), 9794 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 408 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 9 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 0.59, present 0.03, draw 0.19, descriptors 0.07, texture lookups 0.01, uploads 0.00, pipelines 0.01, programs 0.02, commands 0.07, dispatch 0.04, memory sync 0.13, queue submit 0.16, slot wait 0.02
[hos host] vk: a frame: mirrors 11 (94 MB): 1.60 MB synced in 30.5 copies, 39.55 MB written back
[hos host] vk: 1800 presents, 240.0 fps; a frame: 138 draws (0 skipped), 14 dispatches, 17 passes, 31 barriers, 6 submits, 0.0 uploads (0.0 MB), 21 ub updates (11 overlays), GPU-bound wait 0.0 ms (recording slots only); 7203 pipelines (1295 ms), 0 programs (0 failed), 131 textures (167 MB)
[hos host] vk: host time in GPU resource waits: 0.29 ms a frame (fences 0.01, timelines 0.28, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 75.5 full barriers recorded, 49.5 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 15.0; 0x10: 3.0; 0x12: 13.0;
[hos host] vk: GPU time 2.5 ms a frame (the longest submission 3.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 4.21 ms a frame): its jobs 1.18 ms a frame (submits 0.68, presents 0.25, others 0.25), idle 3.03; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 27.65 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 331 captures at a CPU signal; the submits' waits read in 0.003 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 1.19 ms after its hand-over (22.00 at most)
[hos host] vk: texture #138 at 0x107cdd2600 beside #119: 256x32x1 x1 levels 1 layout 0x80000100 class 0x40001 NVN 0x1 target 1, the other 256x39x1 x1 levels 1 layout 0x80000100 class 0x40001 NVN 0x1 target 1
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 23 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: texture #140 at 0x107cdca600 beside #117: 256x46x1 x1 levels 1 layout 0x80000100 class 0x40001 NVN 0x1 target 1, the other 256x39x1 x1 levels 1 layout 0x80000100 class 0x40001 NVN 0x1 target 1
[hos host] vk: (its written part: 9 of 9 KB readable, 2194 bytes not zero; levels L0)
[hos host] vk: texture 0x107cdaf600 256x39x1 x1 levels 1 NVN 0x1 (9 KB of storage) re-uploaded (its memory was written; flags 0x44): what the CPU wrote, 9 KB of it
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.04 over 2216 ranges, 1645 MB), 150 pages written, 150 copied (0.6 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (96 MB), 10 spare buffers, 56 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 7, 94 MB with memory of 120 MB (25 MB spared); blocks given memory later 37, given back 2; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 13 binds (1.5 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 103 dirty pages from their submits' captures, 28259 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 73 runs, 2887.2 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 21692 in captures, 0 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 9 live (144 MB), 0 retired still imported (0 MB), 1 retired given back (20 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 58 KB; 0 made on demand (0 MB kept now); c1 stages: at most 4 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 201 dirty pages from their submits' captures, 28208 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 78 runs, 3085.0 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 24095 in captures, 0 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.04 over 2228 ranges, 1646 MB), 136 pages written, 136 copied (0.5 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (94 MB), 11 spare buffers, 56 texture pages copied (0 MB)
[hos host] vk: a frame: 2 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 0.44, present 0.04, draw 0.12, descriptors 0.04, texture lookups 0.01, uploads 0.00, pipelines 0.01, programs 0.01, commands 0.04, dispatch 0.04, memory sync 0.16, queue submit 0.15, slot wait 0.01
[hos host] vk: a frame: mirrors 11 (94 MB): 1.44 MB synced in 31.4 copies, 39.55 MB written back
[hos host] vk: 1920 presents, 240.2 fps; a frame: 61 draws (0 skipped), 14 dispatches, 16 passes, 31 barriers, 6 submits, 0.1 uploads (0.0 MB), 21 ub updates (11 overlays), GPU-bound wait 0.0 ms (recording slots only); 7268 pipelines (1306 ms), 0 programs (0 failed), 141 textures (168 MB)
[hos host] vk: host time in GPU resource waits: 0.25 ms a frame (fences 0.01, timelines 0.24, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 73.0 full barriers recorded, 46.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 15.0; 0x10: 3.0; 0x12: 13.0;
[hos host] vk: GPU time 2.3 ms a frame (the longest submission 3.8 ms); 0.1 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 7, 94 MB with memory of 120 MB (25 MB spared); blocks given memory later 37, given back 2; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 13 binds (1.5 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 95 dirty pages from their submits' captures, 28430 from earlier ones', 0 from guest memory as it was at the replay; 24 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 79 runs, 3124.5 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 24098 in captures, 0 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 9 live (144 MB), 0 retired still imported (0 MB), 1 retired given back (20 MB)
[hos nn.npln.Worker] mutex 0x100ac110c8 (obj 00000153CA351410): nn.npln.Worker waiting 10 s; held by nn.npln.Worker (count 2, 1 waiting)
[hos Presentation Thread] vi: 1996 frames presented (238.8 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1193, 15.5-17.8 0, 17.8-22 0, 22-30 1, 30-40 0, over 40 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.04 over 2228 ranges, 1646 MB), 139 pages written, 139 copied (0.5 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (66 MB), 9 spare buffers, 56 texture pages copied (0 MB)
[hos host] hid: SDL controller support ready (DualSense, DualShock 4, Switch Pro, Xbox and others)
[hos host] hid: controller "Xbox One Controller" connected (SDL); guid=0300fa675e040000ff02000000007801; mapping=available; mapping-name=""
[hos host] hid: guid=0300fa675e040000ff02000000007801; mapping-string[1/1]="0300fa675e040000ff02000000007801,,a:b0,b:b1,back:b6,dpdown:h0.4,dpleft:h0.8,dpright:h0.2,dpup:h0.1,guide:b10,leftshoulder:b4,leftstick:b8,lefttrigger:a2,leftx:a0,lefty:a1,rightshoulder:b5,rightstick:b9,righttrigger:a5,rightx:a3,righty:a4,start:b7,x:b2,y:b3,platform:Windows,"
[hos ModuleSystemWorker2] hid: 1 controller through SDL
[hos BaseProcExecutor1] vcores: 309824 takes, 75393 waits (mean 35 us, longest 90.3 ms), 34923 kicks, 33944 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: a frame: 1 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 0.38, present 0.03, draw 0.10, descriptors 0.04, texture lookups 0.01, uploads 0.00, pipelines 0.00, programs 0.01, commands 0.04, dispatch 0.04, memory sync 0.12, queue submit 0.14, slot wait 0.01
[hos host] vk: a frame: mirrors 11 (94 MB): 1.40 MB synced in 30.5 copies, 39.55 MB written back
[hos host] vk: 2040 presents, 240.3 fps; a frame: 56 draws (0 skipped), 14 dispatches, 16 passes, 31 barriers, 6 submits, 0.0 uploads (0.0 MB), 21 ub updates (11 overlays), GPU-bound wait 0.0 ms (recording slots only); 7268 pipelines (1306 ms), 0 programs (0 failed), 141 textures (168 MB)
[hos host] vk: host time in GPU resource waits: 0.22 ms a frame (fences 0.01, timelines 0.21, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 72.6 full barriers recorded, 45.6 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 15.0; 0x10: 3.0; 0x12: 13.0;
[hos host] vk: GPU time 2.4 ms a frame (the longest submission 3.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror syncs (600 submits): 1625 dirty pages from their submits' captures, 26828 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 78 runs, 3085.0 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 24096 in captures, 0 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.04 over 2228 ranges, 1646 MB), 139 pages written, 139 copied (0.5 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (90 MB), 7 spare buffers, 56 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: sparse mirrors: 7, 94 MB with memory of 120 MB (25 MB spared); blocks given memory later 37, given back 2; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 13 binds (1.5 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 80 dirty pages from their submits' captures, 28370 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 78 runs, 3085.0 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 24096 in captures, 0 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 9 live (144 MB), 0 retired still imported (0 MB), 1 retired given back (20 MB)
[hos host] vk: a frame: 1 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 0.41, present 0.03, draw 0.10, descriptors 0.04, texture lookups 0.01, uploads 0.00, pipelines 0.01, programs 0.01, commands 0.04, dispatch 0.04, memory sync 0.13, queue submit 0.15, slot wait 0.01
[hos host] vk: a frame: mirrors 11 (94 MB): 1.44 MB synced in 30.5 copies, 39.55 MB written back
[hos host] vk: 2160 presents, 239.7 fps; a frame: 56 draws (0 skipped), 14 dispatches, 16 passes, 31 barriers, 6 submits, 0.0 uploads (0.0 MB), 21 ub updates (11 overlays), GPU-bound wait 0.0 ms (recording slots only); 7268 pipelines (1306 ms), 0 programs (0 failed), 142 textures (168 MB)
[hos host] vk: host time in GPU resource waits: 0.24 ms a frame (fences 0.01, timelines 0.23, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 72.7 full barriers recorded, 45.7 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 15.0; 0x10: 3.0; 0x12: 13.0;
[hos host] vk: GPU time 2.4 ms a frame (the longest submission 3.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.05 over 2228 ranges, 1646 MB), 138 pages written, 138 copied (0.5 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (70 MB), 9 spare buffers, 56 texture pages copied (0 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos host] vk: mirror syncs (600 submits): 211 dirty pages from their submits' captures, 27364 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 78 runs, 3085.0 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 23160 in captures, 62 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.04 over 2228 ranges, 1646 MB), 137 pages written, 137 copied (0.5 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (70 MB), 10 spare buffers, 56 texture pages copied (0 MB)
[hos host] vk: a frame: 1 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 0.40, present 0.03, draw 0.10, descriptors 0.04, texture lookups 0.01, uploads 0.00, pipelines 0.00, programs 0.01, commands 0.03, dispatch 0.04, memory sync 0.13, queue submit 0.15, slot wait 0.01
[hos host] vk: a frame: mirrors 11 (94 MB): 1.40 MB synced in 30.5 copies, 39.55 MB written back
[hos host] vk: 2280 presents, 239.9 fps; a frame: 55 draws (0 skipped), 14 dispatches, 16 passes, 31 barriers, 6 submits, 0.0 uploads (0.0 MB), 21 ub updates (11 overlays), GPU-bound wait 0.0 ms (recording slots only); 7268 pipelines (1306 ms), 0 programs (0 failed), 142 textures (168 MB)
[hos host] vk: host time in GPU resource waits: 0.18 ms a frame (fences 0.01, timelines 0.17, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 72.6 full barriers recorded, 45.6 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 15.0; 0x10: 3.0; 0x12: 13.0;
[hos host] vk: GPU time 2.3 ms a frame (the longest submission 3.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 58 KB; 0 made on demand (0 MB kept now); c1 stages: at most 4 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 7, 94 MB with memory of 120 MB (25 MB spared); blocks given memory later 37, given back 2; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 13 binds (1.5 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 88 dirty pages from their submits' captures, 28439 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 79 runs, 3124.5 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 24098 in captures, 0 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 9 live (144 MB), 0 retired still imported (0 MB), 1 retired given back (20 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.04 over 2228 ranges, 1646 MB), 141 pages written, 141 copied (0.5 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (90 MB), 8 spare buffers, 56 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 821 dirty pages from their submits' captures, 27710 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 79 runs, 3124.5 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 24098 in captures, 0 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: memory: working set 9149 MB (peak 9576), private 13682 MB, staging 128 MB in 2 arenas
[hos host] vk: memory heaps: heap 0 (device): 78 blocks 3020 MB, 1767 allocations 621 MB; used 3555 of 15280 MB; heap 1 (system): 9 blocks 384 MB, 36 allocations 342 MB; used 588 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 2 images 31 MB; 2 free ranges, the largest 96 MB
[hos host] vk: image blocks (render targets): 1 blocks 128 MB, 11 images 74 MB; 1 free ranges, the largest 53 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 131 images 93 MB; 25 free ranges, the largest 128 MB
[hos host] vk: render target images: 0 reused from the pool, 11 made new, 0 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 3555 MB used of 15280 MB allowed (2398 MB of it free in the blocks); textures 168 MB (budget 10928 MB), 142 textures
[hos host] vk: textures: decoded ASTC 30 MB, rendered 114 MB (33 drawn in one frame, kept: 9264 KB), other 7 MB; used in the last 8 presents 111 MB
[hos host] vk: 14 MB: 0x1005f37000 2560x1440x1 x1 levels 1 NVN 0x25 rendered, last used 3 presents ago
[hos host] vk: 14 MB: 0x1004137000 2560x1440x1 x1 levels 1 NVN 0x25 rendered, last used 2 presents ago
[hos host] vk: 14 MB: 0x10000348400 2560x1440x1 x1 levels 1 NVN 0x38 rendered, last used 1 presents ago
[hos host] vk: 14 MB: 0x1001f0ffe00 2560x1440x1 x1 levels 1 NVN 0x3f rendered, last used 1 presents ago
[hos host] vk: 14 MB: 0x1005037000 2560x1440x1 x1 levels 1 NVN 0x25 rendered, last used 1 presents ago
[hos host] vk: 8 MB: 0x7fcd59d200 1664x1280x1 x1 levels 1 NVN 0x87 ASTC, last used 1103 presents ago
[hos host] vk: 7 MB: 0x7fc9d18400 1440x1440x1 x1 levels 1 NVN 0x87 ASTC, last used 590 presents ago
[hos host] vk: 7 MB: 0x1075e31000 1920x1080x1 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos Presentation Thread] vk: presents after the CPU's signal (600): 393 waited for it, 0.34 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos host] vk: status: 600 frames, the slowest 7.2 ms; VRAM 3.5 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 0 program records loaded (0.0 ms), 0 new graphics pipelines, pipelines from the driver's cache 0, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 3469 queued, 3469 loaded (median 0.52 ms, 99th percentile 3.27 ms, worst 45.66 ms, 2774 ms and 852.1 MB read in all); 4426 programs (623 of them compute variants without their code, 0 graphics programs no note names), 7153 graphics pipelines (0 not in a cache), 408 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 37 pipelines made at create taken by draws; 1986 create calls with nothing kept for their stages, 0 before the index; units 5455 (3469 ready, 0 loading), 9888 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 408 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 1 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 0.38, present 0.03, draw 0.09, descriptors 0.04, texture lookups 0.01, uploads 0.00, pipelines 0.00, programs 0.01, commands 0.04, dispatch 0.04, memory sync 0.12, queue submit 0.14, slot wait 0.01
[hos host] vk: a frame: mirrors 11 (94 MB): 1.40 MB synced in 30.5 copies, 39.55 MB written back
[hos host] vk: 2400 presents, 239.9 fps; a frame: 55 draws (0 skipped), 14 dispatches, 16 passes, 31 barriers, 6 submits, 0.0 uploads (0.0 MB), 21 ub updates (11 overlays), GPU-bound wait 0.0 ms (recording slots only); 7268 pipelines (1306 ms), 0 programs (0 failed), 142 textures (168 MB)
[hos host] vk: host time in GPU resource waits: 0.16 ms a frame (fences 0.01, timelines 0.15, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 72.6 full barriers recorded, 45.6 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 15.0; 0x10: 3.0; 0x12: 13.0;
[hos host] vk: GPU time 2.4 ms a frame (the longest submission 3.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 4.17 ms a frame): its jobs 0.87 ms a frame (submits 0.44, presents 0.22, others 0.21), idle 3.30; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 28.59 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 397 captures at a CPU signal; the submits' waits read in 0.003 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 0.88 ms after its hand-over (3.39 at most)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.04 over 2228 ranges, 1646 MB), 138 pages written, 138 copied (0.5 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (72 MB), 9 spare buffers, 56 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 7, 94 MB with memory of 120 MB (25 MB spared); blocks given memory later 37, given back 2; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 13 binds (1.5 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 838 dirty pages from their submits' captures, 27610 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 78 runs, 3085.0 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 24096 in captures, 0 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 9 live (144 MB), 0 retired still imported (0 MB), 1 retired given back (20 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #10000: event 0x100d6c8000 mode 0 value 2499 (now 2498) (lr 0x806661f8)
[hos sead::MainThread] nvn: EventSignal (CPU) #5000: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[a64] unimplemented import _ZN2nn5movie8FinalizeEv (lr 0x80df26c0)
[hos host] vk: a frame: 1 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 0.38, present 0.04, draw 0.10, descriptors 0.04, texture lookups 0.01, uploads 0.00, pipelines 0.00, programs 0.01, commands 0.04, dispatch 0.04, memory sync 0.12, queue submit 0.15, slot wait 0.01
[hos host] vk: a frame: mirrors 11 (94 MB): 1.42 MB synced in 30.5 copies, 39.55 MB written back
[hos host] vk: 2520 presents, 240.1 fps; a frame: 55 draws (0 skipped), 14 dispatches, 16 passes, 31 barriers, 6 submits, 0.0 uploads (0.0 MB), 21 ub updates (11 overlays), GPU-bound wait 0.0 ms (recording slots only); 7268 pipelines (1306 ms), 0 programs (0 failed), 142 textures (168 MB)
[hos host] vk: host time in GPU resource waits: 0.23 ms a frame (fences 0.01, timelines 0.22, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 72.7 full barriers recorded, 45.6 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 15.0; 0x10: 3.0; 0x12: 13.0;
[hos host] vk: GPU time 2.5 ms a frame (the longest submission 3.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror syncs (600 submits): 839 dirty pages from their submits' captures, 27679 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 78 runs, 3085.0 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 24096 in captures, 0 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.04 over 2228 ranges, 1646 MB), 141 pages written, 141 copied (0.5 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (94 MB), 6 spare buffers, 56 texture pages copied (0 MB)
[hos MovieOperateThread] video: a movie of 645 pictures on dav1d: 0.7 ms to decode each (worst 26.8), one shown every 16.7 ms; 4 skipped to keep up with its sound; 500 submissions put off while 16 waited
[hos MovieOperateThread] video: the longest wait between two of its pictures 98 ms
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03
[hos host] vk: sparse mirrors: 7, 94 MB with memory of 120 MB (25 MB spared); blocks given memory later 37, given back 2; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 13 binds (1.5 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 45 dirty pages from their submits' captures, 11272 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 32 runs, 1265.6 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 8887 in captures, 0 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 9 live (144 MB), 0 retired still imported (0 MB), 1 retired given back (20 MB)
[hos Presentation Thread] vi: the movie is over: back to the game's frame rate cap 60
[hos sead::MainThread] vk: capture: a submit 0.07 ms (lock 0.01, scan 0.04 over 2237 ranges, 1646 MB), 106 pages written, 106 copied (0.4 MB)
[hos host] vk: a capture taken (ms): all 0.005; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 24 kept (64 MB), 12 spare buffers, 3519 texture pages copied (13 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 0.36, present 0.03, draw 0.06, descriptors 0.02, texture lookups 0.00, uploads 0.00, pipelines 0.00, programs 0.01, commands 0.02, dispatch 0.02, memory sync 0.18, queue submit 0.14, slot wait 0.01
[hos host] vk: a frame: mirrors 11 (94 MB): 0.62 MB synced in 22.2 copies, 17.14 MB written back
[hos host] vk: 2640 presents, 188.8 fps; a frame: 25 draws (0 skipped), 6 dispatches, 7 passes, 13 barriers, 6 submits, 0.0 uploads (0.0 MB), 8 ub updates (5 overlays), GPU-bound wait 0.0 ms (recording slots only); 7352 pipelines (1315 ms), 0 programs (0 failed), 145 textures (168 MB)
[hos host] vk: host time in GPU resource waits: 0.09 ms a frame (fences 0.01, timelines 0.08, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 39.6 full barriers recorded, 26.4 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 6.4; 0x10: 1.1; 0x12: 5.4;
[hos host] vk: GPU time 1.2 ms a frame (the longest submission 3.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 5676 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: 1 textures retired (145 left, 164 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 58 KB; 0 made on demand (0 MB kept now); c1 stages: at most 4 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 32 dirty pages from their submits' captures, 1138 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 0 runs, 0.0 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 0 in captures, 0 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos Presentation Thread] vk: capture: a submit 0.07 ms (lock 0.01, scan 0.04 over 2237 ranges, 1646 MB), 87 pages written, 87 copied (0.3 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (66 MB), 10 spare buffers, 3746 texture pages copied (14 MB)
[hos BaseProcCreateAndDeleteThread] [debug] nvn: 61 copies of recordings whose control memory was reused let go (25750 live)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 0.40, present 0.03, draw 0.03, descriptors 0.01, texture lookups 0.00, uploads 0.00, pipelines 0.00, programs 0.00, commands 0.01, dispatch 0.00, memory sync 0.26, queue submit 0.14, slot wait 0.01
[hos host] vk: a frame: mirrors 11 (30 MB): 0.06 MB synced in 15.7 copies, 0.00 MB written back
[hos host] vk: 2760 presents, 60.0 fps; a frame: 5 draws (0 skipped), 0 dispatches, 2 passes, 1 barriers, 6 submits, 0.0 uploads (0.0 MB), 1 ub updates (1 overlays), GPU-bound wait 0.0 ms (recording slots only); 7657 pipelines (1363 ms), 0 programs (0 failed), 145 textures (164 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 18.7 full barriers recorded, 13.7 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x12: 1.0;
[hos host] vk: GPU time 0.1 ms a frame (the longest submission 0.2 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vi: 2771 frames presented (154.9 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 636, 15.5-17.8 136, 17.8-22 1, 22-30 2, 30-40 0, over 40 0
[hos host] vk: sparse mirrors: 7, 30 MB with memory of 120 MB (89 MB spared); blocks given memory later 37, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 15 binds (1.8 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 49 dirty pages from their submits' captures, 1248 from earlier ones', 0 from guest memory as it was at the replay; 24 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 0 runs, 0.0 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 0 in captures, 0 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 9 live (144 MB), 0 retired still imported (0 MB), 1 retired given back (20 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 5824 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos nn.npln.Callback] vcores: 200048 takes, 40657 waits (mean 74 us, longest 103.1 ms), 18035 kicks, 17408 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.04
[hos Presentation Thread] vk: capture: a submit 0.07 ms (lock 0.02, scan 0.03 over 1525 ranges, 1196 MB), 115 pages written, 115 copied (0.4 MB)
[hos host] vk: a capture taken (ms): all 0.005; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 25 kept (66 MB), 8 spare buffers, 6288 texture pages copied (24 MB)
[hos host] vk: mirror syncs (600 submits): 73 dirty pages from their submits' captures, 1278 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 0 runs, 0.0 MB compared; 0 pages read into the shadows; 68 MB of shadows; pages the shadows knew that the CPU wrote: 0 in captures, 0 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 5220 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: 4667 programs from the program cache
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 0.47, present 0.04, draw 0.04, descriptors 0.01, texture lookups 0.00, uploads 0.00, pipelines 0.00, programs 0.00, commands 0.02, dispatch 0.00, memory sync 0.33, queue submit 0.14, slot wait 0.01
[hos host] vk: a frame: mirrors 11 (30 MB): 0.06 MB synced in 16.5 copies, 0.00 MB written back
[hos host] vk: 2880 presents, 60.0 fps; a frame: 5 draws (0 skipped), 0 dispatches, 2 passes, 1 barriers, 6 submits, 0.0 uploads (0.0 MB), 1 ub updates (1 overlays), GPU-bound wait 0.0 ms (recording slots only); 8319 pipelines (1504 ms), 0 programs (0 failed), 145 textures (164 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 18.5 full barriers recorded, 13.5 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x12: 1.0;
[hos host] vk: GPU time 0.3 ms a frame (the longest submission 0.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.06
[hos ModuleSystemWorker2] nvn: the game reports counter type 1 (lr 0x800876dc)
[hos host] vk: sampler 407 is nearest: min filter 2, mag filter 0, wrap 7/7/7, lod 0..15 bias 0, aniso 1, compare 0
[hos host] vk: sampler anisotropy: the game asks for 1 (min filter 2, mip filter nearest, LOD bias 0; made with 16)
[hos host] vk: a draw (program 3e753d8ad4012b7b) samples the colour target it writes (130x130, read undefined where it writes)
[hos host] vk: a draw (program 3e753d8ad4012b7b) samples the colour target it writes (65x65, read undefined where it writes)
[hos host] vk: a draw (program 3e753d8ad4012b7b) samples the colour target it writes (32x32, read undefined where it writes)
[hos host] vk: a draw (program 3e753d8ad4012b7b) samples the colour target it writes (16x16, read undefined where it writes)
[hos host] vk: a draw (program 3e753d8ad4012b7b) samples the colour target it writes (8x8, read undefined where it writes)
[hos host] vk: a draw (program 3e753d8ad4012b7b) samples the colour target it writes (4x4, read undefined where it writes)
[hos host] vk: a draw (program 3e753d8ad4012b7b) samples the colour target it writes (2x2, read undefined where it writes)
[hos host] vk: a draw (program 3e753d8ad4012b7b) samples the colour target it writes (1x1, read undefined where it writes)
[hos host] vk: a draw (program 3e753d8ad4012b7b) samples the colour target it writes (130x130, read undefined where it writes)
[hos host] vk: a draw (program 3e753d8ad4012b7b) samples the colour target it writes (65x65, read undefined where it writes)
[hos host] vk: a draw (program 3e753d8ad4012b7b) samples the colour target it writes (32x32, read undefined where it writes)
[hos host] vk: a draw (program 3e753d8ad4012b7b) samples the colour target it writes (16x16, read undefined where it writes)
[hos host] vk: texture #171 at 0x10000000000 beside #6: 256x144x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 1920x1080x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1 (rendered)
[hos host] vk: mesh draw kind 0: 0 1 560, indirect 0 count 0 max 0 stride 0
[hos host] vk: mesh draw: program 1964, 3 stages: [0: stage 1, code 0x7ffb119000, sph type 5 bits24-25 0, isbe 0 payload 0] [1: stage 6, code 0x7ffae43c00, sph type 1 bits24-25 0, isbe 1 payload 256] [2: stage 7, code 0x7ffae4fd00, sph type 3 bits24-25 2, isbe 1 payload 256]
[hos host] vk: import 2.1 ms: commit+properties 0.1, buffer 0.0, allocate 2.0, bind+address 0.0
[hos host] vk: pool 0x104e58b300+0x60 imported in 2.1 ms as 0x104e000000..0x104f800000 (13 imports, 13 ms in all)
[hos host] vk: mesh draw kind 0: 0 4 512, indirect 0 count 0 max 0 stride 0
[hos host] vk: mesh draw: program 1964, 3 stages: [0: stage 1, code 0x7ffb119000, sph type 5 bits24-25 0, isbe 0 payload 0] [1: stage 6, code 0x7ffae43c00, sph type 1 bits24-25 0, isbe 1 payload 256] [2: stage 7, code 0x7ffae4fd00, sph type 3 bits24-25 2, isbe 1 payload 256]
[hos host] vk: mesh draw kind 0: 0 4 512, indirect 0 count 0 max 0 stride 0
[hos host] vk: mesh draw: program 1964, 3 stages: [0: stage 1, code 0x7ffb119000, sph type 5 bits24-25 0, isbe 0 payload 0] [1: stage 6, code 0x7ffae43c00, sph type 1 bits24-25 0, isbe 1 payload 256] [2: stage 7, code 0x7ffae4fd00, sph type 3 bits24-25 2, isbe 1 payload 256]
[hos host] vk: mesh draw kind 0: 0 5 512, indirect 0 count 0 max 0 stride 0
[hos host] vk: mesh draw: program 1964, 3 stages: [0: stage 1, code 0x7ffb119000, sph type 5 bits24-25 0, isbe 0 payload 0] [1: stage 6, code 0x7ffae43c00, sph type 1 bits24-25 0, isbe 1 payload 256] [2: stage 7, code 0x7ffae4fd00, sph type 3 bits24-25 2, isbe 1 payload 256]
[hos host] vk: mesh draw kind 0: 0 3 512, indirect 0 count 0 max 0 stride 0
[hos host] vk: mesh draw: program 1964, 3 stages: [0: stage 1, code 0x7ffb119000, sph type 5 bits24-25 0, isbe 0 payload 0] [1: stage 6, code 0x7ffae43c00, sph type 1 bits24-25 0, isbe 1 payload 256] [2: stage 7, code 0x7ffae4fd00, sph type 3 bits24-25 2, isbe 1 payload 256]
[hos host] vk: mesh draw kind 0: 0 15 512, indirect 0 count 0 max 0 stride 0
[hos host] vk: mesh draw: program 1964, 3 stages: [0: stage 1, code 0x7ffb119000, sph type 5 bits24-25 0, isbe 0 payload 0] [1: stage 6, code 0x7ffae43c00, sph type 1 bits24-25 0, isbe 1 payload 256] [2: stage 7, code 0x7ffae4fd00, sph type 3 bits24-25 2, isbe 1 payload 256]
[hos host] vk: mesh draw kind 0: 0 3 512, indirect 0 count 0 max 0 stride 0
[hos host] vk: mesh draw kind 0: 0 4 512, indirect 0 count 0 max 0 stride 0
[hos host] vk: sampler anisotropy: the game asks for 2 (min filter 5, mip filter linear, LOD bias -0.5; made with 16)
[hos host] vk: texture #195 at 0x10000000000 beside #6: 128x128x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 1920x1080x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1 (rendered)
[hos host] vk: texture #195 at 0x10000000000 beside #171: 128x128x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 256x144x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: big ASTC textures are kept as BC3 (re-encoded on the GPU; ASTC as RGBA8 or RX_VK_ASTC_RGBA8=1: as RGBA8)
[hos host] vk: texture 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e -> vk 137 (ASTC decoded) (191 textures, 587 MB)
[hos host] vk: texture 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 -> vk 137 (ASTC decoded) (192 textures, 850 MB)
[hos host] vk: staging arenas: 3 (64 MB in this one)
[hos host] vk: texture #203 at 0x113755c000 beside #181: 4096x4096x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0xa target 1, the other 4096x4096x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: table entry bound again at frame 2905: prog 4f1e7494c7a00723 ssbo 0 of 3 (c0+0x880) addr 0x108c703000 size 0x79b6000 (before 0)
[hos host] vk: texture #223 at 0x10000000000 beside #6: 1707x960x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 1920x1080x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1 (rendered)
[hos host] vk: texture #223 at 0x10000000000 beside #171: 1707x960x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 256x144x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: texture #223 at 0x10000000000 beside #195: 1707x960x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 128x128x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: slow submit: 91.2 ms: draw 22.7 descriptors 16.3 texture lookups 18.2 uploads 11.7 programs 3.1 dispatch 4.5
[hos host] vk: import 4.0 ms: commit+properties 0.1, buffer 0.0, allocate 3.9, bind+address 0.0
[hos host] vk: pool 0x117883d100+0x700 imported in 4.0 ms as 0x1178400000..0x117c400000 (39 imports, 29 ms in all)
[hos host] vk: import 3.3 ms: commit+properties 0.1, buffer 0.0, allocate 3.1, bind+address 0.0
[hos host] vk: pool 0x117e725000+0x43000 imported in 3.3 ms as 0x1178400000..0x117f000000 (40 imports, 32 ms in all)
[hos host] vk: pool 0x1178400000 remade larger (2 retired)
[hos host] vk: pool 0x1178400000..0x117f000000: mirror made with the GPU's contents of 1 retired pool(s)
[hos host] vk: sampler anisotropy: the game asks for 1 (min filter 1, mip filter nearest, LOD bias 0; made with 16)
[hos host] vk: import 3.0 ms: commit+properties 0.2, buffer 0.0, allocate 2.9, bind+address 0.0
[hos host] vk: pool 0x1146b29e00+0x80 imported in 3.0 ms as 0x1145400000..0x1147c00000 (41 imports, 35 ms in all)
[hos host] vk: import 2.2 ms: commit+properties 0.0, buffer 0.0, allocate 2.2, bind+address 0.0
[hos host] vk: pool 0x115bd19580+0x1b580 imported in 2.2 ms as 0x1159c00000..0x115c000000 (42 imports, 38 ms in all)
[hos host] vk: sampler 419 is nearest: min filter 4, mag filter 0, wrap 7/7/7, lod 0..15 bias 0, aniso 1, compare 0
[hos host] vk: slow submit: 34.3 ms: texture lookups 1.1 uploads 1.1 dispatch 34.2
[hos host] vk: RX_VK_RECORDER=thread: vkCmdCopyBufferToImage did not fit in the room a packet is given (81920 bytes): made directly once the recorder had run what was before it (logged once)
[hos host] vk: a clear after 1 draws of its pass (1707x960, 1 colour targets + depth, last program 3bde059fb051af1f): a pass of its own
[hos host] vk: sampler 406 is nearest: min filter 0, mag filter 0, wrap 7/7/7, lod 0..15 bias 0, aniso 1, compare 0
[hos host] vk: sampler anisotropy: the game asks for 1 (min filter 0, mip filter nearest, LOD bias 0; made with 16)
[hos host] vk: write-back diff: a shadow for pool 0x113b400000 (24 MB; 92 MB of shadows)
[hos host] vk: write-back diff: a shadow for pool 0x1178400000 (108 MB; 200 MB of shadows)
[hos host] vk: write-back diff: a shadow for pool 0x1159c00000 (36 MB; 236 MB of shadows)
[hos host] vk: slow submit: 25.5 ms: draw 11.1 descriptors 6.6 texture lookups 18.5 uploads 5.9 programs 3.8
[hos host] vk: depth-compare sampler: the game's compare mode 1 function 4 -> compare on op 3 (filters min 1 mag 1)
[hos host] vk: texture 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 -> vk 124 (255 textures, 1455 MB)
[hos host] vk: upload: 12288x12288 NVN 0x32 (288 MB) is all zero: cleared on the GPU (checked in 25.1 ms)
[hos host] vk: slow upload 25.1 ms: #262 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32, 294912 of 294912 KB
[hos host] vk: texture #265 at 0x10007506000 beside #247: 1707x960x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1, the other 640x360x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: texture #268 at 0x10001fd1200 beside #250: 426x240x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1, the other 853x480x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1 (rendered)
[hos host] vk: texture #269 at 0x10007506000 beside #247: 853x480x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 640x360x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: texture #269 at 0x10007506000 beside #265: 853x480x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 1707x960x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1 (rendered)
[hos host] vk: texture #270 at 0x100076b6200 beside #264: 853x480x1 x1 levels 1 layout 0x4 class 0x40008 NVN 0x29 target 1, the other 853x480x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x25 target 1 (rendered)
[hos host] vk: texture #275 at 0x1000203d400 beside #267: 107x60x1 x1 levels 1 layout 0x3 class 0x40001 NVN 0x3 target 1, the other 426x240x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1 (rendered)
[hos host] vk: NVN2 program 3d33bb73d3deee34 (stage 7) lowered with extended registers (577 REGMAP words)
[hos host] vk: staging arenas: 4 (64 MB in this one)
[hos host] vk: NVN2 program 463f42630fce83a0 (stage 7) lowered with extended registers (1539 REGMAP words)
[hos host] vk: NVN2 program 66c494fe4cfa930b (stage 7) lowered with extended registers (1460 REGMAP words)
[hos host] vk: NVN2 program b86297c24c8d8c7a (stage 7) lowered with extended registers (1174 REGMAP words)
[hos host] vk: NVN2 program 354dde838352c262 (stage 7) lowered with extended registers (320 REGMAP words)
[hos host] vk: NVN2 program e3fc8fcf540f7a48 (stage 7) lowered with extended registers (1503 REGMAP words)
[hos host] vk: NVN2 program d38b0d52a94ab5a8 (stage 7) lowered with extended registers (337 REGMAP words)
[hos host] vk: NVN2 program b509ae330829ce02 (stage 7) lowered with extended registers (264 REGMAP words)
[hos host] vk: table entry bound again at frame 2905: prog a5da9f84b72d1471 ssbo 0 of 3 (c0+0x880) addr 0x108c703000 size 0x79b6000 (before 0)
[hos host] vk: table entry bound again at frame 2905: prog 507e946d64f2d55e ssbo 0 of 3 (c0+0x880) addr 0x108c703000 size 0x79b6000 (before 0)
[hos host] vk: NVN2 program 0670633431d18cc9 (stage 7) lowered with extended registers (2308 REGMAP words)
[hos host] vk: depth-compare sampler: the game's compare mode 0 function 0 -> compare on op 3 (filters min 1 mag 1)
[hos host] vk: upload: 4096x4096 NVN 0x32 (32 MB) is all zero: cleared on the GPU (checked in 1.1 ms)
[hos host] vk: NVN2 program db295591c4c3f510 (stage 7) lowered with extended registers (331 REGMAP words)
[hos host] vk: texture #294 at 0x10000d60400 beside #234: 853x480x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1, the other 1707x960x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: texture #296 at 0x10000f10600 beside #295: 480x270x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1, the other 960x540x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1 (rendered)
[hos host] vk: texture #301 at 0x1000111aa00 beside #299: 120x67x1 x1 levels 1 layout 0x3 class 0x40004 NVN 0x3f target 1, the other 240x135x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1 (rendered)
[hos host] vk: texture #303 at 0x1000111aa00 beside #299: 60x33x1 x1 levels 1 layout 0x2 class 0x40004 NVN 0x3f target 1, the other 240x135x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1 (rendered)
[hos host] vk: texture #303 at 0x1000111aa00 beside #301: 60x33x1 x1 levels 1 layout 0x2 class 0x40004 NVN 0x3f target 1, the other 120x67x1 x1 levels 1 layout 0x3 class 0x40004 NVN 0x3f target 1 (rendered)
[hos host] vk: texture #305 at 0x1000111aa00 beside #299: 30x16x1 x1 levels 1 layout 0x1 class 0x40004 NVN 0x3f target 1, the other 240x135x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1 (rendered)
[hos host] vk: texture #305 at 0x1000111aa00 beside #301: 30x16x1 x1 levels 1 layout 0x1 class 0x40004 NVN 0x3f target 1, the other 120x67x1 x1 levels 1 layout 0x3 class 0x40004 NVN 0x3f target 1 (rendered)
[hos host] vk: texture #305 at 0x1000111aa00 beside #303: 30x16x1 x1 levels 1 layout 0x1 class 0x40004 NVN 0x3f target 1, the other 60x33x1 x1 levels 1 layout 0x2 class 0x40004 NVN 0x3f target 1 (rendered)
[hos host] vk: texture #306 at 0x10001e20c00 beside #237: 1707x960x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1, the other 853x480x1 x1 levels 1 layout 0x4 class 0x40002 NVN 0x5 target 1 (rendered)
[hos host] vk: texture #307 at 0x10000d60400 beside #234: 427x240x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x14 target 1, the other 1707x960x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: texture #307 at 0x10000d60400 beside #294: 427x240x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x14 target 1, the other 853x480x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1 (rendered)
[hos host] vk: sampler 267 is nearest: min filter 0, mag filter 0, wrap 5/5/5, lod -1000..1000 bias 0, aniso 1, compare 0
[hos host] vk: network 6676619641320ba7: dispatch 54x30x1, 1 textures 1 images: 1707x960x1/122 2560x1440x1/122
[hos host] vk: slow submit: 73.9 ms: draw 68.6 descriptors 47.4 texture lookups 46.1 uploads 44.0 programs 14.8 commands 6.2 dispatch 16.1
[hos host] vk: write-back diff: a shadow for pool 0x100dc00000 (20 MB; 256 MB of shadows)
[hos host] vk: a frame's uploads took 65 ms: ASTC on the GPU 21 (128.2 MB, 10 ms); unswizzled on the GPU 1 (14.1 MB, 1 ms); on the CPU 71 (420.7 MB, 54 ms); [12288x12288 x1 NVN 0x32 on the CPU 288.0 MB 25 ms] [128x128 x378 NVN 0x4b on the CPU 8.7 MB 9 ms] [1365x1365 x90 NVN 0x80 ASTC on the GPU 56.5 MB 6 ms]
[hos sead::MainThread] nvn: GPU waits in 5 s: 312 sync waits (720 ms), 0 polls timed out (0 ms), 1 queue finishes (0 ms)
[hos host] vk: readback pages refreshed from guest memory: 7 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: import 3.1 ms: commit+properties 0.0, buffer 0.0, allocate 3.1, bind+address 0.0
[hos host] vk: pool 0x102fde0a00+0x180 imported in 3.2 ms as 0x102fc00000..0x1033000000 (49 imports, 44 ms in all)
[hos host] vk: a clear after 1 draws of its pass (1707x960, 1 colour targets + depth, last program 3bde059fb051af1f): a pass of its own
[hos host] vk: (its written part: 0 of 0 KB readable, 96 bytes not zero; levels L0)
[hos host] vk: texture 0x113c8ace00 4x4x1 x1 levels 1 NVN 0x2e (0 KB of storage) re-uploaded (its memory was written; flags 0): what the CPU wrote, 0 KB of it
[hos host] vk: upscaler: network 6676619641320ba7 is the gameplay upscale (1707x960 -> 2560x1440)
[hos host] vk: NVIDIA DLSS: feature 1 made (the first; frame 2906, 33.9 ms of CPU): 1707x960 (1280x720 to 2560x1440) -> 2560x1440, mode 2, preset K
[hos host] vk: upscaler: the scene's camera: near 0.100, far 1000.5, vertical field of view 45.0 degrees
[hos host] vk: DLSS Frame Gen (NGX): available, up to 1 made frames between two of the game's (its runtime: the newest nvngx_dlssg.dll in D:\Games\Longshot\ngx, %USERPROFILE%\AppData\Local\Longshot\ngx)
[hos host] vk: NVIDIA DLSS draws OoT's upscale: 1707x960 -> 2560x1440
[hos host] vk: slow submit: 35.3 ms: dispatch 34.8
[hos host] vk: a clear after 1 draws of its pass (1707x960, 1 colour targets + depth, last program 3bde059fb051af1f): a pass of its own
[hos host] vk: (its written part: 0 of 0 KB readable, 96 bytes not zero; levels L0)
[hos host] vk: texture 0x113c8ace00 4x4x1 x1 levels 1 NVN 0x2e (0 KB of storage) re-uploaded (its memory was written; flags 0): what the CPU wrote, 0 KB of it
[hos host] vk: 9 of 9 small textures the GPU drew written into their memory in 1.8 ms, 1 frames after their copies were recorded, the first #155 0x1168866000 260x260 levels 9 NVN 0xd (9 so far, 2204 KB, 2 ms; 0 left, the CPU wrote their memory since; 0 dropped, drawn over or gone; 0 failed)
[hos host] vk: a clear after 1 draws of its pass (1707x960, 1 colour targets + depth, last program 3bde059fb051af1f): a pass of its own
[hos host] vk: (its written part: 0 of 0 KB readable, 96 bytes not zero; levels L0)
[hos host] vk: texture 0x113c8ace00 4x4x1 x1 levels 1 NVN 0x2e (0 KB of storage) re-uploaded (its memory was written; flags 0): what the CPU wrote, 0 KB of it
[hos host] vk: 8 of 8 small textures the GPU drew written into their memory in 1.2 ms, 1 frames after their copies were recorded, the first #310 0x1169e3e000 260x260 levels 9 NVN 0xd (17 so far, 3880 KB, 3 ms; 0 left, the CPU wrote their memory since; 0 dropped, drawn over or gone; 0 failed)
[hos host] vk: texture #241 0x10002121800 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: a clear after 1 draws of its pass (1707x960, 1 colour targets + depth, last program 3bde059fb051af1f): a pass of its own
[hos host] vk: (its written part: 0 of 0 KB readable, 96 bytes not zero; levels L0)
[hos host] vk: texture 0x113c8ace00 4x4x1 x1 levels 1 NVN 0x2e (0 KB of storage) re-uploaded (its memory was written; flags 0): what the CPU wrote, 0 KB of it
[hos host] vk: 8 of 8 small textures the GPU drew written into their memory in 1.3 ms, 1 frames after their copies were recorded, the first #331 0x116b5f2000 260x260 levels 9 NVN 0xd (25 so far, 5556 KB, 4 ms; 0 left, the CPU wrote their memory since; 0 dropped, drawn over or gone; 0 failed)
[hos host] vk: render targets drawn over from another start, let go: 3 so far (10 MB)
[hos host] vk: 4 textures retired (367 left, 1576 MB): budget 0, drawn over 1, dead targets 3
[hos sead::MainThread] vk: capture: a submit 0.09 ms (lock 0.04, scan 0.03 over 747 ranges, 2252 MB), 132 pages written, 132 copied (0.5 MB)
[hos host] vk: texture #241 0x10002121800 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: a capture taken (ms): all 0.006; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.005, bytes copied 0.000; 25 kept (94 MB), 11 spare buffers, 7755 texture pages copied (30 MB)
[hos host] vk: a clear after 1 draws of its pass (1707x960, 1 colour targets + depth, last program 3bde059fb051af1f): a pass of its own
[hos host] vk: (its written part: 0 of 0 KB readable, 96 bytes not zero; levels L0)
[hos host] vk: texture 0x113c8ace00 4x4x1 x1 levels 1 NVN 0x2e (0 KB of storage) re-uploaded (its memory was written; flags 0): what the CPU wrote, 0 KB of it
[hos host] vk: 8 of 8 small textures the GPU drew written into their memory in 1.2 ms, 1 frames after their copies were recorded, the first #347 0x116d04e000 260x260 levels 9 NVN 0xd (33 so far, 7232 KB, 5 ms; 0 left, the CPU wrote their memory since; 0 dropped, drawn over or gone; 0 failed)
[hos host] vk: mirror of pool 0x1178400000 (64 MB) given back: retired, 60 submissions since its sync, GPU-only data, GPU-written
[hos host] vk: (its written part: 0 of 0 KB readable, 96 bytes not zero; levels L0)
[hos host] vk: texture 0x113c8ace00 4x4x1 x1 levels 1 NVN 0x2e (0 KB of storage) re-uploaded (its memory was written; flags 0): what the CPU wrote, 0 KB of it
[hos host] vk: NVN2 program bc3f20d8b42b27c1 (stage 7) lowered with extended registers (2308 REGMAP words)
[hos host] vk: NVN2 program 40d0c0768e874600 (stage 7) lowered with extended registers (331 REGMAP words)
[hos host] vk: 8 of 8 small textures the GPU drew written into their memory in 1.2 ms, 1 frames after their copies were recorded, the first #363 0x116e916000 260x260 levels 9 NVN 0xd (41 so far, 8908 KB, 7 ms; 0 left, the CPU wrote their memory since; 0 dropped, drawn over or gone; 0 failed)
[hos host] vk: (its written part: 0 of 0 KB readable, 96 bytes not zero; levels L0)
[hos host] vk: texture 0x113c8ace00 4x4x1 x1 levels 1 NVN 0x2e (0 KB of storage) re-uploaded (its memory was written; flags 0): what the CPU wrote, 0 KB of it
[hos host] vk: 1 of 1 small textures the GPU drew written into their memory in 0.3 ms, 1 frames after their copies were recorded, the first #379 0x116fcd2000 260x260 levels 9 NVN 0xd (42 so far, 9117 KB, 7 ms; 0 left, the CPU wrote their memory since; 0 dropped, drawn over or gone; 0 failed)
[hos host] vk: texture #241 0x10002121800 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: (its written part: 0 of 0 KB readable, 96 bytes not zero; levels L0)
[hos host] vk: texture 0x113c8ace00 4x4x1 x1 levels 1 NVN 0x2e (0 KB of storage) re-uploaded (its memory was written; flags 0): what the CPU wrote, 0 KB of it
[hos host] vk: texture #241 0x10002121800 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: (its written part: 0 of 0 KB readable, 96 bytes not zero; levels L0)
[hos host] vk: texture 0x113c8ace00 4x4x1 x1 levels 1 NVN 0x2e (0 KB of storage) re-uploaded (its memory was written; flags 0): what the CPU wrote, 0 KB of it
[hos host] vk: texture #241 0x10002121800 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: (its written part: 0 of 0 KB readable, 96 bytes not zero; levels L0)
[hos host] vk: texture 0x113c8ace00 4x4x1 x1 levels 1 NVN 0x2e (0 KB of storage) re-uploaded (its memory was written; flags 0): what the CPU wrote, 0 KB of it
[hos host] vk: texture #241 0x10002121800 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: (its written part: 0 of 0 KB readable, 96 bytes not zero; levels L0)
[hos host] vk: texture 0x113c8ace00 4x4x1 x1 levels 1 NVN 0x2e (0 KB of storage) re-uploaded (its memory was written; flags 0): what the CPU wrote, 0 KB of it
[hos host] vk: texture #241 0x10002121800 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: (its written part: 0 of 0 KB readable, 96 bytes not zero; levels L0)
[hos host] vk: texture 0x113c8ace00 4x4x1 x1 levels 1 NVN 0x2e (0 KB of storage) re-uploaded (its memory was written; flags 0): what the CPU wrote, 0 KB of it
[hos host] vk: texture #241 0x10002121800 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: (its written part: 0 of 0 KB readable, 96 bytes not zero; levels L0)
[hos host] vk: texture 0x113c8ace00 4x4x1 x1 levels 1 NVN 0x2e (0 KB of storage) re-uploaded (its memory was written; flags 0): what the CPU wrote, 0 KB of it
[hos host] vk: texture #241 0x10002121800 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: (its written part: 0 of 0 KB readable, 96 bytes not zero; levels L0)
[hos host] vk: texture 0x113c8ace00 4x4x1 x1 levels 1 NVN 0x2e (0 KB of storage) re-uploaded (its memory was written; flags 0): what the CPU wrote, 0 KB of it
[hos BaseProcExecutor0] map: Graveyard_Child (child)
[hos BaseProcExecutor0] cheats: inventory probe: Weapon_Sword_Kokiri=1 Weapon_Sword_Master=1 Weapon_Sword_Giant=0 Weapon_Sword_Biggoron=0 Weapon_Shield_Deku=1 Weapon_Shield_Hylian=1 Weapon_Shield_Mirror=0 Armor_Adult_Goron=0 Armor_Adult_Zora=0 Armor_Adult_HeavyBoot=0 Armor_Adult_HoverBoot=0 Item_DekuStick=30 Item_DekuNut=40 Item_Bomb=39 Item_Bombchu=37
[hos BaseProcExecutor0] cheats: inventory probe: Weapon_Range_SlingShot=1 Item_DekuSeed=30 Weapon_Range_Bow=1 Item_Arrow_Normal=21 Item_Arrow_Fire=0 Item_Arrow_Ice=0 Item_Arrow_Light=0 Item_DinFire=1 Item_FaroreWind=1 Item_NayruLove=0 Item_Ocarina_Fairy=1 Item_Ocarina_Time=1 Item_Hookshot=1 Item_Longshot=0 Item_Boomerang=1 Item_GlassTruth=0 Item_MagicBean=3
[hos BaseProcExecutor0] cheats: inventory probe: Item_Hammer=0 Item_Bottle=0 Armor_Child_Mask_Keaton=0 Armor_Child_Mask_Skull=0 Armor_Child_Mask_Spooky=0 Armor_Child_Mask_Bunny=0 Armor_Child_Mask_Goron=0 Armor_Child_Mask_Zora=0 Armor_Child_Mask_Gerudo=0 Armor_Child_Mask_Truth=1 Item_Gauntlet_Goron=1 Armor_Adult_Gauntlet_Silver=0 Armor_Adult_Gauntlet_Gold=0
[hos BaseProcExecutor0] cheats: inventory probe: Item_Scale_Silver=1 Item_Scale_Gold=0 Item_BombBag_Small=1 Item_BombBag_Medium=1 Item_BombBag_Large=1 Item_Quiver_Small=1 Item_Quiver_Medium=0 Item_Quiver_Large=0 Item_BulletBag_Small=1 Item_BulletBag_Medium=1 Item_BulletBag_Large=1 Item_Wallet_Medium=1 Item_Wallet_Large=1 Item_FairyBless_MP=1 Item_FairyBless_MPDouble=0
[hos BaseProcExecutor0] cheats: inventory probe: Item_FairyBless_DefenseDouble=0 Item_Stone_Forest=1 Item_Stone_Fire=1 Item_Stone_Water=1 Item_Medal_Forest=1 Item_Medal_Fire=0 Item_Medal_Water=0 Item_Medal_Shadow=0 Item_Medal_Spirit=0 Item_Medal_Light=1 Item_Melody_ZeldaLullaby=1 Item_Melody_EponaSong=1 Item_Melody_SariaSong=1 Item_Melody_SunSong=1
[hos BaseProcExecutor0] cheats: inventory probe: Item_Melody_TimeSong=1 Item_Melody_StormSong=1 Item_Melody_ForestMinuet=1 Item_Melody_FireBolero=0 Item_Melody_WaterSerenade=0 Item_Melody_ShadowNocturne=0 Item_Melody_SpiritRequiem=0 Item_Melody_LightPrelude=1 Item_AgonyStone=1 Item_Token_Gerudo=0 Item_Token_Gold=100 Item_Sword_Kokiri=1 Item_Sword_Giant=0
[hos BaseProcExecutor0] cheats: inventory probe: Item_Sword_Biggoron=0 Item_Shield_Mirror=0 Item_Range_Bow=1 Item_Range_SlingShot=1 Weapon_Range_Hookshot=0 Weapon_Range_Longshot=0 Weapon_Boomerang=1 Weapon_Hammer=0 Item_HeavyBoot=0 Item_HoverBoot=0 Item_Mask_Keaton=0 Item_Gauntlet_Silver=0 Armor_GlassTruth=0 Armor_Child_GlassTruth=0 Armor_Adult_GlassTruth=0
[hos BaseProcExecutor0] cheats: inventory probe: Armor_Child_Gauntlet_Goron=1 Item_Wallet_Small=1
[hos host] vk: texture #241 0x10002121800 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: recorder: 750995 packets run in 10.0 s (busy 0.20 s, spun idle 1.14 s, slept 6383 times, 1464 of them under 200 us), 6 calls made directly (no room); the replay waited for it 32897 times, 37.48 ms in all, the longest 0.09 ms; vkResetDescriptorPool 11035/15.73 ms (max 0.06), replay_mu unlock 10769/13.46 ms (max 0.02), vkEndCommandBuffer 11038/7.96 ms (max 0.09), vkQueueBindSparse 31/0.24 ms (max 0.03), direct recording 14/0.04 ms (max 0.01), no ring room 6/0.04 ms (max 0.01)
[hos host] vk: texture 0x116c953000 260x260x1 x1 levels 1 NVN 0x25 -> vk 37 (500 textures, 1646 MB)
[hos host] vk: (its written part: 0 of 0 KB readable, 96 bytes not zero; levels L0)
[hos host] vk: texture 0x113c8ace00 4x4x1 x1 levels 1 NVN 0x2e (0 KB of storage) re-uploaded (its memory was written; flags 0): what the CPU wrote, 0 KB of it
[hos host] vk: texture #241 0x10002121800 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: pool 0x108c400000 remade larger (3 retired)
[hos host] vk: pool 0x108c000000..0x1094400000: 24 KB the CPU wrote since retired pool 0x108c400000's last sync kept from guest memory, not its mirror
[hos host] vk: pool 0x108c000000..0x1094400000: mirror made with the GPU's contents of 1 retired pool(s)
[hos host] vk: texture #735 at 0x10000d60400 beside #234: 426x240x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 1707x960x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: texture #735 at 0x10000d60400 beside #294: 426x240x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 853x480x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1 (rendered)
[hos host] vk: texture #735 at 0x10000d60400 beside #307: 426x240x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 427x240x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x14 target 1 (rendered)
[hos host] vk: table entry bound again at frame 2921: prog 6669b5f574621826 ssbo 0 of 3 (c0+0x880) addr 0x108c703000 size 0x79b6000 (before 0)
[hos host] vk: table entry bound again at frame 2921: prog 6669b5f574621826 ssbo 0 of 3 (c0+0x880) addr 0x108c703000 size 0x79b6000 (before 0)
[hos host] vk: slow submit: 35.6 ms: draw 32.3 descriptors 17.2 texture lookups 16.1 uploads 12.3 programs 7.4 commands 7.0
[hos host] vk: import 5.3 ms: commit+properties 0.3, buffer 0.0, allocate 5.0, bind+address 0.0
[hos host] vk: pool 0x1142762e00+0x80 imported in 5.3 ms as 0x1141c00000..0x1147c00000 (56 imports, 52 ms in all)
[hos host] vk: pool 0x1145400000 remade larger (4 retired)
[hos host] vk: pool 0x1141c00000..0x1147c00000: 2752 KB the CPU wrote since retired pool 0x1145400000's last sync kept from guest memory, not its mirror
[hos host] vk: pool 0x1141c00000..0x1147c00000: mirror made with the GPU's contents of 1 retired pool(s)
[hos host] vk: texture #758 at 0x10000e38800 beside #737: 853x480x1 x1 levels 1 layout 0x4 class 0x40002 NVN 0x5 target 1, the other 426x240x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: sampler 436 is nearest: min filter 5, mag filter 0, wrap 7/7/7, lod 0..15 bias 0, aniso 1, compare 0
[hos host] vk: texture #767 at 0x1000247e200 beside #762: 3072x3072x1 x3 levels 1 layout 0x4 class 0x1007c NVN 0x32 target 4, the other 426x240x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: write-back diff: a shadow for pool 0x1038400000 (4 MB; 260 MB of shadows)
[hos host] vk: write-back diff: a shadow for pool 0x103d400000 (4 MB; 264 MB of shadows)
[hos host] vk: texture #785 at 0x10007bcae00 beside #779: 1707x960x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 640x360x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: texture #789 at 0x10002181a00 beside #782: 426x240x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1, the other 853x480x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1 (rendered)
[hos host] vk: texture #790 at 0x1000827b000 beside #786: 853x480x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 1707x960x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1 (rendered)
[hos host] vk: texture #801 at 0x100021edc00 beside #788: 107x60x1 x1 levels 1 layout 0x3 class 0x40001 NVN 0x3 target 1, the other 426x240x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1 (rendered)
[hos host] vk: NVN2 program 88fe559e7a177a34 (stage 7) lowered with extended registers (2275 REGMAP words)
[hos host] vk: NVN2 program 7dee88dade548816 (stage 7) lowered with extended registers (338 REGMAP words)
[hos host] vk: NVN2 program 73b819fbe71d2814 (stage 0) lowered with extended registers (1128 REGMAP words)
[hos host] vk: NVN2 program c5f227a6efbe5b41 (stage 0) lowered with extended registers (1141 REGMAP words)
[hos host] vk: NVN2 program 2d6b101e5868b4ea (stage 0) lowered with extended registers (1132 REGMAP words)
[hos host] vk: NVN2 program 56cc6c3a14ce827a (stage 0) lowered with extended registers (1127 REGMAP words)
[hos host] vk: NVN2 program 196c6bfc68efb1dd (stage 0) lowered with extended registers (1127 REGMAP words)
[hos host] vk: NVN2 program 2de89066ce43a6c1 (stage 0) lowered with extended registers (1134 REGMAP words)
[hos host] vk: texture 0x10e26f0a00 768x768x1 x1 levels 10 NVN 0x7b -> vk 37 (ASTC decoded) (1000 textures, 2751 MB)
[hos host] vk: NVN2 program 2d6b101e5868b4ea (stage 0) lowered with extended registers (1132 REGMAP words)
[hos host] vk: NVN2 program 73b819fbe71d2814 (stage 0) lowered with extended registers (1128 REGMAP words)
[hos host] vk: NVN2 program 56cc6c3a14ce827a (stage 0) lowered with extended registers (1127 REGMAP words)
[hos host] vk: NVN2 program 56cc6c3a14ce827a (stage 0) lowered with extended registers (1127 REGMAP words)
[hos host] vk: NVN2 program 2f146a7f7f2b1ab0 (stage 0) lowered with extended registers (1075 REGMAP words)
[hos host] vk: NVN2 program 2d6b101e5868b4ea (stage 0) lowered with extended registers (1132 REGMAP words)
[hos host] vk: NVN2 program 27cb4becca29ce5e (stage 0) lowered with extended registers (1111 REGMAP words)
[hos host] vk: NVN2 program 181939a26df39627 (stage 0) lowered with extended registers (943 REGMAP words)
[hos host] vk: texture #1044 at 0x10000fe8e00 beside #755: 853x480x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1, the other 1707x960x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: NVN2 program 1b65533fbcc6fa94 (stage 0) lowered with extended registers (1154 REGMAP words)
[hos host] vk: texture slot 0xfe (handle 0xfe) is not registered: sampled as the dummy
[hos host] vk: texture slot 0xff (handle 0xff) is not registered: sampled as the dummy
[hos host] vk: NVN2 program e5f2865bdce56993 (stage 0) lowered with extended registers (1129 REGMAP words)
[hos host] vk: NVN2 program 57b9a80d47da5078 (stage 0) lowered with extended registers (1148 REGMAP words)
[hos host] vk: NVN2 program 2d6b101e5868b4ea (stage 0) lowered with extended registers (1132 REGMAP words)
[hos host] vk: a draw (program 515b5da337dfa50b) samples a target the pass wrote, after 1 draws of the pass (1707x960): a pass of its own
[hos host] vk: texture #1077 at 0x10000e38800 beside #737: 480x270x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1, the other 426x240x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: texture #1077 at 0x10000e38800 beside #758: 480x270x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1, the other 853x480x1 x1 levels 1 layout 0x4 class 0x40002 NVN 0x5 target 1 (rendered)
[hos host] vk: texture #1079 at 0x10001199000 beside #1073: 240x135x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1, the other 960x540x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1 (rendered)
[hos host] vk: texture #1082 at 0x100012d5800 beside #1080: 120x67x1 x1 levels 1 layout 0x3 class 0x40004 NVN 0x3f target 1, the other 240x135x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1 (rendered)
[hos host] vk: texture #1086 at 0x10000f06400 beside #1084: 30x16x1 x1 levels 1 layout 0x1 class 0x40004 NVN 0x3f target 1, the other 60x33x1 x1 levels 1 layout 0x2 class 0x40004 NVN 0x3f target 1 (rendered)
[hos host] vk: texture #1087 at 0x100020a9600 beside #266: 1707x960x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1, the other 426x240x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1 (rendered)
[hos host] vk: texture #1088 at 0x10000e38800 beside #737: 427x240x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x14 target 1, the other 426x240x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: texture #1088 at 0x10000e38800 beside #758: 427x240x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x14 target 1, the other 853x480x1 x1 levels 1 layout 0x4 class 0x40002 NVN 0x5 target 1 (rendered)
[hos host] vk: texture #1088 at 0x10000e38800 beside #1077: 427x240x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x14 target 1, the other 480x270x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1 (rendered)
[hos host] vk: texture #1089 at 0x10000ea4a00 beside #738: 1707x960x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x25 target 1, the other 426x240x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: slow submit: 59.2 ms: draw 49.1 descriptors 20.5 texture lookups 22.3 uploads 19.7 programs 24.8 commands 3.4
[hos host] vk: write-back diff: a shadow for pool 0x100f000000 (4 MB; 268 MB of shadows)
[hos host] vk: sparse mirrors: 65, 720 MB with memory of 984 MB (264 MB spared); blocks given memory later 43, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 77 binds (10.2 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 2356 dirty pages from their submits' captures, 23385 from earlier ones', 4839 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 1128 runs, 1009.4 MB compared; 27844 pages read into the shadows; 268 MB of shadows; pages the shadows knew that the CPU wrote: 3696 in captures, 30 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool: 0x7fb4800000 (4 MB, captured, state 2): 905; 0x7fbf800000 (4 MB, captured, state 2): 890; 0x7fbdc00000 (4 MB, captured, state 2): 844; 0x7fbd800000 (4 MB, captured, state 2): 783; 0x7f6f800000 (16 MB, captured, state 2): 688; 0x7f64000000 (4 MB, captured, state 2): 406; 0x7fc1000000 (4 MB, captured, state 2): 291; 0x7f64400000 (4 MB, captured, state 2): 26;
[hos host] vk: imports: 66 live (1004 MB), 2 retired still imported (168 MB), 2 retired given back (84 MB)
[hos host] vk: pool 0x103d400000 remade larger (5 retired)
[hos host] vk: pool 0x103d000000 remade larger (6 retired)
[hos host] vk: pool 0x103d000000..0x103d800000 took in 2 pools
[hos host] vk: pool 0x103d000000..0x103d800000: mirror made with the GPU's contents of 2 retired pool(s)
[hos host] vk: write-back diff: a shadow for pool 0x103d000000 (4 MB; 268 MB of shadows)
[hos host] vk: write-back diff: a shadow for pool 0x103d000000 (8 MB; 276 MB of shadows)
[hos host] vk: write-back diff: a shadow for pool 0x103d400000 (4 MB; 280 MB of shadows)
[hos host] vk: texture #1100 at 0x10007772800 beside #770: 816x816x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 817x817x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: texture #1106 at 0x10007bbce00 beside #1103: 1707x960x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 640x360x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: texture #1108 at 0x1000826d000 beside #1107: 853x480x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 1707x960x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1 (rendered)
[hos host] vk: (its written part: 1 of 1 KB readable, 23 bytes not zero; levels L8 L9 L10)
[hos host] vk: texture 0x10fd0df800 1024x1024x1 x1 levels 11 NVN 0x4b (1367 KB of storage) re-uploaded (its memory was written; flags 0x4): what the CPU wrote, 1 KB of it
[hos host] vk: a draw (program 515b5da337dfa50b) samples a target the pass wrote, after 1 draws of the pass (1707x960): a pass of its own
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: mirror of pool 0x108c400000 (128 MB) given back: retired, 103 submissions since its sync, GPU-only data, GPU-written
[hos host] vk: mirror of pool 0x1145400000 (40 MB) given back: retired, 104 submissions since its sync
[hos host] vk: mirror of pool 0x103d400000 (4 MB) given back: retired, 39 submissions since its sync, GPU-written
[hos host] vk: mirror of pool 0x103d000000 (4 MB) given back: retired, 39 submissions since its sync, GPU-written
[hos host] vk: texture #1124 at 0x10007772800 beside #770: 815x815x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 817x817x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: texture #1124 at 0x10007772800 beside #1100: 815x815x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 816x816x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: texture #1125 at 0x10008775400 beside #1111: 853x480x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 853x480x1 x1 levels 1 layout 0x4 class 0x40008 NVN 0x29 target 1 (rendered)
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: sampler 437 is nearest: min filter 0, mag filter 0, wrap 7/7/7, lod 0..0 bias 0, aniso 1, compare 0
[hos host] vk: a draw (program 515b5da337dfa50b) samples a target the pass wrote, after 1 draws of the pass (1707x960): a pass of its own
[hos host] vk: texture #1088 0x10000e38800 427x240 NVN 0x14: the GPU wrote its storage (submission 20441): uploaded again
[hos host] vk: upload over a drawn image: #1088 0x10000e38800 427x240x1 x1 NVN 0x14 at present 2922 (texture frame 2923), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos host] vk: texture 0x10000e38800 427x240x1 x1 levels 1 NVN 0x14 (432 KB of storage) re-uploaded (its memory was written; flags 0x8): a GPU write into its storage, 432 KB of it, over what the GPU wrote (finalized since)
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: slow submit: 19.5 ms:
[hos host] vk: texture #1128 at 0x10007772800 beside #770: 813x813x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 817x817x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: texture #1128 at 0x10007772800 beside #1100: 813x813x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 816x816x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: texture #1128 at 0x10007772800 beside #1124: 813x813x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 815x815x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: NVN2 program 2d6b101e5868b4ea (stage 0) lowered with extended registers (1132 REGMAP words)
[hos host] vk: NVN2 program 2d6b101e5868b4ea (stage 0) lowered with extended registers (1132 REGMAP words)
[hos host] vk: a draw (program 515b5da337dfa50b) samples a target the pass wrote, after 1 draws of the pass (1707x960): a pass of its own
[hos host] vk: vertex format NVN 0xe -> vk 17
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: a draw (program f66840055b4e30f0) writes a target an earlier draw sampled, after 17 draws of the pass (1707x960): a pass of its own
[hos host] vk: a draw (program 04cc08bc7fb9aaa8) samples a target the pass wrote, after 19 draws of the pass (1707x960): a pass of its own
[hos host] vk: a draw (program 5add9f3bbecb7ed3) samples a target the pass wrote, after 5 draws of the pass (1707x960): a pass of its own
[hos host] vk: a draw (program 515b5da337dfa50b) samples a target the pass wrote, after 1 draws of the pass (1707x960): a pass of its own
[hos host] vk: texture #1263 at 0x10000e38800 beside #737: 960x540x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1, the other 426x240x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: texture #1263 at 0x10000e38800 beside #758: 960x540x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1, the other 853x480x1 x1 levels 1 layout 0x4 class 0x40002 NVN 0x5 target 1 (rendered)
[hos host] vk: texture #1263 at 0x10000e38800 beside #1077: 960x540x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1, the other 480x270x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1 (rendered)
[hos host] vk: texture #1263 at 0x10000e38800 beside #1088: 960x540x1 x1 levels 1 layout 0x4 class 0x40001 NVN 0x1 target 1, the other 427x240x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x14 target 1 (rendered)
[hos host] vk: slow submit: 19.3 ms: draw 19.6 descriptors 4.8 texture lookups 3.6 uploads 2.9 programs 9.5
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: texture slot 0x102 (handle 0x10200102): no view of it; NVN target 1 format 0x25 4x4x1 levels 1 gpu 0x100c922a00, view no (format 0 target -1), wanted view type 2 use 0
[hos host] vk: texture #1266 at 0x1000612e600 beside #769: 640x360x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1, the other 2400x2400x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: texture #1270 at 0x1000621e800 beside #1267: 1707x960x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 640x360x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: texture #1272 at 0x100068cea00 beside #1271: 853x480x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 1707x960x1 x1 levels 1 layout 0x4 class 0x40004 NVN 0x3f target 1 (rendered)
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: replay reads of guest memory as submitted: 20000 (9963 pages from the captures)
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: texture #1297 at 0x10007772800 beside #770: 802x802x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 817x817x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: texture #1297 at 0x10007772800 beside #1100: 802x802x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1, the other 816x816x1 x1 levels 1 layout 0x4 class 0x1007e NVN 0x34 target 1 (rendered)
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: 1 of 1 small textures the GPU drew written into their memory in 0.3 ms, 1 frames after their copies were recorded, the first #1133 0x116fe9f000 260x260 levels 9 NVN 0xd (43 so far, 9327 KB, 7 ms; 0 left, the CPU wrote their memory since; 0 dropped, drawn over or gone; 0 failed)
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: 69 textures retired (1244 left, 2960 MB): budget 0, drawn over 0, dead targets 69
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: program picks: 105678 kept (34466 by the last picks' textures, a uniform buffer bound since), 621 new, 93700 with other textures (of 200000)
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: 11 textures retired (1254 left, 2984 MB): budget 0, drawn over 0, dead targets 11
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: mirror syncs (600 submits): 3286 dirty pages from their submits' captures, 38297 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2995 runs, 1191.1 MB compared; 1139 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 7770 in captures, 52 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: NVN2 program 2e41b85d34167b3b (stage 0) lowered with extended registers (1113 REGMAP words)
[hos host] vk: NVN2 program 196c6bfc68efb1dd (stage 0) lowered with extended registers (1127 REGMAP words)
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: replay reads of guest memory as submitted: 40000 (23363 pages from the captures)
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos OptimizeChangeBanc] nvn: 150000 recordings made, 26276 live copies (9.3 MB), 276 texture copies; 2 command buffers' segments (2.1 MB)
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: texture #767 0x1000247e200 3072x3072 x3 NVN 0x32 (54 MB, rendered or copied into) finalized by the game
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: 9 textures retired (1263 left, 3006 MB): budget 0, drawn over 0, dead targets 9
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: replay reads of guest memory as submitted: 60000 (35146 pages from the captures)
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 69, 756 MB with memory of 1016 MB (260 MB spared); blocks given memory later 396, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 101 binds (12.6 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 326 dirty pages from their submits' captures, 45409 from earlier ones', 24 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3050 runs, 1304.1 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9922 in captures, 5 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool: 0x7fd9400000 (4 MB, captured, state 2): 23; 0x1066000000 (4 MB, captured, state 2): 1;
[hos host] vk: imports: 70 live (1036 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: storage buffer NOT bound (reads zeros): program da7a7ab28b8e73d9 stage 1 c5+0 addr 0x4180000000000200 size 0x20
[hos host] vk: 9 textures retired (1320 left, 3017 MB): budget 0, drawn over 0, dead targets 9
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 4213 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 80000 (48616 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 303 dirty pages from their submits' captures, 42191 from earlier ones', 20 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3201 runs, 1425.2 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9571 in captures, 5 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool: 0x7fd9400000 (4 MB, captured, state 2): 20;
[hos host] vk: texture #1128 0x10007772800 813x813 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 2986 (drawn at 2925)
[hos host] vk: texture #1101 0x10007a3ca00 384x384 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 2989 (drawn at 2928)
[hos host] vk: 11 textures retired (1326 left, 3025 MB): budget 0, drawn over 0, dead targets 11
[hos host] vk: replay reads of guest memory as submitted: 100000 (61591 pages from the captures)
[hos host] vk: memory: working set 10928 MB (peak 10932), private 18874 MB, staging 256 MB in 4 arenas
[hos host] vk: memory heaps: heap 0 (device): 105 blocks 5737 MB, 13696 allocations 4937 MB; used 6446 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 49 allocations 382 MB; used 1517 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 6 blocks 768 MB, 222 images 697 MB; 4 free ranges, the largest 68 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1176 images 1712 MB; 364 free ranges, the largest 128 MB
[hos host] vk: render target images: 33 reused from the pool, 222 made new, 0 destroyed from it; it holds 64 (167 MB)
[hos host] vk: VRAM: 6446 MB used of 15280 MB allowed (800 MB of it free in the blocks); textures 3057 MB (budget 10928 MB), 1337 textures
[hos host] vk: textures: decoded ASTC 1620 MB, rendered 918 MB (115 drawn in one frame, kept: 42180 KB), other 284 MB; used in the last 8 presents 2218 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 1 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 1 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 95 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk: 54 MB: 0x1000247e200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 80 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 4 (529 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 3 (527 KB);
[hos host] vk: 11 textures retired (1326 left, 3025 MB): budget 0, drawn over 0, dead targets 11
[hos Presentation Thread] vk: presents after the CPU's signal (600): 326 waited for it, 2.16 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: a submit's memory work (ms): maps 0.01, capture taken 0.01, writes collected 0.11
[hos host] vk: status: 600 frames, the slowest 338.9 ms; VRAM 6.3 of 14.9 GB; NVIDIA DLSS: 95 frames drawn, 1 left to the game's network, 1 made, jitter +0.313 -0.352 px, actor motion 4132 draws in 75 frames (0.307 ms CPU a frame; poses 4263 read at the draw, 0 copied later), its images 98 MB, its own 143 MB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4873 queued, 4873 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3727 ms and 1110.4 MB read in all); 6678 programs (1498 of them compute variants without their code, 0 graphics programs no note names), 9183 graphics pipelines (0 not in a cache), 674 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 544 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7427 (4873 ready, 0 loading), 13739 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 674 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: 5202 programs from the program cache
[hos host] vk: a frame: 41 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 10.14, present 0.13, draw 5.30, descriptors 2.30, texture lookups 1.41, uploads 0.94, pipelines 0.12, programs 1.17, commands 1.28, dispatch 1.48, memory sync 0.68, queue submit 0.48, slot wait 0.04
[hos host] vk: a frame: mirrors 78 (759 MB): 13.94 MB synced in 892.6 copies, 49.75 MB written back
[hos host] vk: 3000 presents, 44.4 fps; a frame: 1528 draws (0 skipped), 105 dispatches, 141 passes, 128 barriers, 6 submits, 9.0 uploads (5.0 MB), 84 ub updates (58 overlays), GPU-bound wait 0.0 ms (recording slots only); 9345 pipelines (1676 ms), 0 programs (0 failed), 1326 textures (3025 MB)
[hos host] vk: host time in GPU resource waits: 6.26 ms a frame (fences 0.03, timelines 6.24, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 519.9 full barriers recorded, 183.9 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 4.0; 0x8: 2.3; 0x9: 0.8; 0x10: 2.4; 0x11: 30.4; 0x12: 67.5; 0x13: 1.6; 0x21: 3.0; 0x28: 11.2; 0x92: 2.4; 0x97: 1.9; 0x9b: 0.3;
[hos host] vk: GPU time 7.2 ms a frame (the longest submission 49.1 ms); 10.9 textures made a frame
[hos host] vk: a frame: 2.13 MB unswizzled on the CPU in 0.40 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 4 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 13.06 ms a frame): its jobs 3.33 ms a frame (submits 2.09, presents 0.74, others 0.51), idle 9.73; the game waited for room at 1 presents, 0.06 ms each (0.00 a frame; 46.09 jobs queued at a present); 4 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 28.45 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 345 captures at a CPU signal; the submits' waits read in 0.006 ms a frame; readbacks: 475 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 3.34 ms after its hand-over (516.69 at most)
[hos host] vk: pipeline cache: play file 7 saved (2318 KB): 4 pipelines, 4 from the driver's cache, 0 compiled; 10015 more from the start's cache
[hos Presentation Thread] vi: real-time step on: ratio 0.999, game's frame rate 60
[hos host] vk: sparse mirrors: 69, 759 MB with memory of 1016 MB (256 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 105 binds (12.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 376 dirty pages from their submits' captures, 39316 from earlier ones', 2 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3052 runs, 1390.7 MB compared; 2 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9515 in captures, 6 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool: 0x7f6c400000 (16 MB, captured, state 2): 2;
[hos host] vk: imports: 70 live (1036 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos sead::MainThread] vk: capture: a submit 0.19 ms (lock 0.08, scan 0.03 over 871 ranges, 2928 MB), 399 pages written, 399 copied (1.6 MB)
[hos host] vk: a capture taken (ms): all 0.011; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.007, bytes copied 0.000; 25 kept (112 MB), 7 spare buffers, 3470 texture pages copied (13 MB)
[hos host] vk: 1 textures retired (1325 left, 3024 MB): budget 0, drawn over 0, dead targets 1
[hos ModuleSystemWorker5] nvn: CommandBufferSignalEvent #5000: event 0x100d6c8018 mode 0 value 5000 (lr 0x80660c94)
[hos host] vk: replay reads of guest memory as submitted: 120000 (74440 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 65209 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: mirror syncs (600 submits): 422 dirty pages from their submits' captures, 39444 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3060 runs, 1393.4 MB compared; 1 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 10023 in captures, 5 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: program picks: 254391 kept (122649 by the last picks' textures, a uniform buffer bound since), 641 new, 144967 with other textures (of 400000)
[hos Presentation Thread] vi: 3030 frames presented (51.7 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 17, 15.5-17.8 230, 17.8-22 4, 22-30 3, 30-40 1, over 40 4
[hos host] vk: replay reads of guest memory as submitted: 140000 (88016 pages from the captures)
[hos ModuleSystemWorker5] vcores: 285602 takes, 120607 waits (mean 69 us, longest 1000.6 ms), 65202 kicks, 63816 yields, 1 starved grants, 0 escapes in 5 s
[hos host] vk: 1 textures retired (1325 left, 3024 MB): budget 0, drawn over 1, dead targets 0
[hos sead::MainThread] nvn: CommandBufferWaitEvent #15000: event 0x100d6c8048 mode 0 value 5487 (now 5468) (lr 0x806661f8)
[hos host] vk: 7 textures retired (1318 left, 3009 MB): budget 0, drawn over 6, dead targets 1
[hos host] vk: sparse mirrors: 69, 759 MB with memory of 1016 MB (256 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 105 binds (12.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 405 dirty pages from their submits' captures, 38926 from earlier ones', 30 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2996 runs, 1377.1 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9350 in captures, 4 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool: 0x1065800000 (8 MB, captured, state 2): 30;
[hos host] vk: imports: 70 live (1036 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: texture #1435 0x10007772800 784x784 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 3054 (drawn at 2993)
[hos rmbl::VibrationThread] hid: 4096 vibration values, strongest 0.00 since the last count
[hos host] vk: replay reads of guest memory as submitted: 160000 (100369 pages from the captures)
[hos host] vk: 6 textures retired (1313 left, 2993 MB): budget 0, drawn over 6, dead targets 0
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 731 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 407 dirty pages from their submits' captures, 39791 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3103 runs, 1437.9 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9281 in captures, 3 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos ModuleSystemWorker4] vk: readbacks of GPU results: 1325 of 3000 waited for their write-back, 0.10 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: replay reads of guest memory as submitted: 180000 (112550 pages from the captures)
[hos host] vk: 1 textures retired (1312 left, 2990 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: 2 textures retired (1310 left, 2990 MB): budget 0, drawn over 1, dead targets 1
[hos host] vk: sparse mirrors: 69, 759 MB with memory of 1016 MB (256 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 105 binds (12.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 448 dirty pages from their submits' captures, 38785 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2992 runs, 1387.5 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9397 in captures, 3 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 70 live (1036 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: replay reads of guest memory as submitted: 200000 (124870 pages from the captures)
[hos host] vk: 1 textures retired (1310 left, 2990 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos Presentation Thread] vk: capture: a submit 0.11 ms (lock 0.01, scan 0.04 over 943 ranges, 2919 MB), 308 pages written, 308 copied (1.2 MB)
[hos host] vk: a capture taken (ms): all 0.005; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.003, bytes copied 0.000; 25 kept (106 MB), 11 spare buffers, 3120 texture pages copied (12 MB)
[hos host] vk: replay reads of guest memory as submitted: 220000 (137877 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 485 dirty pages from their submits' captures, 39271 from earlier ones', 2 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3012 runs, 1385.0 MB compared; 1 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9459 in captures, 6 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool: 0x7fdf000000 (4 MB, captured, state 2): 2;
[hos host] vk: 12 textures retired (1342 left, 3023 MB): budget 0, drawn over 0, dead targets 12
[hos host] vk: a frame: 53 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.67, present 0.08, draw 3.96, descriptors 1.50, texture lookups 0.10, uploads 0.01, pipelines 0.15, programs 0.71, commands 1.15, dispatch 0.63, memory sync 0.17, queue submit 0.49, slot wait 0.05
[hos host] vk: a frame: mirrors 79 (760 MB): 6.99 MB synced in 1122.5 copies, 63.00 MB written back
[hos host] vk: 3120 presents, 60.0 fps; a frame: 2050 draws (0 skipped), 136 dispatches, 174 passes, 160 barriers, 6 submits, 0.2 uploads (0.1 MB), 86 ub updates (59 overlays), GPU-bound wait 0.0 ms (recording slots only); 9345 pipelines (1676 ms), 0 programs (0 failed), 1342 textures (3023 MB)
[hos host] vk: host time in GPU resource waits: 0.50 ms a frame (fences 0.03, timelines 0.47, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 537.3 full barriers recorded, 232.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 6.9; 0x8: 3.0; 0x9: 1.0; 0x10: 4.9; 0x11: 42.0; 0x12: 78.6; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 8.5 ms a frame (the longest submission 1.9 ms); 0.4 textures made a frame
[hos host] vk: a frame: 0.05 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: queues ordered by their events: 12000 submissions stopped at a wait, 11999 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 17075, not met 0; captures at a CPU event's wait 1757, 0 of them at a wait met on arrival
[hos host] vk: program picks: 400115 kept (209653 by the last picks' textures, a uniform buffer bound since), 652 new, 199232 with other textures (of 600000)
[hos host] vk: 1 textures retired (1345 left, 3031 MB): budget 0, drawn over 0, dead targets 1
[hos host] vk: readback pages refreshed from guest memory: 132111 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: replay reads of guest memory as submitted: 240000 (150283 pages from the captures)
[hos host] vk: mirror of pool 0x1043800000 (4 MB) given back: idle, 6005 submissions since its sync
[hos ModuleSystemWorker3] nvn: 200000 recordings made, 29155 live copies (9.4 MB), 338 texture copies; 6 command buffers' segments (2.3 MB)
[hos host] vk: mirror of pool 0x7fe1000000 (4 MB) given back: idle, 6056 submissions since its sync
[hos host] vk: sparse mirrors: 68, 758 MB with memory of 1012 MB (253 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 106 binds (13.0 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 406 dirty pages from their submits' captures, 39395 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2962 runs, 1365.0 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9722 in captures, 3 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 71 live (1040 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: mirror of pool 0x7fddc00000 (8 MB) given back: idle, 6003 submissions since its sync
[hos host] vk: mirror of pool 0x7fc0800000 (4 MB) given back: idle, 6051 submissions since its sync
[hos host] vk: replay reads of guest memory as submitted: 260000 (162223 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 458 dirty pages from their submits' captures, 39625 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3078 runs, 1428.6 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9281 in captures, 2 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: handle table: element 16 of program 2fd8c7ca964e5a1d names texture #749 (format 83) for a depth comparison: bound as nothing
[hos host] vk: handle table: element 18 of program 2fd8c7ca964e5a1d names texture #750 (format 83) for a depth comparison: bound as nothing
[hos host] vk: handle table: element 19 of program 2fd8c7ca964e5a1d names texture #781 (format 9) for a depth comparison: bound as nothing
[hos host] vk: handle table: element 16 of program 21c7c8a2d0fe7171 names texture #749 (format 83) for a depth comparison: bound as nothing
[hos host] vk: handle table: element 18 of program 21c7c8a2d0fe7171 names texture #750 (format 83) for a depth comparison: bound as nothing
[hos host] vk: handle table: element 19 of program 21c7c8a2d0fe7171 names texture #781 (format 9) for a depth comparison: bound as nothing
[hos host] vk: handle table: element 16 of program 7bd4d62f1691bf85 names texture #749 (format 83) for a depth comparison: bound as nothing
[hos host] vk: handle table: element 18 of program 7bd4d62f1691bf85 names texture #750 (format 83) for a depth comparison: bound as nothing
[hos host] vk: 2 textures retired (1347 left, 3038 MB): budget 0, drawn over 0, dead targets 2
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 500 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 280000 (174497 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 66, 749 MB with memory of 1000 MB (250 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 106 binds (13.0 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 380 dirty pages from their submits' captures, 38963 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2971 runs, 1384.4 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9355 in captures, 6 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 71 live (1040 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: mirror of pool 0x7fb4800000 (4 MB) given back: idle, 6062 submissions since its sync
[hos host] vk: mirror of pool 0x7fbdc00000 (4 MB) given back: idle, 6062 submissions since its sync
[hos host] vk: mirror of pool 0x7fc1000000 (4 MB) given back: idle, 6060 submissions since its sync
[hos host] vk: mirror of pool 0x7fd3400000 (8 MB) given back: idle, 6060 submissions since its sync
[hos host] vk: mirror of pool 0x7fc0000000 (4 MB) given back: idle, 6056 submissions since its sync
[hos host] vk: 18 mirrors given back (289 MB in all); 733 MB of mirrors now, 88 MB of them idle and kept for what the GPU wrote there alone
[hos host] vk: replay reads of guest memory as submitted: 300000 (186583 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.02
[hos Presentation Thread] vk: capture: a submit 0.11 ms (lock 0.01, scan 0.04 over 941 ranges, 2937 MB), 310 pages written, 310 copied (1.2 MB)
[hos host] vk: a capture taken (ms): all 0.005; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.003, bytes copied 0.000; 25 kept (106 MB), 9 spare buffers, 3120 texture pages copied (12 MB)
[hos host] vk: mirror syncs (600 submits): 429 dirty pages from their submits' captures, 39453 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2937 runs, 1361.9 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9701 in captures, 6 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: 2 textures retired (1347 left, 3038 MB): budget 0, drawn over 1, dead targets 1
[hos host] vk: replay reads of guest memory as submitted: 320000 (198616 pages from the captures)
[hos host] vk: mirror of pool 0x1042c00000 (4 MB) given back: idle, 6059 submissions since its sync
[hos host] vk: 2 textures retired (1346 left, 3033 MB): budget 0, drawn over 2, dead targets 0
[hos host] vk: program picks: 546362 kept (296299 by the last picks' textures, a uniform buffer bound since), 652 new, 252985 with other textures (of 800000)
[hos host] vk: sparse mirrors: 60, 732 MB with memory of 972 MB (239 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 106 binds (13.0 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 443 dirty pages from their submits' captures, 40021 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3005 runs, 1420.8 MB compared; 1 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9290 in captures, 3 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 71 live (1040 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: 4 textures retired (1342 left, 3022 MB): budget 0, drawn over 4, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 340000 (210590 pages from the captures)
[hos host] vk: 1 textures retired (1341 left, 3019 MB): budget 0, drawn over 1, dead targets 0
[hos sead::MainThread] nvn: CommandBufferWaitEvent #20000: event 0x100d6c8048 mode 0 value 9287 (now 9268) (lr 0x806661f8)
[hos host] vk: a frame: 48 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.80, present 0.07, draw 4.03, descriptors 1.53, texture lookups 0.09, uploads 0.00, pipelines 0.15, programs 0.72, commands 1.18, dispatch 0.64, memory sync 0.18, queue submit 0.49, slot wait 0.05
[hos host] vk: a frame: mirrors 79 (732 MB): 6.96 MB synced in 1113.6 copies, 62.32 MB written back
[hos host] vk: 3240 presents, 60.0 fps; a frame: 2043 draws (0 skipped), 133 dispatches, 176 passes, 161 barriers, 6 submits, 0.0 uploads (0.0 MB), 86 ub updates (59 overlays), GPU-bound wait 0.0 ms (recording slots only); 9345 pipelines (1676 ms), 0 programs (0 failed), 1341 textures (3019 MB)
[hos host] vk: host time in GPU resource waits: 0.63 ms a frame (fences 0.03, timelines 0.60, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 536.0 full barriers recorded, 233.4 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 6.8; 0x8: 3.0; 0x9: 1.0; 0x10: 4.8; 0x11: 42.0; 0x12: 79.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 8.4 ms a frame (the longest submission 1.9 ms); 0.1 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: readback pages refreshed from guest memory: 198630 pages so far (0 held: may be written ahead in their submission)
[hos ModuleSystemWorker2] vk: readbacks of GPU results: 1541 of 3000 waited for their write-back, 0.06 ms each; 0 looked at the stopped queues first, 1 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: 1 textures retired (1340 left, 3019 MB): budget 0, drawn over 0, dead targets 1
[hos host] vk: mirror syncs (600 submits): 406 dirty pages from their submits' captures, 38665 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2937 runs, 1364.0 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9381 in captures, 4 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: mirror of pool 0x1066000000 (4 MB) given back: idle, 6027 submissions since its sync
[hos host] vk: replay reads of guest memory as submitted: 360000 (222609 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 496 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: sparse mirrors: 59, 729 MB with memory of 968 MB (238 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 106 binds (13.0 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 451 dirty pages from their submits' captures, 39640 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2914 runs, 1360.1 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9793 in captures, 5 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 71 live (1040 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: replay reads of guest memory as submitted: 380000 (234679 pages from the captures)
[hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #10000: event 0x100d6c8024 mode 0 value 10000 (lr 0x80665068)
[hos ModuleSystemWorker4] nvn: DrawMeshTasks: 20000 so far (x1 0 x2 0x20 x3 0x1020752e x4 0x6001ba0)
[hos host] vk: 1 textures retired (1340 left, 3019 MB): budget 0, drawn over 0, dead targets 1
[hos host] vk: 5 textures retired (1336 left, 3008 MB): budget 0, drawn over 4, dead targets 1
[hos host] vk: replay reads of guest memory as submitted: 400000 (246725 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 461 dirty pages from their submits' captures, 39641 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3034 runs, 1423.7 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9360 in captures, 4 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos sead::MainThread] vk: capture: a submit 0.11 ms (lock 0.01, scan 0.04 over 941 ranges, 2937 MB), 311 pages written, 311 copied (1.2 MB)
[hos host] vk: a capture taken (ms): all 0.005; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.003, bytes copied 0.000; 25 kept (106 MB), 8 spare buffers, 3119 texture pages copied (12 MB)
[hos host] vk: replay reads of guest memory as submitted: 420000 (258710 pages from the captures)
[hos host] vk: program picks: 692808 kept (383354 by the last picks' textures, a uniform buffer bound since), 652 new, 306539 with other textures (of 1000000)
[hos host] vk: sparse mirrors: 59, 729 MB with memory of 968 MB (238 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 106 binds (13.0 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 423 dirty pages from their submits' captures, 38718 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2929 runs, 1385.7 MB compared; 1 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9392 in captures, 2 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 71 live (1040 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: 11 textures retired (1339 left, 3012 MB): budget 0, drawn over 0, dead targets 11
[hos host] vk: 13 textures retired (1337 left, 3011 MB): budget 0, drawn over 0, dead targets 13
[hos Presentation Thread] vi: 3331 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos Presentation Thread] nvn: QueueSubmitCommands #20000: queue 0000101004133020 (its #3334), 1 handles (lr 0x80590358)
[hos host] vk: replay reads of guest memory as submitted: 440000 (271473 pages from the captures)
[hos host] vk: mirror of pool 0x7f6c400000 (16 MB) given back: idle, 6006 submissions since its sync
[hos Resource Control] vcores: 244347 takes, 32994 waits (mean 25 us, longest 4.1 ms), 17226 kicks, 16907 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: mirror of pool 0x7fde800000 (4 MB) given back: idle, 6059 submissions since its sync
[hos host] vk: mirror syncs (600 submits): 456 dirty pages from their submits' captures, 39800 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2890 runs, 1385.9 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9698 in captures, 3 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 460000 (284089 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 265398 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: 12 textures retired (1338 left, 3011 MB): budget 0, drawn over 0, dead targets 12
[hos host] vk: a frame: 50 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.67, present 0.07, draw 3.95, descriptors 1.50, texture lookups 0.08, uploads 0.00, pipelines 0.15, programs 0.70, commands 1.16, dispatch 0.63, memory sync 0.18, queue submit 0.48, slot wait 0.05
[hos host] vk: a frame: mirrors 80 (716 MB): 6.98 MB synced in 1114.6 copies, 62.46 MB written back
[hos host] vk: 3360 presents, 60.0 fps; a frame: 2052 draws (0 skipped), 131 dispatches, 176 passes, 161 barriers, 6 submits, 0.0 uploads (0.0 MB), 86 ub updates (59 overlays), GPU-bound wait 0.0 ms (recording slots only); 9345 pipelines (1676 ms), 0 programs (0 failed), 1338 textures (3011 MB)
[hos host] vk: host time in GPU resource waits: 0.70 ms a frame (fences 0.03, timelines 0.67, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 534.5 full barriers recorded, 232.8 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 6.7; 0x8: 3.0; 0x9: 1.0; 0x10: 4.7; 0x11: 42.0; 0x12: 79.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 8.4 ms a frame (the longest submission 1.9 ms); 0.3 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 58, 716 MB with memory of 952 MB (235 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 107 binds (13.0 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 434 dirty pages from their submits' captures, 38243 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2881 runs, 1364.0 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9305 in captures, 2 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 71 live (1040 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: 2 textures retired (1336 left, 3008 MB): budget 0, drawn over 1, dead targets 1
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 500 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 480000 (296502 pages from the captures)
[hos host] vk: 1 textures retired (1336 left, 3006 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: mirror syncs (600 submits): 466 dirty pages from their submits' captures, 39374 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3028 runs, 1445.2 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9348 in captures, 3 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 500000 (308902 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos sead::MainThread] vk: capture: a submit 0.11 ms (lock 0.01, scan 0.04 over 941 ranges, 2937 MB), 311 pages written, 311 copied (1.2 MB)
[hos host] vk: a capture taken (ms): all 0.005; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.003, bytes copied 0.000; 25 kept (112 MB), 7 spare buffers, 3119 texture pages copied (12 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 58, 716 MB with memory of 952 MB (235 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 107 binds (13.0 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 412 dirty pages from their submits' captures, 38600 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2934 runs, 1382.2 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9352 in captures, 4 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 71 live (1040 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: 13 textures retired (1335 left, 3006 MB): budget 0, drawn over 0, dead targets 13
[hos host] vk: program picks: 839441 kept (470780 by the last picks' textures, a uniform buffer bound since), 652 new, 359906 with other textures (of 1200000)
[hos host] vk: replay reads of guest memory as submitted: 520000 (321242 pages from the captures)
[hos host] vk: 3 textures retired (1333 left, 3006 MB): budget 0, drawn over 0, dead targets 3
[hos ModuleSystemWorker1] vk: readbacks of GPU results: 1546 of 3000 waited for their write-back, 0.07 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: 12 textures retired (1334 left, 3008 MB): budget 0, drawn over 0, dead targets 12
[hos host] vk: mirror syncs (600 submits): 406 dirty pages from their submits' captures, 38908 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2923 runs, 1382.9 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9334 in captures, 3 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 540000 (333652 pages from the captures)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #25000: event 0x100d6c8048 mode 0 value 13087 (now 13068) (lr 0x806661f8)
[hos host] vk: sparse mirrors: 58, 716 MB with memory of 952 MB (235 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 107 binds (13.0 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 430 dirty pages from their submits' captures, 39716 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2947 runs, 1403.8 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9805 in captures, 1 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 71 live (1040 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: replay reads of guest memory as submitted: 560000 (345982 pages from the captures)
[hos host] vk: 12 textures retired (1334 left, 3008 MB): budget 0, drawn over 0, dead targets 12
[hos host] vk: readback pages refreshed from guest memory: 331917 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: 12 textures retired (1334 left, 3008 MB): budget 0, drawn over 0, dead targets 12
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 500 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: mirror syncs (600 submits): 398 dirty pages from their submits' captures, 38486 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3066 runs, 1441.4 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9384 in captures, 2 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 580000 (358506 pages from the captures)
[hos host] vk: 12 textures retired (1334 left, 3008 MB): budget 0, drawn over 0, dead targets 12
[hos host] vk: a frame: 50 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.69, present 0.06, draw 3.95, descriptors 1.54, texture lookups 0.13, uploads 0.05, pipelines 0.15, programs 0.69, commands 1.15, dispatch 0.63, memory sync 0.18, queue submit 0.48, slot wait 0.05
[hos host] vk: a frame: mirrors 80 (716 MB): 6.90 MB synced in 1114.3 copies, 63.04 MB written back
[hos host] vk: 3480 presents, 60.0 fps; a frame: 2052 draws (0 skipped), 131 dispatches, 174 passes, 157 barriers, 6 submits, 0.0 uploads (0.1 MB), 84 ub updates (58 overlays), GPU-bound wait 0.0 ms (recording slots only); 9345 pipelines (1676 ms), 0 programs (0 failed), 1334 textures (3008 MB)
[hos host] vk: host time in GPU resource waits: 0.65 ms a frame (fences 0.03, timelines 0.62, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 529.2 full barriers recorded, 229.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 5.7; 0x8: 3.0; 0x9: 1.0; 0x10: 3.7; 0x11: 42.0; 0x12: 78.0; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 8.4 ms a frame (the longest submission 1.9 ms); 0.5 textures made a frame
[hos host] vk: a frame: 0.13 MB unswizzled on the CPU in 0.05 ms
[hos host] vk: sparse mirrors: 58, 716 MB with memory of 952 MB (235 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 107 binds (13.0 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 389 dirty pages from their submits' captures, 39237 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2890 runs, 1365.0 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9737 in captures, 4 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 71 live (1040 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: replay reads of guest memory as submitted: 600000 (370892 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos sead::MainThread] vk: capture: a submit 0.11 ms (lock 0.01, scan 0.04 over 941 ranges, 2937 MB), 310 pages written, 310 copied (1.2 MB)
[hos host] vk: a capture taken (ms): all 0.005; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.003, bytes copied 0.000; 25 kept (112 MB), 7 spare buffers, 3119 texture pages copied (12 MB)
[hos host] vk: recorder: 8312210 packets run in 10.0 s (busy 1.00 s, spun idle 3.38 s, slept 3850 times, 888 of them under 200 us), 0 calls made directly (no room); the replay waited for it 39374 times, 66.05 ms in all, the longest 1.36 ms; vkEndCommandBuffer 15976/40.87 ms (max 1.36), replay_mu unlock 6777/14.03 ms (max 0.12), vkResetDescriptorPool 15976/10.45 ms (max 0.12), direct recording 582/0.50 ms (max 0.01), vkQueueBindSparse 27/0.15 ms (max 0.01), vkDestroyImageView 33/0.05 ms (max 0.00)
[hos host] vk: render targets drawn over from another start, let go: 246 so far (549 MB)
[hos host] vk: program picks: 986097 kept (558079 by the last picks' textures, a uniform buffer bound since), 653 new, 413249 with other textures (of 1400000)
[hos ModuleSystemWorker2] nvn: 250000 recordings made, 29218 live copies (10.0 MB), 354 texture copies; 3 command buffers' segments (2.1 MB)
[hos host] vk: replay reads of guest memory as submitted: 620000 (383305 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 429 dirty pages from their submits' captures, 39408 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3005 runs, 1426.0 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9291 in captures, 2 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 640000 (395596 pages from the captures)
[hos host] vk: 1 textures retired (1336 left, 3014 MB): budget 0, drawn over 1, dead targets 0
[hos ModuleSystemWorker5] nvn: CommandBufferSignalEvent #15000: event 0x100d6c802c mode 0 value 14999 (lr 0x80667688)
[hos host] vk: sparse mirrors: 58, 716 MB with memory of 952 MB (235 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 107 binds (13.0 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 400 dirty pages from their submits' captures, 38911 from earlier ones', 1 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2896 runs, 1365.1 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9274 in captures, 1 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool: 0x7fd9400000 (4 MB, captured, state 2): 1;
[hos host] vk: imports: 71 live (1040 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: mirror of pool 0x1065800000 (8 MB) given back: idle, 6050 submissions since its sync
[hos host] vk: replay reads of guest memory as submitted: 660000 (408251 pages from the captures)
[hos host] vk: 12 textures retired (1342 left, 3024 MB): budget 0, drawn over 0, dead targets 12
[hos host] vk: mirror syncs (600 submits): 416 dirty pages from their submits' captures, 38762 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2913 runs, 1360.6 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9335 in captures, 3 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: NVN2 program 565a7e838231e2fe (stage 0) lowered with extended registers (1132 REGMAP words)
[hos host] vk: NVN2 program e82bff212b12bfa7 (stage 0) lowered with extended registers (1128 REGMAP words)
[hos host] vk: 12 textures retired (1355 left, 3062 MB): budget 0, drawn over 1, dead targets 11
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 500 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 680000 (422975 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 398437 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 60, 732 MB with memory of 972 MB (239 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 110 binds (13.3 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 407 dirty pages from their submits' captures, 37722 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2794 runs, 1378.1 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9296 in captures, 4 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 71 live (1040 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos ModuleSystemWorker3] vk: readbacks of GPU results: 1548 of 3000 waited for their write-back, 0.08 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: replay reads of guest memory as submitted: 700000 (435515 pages from the captures)
[hos host] vk: memory: working set 10905 MB (peak 10932), private 18790 MB, staging 256 MB in 4 arenas
[hos host] vk: memory heaps: heap 0 (device): 105 blocks 5737 MB, 13228 allocations 4794 MB; used 6446 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 49 allocations 382 MB; used 1521 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 6 blocks 768 MB, 155 images 528 MB; 23 free ranges, the largest 68 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1214 images 1765 MB; 383 free ranges, the largest 128 MB
[hos host] vk: render target images: 168 reused from the pool, 261 made new, 106 destroyed from it; it holds 2 (3 MB)
[hos host] vk: VRAM: 6446 MB used of 15280 MB allowed (943 MB of it free in the blocks); textures 3105 MB (budget 10928 MB), 1370 textures
[hos host] vk: textures: decoded ASTC 1657 MB, rendered 913 MB (116 drawn in one frame, kept: 61440 KB), other 299 MB; used in the last 8 presents 2240 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 1 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 1 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 695 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk: 54 MB: 0x1000247e200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 680 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 4 (529 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 3 (527 KB);
[hos host] vk: 12 textures retired (1358 left, 3073 MB): budget 0, drawn over 0, dead targets 12
[hos Presentation Thread] vk: presents after the CPU's signal (600): 4 waited for it, 0.04 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos host] vk: status: 600 frames, the slowest 21.9 ms; VRAM 6.3 of 14.9 GB; NVIDIA DLSS: 600 frames drawn, 1 made, jitter +0.219 -0.426 px, actor motion 33527 draws in 600 frames (0.198 ms CPU a frame; poses 33543 read at the draw, 0 copied later), its images 98 MB, its own 143 MB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4873 queued, 4873 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3727 ms and 1110.4 MB read in all); 6678 programs (1498 of them compute variants without their code, 0 graphics programs no note names), 9183 graphics pipelines (0 not in a cache), 674 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 566 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7427 (4873 ready, 0 loading), 13739 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 674 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 53 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.77, present 0.06, draw 3.99, descriptors 1.51, texture lookups 0.12, uploads 0.02, pipelines 0.15, programs 0.71, commands 1.18, dispatch 0.64, memory sync 0.18, queue submit 0.49, slot wait 0.05
[hos host] vk: a frame: mirrors 83 (732 MB): 7.08 MB synced in 1112.7 copies, 62.20 MB written back
[hos host] vk: 3600 presents, 60.0 fps; a frame: 2057 draws (0 skipped), 129 dispatches, 172 passes, 154 barriers, 6 submits, 0.1 uploads (0.1 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 9345 pipelines (1676 ms), 0 programs (0 failed), 1358 textures (3073 MB)
[hos host] vk: host time in GPU resource waits: 0.70 ms a frame (fences 0.03, timelines 0.67, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 522.3 full barriers recorded, 226.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 4.9; 0x8: 3.0; 0x9: 1.0; 0x10: 2.9; 0x11: 42.0; 0x12: 76.2; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 8.4 ms a frame (the longest submission 2.0 ms); 0.5 textures made a frame
[hos host] vk: a frame: 0.07 MB unswizzled on the CPU in 0.02 ms
[hos host] vk: queues ordered by their events: 15342 submissions stopped at a wait, 15342 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 29000, not met 0; captures at a CPU event's wait 1761, 0 of them at a wait met on arrival
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 7.37 ms a frame (submits 6.85, presents 0.38, others 0.14), idle 9.30; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 165.18 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 6 captures at a CPU signal; the submits' waits read in 0.033 ms a frame; readbacks: 3000 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 7.39 ms after its hand-over (12.51 at most)
[hos host] vk: program picks: 1133322 kept (646935 by the last picks' textures, a uniform buffer bound since), 663 new, 466014 with other textures (of 1600000)
[hos sead::MainThread] vk: capture: a submit 0.11 ms (lock 0.01, scan 0.04 over 940 ranges, 2939 MB), 310 pages written, 310 copied (1.2 MB)
[hos host] vk: a capture taken (ms): all 0.005; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.003, bytes copied 0.000; 25 kept (112 MB), 7 spare buffers, 3119 texture pages copied (12 MB)
[hos host] vk: mirror syncs (600 submits): 437 dirty pages from their submits' captures, 39621 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2782 runs, 1358.0 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9750 in captures, 1 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: 11 textures retired (1358 left, 3073 MB): budget 0, drawn over 0, dead targets 11
[hos host] vk: replay reads of guest memory as submitted: 720000 (447627 pages from the captures)
[hos host] vk: texture #1364 0x10007772800 786x786 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 3616 (drawn at 3555)
[hos host] vk: texture #1355 0x10007772800 787x787 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 3617 (drawn at 3556)
[hos host] vk: 1 textures retired (1357 left, 3070 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 60, 732 MB with memory of 972 MB (239 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 110 binds (13.3 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 404 dirty pages from their submits' captures, 38716 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2823 runs, 1404.2 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9405 in captures, 4 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 71 live (1040 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos Presentation Thread] vi: 3631 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: replay reads of guest memory as submitted: 740000 (460074 pages from the captures)
[hos ModuleSystemWorker2] vcores: 248382 takes, 33070 waits (mean 25 us, longest 5.0 ms), 17485 kicks, 17186 yields, 0 starved grants, 0 escapes in 5 s
[hos sead::MainThread] nvn: CommandBufferWaitEvent #30000: event 0x100d6c8048 mode 0 value 16887 (now 16868) (lr 0x806661f8)
[hos host] vk: replay reads of guest memory as submitted: 760000 (473837 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 428 dirty pages from their submits' captures, 40091 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3057 runs, 1421.9 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9367 in captures, 2 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: 42 textures retired (1349 left, 3029 MB): budget 0, drawn over 0, dead targets 42
[hos host] vk: 12 textures retired (1353 left, 3037 MB): budget 0, drawn over 0, dead targets 12
[hos host] vk: replay reads of guest memory as submitted: 780000 (486703 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 500 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: sparse mirrors: 61, 734 MB with memory of 980 MB (245 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 111 binds (13.4 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 382 dirty pages from their submits' captures, 39194 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2940 runs, 1361.9 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9417 in captures, 3 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 71 live (1040 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: texture #363 0x116e916000 260x260 x1 NVN 0xd the GPU drew, finalized by the game, sampled again at frame 3682 (drawn at 2909)
[hos host] vk: replay reads of guest memory as submitted: 800000 (501484 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 464978 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: texture #367 0x116e980000 260x260 x1 NVN 0xd the GPU drew, finalized by the game, sampled again at frame 3693 (drawn at 2909)
[hos ModuleSystemWorker1] nvn: DrawMeshTasksIndirect: 40000 so far (x1 0x117d4a3040 x2 0x2 x3 0x117d4a3040 x4 0x44b040)
[hos host] vk: mirror syncs (600 submits): 444 dirty pages from their submits' captures, 38860 from earlier ones', 3 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2963 runs, 1361.0 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 9718 in captures, 2 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool: 0x7fd9400000 (4 MB, captured, state 2): 3;
[hos host] vk: 11 textures retired (1365 left, 3043 MB): budget 0, drawn over 0, dead targets 11
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos host] vk: program picks: 1279594 kept (734769 by the last picks' textures, a uniform buffer bound since), 678 new, 519727 with other textures (of 1800000)
[hos host] vk: replay reads of guest memory as submitted: 820000 (514936 pages from the captures)
[hos sead::MainThread] vk: capture: a submit 0.11 ms (lock 0.01, scan 0.04 over 940 ranges, 2939 MB), 313 pages written, 313 copied (1.2 MB)
[hos host] vk: a capture taken (ms): all 0.005; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.003, bytes copied 0.000; 25 kept (112 MB), 7 spare buffers, 3119 texture pages copied (12 MB)
[hos host] vk: 11 textures retired (1365 left, 3043 MB): budget 0, drawn over 0, dead targets 11
[hos host] vk: texture #355 0x116d122000 260x260 x1 NVN 0xd the GPU drew, finalized by the game, sampled again at frame 3711 (drawn at 2908)
[hos host] vk: sparse mirrors: 61, 734 MB with memory of 980 MB (245 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 111 binds (13.4 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 442 dirty pages from their submits' captures, 41194 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3139 runs, 1448.1 MB compared; 1 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 10328 in captures, 3 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 71 live (1040 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: a frame: 62 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.72, present 0.07, draw 3.93, descriptors 1.49, texture lookups 0.12, uploads 0.02, pipelines 0.15, programs 0.71, commands 1.14, dispatch 0.64, memory sync 0.18, queue submit 0.49, slot wait 0.05
[hos host] vk: a frame: mirrors 84 (734 MB): 7.02 MB synced in 1121.5 copies, 62.55 MB written back
[hos host] vk: 3720 presents, 60.0 fps; a frame: 2040 draws (0 skipped), 131 dispatches, 172 passes, 154 barriers, 6 submits, 0.2 uploads (0.1 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 9345 pipelines (1676 ms), 0 programs (0 failed), 1365 textures (3043 MB)
[hos host] vk: host time in GPU resource waits: 0.46 ms a frame (fences 0.03, timelines 0.43, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 524.7 full barriers recorded, 225.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 4.8; 0x8: 3.0; 0x9: 1.0; 0x10: 2.9; 0x11: 42.0; 0x12: 75.9; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 8.5 ms a frame (the longest submission 2.0 ms); 0.8 textures made a frame
[hos host] vk: a frame: 0.09 MB unswizzled on the CPU in 0.02 ms
[hos host] vk: NVN2 program 5c55ab4d22261ede (stage 0) lowered with extended registers (1132 REGMAP words)
[hos host] vk: replay reads of guest memory as submitted: 840000 (528741 pages from the captures)
[hos host] vk: NVN2 program 71a065bfc0e5bf5a (stage 7) lowered with extended registers (338 REGMAP words)
[hos host] vk: 11 textures retired (1369 left, 3050 MB): budget 0, drawn over 0, dead targets 11
[hos host] vk: 11 textures retired (1369 left, 3050 MB): budget 0, drawn over 0, dead targets 11
[hos host] vk: replay reads of guest memory as submitted: 860000 (543092 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 416 dirty pages from their submits' captures, 41978 from earlier ones', 34 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3131 runs, 1426.8 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 10783 in captures, 3 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool: 0x1065800000 (8 MB, captured, state 2): 30; 0x7fd9400000 (4 MB, captured, state 2): 4;
[hos host] vk: replay reads of guest memory as submitted: 880000 (555860 pages from the captures)
[hos ModuleSystemWorker1] vk: readbacks of GPU results: 1542 of 3000 waited for their write-back, 0.04 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: sparse mirrors: 61, 734 MB with memory of 980 MB (245 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 111 binds (13.4 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 438 dirty pages from their submits' captures, 42360 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3291 runs, 1484.8 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 10391 in captures, 1 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 71 live (1040 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 501 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: 11 textures retired (1375 left, 3054 MB): budget 0, drawn over 0, dead targets 11
[hos host] vk: NVN2 program b81f83fe05a2a32a (stage 0) lowered with extended registers (939 REGMAP words)
[hos host] vk: replay reads of guest memory as submitted: 900000 (569632 pages from the captures)
[hos host] vk: mirror of pool 0x7fdf800000 (4 MB) given back: idle, 6028 submissions since its sync
[hos host] vk: mirror of pool 0x7fdf000000 (4 MB) given back: idle, 6044 submissions since its sync
[hos host] vk: 11 textures retired (1379 left, 3056 MB): budget 0, drawn over 0, dead targets 11
[hos host] vk: mirror syncs (600 submits): 430 dirty pages from their submits' captures, 41945 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3151 runs, 1424.4 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 10852 in captures, 1 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos host] vk: replay reads of guest memory as submitted: 920000 (584316 pages from the captures)
[hos host] vk: program picks: 1425447 kept (821382 by the last picks' textures, a uniform buffer bound since), 685 new, 573867 with other textures (of 2000000)
[hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #20000: event 0x100d6c8038 mode 0 value 19999 (lr 0x8066189c)
[hos host] vk: 1 of 1 small textures the GPU drew written into their memory in 0.4 ms, 1 frames after their copies were recorded, the first #1833 0x117015a000 260x260 levels 9 NVN 0xd (44 so far, 9536 KB, 8 ms; 0 left, the CPU wrote their memory since; 0 dropped, drawn over or gone; 0 failed)
[hos host] vk: readback pages refreshed from guest memory: 532275 pages so far (0 held: may be written ahead in their submission)
[hos sead::MainThread] vk: capture: a submit 0.11 ms (lock 0.01, scan 0.04 over 942 ranges, 2947 MB), 319 pages written, 319 copied (1.2 MB)
[hos host] vk: a capture taken (ms): all 0.006; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 25 kept (112 MB), 7 spare buffers, 3818 texture pages copied (14 MB)
[hos host] vk: sparse mirrors: 59, 730 MB with memory of 972 MB (241 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 111 binds (13.4 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 432 dirty pages from their submits' captures, 43545 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3281 runs, 1489.8 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 10428 in captures, 3 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 71 live (1040 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: 11 textures retired (1393 left, 3064 MB): budget 0, drawn over 0, dead targets 11
[hos host] vk: replay reads of guest memory as submitted: 940000 (598430 pages from the captures)
[hos host] vk: NVN2 program 0a28f859e5e692d2 (stage 0) lowered with extended registers (1127 REGMAP words)
[hos host] vk: NVN2 program 5cfe9139ec244422 (stage 0) lowered with extended registers (1132 REGMAP words)
[hos host] vk: NVN2 program 42be3be9f8a7413b (stage 0) lowered with extended registers (944 REGMAP words)
[hos host] vk: mirror syncs (600 submits): 422 dirty pages from their submits' captures, 44394 from earlier ones', 33 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3366 runs, 1495.4 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 11050 in captures, 4 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool: 0x1065800000 (8 MB, captured, state 2): 25; 0x7fd9400000 (4 MB, captured, state 2): 7; 0x1066000000 (4 MB, captured, state 2): 1;
[hos host] vk: 11 textures retired (1398 left, 3065 MB): budget 0, drawn over 0, dead targets 11
[hos sead::MainThread] nvn: CommandBufferWaitEvent #35000: event 0x100d6c8048 mode 0 value 20687 (now 20668) (lr 0x806661f8)
[hos host] vk: replay reads of guest memory as submitted: 960000 (612854 pages from the captures)
[hos host] vk: a frame: 75 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.41, present 0.09, draw 3.74, descriptors 1.43, texture lookups 0.09, uploads 0.01, pipelines 0.14, programs 0.67, commands 1.08, dispatch 0.64, memory sync 0.18, queue submit 0.47, slot wait 0.04
[hos host] vk: a frame: mirrors 85 (733 MB): 7.19 MB synced in 1135.2 copies, 62.22 MB written back
[hos host] vk: 3840 presents, 60.0 fps; a frame: 1920 draws (0 skipped), 137 dispatches, 171 passes, 154 barriers, 6 submits, 0.3 uploads (0.1 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 9345 pipelines (1676 ms), 0 programs (0 failed), 1398 textures (3065 MB)
[hos host] vk: host time in GPU resource waits: 0.29 ms a frame (fences 0.03, timelines 0.26, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 525.6 full barriers recorded, 224.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 4.7; 0x8: 3.0; 0x9: 1.0; 0x10: 2.7; 0x11: 42.0; 0x12: 76.3; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0; 0x9b: 0.0;
[hos host] vk: GPU time 8.3 ms a frame (the longest submission 2.0 ms); 0.8 textures made a frame
[hos host] vk: a frame: 0.03 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: 11 textures retired (1398 left, 3065 MB): budget 0, drawn over 0, dead targets 11
[hos host] vk: replay reads of guest memory as submitted: 980000 (626819 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 60, 733 MB with memory of 976 MB (242 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 112 binds (13.5 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 440 dirty pages from their submits' captures, 43605 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3335 runs, 1493.4 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 11023 in captures, 1 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 71 live (1040 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: mirror of pool 0x7fd3400000 (8 MB) given back: idle, 6064 submissions since its sync
[hos host] vk: 11 textures retired (1398 left, 3065 MB): budget 0, drawn over 0, dead targets 11
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 1258 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos ModuleSystemWorker5] nvn: 300000 recordings made, 29609 live copies (9.4 MB), 379 texture copies; 5 command buffers' segments (2.3 MB)
[hos host] vk: replay reads of guest memory as submitted: 1000000 (640890 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 459 dirty pages from their submits' captures, 44409 from earlier ones', 35 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3312 runs, 1491.0 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 11435 in captures, 5 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool: 0x1065800000 (8 MB, captured, state 2): 28; 0x7fd9400000 (4 MB, captured, state 2): 7;
[hos host] vk: texture #1077 0x10000e38800 480x270 NVN 0x3f: the GPU wrote its storage (submission 20441): uploaded again
[hos host] vk: upload over a drawn image: #1077 0x10000e38800 480x270x1 x1 NVN 0x3f at present 3898 (texture frame 3899), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos host] vk: texture 0x10000e38800 480x270x1 x1 levels 1 NVN 0x3f (720 KB of storage) re-uploaded (its memory was written; flags 0x8): a GPU write into its storage, 720 KB of it, over what the GPU wrote (finalized since)
[hos host] vk: 11 textures retired (1398 left, 3065 MB): budget 0, drawn over 0, dead targets 11
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.02
[hos host] vk: slow submit: 15.1 ms: draw 12.6 descriptors 1.3 texture lookups 1.1 programs 9.7
[hos sead::MainThread] nvn: GPU waits in 5 s: 20 sync waits (156 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: replay reads of guest memory as submitted: 1020000 (655462 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.11 ms (lock 0.01, scan 0.04 over 942 ranges, 2953 MB), 321 pages written, 321 copied (1.3 MB)
[hos host] vk: a capture taken (ms): all 0.005; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.003, bytes copied 0.000; 25 kept (122 MB), 12 spare buffers, 3819 texture pages copied (14 MB)
[hos host] vk: program picks: 1574522 kept (913565 by the last picks' textures, a uniform buffer bound since), 754 new, 624723 with other textures (of 2200000)
[hos host] vk: 9 textures retired (1416 left, 3073 MB): budget 0, drawn over 0, dead targets 9
[hos host] vk: sparse mirrors: 60, 737 MB with memory of 976 MB (238 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 113 binds (13.5 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 502 dirty pages from their submits' captures, 43861 from earlier ones', 1 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3471 runs, 1499.8 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 10919 in captures, 5 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool: 0x1066000000 (4 MB, captured, state 2): 1;
[hos host] vk: imports: 71 live (1040 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: 1 of 1 small textures the GPU drew written into their memory in 0.5 ms, 1 frames after their copies were recorded, the first #1941 0x116de5f000 260x260 levels 9 NVN 0xd (45 so far, 9746 KB, 8 ms; 0 left, the CPU wrote their memory since; 0 dropped, drawn over or gone; 0 failed)
[hos host] vk: mirror of pool 0x7fd3c00000 (4 MB) given back: idle, 6003 submissions since its sync
[hos host] vk: replay reads of guest memory as submitted: 1040000 (671582 pages from the captures)
[hos host] vk: NVN2 program 5cecd4d153b207e0 (stage 0) lowered with extended registers (1134 REGMAP words)
[hos host] vk: readback pages refreshed from guest memory: 598800 pages so far (0 held: may be written ahead in their submission)
[hos Presentation Thread] vi: 3931 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 3, 15.5-17.8 294, 17.8-22 3, 22-30 0, 30-40 0, over 40 0
[hos host] vk: 2 of 2 small textures the GPU drew written into their memory in 0.7 ms, 1 frames after their copies were recorded, the first #1947 0x116de94000 260x260 levels 9 NVN 0xd (47 so far, 10165 KB, 9 ms; 0 left, the CPU wrote their memory since; 0 dropped, drawn over or gone; 0 failed)
[hos host] vk: mirror syncs (600 submits): 551 dirty pages from their submits' captures, 48964 from earlier ones', 31 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4088 runs, 1649.3 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 13012 in captures, 4 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool: 0x1065800000 (8 MB, captured, state 2): 23; 0x7fd9400000 (4 MB, captured, state 2): 7; 0x1066000000 (4 MB, captured, state 2): 1;
[hos ModuleSystemWorker1] vk: readbacks of GPU results: 1545 of 3000 waited for their write-back, 0.02 ms each; 0 looked at the stopped queues first, 1 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos tera::FileResourceMgr] vcores: 236265 takes, 38515 waits (mean 34 us, longest 9.4 ms), 18961 kicks, 18442 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: replay reads of guest memory as submitted: 1060000 (687144 pages from the captures)
[hos host] vk: 1 of 1 small textures the GPU drew written into their memory in 0.3 ms, 1 frames after their copies were recorded, the first #1957 0x11704f4000 260x260 levels 9 NVN 0xd (48 so far, 10374 KB, 9 ms; 0 left, the CPU wrote their memory since; 0 dropped, drawn over or gone; 0 failed)
[hos host] vk: texture #1729 0x100079b2a00 384x384 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 3956 (drawn at 3895)
[hos host] vk: 12 textures retired (1443 left, 3097 MB): budget 0, drawn over 0, dead targets 12
[hos host] vk: a frame: 45 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.15, present 0.08, draw 3.59, descriptors 1.35, texture lookups 0.10, uploads 0.01, pipelines 0.13, programs 0.70, commands 0.99, dispatch 0.66, memory sync 0.19, queue submit 0.44, slot wait 0.04
[hos host] vk: a frame: mirrors 87 (735 MB): 7.33 MB synced in 1147.7 copies, 62.94 MB written back
[hos host] vk: 3960 presents, 60.0 fps; a frame: 1786 draws (0 skipped), 147 dispatches, 168 passes, 153 barriers, 6 submits, 0.3 uploads (0.1 MB), 83 ub updates (58 overlays), GPU-bound wait 0.0 ms (recording slots only); 9346 pipelines (1677 ms), 0 programs (0 failed), 1443 textures (3097 MB)
[hos host] vk: host time in GPU resource waits: 0.18 ms a frame (fences 0.03, timelines 0.15, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 528.7 full barriers recorded, 222.8 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 4.7; 0x8: 3.0; 0x9: 1.0; 0x10: 2.7; 0x11: 42.0; 0x12: 75.9; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0; 0x9b: 0.0;
[hos host] vk: GPU time 7.8 ms a frame (the longest submission 2.1 ms); 0.8 textures made a frame
[hos host] vk: a frame: 0.06 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 60, 735 MB with memory of 976 MB (240 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 114 binds (13.6 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 527 dirty pages from their submits' captures, 47773 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4102 runs, 1656.6 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 12991 in captures, 1 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 72 live (1044 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 1643 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 1080000 (701994 pages from the captures)
[hos host] vk: queues ordered by their events: 18000 submissions stopped at a wait, 17996 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 38476, not met 0; captures at a CPU event's wait 1762, 0 of them at a wait met on arrival
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 637 dirty pages from their submits' captures, 54479 from earlier ones', 5 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4102 runs, 1648.8 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 13515 in captures, 2 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool: 0x7fd9400000 (4 MB, captured, state 2): 5;
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03
[hos host] vk: replay reads of guest memory as submitted: 1100000 (716042 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.01, scan 0.04 over 941 ranges, 2963 MB), 346 pages written, 346 copied (1.4 MB)
[hos host] vk: a capture taken (ms): all 0.006; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 25 kept (138 MB), 12 spare buffers, 4847 texture pages copied (18 MB)
[hos host] vk: sparse mirrors: 60, 735 MB with memory of 976 MB (240 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 114 binds (13.6 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 646 dirty pages from their submits' captures, 52616 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4073 runs, 1698.1 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 12882 in captures, 2 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 72 live (1044 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: program picks: 1721714 kept (1005139 by the last picks' textures, a uniform buffer bound since), 773 new, 677512 with other textures (of 2400000)
[hos host] vk: replay reads of guest memory as submitted: 1120000 (729805 pages from the captures)
[hos host] vk: 12 textures retired (1443 left, 3097 MB): budget 0, drawn over 0, dead targets 12
[hos sead::MainThread] nvn: CommandBufferWaitEvent #40000: event 0x100d6c8048 mode 0 value 24487 (now 24468) (lr 0x806661f8)
[hos BaseProcExecutor5] oc: the note wait turned on (buttons) (the action's kind 1)
[hos host] vk: NVN2 program 44fbb5c9964cd5aa (stage 0) lowered with extended registers (1075 REGMAP words)
[hos host] vk: mirror syncs (600 submits): 508 dirty pages from their submits' captures, 50973 from earlier ones', 34 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4009 runs, 1716.5 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 13427 in captures, 4 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool: 0x1065800000 (8 MB, captured, state 2): 34;
[hos host] vk: texture 0x10007baee00 640x360x1 x1 levels 1 NVN 0x34 -> vk 126 (1500 textures, 3150 MB)
[hos host] vk: texture #1655 0x10007772800 796x796 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 4049 (drawn at 3649)
[hos host] vk: 38 textures retired (1486 left, 3118 MB): budget 0, drawn over 0, dead targets 38
[hos host] vk: texture 0x100089c9800 853x480x1 x1 levels 1 NVN 0x29 -> vk 97 (1500 textures, 3154 MB)
[hos host] vk: replay reads of guest memory as submitted: 1140000 (745361 pages from the captures)
[hos host] vk: 132 textures retired (1497 left, 3166 MB): budget 0, drawn over 0, dead targets 132
[hos host] vk: texture 0x10007ef8c00 640x360x1 x1 levels 1 NVN 0x3f -> vk 122 (1500 textures, 3174 MB)
[hos host] vk: readback pages refreshed from guest memory: 667579 pages so far (0 held: may be written ahead in their submission)
[hos ModuleSystemWorker5] nvn: CommandBufferSignalEvent #25000: event 0x100d6c8044 mode 0 value 24999 (lr 0x802742f0)
[hos host] vk: 128 textures retired (1509 left, 3248 MB): budget 0, drawn over 0, dead targets 128
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 522 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: sparse mirrors: 60, 735 MB with memory of 976 MB (240 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 114 binds (13.6 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 525 dirty pages from their submits' captures, 60949 from earlier ones', 149 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3135 runs, 1830.8 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 15399 in captures, 5 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool: 0x1052400000 (4 MB, captured, state 2): 127; 0x1065800000 (8 MB, captured, state 2): 22;
[hos host] vk: imports: 72 live (1044 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: 13 textures retired (1517 left, 3308 MB): budget 0, drawn over 0, dead targets 13
[hos host] vk: a frame: 35 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 5.83, present 0.07, draw 3.18, descriptors 1.23, texture lookups 0.29, uploads 0.01, pipelines 0.12, programs 0.53, commands 0.91, dispatch 0.66, memory sync 0.19, queue submit 0.41, slot wait 0.04
[hos host] vk: a frame: mirrors 87 (735 MB): 7.84 MB synced in 1200.8 copies, 62.67 MB written back
[hos host] vk: 4080 presents, 60.1 fps; a frame: 1552 draws (0 skipped), 137 dispatches, 167 passes, 152 barriers, 6 submits, 0.4 uploads (0.0 MB), 83 ub updates (58 overlays), GPU-bound wait 0.0 ms (recording slots only); 9348 pipelines (1677 ms), 0 programs (0 failed), 1517 textures (3308 MB)
[hos host] vk: host time in GPU resource waits: 0.16 ms a frame (fences 0.03, timelines 0.13, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 509.5 full barriers recorded, 215.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 4.2; 0x8: 3.0; 0x9: 1.0; 0x10: 2.2; 0x11: 41.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 7.3 ms a frame (the longest submission 2.8 ms); 3.3 textures made a frame
[hos host] vk: a frame: 0.02 MB unswizzled on the CPU in 0.01 ms
[hos host] vk: replay reads of guest memory as submitted: 1160000 (761515 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03
[hos ModuleSystemWorker4] vk: readbacks of GPU results: 1458 of 3000 waited for their write-back, 0.01 ms each; 0 looked at the stopped queues first, 5 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: mirror syncs (600 submits): 704 dirty pages from their submits' captures, 65860 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3321 runs, 2058.1 MB compared; 1 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 16045 in captures, 4 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.01, scan 0.04 over 941 ranges, 2963 MB), 354 pages written, 354 copied (1.4 MB)
[hos host] vk: a capture taken (ms): all 0.005; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.003, bytes copied 0.000; 25 kept (82 MB), 10 spare buffers, 4857 texture pages copied (18 MB)
[hos host] vk: recorder: 7526322 packets run in 10.0 s (busy 0.94 s, spun idle 3.07 s, slept 3853 times, 786 of them under 200 us), 0 calls made directly (no room); the replay waited for it 37193 times, 59.16 ms in all, the longest 0.07 ms; vkEndCommandBuffer 14748/35.43 ms (max 0.07), replay_mu unlock 7066/13.60 ms (max 0.06), vkResetDescriptorPool 14748/9.54 ms (max 0.03), direct recording 598/0.52 ms (max 0.02), vkDestroyImageView 26/0.04 ms (max 0.00), vkQueueBindSparse 7/0.04 ms (max 0.01)
[hos host] vk: render targets drawn over from another start, let go: 811 so far (1967 MB)
[hos ModuleSystemWorker3] nvn: DrawMeshTasksIndirect: 60000 so far (x1 0x117b427040 x2 0x6001d40 x3 0x117b427000 x4 0xf33080)
[hos host] vk: replay reads of guest memory as submitted: 1180000 (776533 pages from the captures)
[hos host] vk: mirror of pool 0x7fc1000000 (4 MB) given back: idle, 6031 submissions since its sync
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 59, 732 MB with memory of 972 MB (239 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 114 binds (13.6 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 710 dirty pages from their submits' captures, 65017 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3160 runs, 1995.7 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 15894 in captures, 3 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 72 live (1044 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: replay reads of guest memory as submitted: 1200000 (791574 pages from the captures)
[hos host] vk: 1 textures retired (1518 left, 3328 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: 11 textures retired (1507 left, 3317 MB): budget 0, drawn over 11, dead targets 0
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 500 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: mirror syncs (600 submits): 681 dirty pages from their submits' captures, 65815 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3147 runs, 1994.8 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 16374 in captures, 3 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: program picks: 1870152 kept (1099962 by the last picks' textures, a uniform buffer bound since), 786 new, 729061 with other textures (of 2600000)
[hos host] vk: 10 textures retired (1497 left, 3267 MB): budget 0, drawn over 10, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 1220000 (806596 pages from the captures)
[hos host] vk: 10 textures retired (1487 left, 3183 MB): budget 0, drawn over 10, dead targets 0
[hos host] vk: memory: working set 10941 MB (peak 10942), private 19152 MB, staging 256 MB in 4 arenas
[hos host] vk: memory heaps: heap 0 (device): 108 blocks 6121 MB, 13380 allocations 5046 MB; used 6770 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 49 allocations 382 MB; used 1525 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 9 blocks 1152 MB, 174 images 688 MB; 41 free ranges, the largest 118 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1347 images 1858 MB; 414 free ranges, the largest 128 MB
[hos host] vk: render target images: 526 reused from the pool, 454 made new, 280 destroyed from it; it holds 37 (178 MB)
[hos host] vk: VRAM: 6770 MB used of 15280 MB allowed (1075 MB of it free in the blocks); textures 3183 MB (budget 10928 MB), 1487 textures
[hos host] vk: textures: decoded ASTC 1719 MB, rendered 900 MB (135 drawn in one frame, kept: 45367 KB), other 322 MB; used in the last 8 presents 1901 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 1 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 1 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 1295 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk: 54 MB: 0x1000247e200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1280 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 6 (881 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 5 (879 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 3 waited for it, 1.53 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03
[hos host] vk: status: 600 frames, the slowest 29.7 ms; VRAM 6.6 of 14.9 GB; NVIDIA DLSS: 600 frames drawn, 1 made, jitter +0.125 -0.278 px, actor motion 31511 draws in 600 frames (0.200 ms CPU a frame; poses 31654 read at the draw, 0 copied later), its images 98 MB, its own 143 MB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4881 queued, 4881 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3735 ms and 1110.7 MB read in all); 6773 programs (1590 of them compute variants without their code, 0 graphics programs no note names), 9186 graphics pipelines (0 not in a cache), 679 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 667 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7435 (4881 ready, 0 loading), 13747 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 679 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 13 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.76, present 0.11, draw 2.62, descriptors 1.03, texture lookups 0.10, uploads 0.00, pipelines 0.10, programs 0.44, commands 0.74, dispatch 0.57, memory sync 0.19, queue submit 0.35, slot wait 0.03
[hos host] vk: a frame: mirrors 87 (732 MB): 7.75 MB synced in 1177.3 copies, 60.56 MB written back
[hos host] vk: 4200 presents, 60.0 fps; a frame: 1222 draws (0 skipped), 93 dispatches, 161 passes, 147 barriers, 6 submits, 0.0 uploads (0.0 MB), 85 ub updates (59 overlays), GPU-bound wait 0.0 ms (recording slots only); 9348 pipelines (1677 ms), 0 programs (0 failed), 1487 textures (3183 MB)
[hos host] vk: host time in GPU resource waits: 0.17 ms a frame (fences 0.02, timelines 0.15, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 445.1 full barriers recorded, 203.7 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 39.0; 0x12: 77.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 7.1 ms a frame (the longest submission 2.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 3 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.66 ms a frame): its jobs 6.64 ms a frame (submits 6.15, presents 0.37, others 0.11), idle 10.03; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 159.28 jobs queued at a present); 3 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.94 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 3 captures at a CPU signal; the submits' waits read in 0.029 ms a frame; readbacks: 3000 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 6.66 ms after its hand-over (19.25 at most)
[hos host] vk: sparse mirrors: 59, 732 MB with memory of 972 MB (239 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 114 binds (13.6 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 673 dirty pages from their submits' captures, 65725 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3234 runs, 2054.4 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 15899 in captures, 3 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 72 live (1044 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.01, scan 0.04 over 941 ranges, 2963 MB), 347 pages written, 347 copied (1.4 MB)
[hos host] vk: a capture taken (ms): all 0.005; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.003, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 4857 texture pages copied (18 MB)
[hos host] vk: mirror of pool 0x7fddc00000 (8 MB) given back: idle, 6048 submissions since its sync
[hos host] vk: mirror of pool 0x7fde800000 (4 MB) given back: idle, 6036 submissions since its sync
[hos host] vk: mirror of pool 0x7fac800000 (4 MB) given back: idle, 6027 submissions since its sync
[hos host] vk: replay reads of guest memory as submitted: 1240000 (822306 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 738033 pages so far (0 held: may be written ahead in their submission)
[hos Presentation Thread] vi: 4232 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos AudioFrameworkThread] vcores: 217851 takes, 32679 waits (mean 34 us, longest 4.5 ms), 16643 kicks, 16256 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: mirror syncs (600 submits): 721 dirty pages from their submits' captures, 64842 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3127 runs, 1995.2 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 15750 in captures, 5 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] nvn: CommandBufferWaitEvent #45000: event 0x100d6c8048 mode 0 value 28287 (now 28268) (lr 0x806661f8)
[hos host] vk: replay reads of guest memory as submitted: 1260000 (837991 pages from the captures)
[hos ModuleSystemWorker3] nvn: 350000 recordings made, 29721 live copies (8.6 MB), 753 texture copies; 6 command buffers' segments (2.3 MB)
[hos ModuleSystemWorker3] vk: readbacks of GPU results: 1465 of 3000 waited for their write-back, 0.02 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 496 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: sparse mirrors: 56, 723 MB with memory of 956 MB (232 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 114 binds (13.6 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 713 dirty pages from their submits' captures, 64779 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3165 runs, 1995.1 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 15849 in captures, 5 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 72 live (1044 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos rmbl::VibrationThread] hid: 8192 vibration values, strongest 0.00 since the last count
[hos host] vk: replay reads of guest memory as submitted: 1280000 (853643 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 731 dirty pages from their submits' captures, 65306 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3244 runs, 2054.6 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 16179 in captures, 3 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.01, scan 0.04 over 941 ranges, 2963 MB), 347 pages written, 347 copied (1.4 MB)
[hos host] vk: a capture taken (ms): all 0.005; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.003, bytes copied 0.000; 25 kept (106 MB), 9 spare buffers, 4857 texture pages copied (18 MB)
[hos host] vk: a frame: 14 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.80, present 0.11, draw 2.67, descriptors 1.03, texture lookups 0.06, uploads 0.00, pipelines 0.10, programs 0.45, commands 0.76, dispatch 0.58, memory sync 0.19, queue submit 0.36, slot wait 0.03
[hos host] vk: a frame: mirrors 87 (723 MB): 7.70 MB synced in 1175.3 copies, 60.61 MB written back
[hos host] vk: 4320 presents, 60.0 fps; a frame: 1219 draws (0 skipped), 93 dispatches, 161 passes, 147 barriers, 6 submits, 0.0 uploads (0.0 MB), 85 ub updates (59 overlays), GPU-bound wait 0.0 ms (recording slots only); 9348 pipelines (1677 ms), 0 programs (0 failed), 1487 textures (3183 MB)
[hos host] vk: host time in GPU resource waits: 0.17 ms a frame (fences 0.02, timelines 0.15, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 444.6 full barriers recorded, 203.7 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 39.0; 0x12: 77.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 7.0 ms a frame (the longest submission 2.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #30000: event 0x100d6c8010 mode 0 value 30002 (lr 0x80660bcc)
[hos host] vk: replay reads of guest memory as submitted: 1300000 (869288 pages from the captures)
[hos host] vk: program picks: 2018319 kept (1194489 by the last picks' textures, a uniform buffer bound since), 786 new, 780894 with other textures (of 2800000)
[hos host] vk: sparse mirrors: 56, 723 MB with memory of 956 MB (232 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 114 binds (13.6 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 601 dirty pages from their submits' captures, 64510 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3243 runs, 2030.9 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 15774 in captures, 3 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 72 live (1044 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: replay reads of guest memory as submitted: 1320000 (885042 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 500 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: mirror syncs (600 submits): 662 dirty pages from their submits' captures, 64856 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3174 runs, 2006.4 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 16214 in captures, 4 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: readback pages refreshed from guest memory: 808125 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03
[hos host] vk: replay reads of guest memory as submitted: 1340000 (900757 pages from the captures)
[hos host] vk: sparse mirrors: 56, 723 MB with memory of 956 MB (232 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 114 binds (13.6 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 666 dirty pages from their submits' captures, 65152 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3269 runs, 2093.5 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 15733 in captures, 6 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 72 live (1044 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos sead::MainThread] vk: capture: a submit 0.12 ms (lock 0.01, scan 0.04 over 941 ranges, 2963 MB), 346 pages written, 346 copied (1.4 MB)
[hos host] vk: a capture taken (ms): all 0.005; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.003, bytes copied 0.000; 25 kept (106 MB), 8 spare buffers, 4856 texture pages copied (18 MB)
[a64] unimplemented import _ZN2nn3hid29IsOunceVibrationDeviceMountedERKNS0_21VibrationDeviceHandleE (lr 0x832b541c)
[a64] unimplemented import _ZN2nn5audio18SetVoiceSrcQualityEPNS0_9VoiceTypeENS1_10SrcQualityE (lr 0x8094266c)
[hos host] vk: 5 textures retired (1488 left, 3183 MB): budget 0, drawn over 0, dead targets 5
[hos ModuleSystemWorker3] vk: readbacks of GPU results: 1466 of 3000 waited for their write-back, 0.01 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos rmbl::VibrationThread] hid: vibration #8656: handle 00000003, low 0.01 @ 129 Hz, high 0.04 @ 334 Hz
[hos rmbl::VibrationThread] hid: vibration #8657: handle 00010003, low 0.01 @ 129 Hz, high 0.04 @ 334 Hz
[hos rmbl::VibrationThread] hid: vibration #8658: handle 00000003, low 0.02 @ 167 Hz, high 0.03 @ 372 Hz
[hos rmbl::VibrationThread] hid: vibration #8659: handle 00010003, low 0.02 @ 167 Hz, high 0.03 @ 372 Hz
[hos rmbl::VibrationThread] hid: vibration #8660: handle 00000003, low 0.00 @ 129 Hz, high 0.02 @ 389 Hz
[hos rmbl::VibrationThread] hid: vibration #8661: handle 00010003, low 0.00 @ 129 Hz, high 0.02 @ 389 Hz
[hos host] vk: mirror syncs (600 submits): 737 dirty pages from their submits' captures, 65930 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3164 runs, 2003.1 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 16248 in captures, 5 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] nvn: CommandBufferWaitEvent #50000: event 0x100d6c8048 mode 0 value 32087 (now 32068) (lr 0x806661f8)
[hos host] vk: replay reads of guest memory as submitted: 1360000 (916680 pages from the captures)
[hos host] vk: a frame: 17 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.70, present 0.06, draw 2.63, descriptors 1.02, texture lookups 0.06, uploads 0.00, pipelines 0.10, programs 0.44, commands 0.74, dispatch 0.57, memory sync 0.19, queue submit 0.35, slot wait 0.03
[hos host] vk: a frame: mirrors 87 (723 MB): 7.67 MB synced in 1172.8 copies, 61.27 MB written back
[hos host] vk: 4440 presents, 60.0 fps; a frame: 1207 draws (0 skipped), 93 dispatches, 160 passes, 146 barriers, 6 submits, 0.0 uploads (0.0 MB), 85 ub updates (59 overlays), GPU-bound wait 0.0 ms (recording slots only); 9348 pipelines (1677 ms), 0 programs (0 failed), 1491 textures (3184 MB)
[hos host] vk: host time in GPU resource waits: 0.11 ms a frame (fences 0.02, timelines 0.08, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 443.6 full barriers recorded, 203.4 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 39.0; 0x12: 77.0; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 7.0 ms a frame (the longest submission 2.7 ms); 0.1 textures made a frame
[hos host] vk: a frame: 0.01 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: texture 0x100022cda00 426x240x1 x1 levels 1 NVN 0x34 -> vk 126 (1500 textures, 3204 MB)
[hos host] vk: texture #248 0x10002041400 853x480 x1 NVN 0x1 the GPU drew, finalized by the game, sampled again at frame 4452 (drawn at 2920)
[hos host] vk: texture #249 0x100020b1600 853x480 x1 NVN 0x1 the GPU drew, finalized by the game, sampled again at frame 4452 (drawn at 2920)
[hos host] vk: texture #250 0x10001fd1200 853x480 x1 NVN 0x1 the GPU drew, finalized by the game, sampled again at frame 4452 (drawn at 2920)
[hos host] vk: texture #308 0x100024d0e00 1707x960 x1 NVN 0x25 the GPU drew, finalized by the game, sampled again at frame 4452 (drawn at 2920)
[hos host] vk: texture #2382 0x10001410600 1707x960 NVN 0xa: the GPU wrote its storage (submission 31158): uploaded again
[hos host] vk: upload over a drawn image: #2382 0x10001410600 1707x960x1 x1 NVN 0xa at present 4453 (texture frame 4454), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos host] vk: texture 0x10001410600 1707x960x1 x1 levels 1 NVN 0xa (6848 KB of storage) re-uploaded (its memory was written; flags 0x8): a GPU write into its storage, 6848 KB of it, over what the GPU wrote (finalized since)
[hos host] vk: 54 textures retired (1485 left, 3138 MB): budget 0, drawn over 1, dead targets 53
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 500 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 56, 723 MB with memory of 956 MB (232 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 114 binds (13.6 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 664 dirty pages from their submits' captures, 65658 from earlier ones', 13 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3260 runs, 2074.8 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 16370 in captures, 4 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool: 0x100dc00000 (20 MB, captured, state 2): 13;
[hos host] vk: imports: 72 live (1044 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: replay reads of guest memory as submitted: 1380000 (932513 pages from the captures)
[hos host] vk: program picks: 2166439 kept (1287739 by the last picks' textures, a uniform buffer bound since), 793 new, 832767 with other textures (of 3000000)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03
[hos sead::MainThread] vk: capture: a submit 0.12 ms (lock 0.01, scan 0.04 over 941 ranges, 2965 MB), 346 pages written, 346 copied (1.3 MB)
[hos host] vk: a capture taken (ms): all 0.005; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.003, bytes copied 0.000; 25 kept (106 MB), 8 spare buffers, 4856 texture pages copied (18 MB)
[hos host] vk: mirror syncs (600 submits): 822 dirty pages from their submits' captures, 66124 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3297 runs, 2055.8 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 16637 in captures, 6 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos BaseProcExecutor4] oc: the note wait turned off (the action's kind 1)
[hos host] vk: texture #780 0x100021f1c00 853x480 x1 NVN 0x1 the GPU drew, finalized by the game, sampled again at frame 4512 (drawn at 4451)
[hos host] vk: texture #781 0x10002261e00 853x480 x1 NVN 0x1 the GPU drew, finalized by the game, sampled again at frame 4512 (drawn at 4451)
[hos host] vk: texture 0x1000818c800 853x480x1 x1 levels 1 NVN 0x25 -> vk 37 (1500 textures, 3286 MB)
[hos host] vk: replay reads of guest memory as submitted: 1400000 (948577 pages from the captures)
[hos host] vk: 123 textures retired (1468 left, 3243 MB): budget 0, drawn over 0, dead targets 123
[hos host] vk: texture 0x10008196400 1707x960x1 x1 levels 1 NVN 0x3f -> vk 122 (1500 textures, 3344 MB)
[hos host] vk: NVN2 program 93a865e7c6041920 (stage 7) lowered with extended registers (323 REGMAP words)
[hos host] vk: NVN2 program b61bb3f963ac32d6 (stage 7) lowered with extended registers (305 REGMAP words)
[hos host] vk: NVN2 program 41eed82125d072ac (stage 0) lowered with extended registers (1132 REGMAP words)
[hos host] vk: NVN2 program 7d5ec9c665cb4958 (stage 0) lowered with extended registers (1127 REGMAP words)
[hos host] vk: 78 textures retired (1486 left, 3351 MB): budget 0, drawn over 0, dead targets 78
[hos host] vk: NVN2 program bc3f20d8b42b27c1 (stage 7) lowered with extended registers (2308 REGMAP words)
[hos Presentation Thread] vi: 4533 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 2, 15.5-17.8 296, 17.8-22 3, 22-30 0, 30-40 0, over 40 0
[hos host] vk: 1 of 1 small textures the GPU drew written into their memory in 0.4 ms, 1 frames after their copies were recorded, the first #2632 0x116f437000 260x260 levels 9 NVN 0xd (49 so far, 10584 KB, 10 ms; 0 left, the CPU wrote their memory since; 0 dropped, drawn over or gone; 0 failed)
[hos host] vk: NVN2 program dda3828b340a8769 (stage 0) lowered with extended registers (1138 REGMAP words)
[hos aal::LowPrioWorkerThread] vcores: 211940 takes, 29178 waits (mean 34 us, longest 4.6 ms), 14929 kicks, 14599 yields, 0 starved grants, 0 escapes in 5 s
[hos ModuleSystemWorker5] nvn: DrawMeshTasksIndirect: 80000 so far (x1 0x117b427030 x2 0 x3 0x117b427000 x4 0xf33080)
[hos host] vk: sparse mirrors: 58, 779 MB with memory of 1020 MB (240 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 116 binds (14.0 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 695 dirty pages from their submits' captures, 70790 from earlier ones', 42 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3874 runs, 2365.1 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 18378 in captures, 6 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool: 0x1065800000 (8 MB, captured, state 2): 42;
[hos host] vk: imports: 73 live (1104 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: texture 0x7fcc3ef200 93x93x1 x1 levels 1 NVN 0x49 -> vk 139 (1500 textures, 3358 MB)
[hos host] vk: replay reads of guest memory as submitted: 1420000 (965650 pages from the captures)
[hos host] vk: a frame: 15 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.58, present 0.07, draw 2.46, descriptors 0.94, texture lookups 0.16, uploads 0.03, pipelines 0.09, programs 0.47, commands 0.65, dispatch 0.58, memory sync 0.20, queue submit 0.34, slot wait 0.03
[hos host] vk: a frame: mirrors 89 (779 MB): 7.94 MB synced in 1144.5 copies, 60.79 MB written back
[hos host] vk: 4560 presents, 60.0 fps; a frame: 1023 draws (0 skipped), 95 dispatches, 148 passes, 142 barriers, 6 submits, 0.7 uploads (0.1 MB), 85 ub updates (59 overlays), GPU-bound wait 0.0 ms (recording slots only); 9349 pipelines (1677 ms), 0 programs (0 failed), 1506 textures (3358 MB)
[hos host] vk: host time in GPU resource waits: 0.23 ms a frame (fences 0.02, timelines 0.21, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 430.0 full barriers recorded, 196.5 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x10: 0.0; 0x11: 39.0; 0x12: 72.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0; 0x9b: 0.0;
[hos host] vk: GPU time 6.9 ms a frame (the longest submission 2.7 ms); 2.3 textures made a frame
[hos host] vk: a frame: 0.10 MB unswizzled on the CPU in 0.03 ms
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 555 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: readback pages refreshed from guest memory: 878362 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: 1 textures retired (1511 left, 3377 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: mirror syncs (600 submits): 642 dirty pages from their submits' captures, 72084 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3883 runs, 2482.3 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 19433 in captures, 7 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] vk: readbacks of GPU results: 1445 of 3000 waited for their write-back, 0.02 ms each; 0 looked at the stopped queues first, 4 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #35000: event 0x100d6c8008 mode 0 value 34997 (lr 0x80660f34)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03
[hos host] vk: replay reads of guest memory as submitted: 1440000 (981839 pages from the captures)
[hos sead::MainThread] vk: capture: a submit 0.12 ms (lock 0.01, scan 0.04 over 898 ranges, 2982 MB), 333 pages written, 333 copied (1.3 MB)
[hos host] vk: a capture taken (ms): all 0.005; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.003, bytes copied 0.000; 25 kept (106 MB), 8 spare buffers, 4909 texture pages copied (19 MB)
[hos host] vk: sparse mirrors: 58, 779 MB with memory of 1020 MB (240 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 116 binds (14.0 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 681 dirty pages from their submits' captures, 71716 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3731 runs, 2462.6 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 18863 in captures, 5 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 73 live (1104 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: 8 textures retired (1503 left, 3304 MB): budget 0, drawn over 8, dead targets 0
[hos sead::MainThread] nvn: CommandBufferWaitEvent #55000: event 0x100d6c8048 mode 0 value 35906 (now 35887) (lr 0x806661f8)
[hos host] vk: replay reads of guest memory as submitted: 1460000 (998019 pages from the captures)
[hos host] vk: 20 textures retired (1496 left, 3237 MB): budget 0, drawn over 5, dead targets 15
[hos host] vk: 2 textures retired (1494 left, 3214 MB): budget 0, drawn over 2, dead targets 0
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 775 dirty pages from their submits' captures, 71157 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3681 runs, 2414.7 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 18924 in captures, 4 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 518 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: a frame: 15 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 3.84, present 0.12, draw 2.00, descriptors 0.79, texture lookups 0.05, uploads 0.01, pipelines 0.08, programs 0.33, commands 0.55, dispatch 0.56, memory sync 0.19, queue submit 0.30, slot wait 0.03
[hos host] vk: a frame: mirrors 89 (779 MB): 6.92 MB synced in 1069.3 copies, 60.41 MB written back
[hos host] vk: 4680 presents, 60.0 fps; a frame: 768 draws (0 skipped), 87 dispatches, 142 passes, 140 barriers, 6 submits, 1.2 uploads (0.0 MB), 85 ub updates (59 overlays), GPU-bound wait 0.0 ms (recording slots only); 9349 pipelines (1677 ms), 0 programs (0 failed), 1494 textures (3214 MB)
[hos host] vk: host time in GPU resource waits: 0.21 ms a frame (fences 0.02, timelines 0.19, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 409.6 full barriers recorded, 193.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.1; 0x8: 3.0; 0x9: 1.0; 0x10: 0.1; 0x11: 39.0; 0x12: 70.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 7.0 ms a frame (the longest submission 2.6 ms); 0.2 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: replay reads of guest memory as submitted: 1480000 (1014102 pages from the captures)
[hos host] vk: 1 textures retired (1493 left, 3211 MB): budget 0, drawn over 0, dead targets 1
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03
[hos sead::MainThread] vk: capture: a submit 0.12 ms (lock 0.01, scan 0.04 over 904 ranges, 2982 MB), 326 pages written, 326 copied (1.3 MB)
[hos host] vk: a capture taken (ms): all 0.005; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.003, bytes copied 0.000; 25 kept (136 MB), 7 spare buffers, 4909 texture pages copied (19 MB)
[hos host] vk: texture 0x10001699000 1707x960x1 x1 levels 1 NVN 0xa -> vk 100 (1500 textures, 3227 MB)
[hos host] vk: texture #782 0x10002181a00 853x480 x1 NVN 0x1 the GPU drew, finalized by the game, sampled again at frame 4707 (drawn at 4451)
[hos host] vk: texture #1088 0x10000e38800 427x240 x1 NVN 0x14 the GPU drew, finalized by the game, sampled again at frame 4707 (drawn at 4451)
[hos host] vk: upload over a drawn image: #1088 0x10000e38800 427x240x1 x1 NVN 0x14 at present 4706 (texture frame 4707), finalized, 370 KB dirty in 1 ranges
[hos host] vk: texture #1089 0x10000ea4a00 1707x960 x1 NVN 0x25 the GPU drew, finalized by the game, sampled again at frame 4707 (drawn at 4451)
[hos host] vk: sparse mirrors: 59, 783 MB with memory of 1024 MB (240 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 117 binds (14.0 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 684 dirty pages from their submits' captures, 71742 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3729 runs, 2447.6 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 18518 in captures, 5 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 73 live (1104 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: texture #1088 0x10000e38800 427x240 NVN 0x14: the GPU wrote its storage (submission 32943): uploaded again
[hos host] vk: upload over a drawn image: #1088 0x10000e38800 427x240x1 x1 NVN 0x14 at present 4707 (texture frame 4708), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos host] vk: recorder: 4830048 packets run in 10.0 s (busy 0.73 s, spun idle 2.27 s, slept 4242 times, 721 of them under 200 us), 0 calls made directly (no room); the replay waited for it 28112 times, 46.71 ms in all, the longest 0.12 ms; vkEndCommandBuffer 10153/24.82 ms (max 0.06), replay_mu unlock 7189/13.69 ms (max 0.08), vkResetDescriptorPool 10154/7.68 ms (max 0.12), direct recording 600/0.49 ms (max 0.01), vkDestroyImageView 13/0.02 ms (max 0.00), vkQueueBindSparse 3/0.01 ms (max 0.01)
[hos host] vk: render targets drawn over from another start, let go: 1126 so far (2672 MB)
[hos host] vk: 42 textures retired (1504 left, 3213 MB): budget 0, drawn over 2, dead targets 40
[hos host] vk: texture #343 0x116c654000 260x260 x1 NVN 0xd the GPU drew, finalized by the game, sampled again at frame 4711 (drawn at 2907)
[hos host] vk: texture #1833 0x117015a000 260x260 x1 NVN 0xd the GPU drew, finalized by the game, sampled again at frame 4711 (drawn at 3803)
[hos ModuleSystemWorker3] nvn: 400000 recordings made, 29759 live copies (9.1 MB), 1007 texture copies; 5 command buffers' segments (2.3 MB)
[hos host] vk: texture #341 0x116c61f000 260x260 x1 NVN 0xd the GPU drew, finalized by the game, sampled again at frame 4715 (drawn at 2907)
[hos host] vk: texture #379 0x116fcd2000 260x260 x1 NVN 0xd the GPU drew, finalized by the game, sampled again at frame 4717 (drawn at 2910)
[hos host] vk: 12 textures retired (1534 left, 3232 MB): budget 0, drawn over 0, dead targets 12
[hos host] vk: program picks: 2299816 kept (1361344 by the last picks' textures, a uniform buffer bound since), 824 new, 899359 with other textures (of 3200000)
[hos host] vk: replay reads of guest memory as submitted: 1500000 (1029888 pages from the captures)
[hos host] vk: 24 textures retired (1538 left, 3243 MB): budget 0, drawn over 0, dead targets 24
[hos host] vk: mirror syncs (600 submits): 561 dirty pages from their submits' captures, 55236 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4222 runs, 1743.9 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 13376 in captures, 4 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: 12 textures retired (1539 left, 3246 MB): budget 0, drawn over 0, dead targets 12
[hos host] vk: 12 textures retired (1541 left, 3251 MB): budget 0, drawn over 0, dead targets 12
[hos sead::MainThread] vk: readbacks of GPU results: 1459 of 3000 waited for their write-back, 0.02 ms each; 0 looked at the stopped queues first, 3 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: replay reads of guest memory as submitted: 1520000 (1044056 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 948381 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: 52 textures retired (1562 left, 3286 MB): budget 0, drawn over 3, dead targets 49
[hos host] vk: sparse mirrors: 64, 793 MB with memory of 1048 MB (254 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 122 binds (14.4 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 496 dirty pages from their submits' captures, 47977 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3854 runs, 1636.8 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 12613 in captures, 2 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 74 live (1108 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: 12 textures retired (1568 left, 3303 MB): budget 0, drawn over 0, dead targets 12
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 284 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 1540000 (1059008 pages from the captures)
[hos host] vk: texture #2722 0x10007772800 806x806 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 4774 (drawn at 4712)
[hos host] vk: texture #2750 0x10007a2ea00 384x384 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 4784 (drawn at 4723)
[hos host] vk: mirror syncs (600 submits): 448 dirty pages from their submits' captures, 44409 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3613 runs, 1534.4 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 12033 in captures, 3 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: memory: working set 10954 MB (peak 10956), private 19103 MB, staging 128 MB in 2 arenas
[hos host] vk: memory heaps: heap 0 (device): 105 blocks 5865 MB, 14484 allocations 5126 MB; used 6518 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 49 allocations 382 MB; used 1589 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 8 blocks 1024 MB, 243 images 790 MB; 43 free ranges, the largest 82 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1400 images 1902 MB; 440 free ranges, the largest 128 MB
[hos host] vk: render target images: 707 reused from the pool, 720 made new, 477 destroyed from it; it holds 75 (195 MB)
[hos host] vk: VRAM: 6518 MB used of 15280 MB allowed (739 MB of it free in the blocks); textures 3311 MB (budget 10928 MB), 1571 textures
[hos host] vk: textures: decoded ASTC 1751 MB, rendered 984 MB (101 drawn in one frame, kept: 33576 KB), other 328 MB; used in the last 8 presents 2031 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 1 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 1 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 1895 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk: 54 MB: 0x1000247e200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 288 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 29 (10341 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 42x41x1 NVN 0x25: 1 (6 KB); 74x32x1 NVN 0x25: 1 (9 KB); 90x34x1 NVN 0x25: 1 (11 KB); 106x105x1 NVN 0x1: 1 (10 KB); 138x96x1 NVN 0x1: 1 (12 KB); 154x98x1 NVN 0x1: 1 (14 KB); 198x40x1 NVN 0x25: 1 (30 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 262x104x1 NVN 0x1: 1 (26 KB); 592x49x1 NVN 0x25: 3 (339 KB); 656x113x1 NVN 0x1: 3 (217 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 3 waited for it, 0.08 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: replay reads of guest memory as submitted: 1560000 (1072117 pages from the captures)
[hos host] vk: status: 600 frames, the slowest 23.3 ms; VRAM 6.4 of 14.9 GB; NVIDIA DLSS: 600 frames drawn, 1 made, jitter +0.313 -0.352 px, actor motion 29480 draws in 600 frames (0.184 ms CPU a frame; poses 29578 read at the draw, 0 copied later), its images 98 MB, its own 143 MB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4885 queued, 4885 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3739 ms and 1111.0 MB read in all); 6777 programs (1590 of them compute variants without their code, 0 graphics programs no note names), 9190 graphics pipelines (0 not in a cache), 679 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 699 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7439 (4885 ready, 0 loading), 13754 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 679 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 23 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 5.73, present 0.12, draw 3.18, descriptors 1.22, texture lookups 0.20, uploads 0.01, pipelines 0.12, programs 0.53, commands 0.94, dispatch 0.66, memory sync 0.20, queue submit 0.42, slot wait 0.04
[hos host] vk: a frame: mirrors 95 (793 MB): 7.47 MB synced in 1145.6 copies, 62.72 MB written back
[hos host] vk: 4800 presents, 59.9 fps; a frame: 1534 draws (0 skipped), 137 dispatches, 164 passes, 152 barriers, 6 submits, 0.5 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 9352 pipelines (1678 ms), 0 programs (0 failed), 1571 textures (3311 MB)
[hos host] vk: host time in GPU resource waits: 0.22 ms a frame (fences 0.03, timelines 0.19, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 504.9 full barriers recorded, 217.7 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 5.1; 0x8: 3.0; 0x9: 1.0; 0x10: 3.1; 0x11: 41.4; 0x12: 74.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 7.7 ms a frame (the longest submission 2.7 ms); 2.0 textures made a frame
[hos host] vk: a frame: 0.03 MB unswizzled on the CPU in 0.01 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 1 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 5.41 ms a frame (submits 4.92, presents 0.38, others 0.11), idle 11.26; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 146.71 jobs queued at a present); 1 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 1.72 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 4 captures at a CPU signal; the submits' waits read in 0.024 ms a frame; readbacks: 3000 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 5.43 ms after its hand-over (16.75 at most)
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.01, scan 0.04 over 871 ranges, 2156 MB), 362 pages written, 362 copied (1.4 MB)
[hos host] vk: a capture taken (ms): all 0.005; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.003, bytes copied 0.000; 25 kept (186 MB), 12 spare buffers, 4446 texture pages copied (17 MB)
[hos host] vk: texture #2749 0x10007772800 795x795 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 4808 (drawn at 4746)
[hos host] vk: texture #2748 0x10007772800 801x801 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 4809 (drawn at 4748)
[hos host] vk: 12 textures retired (1574 left, 3320 MB): budget 0, drawn over 0, dead targets 12
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 64, 793 MB with memory of 1048 MB (254 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 122 binds (14.4 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 517 dirty pages from their submits' captures, 44541 from earlier ones', 1 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3752 runs, 1554.5 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 11626 in captures, 2 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool: 0x7fd9400000 (4 MB, captured, state 2): 1;
[hos host] vk: imports: 74 live (1108 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: texture #2690 0x10007a3ca00 384x384 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 4815 (drawn at 4754)
[hos host] vk: texture #2864 0x10007adac00 384x384 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 4818 (drawn at 4757)
[hos host] vk: 77 textures retired (1539 left, 3219 MB): budget 0, drawn over 0, dead targets 77
[hos host] vk: replay reads of guest memory as submitted: 1580000 (1087601 pages from the captures)
[hos host] vk: texture #2863 0x10007a4aa00 384x384 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 4821 (drawn at 4760)
[hos host] vk: 4 textures retired (1537 left, 3224 MB): budget 0, drawn over 4, dead targets 0
[hos Presentation Thread] vi: 4833 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: program picks: 2447781 kept (1457763 by the last picks' textures, a uniform buffer bound since), 829 new, 951389 with other textures (of 3400000)
[hos host] vk: mirror syncs (600 submits): 513 dirty pages from their submits' captures, 46958 from earlier ones', 40 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3767 runs, 1556.8 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 12176 in captures, 2 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool: 0x1065800000 (8 MB, captured, state 2): 33; 0x7fd9400000 (4 MB, captured, state 2): 7;
[hos host] vk: queues ordered by their events: 24000 submissions stopped at a wait, 23998 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 59866, not met 0; captures at a CPU event's wait 1768, 0 of them at a wait met on arrival
[hos AudioFrameworkThread] vcores: 217168 takes, 29379 waits (mean 33 us, longest 4.3 ms), 14851 kicks, 14555 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: 1 textures retired (1536 left, 3223 MB): budget 0, drawn over 1, dead targets 0
[hos sead::MainThread] nvn: CommandBufferWaitEvent #60000: event 0x100d6c8048 mode 0 value 39706 (now 39687) (lr 0x806661f8)
[hos host] vk: replay reads of guest memory as submitted: 1600000 (1101656 pages from the captures)
[hos host] vk: 13 textures retired (1535 left, 3223 MB): budget 0, drawn over 0, dead targets 13
[hos ModuleSystemWorker5] nvn: CommandBufferSignalEvent #40000: event 0x100d6c8020 mode 0 value 40000 (lr 0x802911b8)
[hos host] vk: sparse mirrors: 64, 793 MB with memory of 1048 MB (254 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 122 binds (14.4 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 649 dirty pages from their submits' captures, 51009 from earlier ones', 37 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4005 runs, 1648.7 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 12858 in captures, 1 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool: 0x1052400000 (4 MB, captured, state 2): 23; 0x7fd9400000 (4 MB, captured, state 2): 14;
[hos host] vk: imports: 74 live (1108 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: replay reads of guest memory as submitted: 1620000 (1115636 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 100 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: readback pages refreshed from guest memory: 1018554 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: mirror syncs (600 submits): 688 dirty pages from their submits' captures, 53070 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3983 runs, 1618.8 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 12941 in captures, 2 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 1640000 (1128949 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.01, scan 0.04 over 871 ranges, 2156 MB), 361 pages written, 361 copied (1.4 MB)
[hos host] vk: a capture taken (ms): all 0.005; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.003, bytes copied 0.000; 25 kept (82 MB), 12 spare buffers, 4446 texture pages copied (17 MB)
[hos host] vk: sparse mirrors: 64, 793 MB with memory of 1048 MB (254 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 122 binds (14.4 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 685 dirty pages from their submits' captures, 52706 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3951 runs, 1617.5 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 12905 in captures, 2 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 74 live (1108 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos ModuleSystemWorker2] vk: readbacks of GPU results: 1442 of 3000 waited for their write-back, 0.01 ms each; 0 looked at the stopped queues first, 5 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: a frame: 22 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.03, present 0.09, draw 3.46, descriptors 1.35, texture lookups 0.10, uploads 0.01, pipelines 0.13, programs 0.59, commands 0.98, dispatch 0.67, memory sync 0.20, queue submit 0.44, slot wait 0.04
[hos host] vk: a frame: mirrors 95 (793 MB): 7.80 MB synced in 1195.7 copies, 62.64 MB written back
[hos host] vk: 4920 presents, 60.1 fps; a frame: 1761 draws (0 skipped), 153 dispatches, 170 passes, 154 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 9352 pipelines (1678 ms), 0 programs (0 failed), 1535 textures (3223 MB)
[hos host] vk: host time in GPU resource waits: 0.11 ms a frame (fences 0.03, timelines 0.09, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 533.1 full barriers recorded, 221.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 4.7; 0x8: 3.0; 0x9: 1.0; 0x10: 2.7; 0x11: 42.0; 0x12: 76.2; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 7.8 ms a frame (the longest submission 2.5 ms); 0.6 textures made a frame
[hos host] vk: a frame: 0.04 MB unswizzled on the CPU in 0.01 ms
[hos host] vk: replay reads of guest memory as submitted: 1660000 (1142303 pages from the captures)
[hos host] vk: 12 textures retired (1535 left, 3223 MB): budget 0, drawn over 0, dead targets 12
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 564 dirty pages from their submits' captures, 50044 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3948 runs, 1618.2 MB compared; 0 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 12879 in captures, 3 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: program picks: 2595098 kept (1552838 by the last picks' textures, a uniform buffer bound since), 829 new, 1004072 with other textures (of 3600000)
[hos host] vk: replay reads of guest memory as submitted: 1680000 (1155841 pages from the captures)
[hos host] vk: 1 textures retired (1535 left, 3224 MB): budget 0, drawn over 0, dead targets 1
[hos host] vk: 1 textures retired (1534 left, 3221 MB): budget 0, drawn over 0, dead targets 1
[hos ModuleSystemWorker1] nvn: DrawMeshTasksIndirect: 100000 so far (x1 0x11789a4000 x2 0x1 x3 0x11789a4000 x4 0x4040)
[hos host] vk: mirror of pool 0x7fd3c00000 (4 MB) given back: idle, 6005 submissions since its sync
[hos host] vk: mirror of pool 0x7fb8800000 (60 MB) given back: idle, 6002 submissions since its sync
[hos host] vk: 33 mirrors given back (389 MB in all); 737 MB of mirrors now, 92 MB of them idle and kept for what the GPU wrote there alone
[hos host] vk: sparse mirrors: 62, 737 MB with memory of 984 MB (246 MB spared); blocks given memory later 455, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 122 binds (14.4 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 522 dirty pages from their submits' captures, 47518 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3999 runs, 1623.6 MB compared; 1 pages read into the shadows; 272 MB of shadows; pages the shadows knew that the CPU wrote: 12853 in captures, 35 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 74 live (1108 MB), 0 retired still imported (0 MB), 6 retired given back (260 MB)
[hos host] vk: mirror of pool 0x7fc0800000 (4 MB) given back: idle, 6044 submissions since its sync
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 99 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 1700000 (1169212 pages from the captures)
[hos host] vk: texture #2080 0x100079b2a00 384x384 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 4985 (drawn at 4924)
[hos sead::MainThread] longjmp to 0x81681690 (value 1, 0 slots above dropped)
[hos host] vk: write-back diff: a shadow for pool 0x115c000000 (16 MB; 288 MB of shadows)
[hos sead::MainThread] nvn: GPU waits in 5 s: 1 sync waits (1 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: mirror syncs (600 submits): 562 dirty pages from their submits' captures, 48924 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3825 runs, 1679.0 MB compared; 1813 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 13170 in captures, 2 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] hid: game window not in front (foreground window: process 33208, class "CASCADIA_HOSTING_WINDOW_CLASS")
[hos host] vk: pool 0x1163400000 remade larger (7 retired)
[hos host] vk: pool 0x1163400000..0x1163c00000: 12 KB the CPU wrote since retired pool 0x1163400000's last sync kept from guest memory, not its mirror
[hos host] vk: pool 0x1163400000..0x1163c00000: mirror made with the GPU's contents of 1 retired pool(s)
[hos host] vk: write-back diff: a shadow for pool 0x1163400000 (8 MB; 296 MB of shadows)
[hos host] vk: write-back diff: a shadow for pool 0x100d400000 (4 MB; 300 MB of shadows)
[hos host] vk: texture slot 0x107 (handle 0x10300107): no view of it; NVN target 1 format 0x25 4x4x1 levels 1 gpu 0x102fdd7800, view no (format 0 target -1), wanted view type 2 use 0
[hos host] vk: texture slot 0x11c (handle 0x1070011c): no view of it; NVN target 4 format 0xa 4x4x1 levels 1 gpu 0x102fde0600, view no (format 0 target -1), wanted view type 2 use 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.04
[hos host] vk: 76 textures retired (1668 left, 3433 MB): budget 0, drawn over 0, dead targets 76
[hos sead::MainThread] nvn: EventSignal (CPU) #10000: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos host] vk: mirror of pool 0x1163400000 (4 MB) given back: retired, 77 submissions since its sync
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.02, scan 0.03 over 776 ranges, 2155 MB), 343 pages written, 343 copied (1.3 MB)
[hos host] vk: a capture taken (ms): all 0.007; GPU wait for late pages 0.002 (1 of 600 takes), pools lock 0.000, retires and stamps 0.003, bytes copied 0.000; 25 kept (98 MB), 9 spare buffers, 4510 texture pages copied (17 MB)
[hos host] vk: readback pages refreshed from guest memory: 1088085 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a frame: 9 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.45, present 0.12, draw 2.39, descriptors 1.01, texture lookups 0.12, uploads 0.04, pipelines 0.09, programs 0.37, commands 0.66, dispatch 0.43, memory sync 0.26, queue submit 0.36, slot wait 0.03
[hos host] vk: a frame: mirrors 98 (748 MB): 6.17 MB synced in 978.4 copies, 40.31 MB written back
[hos host] vk: 5040 presents, 60.1 fps; a frame: 1158 draws (0 skipped), 89 dispatches, 158 passes, 127 barriers, 6 submits, 1.4 uploads (0.3 MB), 235 ub updates (114 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1668 textures (3433 MB)
[hos host] vk: host time in GPU resource waits: 0.10 ms a frame (fences 0.02, timelines 0.08, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 578.6 full barriers recorded, 176.8 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 4.0; 0x8: 1.8; 0x9: 0.6; 0x10: 2.8; 0x11: 25.5; 0x12: 74.8; 0x13: 2.0; 0x21: 3.2; 0x28: 8.4; 0x92: 3.4; 0x97: 0.6;
[hos host] vk: GPU time 5.9 ms a frame (the longest submission 3.8 ms); 1.9 textures made a frame
[hos host] vk: a frame: 0.16 MB unswizzled on the CPU in 0.03 ms
[hos host] vk: mirror of pool 0x7fddc00000 (8 MB) given back: idle, 6058 submissions since its sync
[hos host] vk: sparse mirrors: 62, 742 MB with memory of 996 MB (253 MB spared); blocks given memory later 472, given back 1026; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 127 binds (14.8 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 740 dirty pages from their submits' captures, 69785 from earlier ones', 34 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 329 runs, 464.1 MB compared; 247 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17291 in captures, 63 only in the collection, 63 only by the replay itself
[hos host] vk: read live, by pool: 0x104e000000 (24 MB, captured, state 2): 34;
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 106 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: mirror of pool 0x7fde800000 (4 MB) given back: idle, 6027 submissions since its sync
[hos host] vk: replay reads of guest memory as submitted: 1720000 (1184204 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.01, scan 0.03 over 776 ranges, 2155 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (98 MB), 9 spare buffers, 4510 texture pages copied (17 MB)
[hos host] vk: 2 textures retired (1666 left, 3432 MB): budget 0, drawn over 2, dead targets 0
[hos host] vk: 23 textures retired (1643 left, 3424 MB): budget 0, drawn over 23, dead targets 0
[hos host] vk: mirror syncs (600 submits): 690 dirty pages from their submits' captures, 70912 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17367 in captures, 11 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: 1 textures retired (1642 left, 3424 MB): budget 0, drawn over 1, dead targets 0
[hos Presentation Thread] vi: 5134 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 299, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos BaseProcExecutor1] vcores: 159124 takes, 25639 waits (mean 37 us, longest 15.8 ms), 12630 kicks, 12385 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.56, present 0.09, draw 0.81, descriptors 0.45, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (739 MB): 4.22 MB synced in 735.8 copies, 7.08 MB written back
[hos host] vk: 5160 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.3 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 3.1 ms a frame (the longest submission 2.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: mirror of pool 0x7fac800000 (4 MB) given back: idle, 6046 submissions since its sync
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 60, 737 MB with memory of 988 MB (250 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 752 dirty pages from their submits' captures, 70353 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17385 in captures, 9 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos ModuleSystemWorker4] nvn: 450000 recordings made, 29801 live copies (6.2 MB), 1211 texture copies; 4 command buffers' segments (2.2 MB)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #65000: event 0x100d6c8008 mode 0 value 43189 (now 43186) (lr 0x806661f8)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] vk: capture: a submit 0.09 ms (lock 0.01, scan 0.03 over 776 ranges, 2155 MB), 242 pages written, 242 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (106 MB), 8 spare buffers, 4510 texture pages copied (17 MB)
[hos host] vk: mirror of pool 0x1066000000 (4 MB) given back: idle, 6008 submissions since its sync
[hos host] vk: mirror syncs (600 submits): 758 dirty pages from their submits' captures, 70349 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17397 in captures, 8 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.61, present 0.06, draw 0.84, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.05, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (734 MB): 4.21 MB synced in 734.5 copies, 7.08 MB written back
[hos host] vk: 5280 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.2 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 3.8 ms a frame (the longest submission 3.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.01, scan 0.03 over 776 ranges, 2155 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (82 MB), 12 spare buffers, 4510 texture pages copied (17 MB)
[hos host] vk: recorder: 4369320 packets run in 10.0 s (busy 0.61 s, spun idle 1.90 s, slept 4484 times, 734 of them under 200 us), 0 calls made directly (no room); the replay waited for it 25225 times, 48.96 ms in all, the longest 0.19 ms; vkEndCommandBuffer 9475/24.11 ms (max 0.19), replay_mu unlock 5969/15.77 ms (max 0.09), vkResetDescriptorPool 9475/8.78 ms (max 0.17), direct recording 284/0.24 ms (max 0.01), vkQueueBindSparse 7/0.04 ms (max 0.02), vkDestroyImageView 15/0.02 ms (max 0.00)
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: sparse mirrors: 59, 734 MB with memory of 984 MB (249 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 715 dirty pages from their submits' captures, 70385 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17378 in captures, 12 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: program picks: 2696779 kept (1596544 by the last picks' textures, a uniform buffer bound since), 849 new, 1102371 with other textures (of 3800000)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: readback pages refreshed from guest memory: 1102923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: mirror syncs (600 submits): 741 dirty pages from their submits' captures, 71438 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 335 runs, 474.5 MB compared; 67 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17658 in captures, 11 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] vk: capture: a submit 0.09 ms (lock 0.01, scan 0.03 over 774 ranges, 2143 MB), 243 pages written, 243 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (112 MB), 7 spare buffers, 4510 texture pages copied (17 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10988 MB (peak 10989), private 18817 MB, staging 128 MB in 2 arenas
[hos host] vk: memory heaps: heap 0 (device): 104 blocks 5737 MB, 13536 allocations 5013 MB; used 6391 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 49 allocations 382 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6391 MB used of 15280 MB allowed (724 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 408 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 408 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 408 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 408 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 408 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 2495 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 888 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 694 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 30 waited for it, 0.11 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 23.5 ms; VRAM 6.2 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.52, present 0.06, draw 0.80, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.19, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (734 MB): 4.21 MB synced in 734.6 copies, 7.08 MB written back
[hos host] vk: 5400 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.2 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.2 ms a frame (the longest submission 4.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 7 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.66 ms a frame): its jobs 3.62 ms a frame (submits 3.14, presents 0.33, others 0.15), idle 13.04; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 98.29 jobs queued at a present); 7 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 1.28 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 35 captures at a CPU signal; the submits' waits read in 0.015 ms a frame; readbacks: 960 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 3.62 ms after its hand-over (14.26 at most)
[hos host] vk: replay reads of guest memory as submitted: 1740000 (1202882 pages from the captures)
[hos Presentation Thread] vi: 5434 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 299, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos ModuleSystemWorker1] vcores: 96480 takes, 16867 waits (mean 31 us, longest 1.9 ms), 8171 kicks, 8072 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: sparse mirrors: 59, 734 MB with memory of 984 MB (249 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 745 dirty pages from their submits' captures, 70509 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17406 in captures, 8 only in the collection, 67 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.01, scan 0.03 over 770 ranges, 2127 MB), 241 pages written, 241 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (98 MB), 9 spare buffers, 4510 texture pages copied (17 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror of pool 0x1043800000 (4 MB) given back: idle, 6014 submissions since its sync
[hos rmbl::VibrationThread] hid: 12288 vibration values, strongest 0.04 since the last count
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.56, present 0.06, draw 0.83, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (733 MB): 4.21 MB synced in 735.5 copies, 7.08 MB written back
[hos host] vk: 5520 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.1 full barriers recorded, 106.0 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.5 ms a frame (the longest submission 4.4 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 769 dirty pages from their submits' captures, 71405 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17182 in captures, 108 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: mirror of pool 0x7f6c400000 (16 MB) given back: idle, 6008 submissions since its sync
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: sparse mirrors: 57, 719 MB with memory of 964 MB (244 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 781 dirty pages from their submits' captures, 70350 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 335 runs, 474.5 MB compared; 67 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17483 in captures, 103 only in the collection, 67 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.01, scan 0.03 over 768 ranges, 2113 MB), 240 pages written, 240 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.004; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (106 MB), 12 spare buffers, 4510 texture pages copied (17 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.59, present 0.06, draw 0.83, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (719 MB): 4.21 MB synced in 734.8 copies, 7.08 MB written back
[hos host] vk: 5640 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.1 full barriers recorded, 106.0 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 4.4 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror of pool 0x7fd9400000 (4 MB) given back: idle, 6023 submissions since its sync
[hos host] vk: mirror of pool 0x7fac000000 (8 MB) given back: idle, 6023 submissions since its sync
[hos host] vk: mirror syncs (600 submits): 740 dirty pages from their submits' captures, 70368 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17378 in captures, 10 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: mirror of pool 0x7f64000000 (4 MB) given back: idle, 6062 submissions since its sync
[hos host] vk: mirror of pool 0x7f6b800000 (12 MB) given back: idle, 6041 submissions since its sync
[hos host] vk: mirror of pool 0x7fd9c00000 (4 MB) given back: idle, 6032 submissions since its sync
[hos host] vk: mirror of pool 0x7f64400000 (4 MB) given back: idle, 6032 submissions since its sync
[hos host] vk: mirror of pool 0x7f68800000 (4 MB) given back: idle, 6032 submissions since its sync
[hos host] vk: mirror of pool 0x7fdfc00000 (8 MB) given back: idle, 6032 submissions since its sync
[hos host] vk: mirror of pool 0x7fbd800000 (4 MB) given back: idle, 6031 submissions since its sync
[hos host] vk: mirror of pool 0x7f68c00000 (28 MB) given back: idle, 6030 submissions since its sync
[hos host] vk: mirror of pool 0x7f6e400000 (20 MB) given back: idle, 6030 submissions since its sync
[hos host] vk: mirror of pool 0x7f6f800000 (16 MB) given back: idle, 6030 submissions since its sync
[hos host] vk: mirror of pool 0x1043400000 (4 MB) given back: idle, 6029 submissions since its sync
[hos host] vk: mirror of pool 0x104cc00000 (16 MB) given back: idle, 6029 submissions since its sync
[hos host] vk: mirror of pool 0x1065800000 (8 MB) given back: idle, 6029 submissions since its sync
[hos host] vk: mirror of pool 0x1165c00000 (8 MB) given back: idle, 6029 submissions since its sync
[hos host] vk: mirror of pool 0x1167000000 (8 MB) given back: idle, 6029 submissions since its sync
[hos host] vk: mirror of pool 0x7f67400000 (20 MB) given back: idle, 6029 submissions since its sync
[hos host] vk: mirror of pool 0x7f6a800000 (16 MB) given back: idle, 6029 submissions since its sync
[hos host] vk: mirror of pool 0x1041c00000 (4 MB) given back: idle, 6029 submissions since its sync
[hos host] vk: mirror of pool 0x7fbf800000 (4 MB) given back: idle, 6029 submissions since its sync
[hos host] vk: mirror of pool 0x7f6d400000 (4 MB) given back: idle, 6028 submissions since its sync
[hos host] vk: mirror of pool 0x7fda400000 (4 MB) given back: idle, 6028 submissions since its sync
[hos host] vk: mirror of pool 0x7fdac00000 (8 MB) given back: idle, 6028 submissions since its sync
[hos host] vk: mirror of pool 0x7fdb800000 (8 MB) given back: idle, 6028 submissions since its sync
[hos host] vk: mirror of pool 0x7fdc000000 (8 MB) given back: idle, 6028 submissions since its sync
[hos host] vk: mirror of pool 0x7fa2c00000 (8 MB) given back: idle, 6028 submissions since its sync
[hos host] vk: mirror of pool 0x7fe2400000 (4 MB) given back: idle, 6028 submissions since its sync
[hos host] vk: 69 mirrors given back (577 MB in all); 563 MB of mirrors now, 388 MB of them idle and kept for what the GPU wrote there alone
[hos host] vk: slow submit: 18.2 ms:
[hos sead::MainThread] nvn: GPU waits in 5 s: 1 sync waits (8 ms), 0 polls timed out (0 ms), 6 queue finishes (9 ms)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos sead::MainThread] vk: capture: a submit 0.09 ms (lock 0.01, scan 0.03 over 766 ranges, 2103 MB), 240 pages written, 240 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.004; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (106 MB), 8 spare buffers, 4510 texture pages copied (17 MB)
[hos host] vk: readback pages refreshed from guest memory: 1114923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: texture slots registered again at another size: 200000 (of 272901 registrations; slot 29429 256x256 -> 128x128)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 685 dirty pages from their submits' captures, 70562 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17188 in captures, 21 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vi: 5735 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 299, 17.8-22 0, 22-30 1, 30-40 0, over 40 0
[hos tera::FileResourceMgr] vcores: 97188 takes, 17235 waits (mean 30 us, longest 1.8 ms), 8534 kicks, 8411 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: replay reads of guest memory as submitted: 1760000 (1221558 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.70, present 0.06, draw 0.82, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 735.0 copies, 7.08 MB written back
[hos host] vk: 5760 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.08 ms a frame (fences 0.01, timelines 0.07, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.2 ms a frame (the longest submission 4.1 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos ModuleSystemWorker1] vk: readbacks of GPU results: 684 of 3000 waited for their write-back, 0.01 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: mirror syncs (600 submits): 685 dirty pages from their submits' captures, 70418 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17362 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] vk: capture: a submit 0.09 ms (lock 0.01, scan 0.03 over 761 ranges, 2081 MB), 241 pages written, 241 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (112 MB), 7 spare buffers, 4510 texture pages copied (17 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] nvn: CommandBufferSignalEvent #45000: event 0x100d6c8000 mode 0 value 44999 (lr 0x80664f14)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 735 dirty pages from their submits' captures, 70446 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17395 in captures, 11 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.54, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.3 copies, 7.08 MB written back
[hos host] vk: 5880 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.2 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.5 ms a frame (the longest submission 4.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: capture: a submit 0.09 ms (lock 0.01, scan 0.03 over 760 ranges, 2075 MB), 241 pages written, 241 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (112 MB), 7 spare buffers, 4510 texture pages copied (17 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: recorder: 1870841 packets run in 10.0 s (busy 0.32 s, spun idle 0.91 s, slept 4965 times, 664 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15700 times, 35.73 ms in all, the longest 0.13 ms; replay_mu unlock 4830/17.05 ms (max 0.13), vkEndCommandBuffer 5435/11.77 ms (max 0.08), vkResetDescriptorPool 5435/6.91 ms (max 0.04)
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: program picks: 2765187 kept (1602387 by the last picks' textures, a uniform buffer bound since), 849 new, 1233963 with other textures (of 4000000)
[hos host] vk: mirror syncs (600 submits): 698 dirty pages from their submits' captures, 70402 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17394 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 706 dirty pages from their submits' captures, 71477 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 335 runs, 474.5 MB compared; 67 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17631 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] vk: capture: a submit 0.09 ms (lock 0.01, scan 0.03 over 760 ranges, 2075 MB), 240 pages written, 240 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (112 MB), 7 spare buffers, 4510 texture pages copied (17 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10992 MB (peak 10996), private 18756 MB, staging 128 MB in 2 arenas
[hos host] vk: memory heaps: heap 0 (device): 103 blocks 5673 MB, 10799 allocations 4842 MB; used 6327 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 49 allocations 382 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6327 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1008 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 1008 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 1008 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1008 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1008 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 3095 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1488 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1294 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 34 waited for it, 0.29 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 33.0 ms; VRAM 6.2 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.58, present 0.06, draw 0.85, descriptors 0.48, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.05, memory sync 0.20, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.2 copies, 7.08 MB written back
[hos host] vk: 6000 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.2 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.7 ms a frame (the longest submission 4.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.10 ms a frame (submits 1.71, presents 0.28, others 0.12), idle 14.56; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 36 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.11 ms after its hand-over (20.13 at most)
[hos Presentation Thread] vi: real-time step on: ratio 1.002, game's frame rate 60
[hos sead::MainThread] nvn: CommandBufferWaitEvent #70000: event 0x100d6c8008 mode 0 value 45688 (now 45685) (lr 0x806661f8)
[hos host] vk: readback pages refreshed from guest memory: 1126923 pages so far (0 held: may be written ahead in their submission)
[hos Presentation Thread] vi: 6035 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 298, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos ModuleSystemWorker1] vcores: 96095 takes, 17781 waits (mean 31 us, longest 2.5 ms), 8866 kicks, 8724 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: mirror syncs (600 submits): 703 dirty pages from their submits' captures, 70544 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17391 in captures, 10 only in the collection, 67 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 1780000 (1240238 pages from the captures)
[hos sead::MainThread] nvn: 500000 recordings made, 29761 live copies (6.2 MB), 1211 texture copies; 5 command buffers' segments (2.3 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 760 ranges, 2075 MB), 241 pages written, 241 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (82 MB), 9 spare buffers, 4510 texture pages copied (17 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 733 dirty pages from their submits' captures, 70371 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17372 in captures, 11 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.52, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 735.4 copies, 7.08 MB written back
[hos host] vk: 6120 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.2 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.8 ms a frame (the longest submission 4.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 700 dirty pages from their submits' captures, 70412 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17394 in captures, 10 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 760 ranges, 2075 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (106 MB), 12 spare buffers, 4510 texture pages copied (17 MB)
[hos host] vk: queues ordered by their events: 30000 submissions stopped at a wait, 29998 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 71008, not met 0; captures at a CPU event's wait 1852, 0 of them at a wait met on arrival
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.50, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.7 copies, 7.08 MB written back
[hos host] vk: 6240 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.2 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.1 ms a frame (the longest submission 5.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 805 dirty pages from their submits' captures, 71380 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 335 runs, 474.5 MB compared; 67 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17696 in captures, 6 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.01, scan 0.03 over 760 ranges, 2073 MB), 243 pages written, 243 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (106 MB), 9 spare buffers, 4510 texture pages copied (17 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 793 dirty pages from their submits' captures, 70323 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17453 in captures, 6 only in the collection, 67 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vi: 6336 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 2, 15.5-17.8 298, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos ModuleSystemWorker1] vcores: 93950 takes, 17403 waits (mean 31 us, longest 2.1 ms), 8615 kicks, 8464 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: readback pages refreshed from guest memory: 1138923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.53, present 0.06, draw 0.78, descriptors 0.43, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.19, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 735.7 copies, 7.08 MB written back
[hos host] vk: 6360 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.2 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.0 ms a frame (the longest submission 5.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 684 dirty pages from their submits' captures, 70569 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17347 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 751 ranges, 1829 MB), 239 pages written, 239 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (82 MB), 12 spare buffers, 96 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: replay reads of guest memory as submitted: 1800000 (1258914 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 696 dirty pages from their submits' captures, 70395 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17367 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.50, present 0.06, draw 0.83, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.0 copies, 7.08 MB written back
[hos host] vk: 6480 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.3 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.1 ms a frame (the longest submission 4.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 751 ranges, 1829 MB), 240 pages written, 240 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (106 MB), 9 spare buffers, 96 texture pages copied (0 MB)
[hos host] vk: program picks: 2833576 kept (1608237 by the last picks' textures, a uniform buffer bound since), 849 new, 1365574 with other textures (of 4200000)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1870946 packets run in 10.0 s (busy 0.32 s, spun idle 0.90 s, slept 4974 times, 662 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15716 times, 35.75 ms in all, the longest 0.13 ms; replay_mu unlock 4831/16.75 ms (max 0.13), vkEndCommandBuffer 5443/12.11 ms (max 0.08), vkResetDescriptorPool 5442/6.89 ms (max 0.05)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 726 dirty pages from their submits' captures, 70298 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17385 in captures, 11 only in the collection, 67 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: mirror syncs (600 submits): 739 dirty pages from their submits' captures, 70276 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17402 in captures, 11 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.01, scan 0.03 over 749 ranges, 1821 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (98 MB), 12 spare buffers, 96 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10977 MB (peak 10996), private 18742 MB, staging 128 MB in 2 arenas
[hos host] vk: memory heaps: heap 0 (device): 103 blocks 5673 MB, 10799 allocations 4842 MB; used 6327 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 49 allocations 382 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6327 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1608 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 1608 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 1608 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1608 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1608 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 3695 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 2088 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1894 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 39 waited for it, 0.05 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.1 ms; VRAM 6.2 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.47, present 0.06, draw 0.80, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.4 copies, 7.08 MB written back
[hos host] vk: 6600 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.3 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.2 ms a frame (the longest submission 5.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 1.99 ms a frame (submits 1.60, presents 0.27, others 0.12), idle 14.68; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 44 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.00 ms after its hand-over (2.91 at most)
[hos Presentation Thread] vi: 6636 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos NavMeshCAStepDepWorker1] vcores: 93199 takes, 16407 waits (mean 31 us, longest 2.1 ms), 8073 kicks, 7930 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 691 dirty pages from their submits' captures, 70532 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17358 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos sead::MainThread] nvn: QueueSubmitCommands #40000: queue 000010100D6BF020 (its #6666), 1 handles (lr 0x80666be0)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 748 ranges, 1819 MB), 240 pages written, 240 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (112 MB), 7 spare buffers, 96 texture pages copied (0 MB)
[hos host] vk: readback pages refreshed from guest memory: 1150923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 673 dirty pages from their submits' captures, 70342 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17115 in captures, 10 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.49, present 0.06, draw 0.79, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.19, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.3 copies, 7.08 MB written back
[hos host] vk: 6720 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.2 ms a frame (the longest submission 5.1 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos rmbl::VibrationThread] hid: 16384 vibration values, strongest 0.00 since the last count
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 1820000 (1277593 pages from the captures)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 645 dirty pages from their submits' captures, 70357 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17317 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 748 ranges, 1819 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (82 MB), 9 spare buffers, 96 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.48, present 0.08, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.1 copies, 7.08 MB written back
[hos host] vk: 6840 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.3 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.2 ms a frame (the longest submission 5.1 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 683 dirty pages from their submits' captures, 69256 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17368 in captures, 11 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] nvn: CommandBufferWaitEvent #75000: event 0x100d6c8004 mode 0 value 48189 (now 48183) (lr 0x80a47c2c)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 740 dirty pages from their submits' captures, 70279 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17418 in captures, 8 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vi: 6937 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos NavMeshCAStepDepWorker1] vcores: 93717 takes, 17164 waits (mean 30 us, longest 2.2 ms), 8464 kicks, 8315 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.49, present 0.06, draw 0.79, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.19, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.4 copies, 7.08 MB written back
[hos host] vk: 6960 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.3 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.2 ms a frame (the longest submission 5.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror syncs (600 submits): 682 dirty pages from their submits' captures, 71553 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17359 in captures, 11 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 240 pages written, 240 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos sead::MainThread] nvn: 550000 recordings made, 29753 live copies (6.2 MB), 1211 texture copies; 5 command buffers' segments (2.3 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: readback pages refreshed from guest memory: 1162923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 671 dirty pages from their submits' captures, 70336 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17385 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 1840000 (1296270 pages from the captures)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.47, present 0.06, draw 0.79, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.3 copies, 7.08 MB written back
[hos host] vk: 7080 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.3 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.2 ms a frame (the longest submission 5.1 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: program picks: 2902008 kept (1614087 by the last picks' textures, a uniform buffer bound since), 849 new, 1497142 with other textures (of 4400000)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 646 dirty pages from their submits' captures, 69292 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17337 in captures, 12 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871083 packets run in 10.0 s (busy 0.31 s, spun idle 0.88 s, slept 4989 times, 664 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15779 times, 34.34 ms in all, the longest 0.10 ms; replay_mu unlock 4851/16.11 ms (max 0.05), vkEndCommandBuffer 5464/11.41 ms (max 0.10), vkResetDescriptorPool 5464/6.82 ms (max 0.09)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 666 dirty pages from their submits' captures, 70334 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17320 in captures, 10 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10977 MB (peak 10996), private 18613 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6199 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6199 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 2208 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 2208 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 2208 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 2208 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 2208 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 4295 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 2688 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 2494 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 53 waited for it, 0.04 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 17.9 ms; VRAM 6.1 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.50, present 0.06, draw 0.81, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.2 copies, 7.08 MB written back
[hos host] vk: 7200 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.2 ms a frame (the longest submission 5.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: queues ordered by their events: 34105 submissions stopped at a wait, 34105 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 77026, not met 0; captures at a CPU event's wait 1947, 0 of them at a wait met on arrival
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 1.96 ms a frame (submits 1.53, presents 0.26, others 0.17), idle 14.70; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 64 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 1.97 ms after its hand-over (3.55 at most)
[hos Presentation Thread] vi: 7238 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: mirror syncs (600 submits): 628 dirty pages from their submits' captures, 69466 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17025 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos ModuleSystemWorker1] vcores: 94211 takes, 16961 waits (mean 30 us, longest 1.8 ms), 8451 kicks, 8290 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos ModuleSystemWorker2] vk: readbacks of GPU results: 0 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 571 dirty pages from their submits' captures, 70430 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17274 in captures, 18 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.57, present 0.07, draw 0.86, descriptors 0.48, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.22, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.5 copies, 7.08 MB written back
[hos host] vk: 7320 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 5.1 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: readback pages refreshed from guest memory: 1174923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: mirror syncs (600 submits): 580 dirty pages from their submits' captures, 70425 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16979 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: replay reads of guest memory as submitted: 1860000 (1314947 pages from the captures)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 643 dirty pages from their submits' captures, 69306 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17339 in captures, 11 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.55, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.0 copies, 7.08 MB written back
[hos host] vk: 7440 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 4.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] nvn: CommandBufferSignalEvent #50000: event 0x100d6c8008 mode 0 value 49999 (lr 0x80666598)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] nvn: EventSignal (CPU) #15000: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 615 dirty pages from their submits' captures, 70467 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17303 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vi: 7539 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos NavMeshCAStepDepWorker1] vcores: 96615 takes, 16919 waits (mean 30 us, longest 1.7 ms), 8272 kicks, 8150 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.53, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.7 copies, 7.08 MB written back
[hos host] vk: 7560 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.3 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 4.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 642 dirty pages from their submits' captures, 70506 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17337 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 688 dirty pages from their submits' captures, 70332 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17359 in captures, 12 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: queues ordered by their events: 36000 submissions stopped at a wait, 35998 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 79780, not met 0; captures at a CPU event's wait 2004, 0 of them at a wait met on arrival
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 240 pages written, 240 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: program picks: 2970448 kept (1619937 by the last picks' textures, a uniform buffer bound since), 849 new, 1628702 with other textures (of 4600000)
[hos host] vk: readback pages refreshed from guest memory: 1186923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.52, present 0.06, draw 0.81, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.1 copies, 7.08 MB written back
[hos host] vk: 7680 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.3 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 4.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] nvn: CommandBufferWaitEvent #80000: event 0x100d6c8008 mode 0 value 50689 (now 50686) (lr 0x806661f8)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 630 dirty pages from their submits' captures, 70367 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17310 in captures, 16 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871061 packets run in 10.0 s (busy 0.32 s, spun idle 0.90 s, slept 4964 times, 661 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15805 times, 37.87 ms in all, the longest 0.10 ms; replay_mu unlock 4861/17.60 ms (max 0.05), vkEndCommandBuffer 5472/12.49 ms (max 0.09), vkResetDescriptorPool 5472/7.78 ms (max 0.10)
[hos host] vk: replay reads of guest memory as submitted: 1880000 (1333626 pages from the captures)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 698 dirty pages from their submits' captures, 70312 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17340 in captures, 11 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10977 MB (peak 10996), private 18613 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6199 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6199 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 2808 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 2808 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 2808 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 2808 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 2808 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 4895 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 3288 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 3094 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 68 waited for it, 0.06 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.3 ms; VRAM 6.1 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.54, present 0.06, draw 0.83, descriptors 0.47, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.1 copies, 7.08 MB written back
[hos host] vk: 7800 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.4 ms a frame (the longest submission 4.4 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.05 ms a frame (submits 1.57, presents 0.28, others 0.20), idle 14.62; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 74 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.06 ms after its hand-over (2.90 at most)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 692 dirty pages from their submits' captures, 70461 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17070 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vi: 7839 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 2, 15.5-17.8 296, 17.8-22 2, 22-30 0, 30-40 0, over 40 0
[hos ModuleSystemWorker1] vcores: 95960 takes, 17143 waits (mean 30 us, longest 1.9 ms), 8482 kicks, 8323 yields, 0 starved grants, 0 escapes in 5 s
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (80 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos ModuleSystemWorker3] nvn: 600000 recordings made, 29745 live copies (6.2 MB), 1211 texture copies; 4 command buffers' segments (2.2 MB)
[hos host] vk: mirror syncs (600 submits): 591 dirty pages from their submits' captures, 69341 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17268 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.60, present 0.07, draw 0.85, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.20, queue submit 0.20, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.8 copies, 7.08 MB written back
[hos host] vk: 7920 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.5 ms a frame (the longest submission 4.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 581 dirty pages from their submits' captures, 69355 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17016 in captures, 12 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos rmbl::VibrationThread] hid: 20480 vibration values, strongest 0.00 since the last count
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: readback pages refreshed from guest memory: 1198923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: mirror syncs (600 submits): 651 dirty pages from their submits' captures, 70368 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17329 in captures, 14 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.51, present 0.06, draw 0.85, descriptors 0.47, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.2 copies, 7.08 MB written back
[hos host] vk: 8040 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.7 ms a frame (the longest submission 4.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 1900000 (1352302 pages from the captures)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 684 dirty pages from their submits' captures, 70328 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17336 in captures, 11 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos NavMeshCAStepDepWorker1] vcores: 95506 takes, 16822 waits (mean 31 us, longest 2.1 ms), 8267 kicks, 8065 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 8140 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 657 dirty pages from their submits' captures, 70507 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17333 in captures, 13 only in the collection, 67 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.52, present 0.06, draw 0.83, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.9 copies, 7.08 MB written back
[hos host] vk: 8160 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.3 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.9 ms a frame (the longest submission 5.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 738 dirty pages from their submits' captures, 70278 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17413 in captures, 12 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: program picks: 3038885 kept (1625783 by the last picks' textures, a uniform buffer bound since), 849 new, 1760265 with other textures (of 4800000)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.48, present 0.06, draw 0.79, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.2 copies, 7.08 MB written back
[hos host] vk: 8280 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.1 ms a frame (the longest submission 4.1 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror syncs (600 submits): 567 dirty pages from their submits' captures, 69436 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16997 in captures, 18 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871172 packets run in 10.0 s (busy 0.32 s, spun idle 0.90 s, slept 4985 times, 661 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15837 times, 37.13 ms in all, the longest 0.12 ms; replay_mu unlock 4875/17.61 ms (max 0.12), vkEndCommandBuffer 5481/12.09 ms (max 0.09), vkResetDescriptorPool 5481/7.43 ms (max 0.09)
[hos host] vk: readback pages refreshed from guest memory: 1210923 pages so far (0 held: may be written ahead in their submission)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 616 dirty pages from their submits' captures, 70401 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17323 in captures, 12 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10977 MB (peak 10996), private 18613 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6199 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6199 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 3408 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 3408 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 3408 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 3408 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 3408 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 5495 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 3888 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 3694 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 77 waited for it, 0.05 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.1 ms; VRAM 6.1 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.48, present 0.06, draw 0.80, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 732.9 copies, 7.08 MB written back
[hos host] vk: 8400 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.2 ms a frame (the longest submission 4.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.02 ms a frame (submits 1.52, presents 0.28, others 0.22), idle 14.64; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 86 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.03 ms after its hand-over (2.84 at most)
[hos host] vk: replay reads of guest memory as submitted: 1920000 (1370982 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 571 dirty pages from their submits' captures, 69359 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17028 in captures, 18 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos aglTextureDataMgr::Compaction] vcores: 94038 takes, 16734 waits (mean 30 us, longest 1.8 ms), 8245 kicks, 8079 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 8440 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 649 dirty pages from their submits' captures, 69426 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17056 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.48, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.8 copies, 7.08 MB written back
[hos host] vk: 8520 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.2 ms a frame (the longest submission 4.2 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] nvn: CommandBufferWaitEvent #85000: event 0x100d6c8008 mode 0 value 53188 (now 53185) (lr 0x806661f8)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 684 dirty pages from their submits' captures, 70320 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17356 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 676 dirty pages from their submits' captures, 70339 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17336 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.48, present 0.06, draw 0.80, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.5 copies, 7.08 MB written back
[hos host] vk: 8640 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.3 ms a frame (the longest submission 5.1 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: readback pages refreshed from guest memory: 1222923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: mirror syncs (600 submits): 785 dirty pages from their submits' captures, 70232 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17435 in captures, 7 only in the collection, 67 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: replay reads of guest memory as submitted: 1940000 (1389658 pages from the captures)
[hos NavMeshCAStepDepWorker1] vcores: 94479 takes, 16883 waits (mean 30 us, longest 2.1 ms), 8359 kicks, 8198 yields, 0 starved grants, 0 escapes in 5 s
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 241 pages written, 241 copied (0.9 MB)
[hos Presentation Thread] vi: 8741 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (112 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 720 dirty pages from their submits' captures, 70437 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17370 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.48, present 0.06, draw 0.77, descriptors 0.43, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.19, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.6 copies, 7.08 MB written back
[hos host] vk: 8760 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.2 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.3 ms a frame (the longest submission 5.1 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos ModuleSystemWorker5] nvn: 650000 recordings made, 29769 live copies (6.2 MB), 1211 texture copies; 3 command buffers' segments (2.1 MB)
[hos ModuleSystemWorker1] vk: readbacks of GPU results: 0 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 633 dirty pages from their submits' captures, 70371 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17049 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: program picks: 3107288 kept (1631627 by the last picks' textures, a uniform buffer bound since), 849 new, 1891862 with other textures (of 5000000)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.49, present 0.06, draw 0.81, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.3 copies, 7.08 MB written back
[hos host] vk: 8880 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.3 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.3 ms a frame (the longest submission 5.1 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 761 dirty pages from their submits' captures, 70278 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 335 runs, 474.5 MB compared; 67 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17669 in captures, 8 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871175 packets run in 10.0 s (busy 0.31 s, spun idle 0.88 s, slept 4986 times, 663 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15810 times, 35.12 ms in all, the longest 0.09 ms; replay_mu unlock 4858/16.75 ms (max 0.09), vkEndCommandBuffer 5476/11.56 ms (max 0.07), vkResetDescriptorPool 5476/6.82 ms (max 0.09)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 242 pages written, 242 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 680 dirty pages from their submits' captures, 70329 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17346 in captures, 15 only in the collection, 67 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: readback pages refreshed from guest memory: 1234923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10977 MB (peak 10996), private 18613 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6199 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6199 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 4008 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 4008 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 4008 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 4008 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 4008 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 6095 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 4488 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 4294 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 58 waited for it, 0.05 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.0 ms; VRAM 6.1 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.51, present 0.06, draw 0.80, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.0 copies, 7.08 MB written back
[hos host] vk: 9000 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.3 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.3 ms a frame (the longest submission 5.4 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 1.97 ms a frame (submits 1.52, presents 0.27, others 0.18), idle 14.70; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 71 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 1.98 ms after its hand-over (2.76 at most)
[hos Presentation Thread] vi: real-time step on: ratio 0.996, game's frame rate 60
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 560 dirty pages from their submits' captures, 69383 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17011 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos aglTextureDataMgr::Compaction] vcores: 94427 takes, 17375 waits (mean 30 us, longest 1.8 ms), 8651 kicks, 8493 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 9042 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: replay reads of guest memory as submitted: 1960000 (1408336 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 477 dirty pages from their submits' captures, 69672 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16942 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: queues ordered by their events: 42000 submissions stopped at a wait, 41999 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 88474, not met 0; captures at a CPU event's wait 2209, 0 of them at a wait met on arrival
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.67, present 0.07, draw 0.92, descriptors 0.51, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.07, commands 0.23, dispatch 0.05, memory sync 0.19, queue submit 0.21, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.0 copies, 7.08 MB written back
[hos host] vk: 9120 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.9 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.9 ms a frame (the longest submission 5.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 229 pages written, 229 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #55000: event 0x100d6c8004 mode 0 value 54999 (lr 0x80665068)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 384 dirty pages from their submits' captures, 69631 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16556 in captures, 15 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos rmbl::VibrationThread] hid: 24576 vibration values, strongest 0.00 since the last count
[hos host] vk: mirror syncs (600 submits): 629 dirty pages from their submits' captures, 69394 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17289 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] vk: capture: a submit 0.09 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.62, present 0.06, draw 0.87, descriptors 0.49, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.20, queue submit 0.20, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.8 copies, 7.08 MB written back
[hos host] vk: 9240 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 3.5 ms a frame (the longest submission 4.4 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 663 dirty pages from their submits' captures, 70438 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17339 in captures, 15 only in the collection, 67 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: readback pages refreshed from guest memory: 1246923 pages so far (0 held: may be written ahead in their submission)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 631 dirty pages from their submits' captures, 69539 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17039 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos ModuleSystemWorker1] vcores: 96621 takes, 17560 waits (mean 30 us, longest 2.3 ms), 8723 kicks, 8544 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 9343 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.50, present 0.06, draw 0.79, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 735.3 copies, 7.08 MB written back
[hos host] vk: 9360 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.1 ms a frame (the longest submission 5.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos ModuleSystemWorker1] nvn: CommandBufferWaitEvent #90000: event 0x100d6c8004 mode 0 value 55689 (now 55683) (lr 0x80a47c2c)
[hos host] vk: replay reads of guest memory as submitted: 1980000 (1427014 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 707 dirty pages from their submits' captures, 70389 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17351 in captures, 14 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: program picks: 3175680 kept (1637477 by the last picks' textures, a uniform buffer bound since), 849 new, 2023470 with other textures (of 5200000)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 511 dirty pages from their submits' captures, 69513 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16883 in captures, 11 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.70, present 0.07, draw 0.90, descriptors 0.50, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.07, commands 0.22, dispatch 0.05, memory sync 0.20, queue submit 0.21, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.5 copies, 7.08 MB written back
[hos host] vk: 9480 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 5.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871324 packets run in 10.0 s (busy 0.34 s, spun idle 0.93 s, slept 4963 times, 662 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15912 times, 41.93 ms in all, the longest 0.14 ms; replay_mu unlock 4892/19.80 ms (max 0.14), vkEndCommandBuffer 5510/14.25 ms (max 0.11), vkResetDescriptorPool 5510/7.89 ms (max 0.06)
[hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 234 pages written, 234 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 387 dirty pages from their submits' captures, 69627 from earlier ones', 0 from guest memory as it was at the replay; 24 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16833 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10976 MB (peak 10996), private 18612 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6199 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6199 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 4608 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 4608 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 4608 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 4608 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 4608 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 6695 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 5088 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 4894 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 103 waited for it, 0.05 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: mirror syncs (600 submits): 524 dirty pages from their submits' captures, 69489 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16966 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: status: 600 frames, the slowest 18.1 ms; VRAM 6.1 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.70, present 0.07, draw 0.90, descriptors 0.49, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.07, commands 0.23, dispatch 0.05, memory sync 0.20, queue submit 0.21, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.1 copies, 7.08 MB written back
[hos host] vk: 9600 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.0 ms a frame (the longest submission 4.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.19 ms a frame (submits 1.57, presents 0.30, others 0.32), idle 14.48; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 119 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.20 ms after its hand-over (3.94 at most)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos ModuleSystemWorker1] vcores: 95924 takes, 17861 waits (mean 32 us, longest 2.2 ms), 8932 kicks, 8732 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 9643 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: readback pages refreshed from guest memory: 1258923 pages so far (0 held: may be written ahead in their submission)
[hos sead::MainThread] nvn: 700000 recordings made, 29779 live copies (5.9 MB), 1211 texture copies; 2 command buffers' segments (2.1 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 699 dirty pages from their submits' captures, 70560 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17356 in captures, 10 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.55, present 0.07, draw 0.86, descriptors 0.48, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.22, dispatch 0.04, memory sync 0.18, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 735.0 copies, 7.08 MB written back
[hos host] vk: 9720 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 3.1 ms a frame (the longest submission 3.2 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: replay reads of guest memory as submitted: 2000000 (1445690 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 607 dirty pages from their submits' captures, 69416 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16982 in captures, 17 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 647 dirty pages from their submits' captures, 71536 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17321 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 240 pages written, 240 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.46, present 0.06, draw 0.79, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.6 copies, 7.08 MB written back
[hos host] vk: 9840 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.1 full barriers recorded, 106.0 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.1 ms a frame (the longest submission 3.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror syncs (600 submits): 666 dirty pages from their submits' captures, 69378 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17369 in captures, 8 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 236 pages written, 236 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 628 dirty pages from their submits' captures, 70554 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17050 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos OptimizeChangeBanc] vcores: 93560 takes, 17028 waits (mean 30 us, longest 1.9 ms), 8411 kicks, 8237 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 9944 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 299, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.45, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.22 MB synced in 734.8 copies, 7.08 MB written back
[hos host] vk: 9960 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.7 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.5 ms a frame (the longest submission 3.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: readback pages refreshed from guest memory: 1270923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: mirror syncs (600 submits): 626 dirty pages from their submits' captures, 69535 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17294 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] nvn: QueueSubmitCommands #60000: queue 000010100D640020 (its #9999), 1 handles (lr 0x805282f4)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] nvn: EventSignal (CPU) #20000: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos host] vk: program picks: 3244114 kept (1643327 by the last picks' textures, a uniform buffer bound since), 849 new, 2155036 with other textures (of 5400000)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 2020000 (1464370 pages from the captures)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 736 dirty pages from their submits' captures, 70374 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17403 in captures, 12 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.47, present 0.06, draw 0.81, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.5 copies, 7.08 MB written back
[hos host] vk: 10080 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.3 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.8 ms a frame (the longest submission 4.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871345 packets run in 10.0 s (busy 0.32 s, spun idle 0.90 s, slept 4988 times, 662 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15855 times, 36.81 ms in all, the longest 0.13 ms; replay_mu unlock 4873/17.53 ms (max 0.13), vkEndCommandBuffer 5491/12.31 ms (max 0.09), vkResetDescriptorPool 5491/6.97 ms (max 0.07)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 567 dirty pages from their submits' captures, 69463 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16996 in captures, 11 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 530 dirty pages from their submits' captures, 69499 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16978 in captures, 15 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #95000: event 0x100d6c8008 mode 0 value 58189 (now 58186) (lr 0x806661f8)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10975 MB (peak 10996), private 18611 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6199 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6199 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 5208 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 5208 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 5208 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 5208 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 5208 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 7295 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 5688 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 5494 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos Presentation Thread] vk: presents after the CPU's signal (600): 86 waited for it, 0.05 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: status: 600 frames, the slowest 17.9 ms; VRAM 6.1 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.59, present 0.07, draw 0.87, descriptors 0.48, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.07, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.20, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.5 copies, 7.08 MB written back
[hos host] vk: 10200 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.9 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.7 ms a frame (the longest submission 5.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.00 ms a frame (submits 1.48, presents 0.27, others 0.25), idle 14.67; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 99 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.01 ms after its hand-over (3.08 at most)
[hos NavMeshCAStepDepWorker1] vcores: 94346 takes, 17261 waits (mean 30 us, longest 1.7 ms), 8564 kicks, 8375 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 10244 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: mirror syncs (600 submits): 602 dirty pages from their submits' captures, 70636 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17317 in captures, 12 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos ModuleSystemWorker2] vk: readbacks of GPU results: 0 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 240 pages written, 240 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (112 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: readback pages refreshed from guest memory: 1282923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.50, present 0.06, draw 0.81, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 735.0 copies, 7.08 MB written back
[hos host] vk: 10320 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.3 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 3.9 ms a frame (the longest submission 4.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 622 dirty pages from their submits' captures, 69396 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17043 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: mirror syncs (600 submits): 343 dirty pages from their submits' captures, 68596 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16539 in captures, 12 only in the collection, 63 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 2040000 (1483046 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 225 pages written, 225 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (86 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos rmbl::VibrationThread] hid: 28672 vibration values, strongest 0.00 since the last count
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.70, present 0.06, draw 0.88, descriptors 0.48, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.23, dispatch 0.05, memory sync 0.20, queue submit 0.21, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.0 copies, 7.08 MB written back
[hos host] vk: 10440 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 645.1 full barriers recorded, 106.4 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.2 ms a frame (the longest submission 4.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 563 dirty pages from their submits' captures, 69442 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16983 in captures, 18 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 665 dirty pages from their submits' captures, 69364 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17082 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos NavMeshCAStepDepWorker1] vcores: 94774 takes, 17311 waits (mean 30 us, longest 2.1 ms), 8569 kicks, 8400 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: queues ordered by their events: 48000 submissions stopped at a wait, 47996 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 97085, not met 0; captures at a CPU event's wait 2466, 0 of them at a wait met on arrival
[hos Presentation Thread] vi: 10545 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos ModuleSystemWorker1] nvn: 750000 recordings made, 29777 live copies (6.2 MB), 1211 texture copies; 4 command buffers' segments (2.2 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.52, present 0.06, draw 0.84, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 735.0 copies, 7.08 MB written back
[hos host] vk: 10560 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.4 ms a frame (the longest submission 4.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 551 dirty pages from their submits' captures, 69618 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16990 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: program picks: 3312555 kept (1649176 by the last picks' textures, a uniform buffer bound since), 849 new, 2286595 with other textures (of 5600000)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: readback pages refreshed from guest memory: 1294923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: mirror syncs (600 submits): 548 dirty pages from their submits' captures, 69489 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16994 in captures, 11 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.56, present 0.06, draw 0.81, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.19, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.6 copies, 7.08 MB written back
[hos host] vk: 10680 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.3 ms a frame (the longest submission 4.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 234 pages written, 234 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871521 packets run in 10.0 s (busy 0.33 s, spun idle 0.92 s, slept 4953 times, 663 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15999 times, 39.44 ms in all, the longest 0.09 ms; replay_mu unlock 4927/18.89 ms (max 0.09), vkEndCommandBuffer 5536/12.88 ms (max 0.09), vkResetDescriptorPool 5536/7.68 ms (max 0.08)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 523 dirty pages from their submits' captures, 70590 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17216 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: replay reads of guest memory as submitted: 2060000 (1501726 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 515 dirty pages from their submits' captures, 69558 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16694 in captures, 17 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10975 MB (peak 10996), private 18607 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 5808 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 5808 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 5808 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 5808 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 5808 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 7895 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 6288 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 6094 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos sead::MainThread] nvn: CommandBufferSignalEvent #60000: event 0x100d6c8000 mode 0 value 59999 (lr 0x80664f14)
[hos Presentation Thread] vk: presents after the CPU's signal (600): 106 waited for it, 0.05 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.0 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.55, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.18, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.1 copies, 7.08 MB written back
[hos host] vk: 10800 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.8 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.2 ms a frame (the longest submission 4.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: queues ordered by their events: 49087 submissions stopped at a wait, 49087 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 98626, not met 0; captures at a CPU event's wait 2529, 0 of them at a wait met on arrival
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.10 ms a frame (submits 1.46, presents 0.30, others 0.34), idle 14.56; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 133 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.11 ms after its hand-over (4.35 at most)
[hos ModuleSystemWorker5] vcores: 94890 takes, 17385 waits (mean 30 us, longest 2.0 ms), 8621 kicks, 8441 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 565 dirty pages from their submits' captures, 69595 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16963 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vi: 10845 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (94 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 703 dirty pages from their submits' captures, 69320 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17367 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.46, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 735.3 copies, 7.08 MB written back
[hos host] vk: 10920 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.4 ms a frame (the longest submission 4.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: readback pages refreshed from guest memory: 1306923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 663 dirty pages from their submits' captures, 70429 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17347 in captures, 16 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 240 pages written, 240 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] nvn: CommandBufferWaitEvent #100000: event 0x100d6c8008 mode 0 value 60688 (now 60685) (lr 0x806661f8)
[hos host] vk: mirror syncs (600 submits): 561 dirty pages from their submits' captures, 69460 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16997 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.50, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.9 copies, 7.08 MB written back
[hos host] vk: 11040 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.7 ms a frame (the longest submission 4.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: replay reads of guest memory as submitted: 2080000 (1520402 pages from the captures)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 710 dirty pages from their submits' captures, 70398 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17369 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos BaseProcExecutor2] vcores: 93447 takes, 17051 waits (mean 30 us, longest 1.8 ms), 8470 kicks, 8275 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 11146 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.53, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 735.0 copies, 7.08 MB written back
[hos host] vk: 11160 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.7 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.3 ms a frame (the longest submission 4.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 522 dirty pages from their submits' captures, 68563 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16725 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: program picks: 3380993 kept (1655023 by the last picks' textures, a uniform buffer bound since), 849 new, 2418157 with other textures (of 5800000)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 659 dirty pages from their submits' captures, 70442 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17283 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: readback pages refreshed from guest memory: 1318923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.53, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.3 copies, 7.08 MB written back
[hos host] vk: 11280 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.1 ms a frame (the longest submission 4.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror syncs (600 submits): 649 dirty pages from their submits' captures, 69379 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17073 in captures, 12 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871519 packets run in 10.0 s (busy 0.32 s, spun idle 0.89 s, slept 4981 times, 661 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15918 times, 37.68 ms in all, the longest 0.13 ms; replay_mu unlock 4896/17.65 ms (max 0.11), vkEndCommandBuffer 5511/12.33 ms (max 0.13), vkResetDescriptorPool 5511/7.70 ms (max 0.08)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 674 dirty pages from their submits' captures, 70431 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17323 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: replay reads of guest memory as submitted: 2100000 (1539080 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10975 MB (peak 10996), private 18607 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 6408 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 6408 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 6408 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 6408 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 6408 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 8495 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 6888 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 6694 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 83 waited for it, 0.06 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.1 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.50, present 0.06, draw 0.79, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.19, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.0 copies, 7.08 MB written back
[hos host] vk: 11400 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.2 ms a frame (the longest submission 3.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 1.99 ms a frame (submits 1.47, presents 0.27, others 0.26), idle 14.67; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 103 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.00 ms after its hand-over (2.85 at most)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 615 dirty pages from their submits' captures, 69420 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17043 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos BaseProcExecutor1] vcores: 94538 takes, 17378 waits (mean 29 us, longest 1.9 ms), 8689 kicks, 8521 yields, 0 starved grants, 0 escapes in 5 s
[hos ModuleSystemWorker2] nvn: 800000 recordings made, 29769 live copies (6.2 MB), 1211 texture copies; 4 command buffers' segments (2.2 MB)
[hos Presentation Thread] vi: 11447 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 548 dirty pages from their submits' captures, 69612 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16937 in captures, 20 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.53, present 0.06, draw 0.80, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.6 copies, 7.08 MB written back
[hos host] vk: 11520 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.8 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.7 ms a frame (the longest submission 4.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 630 dirty pages from their submits' captures, 69464 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17090 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: readback pages refreshed from guest memory: 1330923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 604 dirty pages from their submits' captures, 69413 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17015 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.56, present 0.06, draw 0.85, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.8 copies, 7.08 MB written back
[hos host] vk: 11640 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.9 ms a frame (the longest submission 5.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos rmbl::VibrationThread] hid: 32768 vibration values, strongest 0.00 since the last count
[hos host] vk: mirror syncs (600 submits): 532 dirty pages from their submits' captures, 69488 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16963 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: replay reads of guest memory as submitted: 2120000 (1557758 pages from the captures)
[hos BaseProcExecutor2] vcores: 94828 takes, 17328 waits (mean 29 us, longest 2.0 ms), 8680 kicks, 8528 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 11747 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 236 pages written, 236 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 682 dirty pages from their submits' captures, 70573 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17344 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: program picks: 3449390 kept (1660867 by the last picks' textures, a uniform buffer bound since), 849 new, 2549760 with other textures (of 6000000)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.57, present 0.06, draw 0.82, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.20, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.9 copies, 7.08 MB written back
[hos host] vk: 11760 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.4 ms a frame (the longest submission 4.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos ModuleSystemWorker2] vk: readbacks of GPU results: 0 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 485 dirty pages from their submits' captures, 68446 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16660 in captures, 19 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos ModuleSystemWorker3] nvn: CommandBufferWaitEvent #105000: event 0x100d6c8004 mode 0 value 63189 (now 63183) (lr 0x80a47c2c)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.56, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.9 copies, 7.08 MB written back
[hos host] vk: 11880 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 5.1 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 675 dirty pages from their submits' captures, 70413 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17332 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871561 packets run in 10.0 s (busy 0.32 s, spun idle 0.91 s, slept 4972 times, 660 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15970 times, 38.69 ms in all, the longest 0.13 ms; replay_mu unlock 4916/18.20 ms (max 0.12), vkEndCommandBuffer 5527/12.25 ms (max 0.12), vkResetDescriptorPool 5527/8.24 ms (max 0.13)
[hos host] vk: readback pages refreshed from guest memory: 1342923 pages so far (0 held: may be written ahead in their submission)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 700 dirty pages from their submits' captures, 69313 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17104 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: queues ordered by their events: 54000 submissions stopped at a wait, 53999 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 105664, not met 0; captures at a CPU event's wait 2749, 0 of them at a wait met on arrival
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10975 MB (peak 10996), private 18606 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 7008 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 7008 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 7008 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 7008 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 7008 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 9095 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 7488 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 7294 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 108 waited for it, 0.06 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.0 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.50, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.5 copies, 7.08 MB written back
[hos host] vk: 12000 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.4 ms a frame (the longest submission 3.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.07 ms a frame (submits 1.48, presents 0.29, others 0.30), idle 14.60; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 119 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.08 ms after its hand-over (3.06 at most)
[hos Presentation Thread] vi: real-time step on: ratio 1.000, game's frame rate 60
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 679 dirty pages from their submits' captures, 70423 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17369 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: replay reads of guest memory as submitted: 2140000 (1576434 pages from the captures)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos BaseProcExecutor1] vcores: 95461 takes, 17330 waits (mean 30 us, longest 2.6 ms), 8503 kicks, 8353 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 12048 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 554 dirty pages from their submits' captures, 69608 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16995 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.56, present 0.07, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.20, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.4 copies, 7.08 MB written back
[hos host] vk: 12120 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.8 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.8 ms a frame (the longest submission 4.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 615 dirty pages from their submits' captures, 69419 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17016 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 522 dirty pages from their submits' captures, 70584 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17204 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.54, present 0.06, draw 0.83, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.8 copies, 7.08 MB written back
[hos host] vk: 12240 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.9 ms a frame (the longest submission 3.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: readback pages refreshed from guest memory: 1354923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 648 dirty pages from their submits' captures, 69373 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17048 in captures, 18 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos ModuleSystemWorker3] nvn: 850000 recordings made, 29761 live copies (6.2 MB), 1211 texture copies; 3 command buffers' segments (2.1 MB)
[hos tera::FileResourceMgr] vcores: 95722 takes, 17181 waits (mean 30 us, longest 1.7 ms), 8533 kicks, 8345 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: mirror syncs (600 submits): 733 dirty pages from their submits' captures, 70520 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17374 in captures, 11 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: program picks: 3517787 kept (1666717 by the last picks' textures, a uniform buffer bound since), 849 new, 2681363 with other textures (of 6200000)
[hos Presentation Thread] vi: 12348 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 299, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.54, present 0.06, draw 0.83, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.22 MB synced in 735.3 copies, 7.08 MB written back
[hos host] vk: 12360 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.9 ms a frame (the longest submission 4.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: replay reads of guest memory as submitted: 2160000 (1595114 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 654 dirty pages from their submits' captures, 70495 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17087 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #65000: event 0x100d6c8008 mode 0 value 64999 (lr 0x80666598)
[hos host] vk: mirror syncs (600 submits): 512 dirty pages from their submits' captures, 69417 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17211 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.56, present 0.06, draw 0.84, descriptors 0.47, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 732.9 copies, 7.08 MB written back
[hos host] vk: 12480 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.7 ms a frame (the longest submission 5.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] nvn: EventSignal (CPU) #25000: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871360 packets run in 10.0 s (busy 0.32 s, spun idle 0.91 s, slept 4990 times, 665 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15898 times, 37.24 ms in all, the longest 0.10 ms; replay_mu unlock 4896/17.72 ms (max 0.08), vkEndCommandBuffer 5501/12.03 ms (max 0.10), vkResetDescriptorPool 5501/7.49 ms (max 0.10)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 5 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 591 dirty pages from their submits' captures, 69340 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17025 in captures, 16 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: readback pages refreshed from guest memory: 1366923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10975 MB (peak 10996), private 18607 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 7608 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 7608 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 7608 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 7608 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 7608 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 9695 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 8088 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 7894 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 108 waited for it, 0.04 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.0 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.57, present 0.06, draw 0.83, descriptors 0.46, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.20, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 732.1 copies, 7.08 MB written back
[hos host] vk: 12600 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.9 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 4.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.08 ms a frame (submits 1.49, presents 0.29, others 0.30), idle 14.58; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 122 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.09 ms after its hand-over (3.03 at most)
[hos host] vk: mirror syncs (600 submits): 353 dirty pages from their submits' captures, 68502 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16572 in captures, 15 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 227 pages written, 227 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos PlacementMgr] vcores: 96226 takes, 17123 waits (mean 30 us, longest 2.0 ms), 8368 kicks, 8211 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 12649 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 496 dirty pages from their submits' captures, 69572 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16705 in captures, 17 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #110000: event 0x100d6c8008 mode 0 value 65689 (now 65686) (lr 0x806661f8)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: replay reads of guest memory as submitted: 2180000 (1613790 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 230 pages written, 230 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.60, present 0.07, draw 0.88, descriptors 0.48, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.07, commands 0.22, dispatch 0.04, memory sync 0.20, queue submit 0.20, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.1 copies, 7.08 MB written back
[hos host] vk: 12720 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 645.0 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.0 ms a frame (the longest submission 4.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 493 dirty pages from their submits' captures, 68354 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16925 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 381 dirty pages from their submits' captures, 68468 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16587 in captures, 19 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (112 MB), 5 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.67, present 0.06, draw 0.89, descriptors 0.49, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.07, commands 0.23, dispatch 0.05, memory sync 0.20, queue submit 0.21, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 732.3 copies, 7.08 MB written back
[hos host] vk: 12840 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.9 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.1 ms a frame (the longest submission 4.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror syncs (600 submits): 592 dirty pages from their submits' captures, 69339 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17006 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos rmbl::VibrationThread] hid: 36864 vibration values, strongest 0.00 since the last count
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: readback pages refreshed from guest memory: 1378923 pages so far (0 held: may be written ahead in their submission)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 503 dirty pages from their submits' captures, 69444 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16965 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: program picks: 3586221 kept (1672567 by the last picks' textures, a uniform buffer bound since), 849 new, 2812929 with other textures (of 6400000)
[hos ModuleSystemWorker1] vcores: 96855 takes, 17372 waits (mean 32 us, longest 2.4 ms), 8697 kicks, 8498 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 12949 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.72, present 0.06, draw 0.92, descriptors 0.51, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.07, commands 0.23, dispatch 0.05, memory sync 0.20, queue submit 0.22, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.2 copies, 7.08 MB written back
[hos host] vk: 12960 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.9 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.3 ms a frame (the longest submission 5.4 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror syncs (600 submits): 450 dirty pages from their submits' captures, 68557 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16636 in captures, 12 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 228 pages written, 228 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 2200000 (1632469 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 556 dirty pages from their submits' captures, 69376 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16968 in captures, 18 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.54, present 0.06, draw 0.84, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 732.8 copies, 7.08 MB written back
[hos host] vk: 13080 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.7 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 3.9 ms a frame (the longest submission 4.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871712 packets run in 10.0 s (busy 0.34 s, spun idle 0.93 s, slept 4946 times, 664 of them under 200 us), 0 calls made directly (no room); the replay waited for it 16106 times, 41.88 ms in all, the longest 0.10 ms; replay_mu unlock 4964/20.45 ms (max 0.10), vkEndCommandBuffer 5571/13.47 ms (max 0.07), vkResetDescriptorPool 5571/7.97 ms (max 0.05)
[hos host] vk: mirror syncs (600 submits): 648 dirty pages from their submits' captures, 69290 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17085 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 633 dirty pages from their submits' captures, 70445 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17287 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10975 MB (peak 10996), private 18607 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 8208 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 8208 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 8208 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 8208 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 8208 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 10295 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 8688 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 8494 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 132 waited for it, 0.06 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 17.8 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.50, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.0 copies, 7.08 MB written back
[hos host] vk: 13200 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.2 ms a frame (the longest submission 4.2 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.17 ms a frame (submits 1.45, presents 0.31, others 0.40), idle 14.49; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 159 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.18 ms after its hand-over (3.59 at most)
[hos host] vk: readback pages refreshed from guest memory: 1390923 pages so far (0 held: may be written ahead in their submission)
[hos ModuleSystemWorker2] nvn: 900000 recordings made, 29753 live copies (6.2 MB), 1211 texture copies; 3 command buffers' segments (2.1 MB)
[hos NavMeshCAStepDepWorker1] vcores: 96120 takes, 17684 waits (mean 29 us, longest 1.9 ms), 8851 kicks, 8687 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 13249 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 299, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: mirror syncs (600 submits): 515 dirty pages from their submits' captures, 68485 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16727 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos ModuleSystemWorker1] vk: readbacks of GPU results: 0 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 593 dirty pages from their submits' captures, 70410 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17265 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.53, present 0.06, draw 0.83, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.5 copies, 7.08 MB written back
[hos host] vk: 13320 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.7 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 4.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] nvn: QueueSubmitCommands #80000: queue 0000101004133020 (its #13339), 1 handles (lr 0x80590358)
[hos host] vk: replay reads of guest memory as submitted: 2220000 (1651146 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 625 dirty pages from their submits' captures, 69304 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17061 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: queues ordered by their events: 60000 submissions stopped at a wait, 59998 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 114178, not met 0; captures at a CPU event's wait 3072, 0 of them at a wait met on arrival
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.50, present 0.06, draw 0.80, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.1 copies, 7.08 MB written back
[hos host] vk: 13440 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.0 ms a frame (the longest submission 4.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 662 dirty pages from their submits' captures, 70351 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17335 in captures, 11 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 619 dirty pages from their submits' captures, 70384 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17345 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: program picks: 3654662 kept (1678415 by the last picks' textures, a uniform buffer bound since), 849 new, 2944488 with other textures (of 6600000)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #115000: event 0x100d6c8008 mode 0 value 68188 (now 68185) (lr 0x806661f8)
[hos Resource Memory] vcores: 94760 takes, 17353 waits (mean 30 us, longest 2.0 ms), 8583 kicks, 8443 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 13549 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 2, 15.5-17.8 298, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: readback pages refreshed from guest memory: 1402923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.58, present 0.06, draw 0.85, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.3 copies, 7.08 MB written back
[hos host] vk: 13560 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.7 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.5 ms a frame (the longest submission 6.4 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 378 dirty pages from their submits' captures, 68616 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16592 in captures, 16 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 230 pages written, 230 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 531 dirty pages from their submits' captures, 69387 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16959 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.58, present 0.06, draw 0.83, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 732.4 copies, 7.08 MB written back
[hos host] vk: 13680 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.8 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 4.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: replay reads of guest memory as submitted: 2240000 (1669823 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 458 dirty pages from their submits' captures, 68385 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16655 in captures, 17 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871483 packets run in 10.0 s (busy 0.32 s, spun idle 0.90 s, slept 4969 times, 662 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15977 times, 38.47 ms in all, the longest 0.08 ms; replay_mu unlock 4915/18.46 ms (max 0.08), vkEndCommandBuffer 5531/12.54 ms (max 0.08), vkResetDescriptorPool 5531/7.47 ms (max 0.06)
[hos host] vk: mirror syncs (600 submits): 654 dirty pages from their submits' captures, 69293 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17057 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10975 MB (peak 10996), private 18607 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 8808 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 8808 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 8808 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 8808 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 8808 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 10895 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 9288 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 9094 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 122 waited for it, 0.05 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.0 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.58, present 0.06, draw 0.85, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 732.6 copies, 7.08 MB written back
[hos host] vk: 13800 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.8 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.4 ms a frame (the longest submission 4.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.09 ms a frame (submits 1.45, presents 0.29, others 0.35), idle 14.58; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 138 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.10 ms after its hand-over (3.15 at most)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 509 dirty pages from their submits' captures, 69419 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16960 in captures, 17 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Resource Memory] vcores: 95872 takes, 17512 waits (mean 30 us, longest 2.0 ms), 8776 kicks, 8586 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 13850 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: readback pages refreshed from guest memory: 1414923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 494 dirty pages from their submits' captures, 69585 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16946 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.55, present 0.07, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.2 copies, 7.08 MB written back
[hos host] vk: 13920 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.3 ms a frame (the longest submission 4.4 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 234 pages written, 234 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 536 dirty pages from their submits' captures, 69392 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16957 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: replay reads of guest memory as submitted: 2260000 (1688502 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 555 dirty pages from their submits' captures, 69447 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16980 in captures, 17 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.52, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 732.6 copies, 7.08 MB written back
[hos host] vk: 14040 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 4.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 547 dirty pages from their submits' captures, 69388 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16985 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: program picks: 3723100 kept (1684263 by the last picks' textures, a uniform buffer bound since), 849 new, 3076050 with other textures (of 6800000)
[hos rmbl::VibrationThread] hid: 40960 vibration values, strongest 0.00 since the last count
[hos ModuleSystemWorker2] nvn: 950000 recordings made, 29745 live copies (6.2 MB), 1211 texture copies; 4 command buffers' segments (2.2 MB)
[hos ModuleSystemWorker5] nvn: CommandBufferSignalEvent #70000: event 0x100d6c8004 mode 0 value 69999 (lr 0x80665068)
[hos NavMeshCAStepDepWorker1] vcores: 95263 takes, 16786 waits (mean 30 us, longest 1.8 ms), 8262 kicks, 8079 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 14150 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.49, present 0.06, draw 0.80, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.5 copies, 7.08 MB written back
[hos host] vk: 14160 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.8 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.0 ms a frame (the longest submission 4.2 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror syncs (600 submits): 604 dirty pages from their submits' captures, 69469 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17015 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: readback pages refreshed from guest memory: 1426923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 607 dirty pages from their submits' captures, 69316 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17050 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.49, present 0.06, draw 0.81, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.3 copies, 7.08 MB written back
[hos host] vk: 14280 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.3 ms a frame (the longest submission 4.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror syncs (600 submits): 717 dirty pages from their submits' captures, 71369 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 335 runs, 474.5 MB compared; 67 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17632 in captures, 10 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871504 packets run in 10.0 s (busy 0.32 s, spun idle 0.89 s, slept 4992 times, 662 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15963 times, 37.52 ms in all, the longest 0.08 ms; replay_mu unlock 4917/18.00 ms (max 0.06), vkEndCommandBuffer 5523/12.32 ms (max 0.08), vkResetDescriptorPool 5523/7.20 ms (max 0.07)
[hos host] vk: replay reads of guest memory as submitted: 2280000 (1707178 pages from the captures)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 590 dirty pages from their submits' captures, 69337 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17023 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos ModuleSystemWorker4] nvn: CommandBufferWaitEvent #120000: event 0x100d6c8004 mode 0 value 70689 (now 70683) (lr 0x80a47c2c)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10975 MB (peak 10996), private 18607 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 9408 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 9408 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 9408 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 9408 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 9408 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 11495 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 9888 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 9694 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 104 waited for it, 0.04 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.2 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.51, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.1 copies, 7.08 MB written back
[hos host] vk: 14400 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.5 ms a frame (the longest submission 4.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: queues ordered by their events: 64244 submissions stopped at a wait, 64244 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 120226, not met 0; captures at a CPU event's wait 3286, 0 of them at a wait met on arrival
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.01 ms a frame (submits 1.46, presents 0.27, others 0.29), idle 14.65; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 116 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.02 ms after its hand-over (3.15 at most)
[hos host] vk: mirror syncs (600 submits): 644 dirty pages from their submits' captures, 69284 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17072 in captures, 11 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos NavMeshCAStepDepWorker1] vcores: 94541 takes, 16832 waits (mean 30 us, longest 1.8 ms), 8354 kicks, 8208 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos Presentation Thread] vi: 14450 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 620 dirty pages from their submits' captures, 70525 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17300 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.50, present 0.07, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.1 copies, 7.08 MB written back
[hos host] vk: 14520 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.6 ms a frame (the longest submission 4.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: readback pages refreshed from guest memory: 1438923 pages so far (0 held: may be written ahead in their submission)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (112 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 672 dirty pages from their submits' captures, 69266 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17081 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 618 dirty pages from their submits' captures, 70392 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17320 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.56, present 0.06, draw 0.85, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.22, dispatch 0.04, memory sync 0.20, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 732.9 copies, 7.08 MB written back
[hos host] vk: 14640 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.5 ms a frame (the longest submission 5.1 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 2300000 (1725858 pages from the captures)
[hos host] vk: program picks: 3791491 kept (1690107 by the last picks' textures, a uniform buffer bound since), 849 new, 3207659 with other textures (of 7000000)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 603 dirty pages from their submits' captures, 69328 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17041 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos NavMeshCAStepDepWorker1] vcores: 95048 takes, 17333 waits (mean 29 us, longest 1.9 ms), 8697 kicks, 8515 yields, 0 starved grants, 0 escapes in 5 s
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 239 pages written, 239 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos Presentation Thread] vi: 14751 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 726 dirty pages from their submits' captures, 70436 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17382 in captures, 11 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.52, present 0.06, draw 0.82, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.2 copies, 7.08 MB written back
[hos host] vk: 14760 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.3 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.5 ms a frame (the longest submission 5.1 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: readbacks of GPU results: 0 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 666 dirty pages from their submits' captures, 70426 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17348 in captures, 11 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: queues ordered by their events: 66000 submissions stopped at a wait, 65999 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 122764, not met 0; captures at a CPU event's wait 3349, 0 of them at a wait met on arrival
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (112 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: readback pages refreshed from guest memory: 1450923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.52, present 0.06, draw 0.85, descriptors 0.48, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.4 copies, 7.08 MB written back
[hos host] vk: 14880 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.3 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.5 ms a frame (the longest submission 5.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 681 dirty pages from their submits' captures, 70330 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17373 in captures, 12 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871331 packets run in 10.0 s (busy 0.32 s, spun idle 0.89 s, slept 4981 times, 661 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15863 times, 36.95 ms in all, the longest 0.09 ms; replay_mu unlock 4884/17.66 ms (max 0.09), vkEndCommandBuffer 5490/11.86 ms (max 0.06), vkResetDescriptorPool 5489/7.43 ms (max 0.09)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 592 dirty pages from their submits' captures, 69324 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17004 in captures, 18 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10975 MB (peak 10996), private 18607 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 10008 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 10008 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 10008 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 10008 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 10008 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 12095 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 10488 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 10294 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos sead::MainThread] nvn: EventSignal (CPU) #30000: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos Presentation Thread] vk: presents after the CPU's signal (600): 77 waited for it, 0.07 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.3 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.52, present 0.06, draw 0.83, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.0 copies, 7.08 MB written back
[hos host] vk: 15000 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.5 ms a frame (the longest submission 4.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.03 ms a frame (submits 1.52, presents 0.27, others 0.24), idle 14.64; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 92 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.04 ms after its hand-over (3.32 at most)
[hos Presentation Thread] vi: real-time step on: ratio 0.996, game's frame rate 60
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 620 dirty pages from their submits' captures, 69312 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17034 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: replay reads of guest memory as submitted: 2320000 (1744534 pages from the captures)
[hos ModuleSystemWorker4] nvn: 1000000 recordings made, 29746 live copies (6.2 MB), 1211 texture copies; 5 command buffers' segments (2.3 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos ModuleSystemWorker1] vcores: 95882 takes, 17045 waits (mean 30 us, longest 2.0 ms), 8527 kicks, 8344 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 15051 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 299, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: mirror syncs (600 submits): 562 dirty pages from their submits' captures, 69560 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16943 in captures, 18 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.61, present 0.07, draw 0.83, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.20, queue submit 0.20, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.9 copies, 7.08 MB written back
[hos host] vk: 15120 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.6 ms a frame (the longest submission 4.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 584 dirty pages from their submits' captures, 70501 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17256 in captures, 18 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: readback pages refreshed from guest memory: 1462923 pages so far (0 held: may be written ahead in their submission)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #125000: event 0x100d6c8008 mode 0 value 73189 (now 73186) (lr 0x806661f8)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 573 dirty pages from their submits' captures, 69450 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17019 in captures, 15 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.54, present 0.06, draw 0.82, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.8 copies, 7.08 MB written back
[hos host] vk: 15240 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.1 ms a frame (the longest submission 5.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: program picks: 3859894 kept (1695957 by the last picks' textures, a uniform buffer bound since), 849 new, 3339256 with other textures (of 7200000)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 581 dirty pages from their submits' captures, 69437 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17000 in captures, 10 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 603 dirty pages from their submits' captures, 70495 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17284 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos ModuleSystemWorker1] vcores: 95217 takes, 17154 waits (mean 29 us, longest 1.8 ms), 8544 kicks, 8400 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: replay reads of guest memory as submitted: 2340000 (1763213 pages from the captures)
[hos rmbl::VibrationThread] hid: 45056 vibration values, strongest 0.00 since the last count
[hos Presentation Thread] vi: 15351 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.51, present 0.06, draw 0.81, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 735.0 copies, 7.08 MB written back
[hos host] vk: 15360 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.5 ms a frame (the longest submission 5.2 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 660 dirty pages from their submits' captures, 70602 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17329 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 640 dirty pages from their submits' captures, 69382 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17056 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.50, present 0.06, draw 0.80, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.19, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.0 copies, 7.08 MB written back
[hos host] vk: 15480 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.4 ms a frame (the longest submission 5.2 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871363 packets run in 10.0 s (busy 0.32 s, spun idle 0.90 s, slept 4979 times, 661 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15910 times, 37.11 ms in all, the longest 0.09 ms; replay_mu unlock 4896/17.84 ms (max 0.07), vkEndCommandBuffer 5507/11.88 ms (max 0.09), vkResetDescriptorPool 5507/7.39 ms (max 0.09)
[hos host] vk: readback pages refreshed from guest memory: 1474923 pages so far (0 held: may be written ahead in their submission)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 668 dirty pages from their submits' captures, 70440 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17341 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10975 MB (peak 10996), private 18607 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 10608 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 10608 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 10608 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 10608 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 10608 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 12695 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 11088 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 10894 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 93 waited for it, 0.07 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.2 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.52, present 0.06, draw 0.81, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.4 copies, 7.08 MB written back
[hos host] vk: 15600 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.6 ms a frame (the longest submission 5.1 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.05 ms a frame (submits 1.50, presents 0.28, others 0.27), idle 14.62; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 106 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.06 ms after its hand-over (2.94 at most)
[hos host] vk: mirror syncs (600 submits): 637 dirty pages from their submits' captures, 69390 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17075 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos NavMeshCAStepDepWorker1] vcores: 94772 takes, 17151 waits (mean 30 us, longest 1.8 ms), 8445 kicks, 8321 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 15652 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 298, 17.8-22 2, 22-30 0, 30-40 0, over 40 0
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 613 dirty pages from their submits' captures, 69626 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17039 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: replay reads of guest memory as submitted: 2360000 (1781890 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 236 pages written, 236 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.46, present 0.06, draw 0.77, descriptors 0.43, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.19, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.8 copies, 7.08 MB written back
[hos host] vk: 15720 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.4 ms a frame (the longest submission 4.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror syncs (600 submits): 609 dirty pages from their submits' captures, 69402 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17030 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 640 dirty pages from their submits' captures, 70471 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17315 in captures, 11 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #75000: event 0x100d6c8000 mode 0 value 74999 (lr 0x80664f14)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.47, present 0.06, draw 0.81, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.3 copies, 7.08 MB written back
[hos host] vk: 15840 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.7 ms a frame (the longest submission 4.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: readback pages refreshed from guest memory: 1486923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: program picks: 3928328 kept (1701807 by the last picks' textures, a uniform buffer bound since), 849 new, 3470822 with other textures (of 7400000)
[hos host] vk: mirror syncs (600 submits): 678 dirty pages from their submits' captures, 70432 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17357 in captures, 9 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] nvn: 1050000 recordings made, 29779 live copies (5.9 MB), 1211 texture copies; 2 command buffers' segments (2.1 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 614 dirty pages from their submits' captures, 69408 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17048 in captures, 12 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos ModuleSystemWorker1] vcores: 94285 takes, 16876 waits (mean 29 us, longest 1.8 ms), 8425 kicks, 8270 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 15953 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.54, present 0.06, draw 0.84, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.9 copies, 7.08 MB written back
[hos host] vk: 15960 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.7 ms a frame (the longest submission 5.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 548 dirty pages from their submits' captures, 69605 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16997 in captures, 17 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: replay reads of guest memory as submitted: 2380000 (1800566 pages from the captures)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (86 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #130000: event 0x100d6c8008 mode 0 value 75688 (now 75685) (lr 0x806661f8)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 577 dirty pages from their submits' captures, 69440 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17002 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.54, present 0.06, draw 0.83, descriptors 0.46, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.6 copies, 7.08 MB written back
[hos host] vk: 16080 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.7 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.4 ms a frame (the longest submission 5.1 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1874584 packets run in 10.0 s (busy 0.31 s, spun idle 0.90 s, slept 4975 times, 668 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15954 times, 35.67 ms in all, the longest 0.06 ms; replay_mu unlock 4910/17.16 ms (max 0.04), vkEndCommandBuffer 5522/11.52 ms (max 0.06), vkResetDescriptorPool 5522/7.00 ms (max 0.03)
[hos host] vk: mirror syncs (600 submits): 600 dirty pages from their submits' captures, 70495 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17040 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: readback pages refreshed from guest memory: 1498923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 643 dirty pages from their submits' captures, 69382 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17294 in captures, 16 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10975 MB (peak 10996), private 18607 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 11208 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 11208 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 11208 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 11208 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 11208 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 13295 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 11688 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 11494 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 92 waited for it, 0.06 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.0 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.55, present 0.06, draw 0.84, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.2 copies, 7.08 MB written back
[hos host] vk: 16200 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.3 ms a frame (the longest submission 5.1 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.02 ms a frame (submits 1.47, presents 0.28, others 0.27), idle 14.65; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 107 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.03 ms after its hand-over (3.32 at most)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (112 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos ModuleSystemWorker1] vcores: 95106 takes, 17047 waits (mean 30 us, longest 1.9 ms), 8488 kicks, 8298 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 16253 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: mirror syncs (600 submits): 625 dirty pages from their submits' captures, 70618 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17298 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: queues ordered by their events: 72000 submissions stopped at a wait, 71999 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 131386, not met 0; captures at a CPU event's wait 3601, 0 of them at a wait met on arrival
[hos ModuleSystemWorker1] vk: readbacks of GPU results: 0 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (112 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.53, present 0.06, draw 0.85, descriptors 0.48, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.7 copies, 7.08 MB written back
[hos host] vk: 16320 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.2 ms a frame (the longest submission 4.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 569 dirty pages from their submits' captures, 69464 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16998 in captures, 12 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: replay reads of guest memory as submitted: 2400000 (1819246 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 391 dirty pages from their submits' captures, 68560 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16576 in captures, 18 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 230 pages written, 230 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: program picks: 3996770 kept (1707655 by the last picks' textures, a uniform buffer bound since), 849 new, 3602380 with other textures (of 7600000)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.64, present 0.06, draw 0.92, descriptors 0.51, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.07, commands 0.23, dispatch 0.05, memory sync 0.19, queue submit 0.20, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.5 copies, 7.08 MB written back
[hos host] vk: 16440 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.8 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.5 ms a frame (the longest submission 5.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 653 dirty pages from their submits' captures, 70519 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17330 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: readback pages refreshed from guest memory: 1510923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 640 dirty pages from their submits' captures, 69381 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17051 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos NavMeshCAStepDepWorker1] vcores: 97237 takes, 17860 waits (mean 30 us, longest 2.1 ms), 8933 kicks, 8739 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 16554 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.53, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.8 copies, 7.08 MB written back
[hos host] vk: 16560 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.5 ms a frame (the longest submission 3.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos rmbl::VibrationThread] hid: 49152 vibration values, strongest 0.00 since the last count
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 609 dirty pages from their submits' captures, 70636 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17033 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 236 pages written, 236 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 647 dirty pages from their submits' captures, 69379 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17351 in captures, 16 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] nvn: QueueSubmitCommands #100000: queue 000010100D6BF020 (its #16666), 1 handles (lr 0x80666be0)
[hos host] vk: replay reads of guest memory as submitted: 2420000 (1837922 pages from the captures)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.50, present 0.06, draw 0.78, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.19, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.0 copies, 7.08 MB written back
[hos host] vk: 16680 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.1 ms a frame (the longest submission 4.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871427 packets run in 10.0 s (busy 0.32 s, spun idle 0.91 s, slept 4965 times, 661 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15931 times, 37.99 ms in all, the longest 0.08 ms; replay_mu unlock 4909/18.70 ms (max 0.08), vkEndCommandBuffer 5511/12.02 ms (max 0.07), vkResetDescriptorPool 5511/7.27 ms (max 0.06)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 591 dirty pages from their submits' captures, 69434 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17023 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: mirror syncs (600 submits): 709 dirty pages from their submits' captures, 70384 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17363 in captures, 11 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10975 MB (peak 10996), private 18607 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 11808 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 11808 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 11808 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 11808 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 11808 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 13895 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 12288 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 12094 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 88 waited for it, 0.07 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.5 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.47, present 0.06, draw 0.79, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.3 copies, 7.08 MB written back
[hos host] vk: 16800 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.3 ms a frame (the longest submission 4.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.05 ms a frame (submits 1.49, presents 0.28, others 0.28), idle 14.61; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 109 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.06 ms after its hand-over (3.40 at most)
[hos sead::MainThread] nvn: 1100000 recordings made, 29777 live copies (6.2 MB), 1211 texture copies; 5 command buffers' segments (2.3 MB)
[hos host] vk: readback pages refreshed from guest memory: 1522923 pages so far (0 held: may be written ahead in their submission)
[hos NavMeshCAStepDepWorker1] vcores: 95249 takes, 17436 waits (mean 28 us, longest 1.7 ms), 8631 kicks, 8479 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 658 dirty pages from their submits' captures, 70441 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17314 in captures, 14 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vi: 16855 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 299, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos ModuleSystemWorker1] nvn: CommandBufferWaitEvent #135000: event 0x100d6c8004 mode 0 value 78189 (now 78183) (lr 0x80a47c2c)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 500 dirty pages from their submits' captures, 69661 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16937 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.57, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.5 copies, 7.08 MB written back
[hos host] vk: 16920 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.6 ms a frame (the longest submission 5.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 552 dirty pages from their submits' captures, 69459 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16978 in captures, 18 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 2440000 (1856602 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: program picks: 4065203 kept (1713499 by the last picks' textures, a uniform buffer bound since), 849 new, 3733947 with other textures (of 7800000)
[hos host] vk: mirror syncs (600 submits): 641 dirty pages from their submits' captures, 70478 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17077 in captures, 17 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.54, present 0.06, draw 0.84, descriptors 0.48, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.0 copies, 7.08 MB written back
[hos host] vk: 17040 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.8 ms a frame (the longest submission 5.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 605 dirty pages from their submits' captures, 69422 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17325 in captures, 14 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] vcores: 95371 takes, 17131 waits (mean 32 us, longest 2.0 ms), 8446 kicks, 8296 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: readback pages refreshed from guest memory: 1534923 pages so far (0 held: may be written ahead in their submission)
[hos Presentation Thread] vi: 17155 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.52, present 0.06, draw 0.79, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.19, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 735.0 copies, 7.08 MB written back
[hos host] vk: 17160 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.8 ms a frame (the longest submission 6.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror syncs (600 submits): 667 dirty pages from their submits' captures, 70581 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17330 in captures, 14 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 695 dirty pages from their submits' captures, 69333 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17093 in captures, 10 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.02 over 745 ranges, 1580 MB), 236 pages written, 236 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.46, present 0.06, draw 0.80, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.6 copies, 7.08 MB written back
[hos host] vk: 17280 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.4 ms a frame (the longest submission 4.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 707 dirty pages from their submits' captures, 70472 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17380 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871368 packets run in 10.0 s (busy 0.31 s, spun idle 0.89 s, slept 4998 times, 662 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15865 times, 36.87 ms in all, the longest 0.09 ms; replay_mu unlock 4877/17.46 ms (max 0.06), vkEndCommandBuffer 5494/12.05 ms (max 0.07), vkResetDescriptorPool 5494/7.35 ms (max 0.09)
[hos host] vk: replay reads of guest memory as submitted: 2460000 (1875278 pages from the captures)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.02 over 745 ranges, 1580 MB), 240 pages written, 240 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 675 dirty pages from their submits' captures, 70434 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17357 in captures, 11 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10975 MB (peak 10996), private 18606 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 12408 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 12408 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 12408 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 12408 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 12408 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 14495 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 12888 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 12694 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 81 waited for it, 0.06 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.0 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.47, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.6 copies, 7.08 MB written back
[hos host] vk: 17400 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.2 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.2 ms a frame (the longest submission 4.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.01 ms a frame (submits 1.50, presents 0.27, others 0.24), idle 14.65; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 91 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.02 ms after its hand-over (3.12 at most)
[hos host] vk: mirror syncs (600 submits): 683 dirty pages from their submits' captures, 70427 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17092 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos AudioFrameworkThread] vcores: 95343 takes, 17555 waits (mean 30 us, longest 1.9 ms), 8750 kicks, 8562 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 17455 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 298, 17.8-22 2, 22-30 0, 30-40 0, over 40 0
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 236 pages written, 236 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #80000: event 0x100d6c8008 mode 0 value 79999 (lr 0x80666598)
[hos host] vk: readback pages refreshed from guest memory: 1546923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 646 dirty pages from their submits' captures, 69516 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17339 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] nvn: EventSignal (CPU) #35000: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.51, present 0.06, draw 0.78, descriptors 0.43, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.8 copies, 7.08 MB written back
[hos host] vk: 17520 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.3 ms a frame (the longest submission 5.2 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (112 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 569 dirty pages from their submits' captures, 69445 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16981 in captures, 17 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: program picks: 4133592 kept (1719347 by the last picks' textures, a uniform buffer bound since), 849 new, 3865558 with other textures (of 8000000)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 670 dirty pages from their submits' captures, 70436 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17337 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.49, present 0.06, draw 0.82, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.1 copies, 7.08 MB written back
[hos host] vk: 17640 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.1 ms a frame (the longest submission 4.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: replay reads of guest memory as submitted: 2480000 (1893956 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 406 dirty pages from their submits' captures, 68532 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16623 in captures, 17 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos ModuleSystemWorker1] nvn: 1150000 recordings made, 29769 live copies (6.2 MB), 1211 texture copies; 5 command buffers' segments (2.3 MB)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #140000: event 0x100d6c8008 mode 0 value 80689 (now 80686) (lr 0x806661f8)
[hos host] vk: queues ordered by their events: 78000 submissions stopped at a wait, 77997 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 140002, not met 0; captures at a CPU event's wait 3855, 0 of them at a wait met on arrival
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos ModuleSystemWorker3] vcores: 95634 takes, 17469 waits (mean 30 us, longest 1.9 ms), 8696 kicks, 8547 yields, 0 starved grants, 0 escapes in 5 s
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos Presentation Thread] vi: 17755 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 298, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 632 dirty pages from their submits' captures, 69470 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17062 in captures, 11 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.63, present 0.06, draw 0.87, descriptors 0.48, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.22, dispatch 0.04, memory sync 0.19, queue submit 0.20, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.5 copies, 7.08 MB written back
[hos host] vk: 17760 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.9 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.7 ms a frame (the longest submission 6.2 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos ModuleSystemWorker2] vk: readbacks of GPU results: 0 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: readback pages refreshed from guest memory: 1558923 pages so far (0 held: may be written ahead in their submission)
[hos rmbl::VibrationThread] hid: 53248 vibration values, strongest 0.00 since the last count
[hos host] vk: mirror syncs (600 submits): 509 dirty pages from their submits' captures, 69592 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16898 in captures, 18 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.60, present 0.06, draw 0.85, descriptors 0.47, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.20, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.6 copies, 7.08 MB written back
[hos host] vk: 17880 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 3.4 ms a frame (the longest submission 4.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 634 dirty pages from their submits' captures, 70480 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17329 in captures, 11 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871401 packets run in 10.0 s (busy 0.32 s, spun idle 0.91 s, slept 4998 times, 661 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15914 times, 38.35 ms in all, the longest 0.11 ms; replay_mu unlock 4894/18.34 ms (max 0.10), vkEndCommandBuffer 5510/12.41 ms (max 0.07), vkResetDescriptorPool 5510/7.59 ms (max 0.11)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 578 dirty pages from their submits' captures, 70520 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17262 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 2500000 (1912634 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10975 MB (peak 10996), private 18607 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 13008 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 13008 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 13008 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 13008 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 13008 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 15095 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 13488 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 13294 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 97 waited for it, 0.05 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.1 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.60, present 0.06, draw 0.81, descriptors 0.45, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.1 copies, 7.08 MB written back
[hos host] vk: 18000 presents, 59.9 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 3.2 ms a frame (the longest submission 3.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: queues ordered by their events: 79264 submissions stopped at a wait, 79264 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 141826, not met 0; captures at a CPU event's wait 3906, 0 of them at a wait met on arrival
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.10 ms a frame (submits 1.51, presents 0.29, others 0.30), idle 14.57; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 115 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.11 ms after its hand-over (3.43 at most)
[hos Presentation Thread] vi: real-time step on: ratio 1.000, game's frame rate 60
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 620 dirty pages from their submits' captures, 69407 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17041 in captures, 14 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos ModuleSystemWorker5] vcores: 95748 takes, 17345 waits (mean 31 us, longest 1.9 ms), 8609 kicks, 8440 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos Presentation Thread] vi: 18056 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: mirror syncs (600 submits): 411 dirty pages from their submits' captures, 68753 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16609 in captures, 15 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.71, present 0.07, draw 0.88, descriptors 0.48, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.23, dispatch 0.05, memory sync 0.19, queue submit 0.21, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.2 copies, 7.08 MB written back
[hos host] vk: 18120 presents, 60.1 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.9 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.1 ms a frame (the longest submission 4.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: readback pages refreshed from guest memory: 1570923 pages so far (0 held: may be written ahead in their submission)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 230 pages written, 230 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 598 dirty pages from their submits' captures, 69418 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17022 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: program picks: 4202001 kept (1725197 by the last picks' textures, a uniform buffer bound since), 849 new, 3997149 with other textures (of 8200000)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 461 dirty pages from their submits' captures, 69571 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16905 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.65, present 0.06, draw 0.85, descriptors 0.48, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.20, queue submit 0.20, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.2 copies, 7.08 MB written back
[hos host] vk: 18240 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.8 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.4 ms a frame (the longest submission 4.4 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 554 dirty pages from their submits' captures, 69473 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16986 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: replay reads of guest memory as submitted: 2520000 (1931310 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos ModuleSystemWorker5] vcores: 97846 takes, 17340 waits (mean 31 us, longest 2.4 ms), 8533 kicks, 8379 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: mirror syncs (600 submits): 592 dirty pages from their submits' captures, 69427 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17016 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vi: 18357 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.64, present 0.06, draw 0.86, descriptors 0.49, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.21, queue submit 0.20, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.2 copies, 7.08 MB written back
[hos host] vk: 18360 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.2 ms a frame (the longest submission 4.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 630 dirty pages from their submits' captures, 70520 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17302 in captures, 17 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: readback pages refreshed from guest memory: 1582923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: mirror syncs (600 submits): 670 dirty pages from their submits' captures, 70335 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17066 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.54, present 0.06, draw 0.81, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.6 copies, 7.08 MB written back
[hos host] vk: 18480 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.3 ms a frame (the longest submission 3.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871445 packets run in 10.0 s (busy 0.34 s, spun idle 0.93 s, slept 4979 times, 661 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15965 times, 40.59 ms in all, the longest 0.10 ms; replay_mu unlock 4919/19.44 ms (max 0.04), vkEndCommandBuffer 5523/13.03 ms (max 0.08), vkResetDescriptorPool 5523/8.13 ms (max 0.10)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #145000: event 0x100d6c8008 mode 0 value 83188 (now 83185) (lr 0x806661f8)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 690 dirty pages from their submits' captures, 69249 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17394 in captures, 11 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos ModuleSystemWorker3] nvn: 1200000 recordings made, 29761 live copies (6.2 MB), 1211 texture copies; 5 command buffers' segments (2.3 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10976 MB (peak 10996), private 18607 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 13608 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 13608 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 13608 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 13608 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 13608 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 15695 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 14088 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 13894 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 106 waited for it, 0.05 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.1 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.53, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.7 copies, 7.08 MB written back
[hos host] vk: 18600 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.7 ms a frame (the longest submission 4.1 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.66 ms a frame): its jobs 2.16 ms a frame (submits 1.54, presents 0.29, others 0.33), idle 14.51; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 125 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.17 ms after its hand-over (3.89 at most)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 694 dirty pages from their submits' captures, 70318 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17368 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos BaseProcExecutor2] vcores: 95836 takes, 17061 waits (mean 30 us, longest 2.0 ms), 8421 kicks, 8281 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: replay reads of guest memory as submitted: 2540000 (1949990 pages from the captures)
[hos Presentation Thread] vi: 18658 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 2, 15.5-17.8 298, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 650 dirty pages from their submits' captures, 69447 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17074 in captures, 10 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.57, present 0.07, draw 0.83, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.1 copies, 7.08 MB written back
[hos host] vk: 18720 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.1 ms a frame (the longest submission 4.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 558 dirty pages from their submits' captures, 69373 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17005 in captures, 18 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: program picks: 4270436 kept (1731047 by the last picks' textures, a uniform buffer bound since), 849 new, 4128714 with other textures (of 8400000)
[hos host] vk: readback pages refreshed from guest memory: 1594923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 658 dirty pages from their submits' captures, 70361 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17340 in captures, 12 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.56, present 0.06, draw 0.83, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.1 copies, 7.08 MB written back
[hos host] vk: 18840 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.4 ms a frame (the longest submission 4.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror syncs (600 submits): 608 dirty pages from their submits' captures, 70412 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17277 in captures, 11 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 663 dirty pages from their submits' captures, 69344 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17069 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos BaseProcExecutor1] vcores: 94973 takes, 16883 waits (mean 30 us, longest 1.7 ms), 8385 kicks, 8197 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 18958 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 299, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.58, present 0.06, draw 0.82, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.20, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.1 copies, 7.08 MB written back
[hos host] vk: 18960 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.5 ms a frame (the longest submission 5.2 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: replay reads of guest memory as submitted: 2560000 (1968666 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 595 dirty pages from their submits' captures, 70553 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16987 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos rmbl::VibrationThread] hid: 57344 vibration values, strongest 0.00 since the last count
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 624 dirty pages from their submits' captures, 69313 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17338 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.58, present 0.06, draw 0.83, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.9 copies, 7.08 MB written back
[hos host] vk: 19080 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.4 ms a frame (the longest submission 5.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: readback pages refreshed from guest memory: 1606923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: recorder: 1871452 packets run in 10.0 s (busy 0.32 s, spun idle 0.92 s, slept 5000 times, 661 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15881 times, 37.55 ms in all, the longest 0.09 ms; replay_mu unlock 4887/17.94 ms (max 0.09), vkEndCommandBuffer 5497/12.34 ms (max 0.09), vkResetDescriptorPool 5497/7.27 ms (max 0.08)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 621 dirty pages from their submits' captures, 70382 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17277 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: queues ordered by their events: 84000 submissions stopped at a wait, 83998 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 148612, not met 0; captures at a CPU event's wait 4116, 0 of them at a wait met on arrival
[hos sead::MainThread] nvn: CommandBufferSignalEvent #85000: event 0x100d6c8004 mode 0 value 84999 (lr 0x80665068)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 619 dirty pages from their submits' captures, 69307 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17022 in captures, 18 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10975 MB (peak 10996), private 18607 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 14208 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 14208 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 14208 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 14208 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 14208 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 16295 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 14688 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 14494 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 89 waited for it, 0.06 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.0 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.51, present 0.06, draw 0.81, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.1 copies, 7.08 MB written back
[hos host] vk: 19200 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.5 ms a frame (the longest submission 4.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.08 ms a frame (submits 1.55, presents 0.28, others 0.26), idle 14.58; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 96 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.09 ms after its hand-over (3.67 at most)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos BaseProcExecutor1] vcores: 94792 takes, 17100 waits (mean 30 us, longest 2.1 ms), 8503 kicks, 8315 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 19258 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 654 dirty pages from their submits' captures, 70355 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17322 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos ModuleSystemWorker2] vk: readbacks of GPU results: 0 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 2580000 (1987345 pages from the captures)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.51, present 0.06, draw 0.79, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.1 copies, 7.08 MB written back
[hos host] vk: 19320 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.0 ms a frame (the longest submission 5.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 704 dirty pages from their submits' captures, 70449 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17365 in captures, 11 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: program picks: 4338878 kept (1736895 by the last picks' textures, a uniform buffer bound since), 849 new, 4260272 with other textures (of 8600000)
[hos ModuleSystemWorker1] nvn: CommandBufferWaitEvent #150000: event 0x100d6c8004 mode 0 value 85689 (now 85683) (lr 0x80a47c2c)
[hos host] vk: mirror syncs (600 submits): 669 dirty pages from their submits' captures, 69253 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17082 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: readback pages refreshed from guest memory: 1618923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.46, present 0.06, draw 0.78, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.19, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.5 copies, 7.08 MB written back
[hos host] vk: 19440 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.3 ms a frame (the longest submission 5.2 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 675 dirty pages from their submits' captures, 70347 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17364 in captures, 14 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos ModuleSystemWorker3] nvn: 1250000 recordings made, 29753 live copies (6.2 MB), 1211 texture copies; 4 command buffers' segments (2.2 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 667 dirty pages from their submits' captures, 70348 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17316 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos BaseProcExecutor1] vcores: 92583 takes, 16797 waits (mean 30 us, longest 2.0 ms), 8260 kicks, 8074 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 19559 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.47, present 0.06, draw 0.82, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.1 copies, 7.08 MB written back
[hos host] vk: 19560 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.6 ms a frame (the longest submission 5.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 613 dirty pages from their submits' captures, 70536 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17269 in captures, 18 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 2600000 (2006022 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 716 dirty pages from their submits' captures, 70303 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17374 in captures, 11 only in the collection, 67 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.50, present 0.06, draw 0.79, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.0 copies, 7.08 MB written back
[hos host] vk: 19680 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.3 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.5 ms a frame (the longest submission 5.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871270 packets run in 10.0 s (busy 0.31 s, spun idle 0.89 s, slept 4993 times, 662 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15794 times, 34.66 ms in all, the longest 0.07 ms; replay_mu unlock 4849/16.35 ms (max 0.04), vkEndCommandBuffer 5473/11.58 ms (max 0.07), vkResetDescriptorPool 5472/6.73 ms (max 0.03)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 631 dirty pages from their submits' captures, 70440 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17010 in captures, 17 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: readback pages refreshed from guest memory: 1630923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: mirror syncs (600 submits): 688 dirty pages from their submits' captures, 70323 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 335 runs, 474.5 MB compared; 67 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17617 in captures, 12 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10976 MB (peak 10996), private 18608 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 14808 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 14808 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 14808 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 14808 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 14808 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 16895 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 15288 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 15094 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 240 pages written, 240 copied (0.9 MB)
[hos Presentation Thread] vk: presents after the CPU's signal (600): 65 waited for it, 0.04 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: status: 600 frames, the slowest 18.0 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.49, present 0.06, draw 0.83, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.2 copies, 7.08 MB written back
[hos host] vk: 19800 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.3 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.6 ms a frame (the longest submission 5.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 1.97 ms a frame (submits 1.52, presents 0.26, others 0.18), idle 14.70; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 69 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 1.98 ms after its hand-over (2.90 at most)
[hos rmbl::VibrationThread] vcores: 93627 takes, 17499 waits (mean 28 us, longest 1.9 ms), 8724 kicks, 8548 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 671 dirty pages from their submits' captures, 69266 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17081 in captures, 9 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vi: 19859 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 638 dirty pages from their submits' captures, 70521 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17076 in captures, 12 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.60, present 0.07, draw 0.88, descriptors 0.49, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.22, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.1 copies, 7.08 MB written back
[hos host] vk: 19920 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.6 ms a frame (the longest submission 5.4 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: program picks: 4407308 kept (1742739 by the last picks' textures, a uniform buffer bound since), 849 new, 4391842 with other textures (of 8800000)
[hos host] vk: replay reads of guest memory as submitted: 2620000 (2024700 pages from the captures)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 621 dirty pages from their submits' captures, 69310 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17290 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos Presentation Thread] nvn: QueueSubmitCommands #120000: queue 000010100D640020 (its #19999), 1 handles (lr 0x805282f4)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] nvn: EventSignal (CPU) #40000: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.51, present 0.06, draw 0.80, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 732.8 copies, 7.08 MB written back
[hos host] vk: 20040 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.7 ms a frame (the longest submission 6.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror syncs (600 submits): 551 dirty pages from their submits' captures, 69382 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17005 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: readback pages refreshed from guest memory: 1642923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 577 dirty pages from their submits' captures, 69346 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17010 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos BaseProcExecutor1] vcores: 93173 takes, 16742 waits (mean 29 us, longest 1.9 ms), 8256 kicks, 8084 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 20159 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 299, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.54, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 732.7 copies, 7.08 MB written back
[hos host] vk: 20160 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.7 ms a frame (the longest submission 6.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror syncs (600 submits): 587 dirty pages from their submits' captures, 70562 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17013 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #155000: event 0x100d6c8008 mode 0 value 88189 (now 88186) (lr 0x806661f8)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 667 dirty pages from their submits' captures, 69266 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17349 in captures, 14 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos rmbl::VibrationThread] hid: 61440 vibration values, strongest 0.00 since the last count
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.56, present 0.06, draw 0.87, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.22, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.0 copies, 7.08 MB written back
[hos host] vk: 20280 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 4.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: replay reads of guest memory as submitted: 2640000 (2043378 pages from the captures)
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871320 packets run in 10.0 s (busy 0.32 s, spun idle 0.91 s, slept 4985 times, 660 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15894 times, 37.19 ms in all, the longest 0.08 ms; replay_mu unlock 4888/17.85 ms (max 0.05), vkEndCommandBuffer 5503/12.11 ms (max 0.08), vkResetDescriptorPool 5503/7.22 ms (max 0.07)
[hos host] vk: mirror syncs (600 submits): 494 dirty pages from their submits' captures, 69449 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16902 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] nvn: 1300000 recordings made, 29745 live copies (6.2 MB), 1211 texture copies; 4 command buffers' segments (2.2 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 513 dirty pages from their submits' captures, 69416 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16939 in captures, 19 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10976 MB (peak 10996), private 18608 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 15408 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 15408 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 15408 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 15408 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 15408 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 17495 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 15888 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 15694 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 99 waited for it, 0.05 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 17.9 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.62, present 0.06, draw 0.83, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.20, queue submit 0.20, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 732.4 copies, 7.08 MB written back
[hos host] vk: 20400 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.7 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.3 ms a frame (the longest submission 4.4 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.09 ms a frame (submits 1.51, presents 0.28, others 0.30), idle 14.58; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 115 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.10 ms after its hand-over (3.30 at most)
[hos host] vk: readback pages refreshed from guest memory: 1654923 pages so far (0 held: may be written ahead in their submission)
[hos BaseProcExecutor1] vcores: 95189 takes, 17406 waits (mean 30 us, longest 1.8 ms), 8620 kicks, 8464 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: mirror syncs (600 submits): 538 dirty pages from their submits' captures, 69395 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16980 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vi: 20460 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 2, 15.5-17.8 298, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 567 dirty pages from their submits' captures, 69517 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16951 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.60, present 0.07, draw 0.82, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.20, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.3 copies, 7.08 MB written back
[hos host] vk: 20520 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.7 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.4 ms a frame (the longest submission 4.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: program picks: 4475694 kept (1748587 by the last picks' textures, a uniform buffer bound since), 849 new, 4523456 with other textures (of 9000000)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 630 dirty pages from their submits' captures, 70452 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17034 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: queues ordered by their events: 90000 submissions stopped at a wait, 89998 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 157264, not met 0; captures at a CPU event's wait 4348, 0 of them at a wait met on arrival
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: replay reads of guest memory as submitted: 2660000 (2062054 pages from the captures)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 681 dirty pages from their submits' captures, 69252 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17349 in captures, 10 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.53, present 0.06, draw 0.80, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.1 copies, 7.08 MB written back
[hos host] vk: 20640 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.6 ms a frame (the longest submission 4.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 240 pages written, 240 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (112 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 687 dirty pages from their submits' captures, 70323 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17355 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos ModuleSystemWorker1] vcores: 94107 takes, 16490 waits (mean 30 us, longest 1.8 ms), 8091 kicks, 7936 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: readback pages refreshed from guest memory: 1666923 pages so far (0 held: may be written ahead in their submission)
[hos Presentation Thread] vi: 20760 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.49, present 0.06, draw 0.79, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.2 copies, 7.08 MB written back
[hos host] vk: 20760 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.6 ms a frame (the longest submission 4.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 640 dirty pages from their submits' captures, 69365 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17056 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 236 pages written, 236 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos ModuleSystemWorker3] vk: readbacks of GPU results: 0 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos ModuleSystemWorker4] nvn: CommandBufferSignalEvent #90000: event 0x100d6c8000 mode 0 value 89999 (lr 0x80664f14)
[hos host] vk: mirror syncs (600 submits): 668 dirty pages from their submits' captures, 70413 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17318 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.52, present 0.06, draw 0.83, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.8 copies, 7.08 MB written back
[hos host] vk: 20880 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.6 ms a frame (the longest submission 4.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 637 dirty pages from their submits' captures, 70368 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17300 in captures, 16 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871308 packets run in 10.0 s (busy 0.32 s, spun idle 0.91 s, slept 4999 times, 664 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15892 times, 36.53 ms in all, the longest 0.07 ms; replay_mu unlock 4890/17.61 ms (max 0.04), vkEndCommandBuffer 5501/11.94 ms (max 0.07), vkResetDescriptorPool 5501/6.97 ms (max 0.03)
[hos host] vk: replay reads of guest memory as submitted: 2680000 (2080734 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 661 dirty pages from their submits' captures, 70340 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17339 in captures, 14 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10976 MB (peak 10996), private 18608 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 16008 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 16008 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 16008 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 16008 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 16008 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 18095 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 16488 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 16294 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 76 waited for it, 0.06 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 17.9 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.50, present 0.06, draw 0.84, descriptors 0.48, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.2 copies, 7.08 MB written back
[hos host] vk: 21000 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.3 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.7 ms a frame (the longest submission 4.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.03 ms a frame (submits 1.53, presents 0.27, others 0.23), idle 14.63; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 88 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.04 ms after its hand-over (2.80 at most)
[hos Presentation Thread] vi: real-time step on: ratio 1.002, game's frame rate 60
[hos sead::MainThread] nvn: CommandBufferWaitEvent #160000: event 0x100d6c8008 mode 0 value 90688 (now 90685) (lr 0x806661f8)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 641 dirty pages from their submits' captures, 70415 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17309 in captures, 12 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos ModuleSystemWorker4] vcores: 93827 takes, 16774 waits (mean 30 us, longest 2.0 ms), 8274 kicks, 8126 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 21061 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 299, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: readback pages refreshed from guest memory: 1678923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: mirror syncs (600 submits): 574 dirty pages from their submits' captures, 69599 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17002 in captures, 17 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: program picks: 4544108 kept (1754437 by the last picks' textures, a uniform buffer bound since), 849 new, 4655042 with other textures (of 9200000)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.57, present 0.07, draw 0.83, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.6 copies, 7.08 MB written back
[hos host] vk: 21120 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.7 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.8 ms a frame (the longest submission 5.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 230 pages written, 230 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (72 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 443 dirty pages from their submits' captures, 69588 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16608 in captures, 15 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 502 dirty pages from their submits' captures, 68454 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16961 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.58, present 0.06, draw 0.81, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.18, queue submit 0.20, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.4 copies, 7.08 MB written back
[hos host] vk: 21240 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.9 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.5 ms a frame (the longest submission 5.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos ModuleSystemWorker4] nvn: 1350000 recordings made, 29769 live copies (6.2 MB), 1211 texture copies; 2 command buffers' segments (2.1 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 577 dirty pages from their submits' captures, 69443 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16999 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: replay reads of guest memory as submitted: 2700000 (2099410 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos tera::FileResourceMgr] vcores: 94613 takes, 17472 waits (mean 31 us, longest 2.0 ms), 8568 kicks, 8419 yields, 0 starved grants, 0 escapes in 5 s
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (112 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 657 dirty pages from their submits' captures, 70526 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17329 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.52, present 0.06, draw 0.84, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.18, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.0 copies, 7.08 MB written back
[hos host] vk: 21360 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.5 ms a frame (the longest submission 4.2 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vi: 21361 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: readback pages refreshed from guest memory: 1690923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 686 dirty pages from their submits' captures, 69482 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17101 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 236 pages written, 236 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.51, present 0.06, draw 0.81, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.19, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 735.3 copies, 7.08 MB written back
[hos host] vk: 21480 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.0 ms a frame (the longest submission 5.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror syncs (600 submits): 688 dirty pages from their submits' captures, 70419 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17363 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos rmbl::VibrationThread] hid: 65536 vibration values, strongest 0.00 since the last count
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871395 packets run in 10.0 s (busy 0.32 s, spun idle 0.90 s, slept 4976 times, 662 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15938 times, 37.70 ms in all, the longest 0.08 ms; replay_mu unlock 4909/18.12 ms (max 0.06), vkEndCommandBuffer 5515/12.46 ms (max 0.08), vkResetDescriptorPool 5514/7.12 ms (max 0.02)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (112 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 686 dirty pages from their submits' captures, 70426 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17347 in captures, 8 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10976 MB (peak 10996), private 18608 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 16608 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 16608 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 16608 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 16608 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 16608 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 18695 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 17088 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 16894 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 102 waited for it, 0.05 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 17.8 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.51, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.6 copies, 7.08 MB written back
[hos host] vk: 21600 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.3 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 4.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: queues ordered by their events: 94270 submissions stopped at a wait, 94270 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 163426, not met 0; captures at a CPU event's wait 4512, 0 of them at a wait met on arrival
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.06 ms a frame (submits 1.49, presents 0.28, others 0.29), idle 14.61; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 113 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.07 ms after its hand-over (3.38 at most)
[hos host] vk: mirror syncs (600 submits): 729 dirty pages from their submits' captures, 70378 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17378 in captures, 10 only in the collection, 67 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 2720000 (2118089 pages from the captures)
[hos AudioFrameworkThread] vcores: 94289 takes, 16594 waits (mean 30 us, longest 2.3 ms), 8162 kicks, 8008 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos Presentation Thread] vi: 21662 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 627 dirty pages from their submits' captures, 70610 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17004 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: program picks: 4612544 kept (1760287 by the last picks' textures, a uniform buffer bound since), 849 new, 4786606 with other textures (of 9400000)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.52, present 0.07, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 735.0 copies, 7.08 MB written back
[hos host] vk: 21720 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.3 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.5 ms a frame (the longest submission 4.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: readback pages refreshed from guest memory: 1702923 pages so far (0 held: may be written ahead in their submission)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 657 dirty pages from their submits' captures, 69363 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17338 in captures, 12 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 675 dirty pages from their submits' captures, 70420 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17345 in captures, 11 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.55, present 0.06, draw 0.86, descriptors 0.49, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.0 copies, 7.08 MB written back
[hos host] vk: 21840 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 4.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos ModuleSystemWorker3] nvn: CommandBufferWaitEvent #165000: event 0x100d6c8004 mode 0 value 93189 (now 93183) (lr 0x80a47c2c)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 566 dirty pages from their submits' captures, 70532 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17239 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos sead::MainThread] vcores: 94485 takes, 17062 waits (mean 30 us, longest 1.7 ms), 8499 kicks, 8328 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 644 dirty pages from their submits' captures, 70469 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17061 in captures, 12 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: replay reads of guest memory as submitted: 2740000 (2136766 pages from the captures)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.49, present 0.06, draw 0.81, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.2 copies, 7.08 MB written back
[hos host] vk: 21960 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.4 ms a frame (the longest submission 4.2 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vi: 21963 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 299, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 609 dirty pages from their submits' captures, 69563 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17320 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: queues ordered by their events: 96000 submissions stopped at a wait, 95997 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 165934, not met 0; captures at a CPU event's wait 4567, 0 of them at a wait met on arrival
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: readback pages refreshed from guest memory: 1714923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 662 dirty pages from their submits' captures, 70438 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17319 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.46, present 0.06, draw 0.78, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.19, dispatch 0.04, memory sync 0.17, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.9 copies, 7.08 MB written back
[hos host] vk: 22080 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.8 ms a frame (the longest submission 4.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871245 packets run in 10.0 s (busy 0.31 s, spun idle 0.89 s, slept 4973 times, 663 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15794 times, 35.24 ms in all, the longest 0.10 ms; replay_mu unlock 4854/16.54 ms (max 0.04), vkEndCommandBuffer 5470/11.51 ms (max 0.08), vkResetDescriptorPool 5470/7.19 ms (max 0.10)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 738 dirty pages from their submits' captures, 70369 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17375 in captures, 12 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] nvn: 1400000 recordings made, 29779 live copies (5.9 MB), 1211 texture copies; 2 command buffers' segments (2.1 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10976 MB (peak 10996), private 18608 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 17208 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 17208 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 17208 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 17208 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 17208 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 19295 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 17688 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 17494 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 64 waited for it, 0.05 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.1 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.47, present 0.06, draw 0.80, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.6 copies, 7.08 MB written back
[hos host] vk: 22200 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.2 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.2 ms a frame (the longest submission 4.2 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 1.98 ms a frame (submits 1.53, presents 0.26, others 0.19), idle 14.69; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 72 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 1.99 ms after its hand-over (2.67 at most)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 712 dirty pages from their submits' captures, 70477 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17398 in captures, 11 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.02 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos ModuleSystemWorker1] vcores: 93171 takes, 16806 waits (mean 29 us, longest 1.8 ms), 8390 kicks, 8188 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 22264 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: mirror syncs (600 submits): 617 dirty pages from their submits' captures, 69545 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17031 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos ModuleSystemWorker2] vk: readbacks of GPU results: 0 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: replay reads of guest memory as submitted: 2760000 (2155442 pages from the captures)
[hos host] vk: program picks: 4680983 kept (1766135 by the last picks' textures, a uniform buffer bound since), 849 new, 4918167 with other textures (of 9600000)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.50, present 0.06, draw 0.81, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.8 copies, 7.08 MB written back
[hos host] vk: 22320 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.5 ms a frame (the longest submission 5.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 573 dirty pages from their submits' captures, 69452 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17008 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: readback pages refreshed from guest memory: 1726923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 645 dirty pages from their submits' captures, 70446 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17325 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.02 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.46, present 0.06, draw 0.79, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.19, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.5 copies, 7.08 MB written back
[hos host] vk: 22440 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.7 ms a frame (the longest submission 4.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] nvn: CommandBufferSignalEvent #95000: event 0x100d6c8008 mode 0 value 94999 (lr 0x80666598)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 691 dirty pages from their submits' captures, 69328 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17128 in captures, 12 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] nvn: EventSignal (CPU) #45000: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 704 dirty pages from their submits' captures, 70395 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17368 in captures, 10 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos ModuleSystemWorker3] vcores: 92870 takes, 16914 waits (mean 30 us, longest 1.8 ms), 8364 kicks, 8171 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.47, present 0.06, draw 0.81, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.6 copies, 7.08 MB written back
[hos host] vk: 22560 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.7 ms a frame (the longest submission 4.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vi: 22565 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 662 dirty pages from their submits' captures, 69500 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17085 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: replay reads of guest memory as submitted: 2780000 (2174122 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.02 over 745 ranges, 1580 MB), 236 pages written, 236 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 628 dirty pages from their submits' captures, 70473 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17345 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.45, present 0.06, draw 0.76, descriptors 0.43, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.19, dispatch 0.04, memory sync 0.17, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.9 copies, 7.08 MB written back
[hos host] vk: 22680 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.7 ms a frame (the longest submission 4.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] nvn: CommandBufferWaitEvent #170000: event 0x100d6c8008 mode 0 value 95689 (now 95686) (lr 0x806661f8)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871483 packets run in 10.0 s (busy 0.30 s, spun idle 0.88 s, slept 5007 times, 662 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15839 times, 34.53 ms in all, the longest 0.07 ms; replay_mu unlock 4849/16.33 ms (max 0.04), vkEndCommandBuffer 5495/11.29 ms (max 0.07), vkResetDescriptorPool 5495/6.92 ms (max 0.05)
[hos host] vk: readback pages refreshed from guest memory: 1738923 pages so far (0 held: may be written ahead in their submission)
[hos rmbl::VibrationThread] hid: 69632 vibration values, strongest 0.00 since the last count
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 604 dirty pages from their submits' captures, 69431 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17024 in captures, 14 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10976 MB (peak 10996), private 18608 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 17808 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 17808 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 17808 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 17808 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 17808 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 19895 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 18288 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 18094 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 87 waited for it, 0.05 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 17.9 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.48, present 0.06, draw 0.78, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.19, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.6 copies, 7.08 MB written back
[hos host] vk: 22800 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.7 ms a frame (the longest submission 4.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 1.95 ms a frame (submits 1.45, presents 0.25, others 0.25), idle 14.72; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 100 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 1.96 ms after its hand-over (3.38 at most)
[hos host] vk: mirror syncs (600 submits): 724 dirty pages from their submits' captures, 70389 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17389 in captures, 9 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos PlayReporter] vcores: 93543 takes, 16861 waits (mean 28 us, longest 1.9 ms), 8457 kicks, 8260 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 22866 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 548 dirty pages from their submits' captures, 69474 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16719 in captures, 15 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: program picks: 4749409 kept (1771977 by the last picks' textures, a uniform buffer bound since), 849 new, 5049741 with other textures (of 9800000)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.02 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.48, present 0.06, draw 0.79, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.20, dispatch 0.04, memory sync 0.17, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.9 copies, 7.08 MB written back
[hos host] vk: 22920 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.7 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.7 ms a frame (the longest submission 4.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror syncs (600 submits): 637 dirty pages from their submits' captures, 69530 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17336 in captures, 14 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 2800000 (2192798 pages from the captures)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 516 dirty pages from their submits' captures, 69587 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16976 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.49, present 0.06, draw 0.81, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.7 copies, 7.08 MB written back
[hos host] vk: 23040 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.7 ms a frame (the longest submission 5.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: readback pages refreshed from guest memory: 1750923 pages so far (0 held: may be written ahead in their submission)
[hos ModuleSystemWorker5] nvn: 1450000 recordings made, 29777 live copies (6.2 MB), 1211 texture copies; 5 command buffers' segments (2.3 MB)
[hos host] vk: mirror syncs (600 submits): 618 dirty pages from their submits' captures, 70471 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17306 in captures, 14 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 539 dirty pages from their submits' captures, 69473 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16961 in captures, 18 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos ModuleSystemWorker4] vcores: 93642 takes, 16434 waits (mean 30 us, longest 2.1 ms), 8145 kicks, 7949 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.49, present 0.06, draw 0.82, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.5 copies, 7.08 MB written back
[hos host] vk: 23160 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.7 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.7 ms a frame (the longest submission 4.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vi: 23166 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 612 dirty pages from their submits' captures, 69548 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17036 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.02 over 745 ranges, 1580 MB), 236 pages written, 236 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 705 dirty pages from their submits' captures, 70403 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17371 in captures, 10 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: replay reads of guest memory as submitted: 2820000 (2211478 pages from the captures)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.47, present 0.06, draw 0.78, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.19, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 735.2 copies, 7.08 MB written back
[hos host] vk: 23280 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.7 ms a frame (the longest submission 4.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.02 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871486 packets run in 10.0 s (busy 0.31 s, spun idle 0.89 s, slept 5018 times, 663 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15903 times, 34.70 ms in all, the longest 0.09 ms; replay_mu unlock 4883/16.52 ms (max 0.08), vkEndCommandBuffer 5510/11.38 ms (max 0.09), vkResetDescriptorPool 5510/6.81 ms (max 0.09)
[hos host] vk: mirror syncs (600 submits): 577 dirty pages from their submits' captures, 69437 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17012 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] nvn: QueueSubmitCommands #140000: queue 0000101004133020 (its #23339), 1 handles (lr 0x80590358)
[hos host] vk: readback pages refreshed from guest memory: 1762923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 593 dirty pages from their submits' captures, 69422 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17030 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: memory: working set 10976 MB (peak 10996), private 18608 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 18408 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 18408 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 18408 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 18408 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 18408 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 20495 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 18888 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 18694 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 99 waited for it, 0.07 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 17.8 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.47, present 0.06, draw 0.79, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.1 copies, 7.08 MB written back
[hos host] vk: 23400 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.8 ms a frame (the longest submission 4.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 1.96 ms a frame (submits 1.42, presents 0.26, others 0.28), idle 14.71; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 116 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 1.97 ms after its hand-over (2.88 at most)
[hos ModuleSystemWorker3] vcores: 92412 takes, 16944 waits (mean 29 us, longest 1.8 ms), 8504 kicks, 8302 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: mirror syncs (600 submits): 667 dirty pages from their submits' captures, 70420 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17336 in captures, 14 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: program picks: 4817795 kept (1777827 by the last picks' textures, a uniform buffer bound since), 849 new, 5181355 with other textures (of 10000000)
[hos host] vk: queues ordered by their events: 102000 submissions stopped at a wait, 101996 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 174575, not met 0; captures at a CPU event's wait 4806, 0 of them at a wait met on arrival
[hos Presentation Thread] vi: 23466 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.02 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 613 dirty pages from their submits' captures, 69537 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17051 in captures, 17 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.44, present 0.06, draw 0.79, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.20, dispatch 0.04, memory sync 0.17, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 735.1 copies, 7.08 MB written back
[hos host] vk: 23520 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.7 ms a frame (the longest submission 4.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] nvn: CommandBufferWaitEvent #175000: event 0x100d6c8008 mode 0 value 98188 (now 98185) (lr 0x806661f8)
[hos host] vk: mirror syncs (600 submits): 571 dirty pages from their submits' captures, 70539 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16989 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: replay reads of guest memory as submitted: 2840000 (2230154 pages from the captures)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.56, present 0.06, draw 0.83, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.18, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.8 copies, 7.08 MB written back
[hos host] vk: 23640 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.5 ms a frame (the longest submission 5.4 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 586 dirty pages from their submits' captures, 69442 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17003 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (112 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: readback pages refreshed from guest memory: 1774923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 613 dirty pages from their submits' captures, 69416 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17272 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos BaseProcExecutor1] vcores: 94607 takes, 17544 waits (mean 29 us, longest 1.7 ms), 8805 kicks, 8618 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.52, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.18, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.1 copies, 7.08 MB written back
[hos host] vk: 23760 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.4 ms a frame (the longest submission 4.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vi: 23767 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos sead::MainThread] vk: readbacks of GPU results: 0 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 615 dirty pages from their submits' captures, 69560 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17058 in captures, 16 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.02 over 745 ranges, 1580 MB), 236 pages written, 236 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 511 dirty pages from their submits' captures, 69577 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16918 in captures, 17 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.59, present 0.06, draw 0.87, descriptors 0.49, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.22, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.5 copies, 7.08 MB written back
[hos host] vk: 23880 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.7 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.8 ms a frame (the longest submission 4.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (112 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871547 packets run in 10.0 s (busy 0.32 s, spun idle 0.90 s, slept 4961 times, 662 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15933 times, 37.64 ms in all, the longest 0.12 ms; replay_mu unlock 4893/17.95 ms (max 0.09), vkEndCommandBuffer 5520/12.60 ms (max 0.12), vkResetDescriptorPool 5520/7.10 ms (max 0.07)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 589 dirty pages from their submits' captures, 69438 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17008 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: replay reads of guest memory as submitted: 2860000 (2248832 pages from the captures)
[hos ModuleSystemWorker4] nvn: 1500000 recordings made, 29769 live copies (6.2 MB), 1211 texture copies; 5 command buffers' segments (2.3 MB)
[hos rmbl::VibrationThread] hid: 73728 vibration values, strongest 0.00 since the last count
[hos host] vk: mirror syncs (600 submits): 473 dirty pages from their submits' captures, 69544 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16916 in captures, 17 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 5 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10976 MB (peak 10996), private 18608 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 19008 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 19008 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 19008 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 19008 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 19008 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 21095 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 19488 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 19294 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 106 waited for it, 0.06 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.0 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.63, present 0.06, draw 0.85, descriptors 0.47, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.07, commands 0.21, dispatch 0.05, memory sync 0.19, queue submit 0.20, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 732.9 copies, 7.08 MB written back
[hos host] vk: 24000 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.8 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.2 ms a frame (the longest submission 5.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.07 ms a frame (submits 1.47, presents 0.28, others 0.32), idle 14.60; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 126 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.08 ms after its hand-over (3.44 at most)
[hos Presentation Thread] vi: real-time step on: ratio 1.004, game's frame rate 60
[hos host] vk: readback pages refreshed from guest memory: 1786923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 319 dirty pages from their submits' captures, 68633 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16533 in captures, 14 only in the collection, 63 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: program picks: 4886214 kept (1783677 by the last picks' textures, a uniform buffer bound since), 849 new, 5312936 with other textures (of 10200000)
[hos BaseProcExecutor1] vcores: 96362 takes, 17477 waits (mean 31 us, longest 2.5 ms), 8622 kicks, 8449 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 24067 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 225 pages written, 225 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 499 dirty pages from their submits' captures, 68589 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16636 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.65, present 0.07, draw 0.85, descriptors 0.48, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.05, memory sync 0.19, queue submit 0.21, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.6 copies, 7.08 MB written back
[hos host] vk: 24120 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 645.0 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 3.9 ms a frame (the longest submission 4.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #100000: event 0x100d6c8004 mode 0 value 99999 (lr 0x80665068)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 230 pages written, 230 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 431 dirty pages from their submits' captures, 68497 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16621 in captures, 20 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 619 dirty pages from their submits' captures, 69391 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17046 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.58, present 0.06, draw 0.84, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.5 copies, 7.08 MB written back
[hos host] vk: 24240 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.9 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 3.9 ms a frame (the longest submission 4.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 2880000 (2267510 pages from the captures)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 588 dirty pages from their submits' captures, 70508 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17238 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos BaseProcExecutor2] vcores: 95695 takes, 17435 waits (mean 29 us, longest 2.1 ms), 8698 kicks, 8522 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: readback pages refreshed from guest memory: 1798923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.57, present 0.06, draw 0.87, descriptors 0.49, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.22, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.4 copies, 7.08 MB written back
[hos host] vk: 24360 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.2 ms a frame (the longest submission 4.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos ModuleSystemWorker4] nvn: CommandBufferWaitEvent #180000: event 0x100d6c8004 mode 0 value 100689 (now 100683) (lr 0x80a47c2c)
[hos host] vk: mirror syncs (600 submits): 605 dirty pages from their submits' captures, 69346 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17020 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vi: 24368 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 299, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 621 dirty pages from their submits' captures, 70532 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17299 in captures, 14 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.58, present 0.06, draw 0.86, descriptors 0.48, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.22, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.0 copies, 7.08 MB written back
[hos host] vk: 24480 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.3 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.4 ms a frame (the longest submission 4.4 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 674 dirty pages from their submits' captures, 70340 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17355 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871455 packets run in 10.0 s (busy 0.33 s, spun idle 0.92 s, slept 4973 times, 663 of them under 200 us), 0 calls made directly (no room); the replay waited for it 16013 times, 40.22 ms in all, the longest 0.11 ms; replay_mu unlock 4933/19.41 ms (max 0.11), vkEndCommandBuffer 5540/13.05 ms (max 0.11), vkResetDescriptorPool 5540/7.75 ms (max 0.07)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 653 dirty pages from their submits' captures, 69287 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17075 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10976 MB (peak 10996), private 18608 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 19608 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 19608 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 19608 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 19608 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 19608 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 21695 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 20088 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 19894 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 114 waited for it, 0.06 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: replay reads of guest memory as submitted: 2900000 (2286186 pages from the captures)
[hos host] vk: status: 600 frames, the slowest 17.9 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.52, present 0.06, draw 0.81, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.0 copies, 7.08 MB written back
[hos host] vk: 24600 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.7 ms a frame (the longest submission 5.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.11 ms a frame (submits 1.50, presents 0.28, others 0.33), idle 14.55; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 127 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.12 ms after its hand-over (3.17 at most)
[hos host] vk: program picks: 4954652 kept (1789527 by the last picks' textures, a uniform buffer bound since), 849 new, 5444498 with other textures (of 10400000)
[hos host] vk: mirror syncs (600 submits): 647 dirty pages from their submits' captures, 70446 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17320 in captures, 14 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos BaseProcExecutor1] vcores: 95784 takes, 17201 waits (mean 29 us, longest 2.0 ms), 8568 kicks, 8426 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos Presentation Thread] vi: 24669 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: readback pages refreshed from guest memory: 1810923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 606 dirty pages from their submits' captures, 70538 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17286 in captures, 16 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.54, present 0.07, draw 0.85, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.22, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.0 copies, 7.08 MB written back
[hos host] vk: 24720 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.3 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.7 ms a frame (the longest submission 4.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 648 dirty pages from their submits' captures, 70366 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17083 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 598 dirty pages from their submits' captures, 69332 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17270 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] nvn: 1550000 recordings made, 29761 live copies (6.2 MB), 1211 texture copies; 4 command buffers' segments (2.2 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.56, present 0.06, draw 0.86, descriptors 0.49, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 732.8 copies, 7.08 MB written back
[hos host] vk: 24840 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 4.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (102 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: queues ordered by their events: 108000 submissions stopped at a wait, 107999 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 183136, not met 0; captures at a CPU event's wait 5101, 0 of them at a wait met on arrival
[hos host] vk: mirror syncs (600 submits): 481 dirty pages from their submits' captures, 69445 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16908 in captures, 16 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: replay reads of guest memory as submitted: 2920000 (2304866 pages from the captures)
[hos BaseProcExecutor1] vcores: 94749 takes, 16961 waits (mean 31 us, longest 2.2 ms), 8376 kicks, 8217 yields, 0 starved grants, 0 escapes in 5 s
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 430 dirty pages from their submits' captures, 68416 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16620 in captures, 18 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.64, present 0.06, draw 0.88, descriptors 0.49, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.22, dispatch 0.05, memory sync 0.20, queue submit 0.20, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 731.8 copies, 7.08 MB written back
[hos host] vk: 24960 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.9 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 4.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vi: 24970 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: readback pages refreshed from guest memory: 1822923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] nvn: EventSignal (CPU) #50000: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos host] vk: mirror syncs (600 submits): 599 dirty pages from their submits' captures, 70556 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17291 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.58, present 0.06, draw 0.85, descriptors 0.48, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.5 copies, 7.08 MB written back
[hos host] vk: 25080 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.5 ms a frame (the longest submission 4.4 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 496 dirty pages from their submits' captures, 69429 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16932 in captures, 18 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871279 packets run in 10.0 s (busy 0.33 s, spun idle 0.92 s, slept 4999 times, 663 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15906 times, 37.79 ms in all, the longest 0.08 ms; replay_mu unlock 4892/18.37 ms (max 0.06), vkEndCommandBuffer 5507/12.32 ms (max 0.08), vkResetDescriptorPool 5507/7.11 ms (max 0.03)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 615 dirty pages from their submits' captures, 69318 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17029 in captures, 10 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos rmbl::VibrationThread] hid: 77824 vibration values, strongest 0.00 since the last count
[hos sead::MainThread] nvn: CommandBufferWaitEvent #185000: event 0x100d6c8008 mode 0 value 103189 (now 103186) (lr 0x806661f8)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10976 MB (peak 10996), private 18608 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 20208 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 20208 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 20208 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 20208 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 20208 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 22295 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 20688 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 20494 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 92 waited for it, 0.07 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.0 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.56, present 0.06, draw 0.83, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.1 copies, 7.08 MB written back
[hos host] vk: 25200 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.4 ms a frame (the longest submission 4.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: queues ordered by their events: 109323 submissions stopped at a wait, 109323 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 185026, not met 0; captures at a CPU event's wait 5165, 0 of them at a wait met on arrival
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.10 ms a frame (submits 1.53, presents 0.28, others 0.30), idle 14.56; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 112 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.11 ms after its hand-over (3.16 at most)
[hos host] vk: program picks: 5023091 kept (1795375 by the last picks' textures, a uniform buffer bound since), 849 new, 5576059 with other textures (of 10600000)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 628 dirty pages from their submits' captures, 70388 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17314 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos BaseProcExecutor1] vcores: 96530 takes, 17403 waits (mean 29 us, longest 2.0 ms), 8721 kicks, 8543 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: replay reads of guest memory as submitted: 2940000 (2323542 pages from the captures)
[hos Presentation Thread] vi: 25270 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: mirror syncs (600 submits): 572 dirty pages from their submits' captures, 69360 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17002 in captures, 16 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] vk: readbacks of GPU results: 0 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.55, present 0.06, draw 0.85, descriptors 0.48, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.9 copies, 7.08 MB written back
[hos host] vk: 25320 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.7 ms a frame (the longest submission 4.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: readback pages refreshed from guest memory: 1834923 pages so far (0 held: may be written ahead in their submission)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 637 dirty pages from their submits' captures, 70517 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17045 in captures, 17 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 479 dirty pages from their submits' captures, 68394 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16931 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.61, present 0.06, draw 0.85, descriptors 0.48, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 732.5 copies, 7.08 MB written back
[hos host] vk: 25440 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.8 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 4.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 650 dirty pages from their submits' captures, 70441 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17329 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 641 dirty pages from their submits' captures, 69289 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17055 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos ModuleSystemWorker1] vcores: 95352 takes, 17307 waits (mean 30 us, longest 1.8 ms), 8625 kicks, 8470 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.53, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.2 copies, 7.08 MB written back
[hos host] vk: 25560 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.4 ms a frame (the longest submission 4.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vi: 25571 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos host] vk: replay reads of guest memory as submitted: 2960000 (2342221 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 680 dirty pages from their submits' captures, 70479 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17348 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (112 MB), 5 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: readback pages refreshed from guest memory: 1846923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: mirror syncs (600 submits): 587 dirty pages from their submits' captures, 69332 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16998 in captures, 16 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.51, present 0.06, draw 0.78, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.19, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.9 copies, 7.08 MB written back
[hos host] vk: 25680 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 4.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871466 packets run in 10.0 s (busy 0.32 s, spun idle 0.91 s, slept 4990 times, 661 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15922 times, 37.33 ms in all, the longest 0.10 ms; replay_mu unlock 4901/18.12 ms (max 0.08), vkEndCommandBuffer 5511/12.01 ms (max 0.08), vkResetDescriptorPool 5510/7.19 ms (max 0.10)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos ModuleSystemWorker4] nvn: 1600000 recordings made, 29753 live copies (6.2 MB), 1211 texture copies; 7 command buffers' segments (2.4 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 580 dirty pages from their submits' captures, 69354 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17033 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: program picks: 5091510 kept (1801217 by the last picks' textures, a uniform buffer bound since), 849 new, 5707640 with other textures (of 10800000)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10975 MB (peak 10996), private 18606 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 20808 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 20808 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 20808 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 20808 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 20808 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 22895 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 21288 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 21094 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #105000: event 0x100d6c8000 mode 0 value 104999 (lr 0x80664f14)
[hos Presentation Thread] vk: presents after the CPU's signal (600): 106 waited for it, 0.05 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 17.8 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.55, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 732.5 copies, 7.08 MB written back
[hos host] vk: 25800 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.8 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.1 ms a frame (the longest submission 5.4 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.07 ms a frame (submits 1.49, presents 0.28, others 0.30), idle 14.60; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 118 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.08 ms after its hand-over (3.22 at most)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 457 dirty pages from their submits' captures, 69466 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16911 in captures, 17 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 230 pages written, 230 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos tera::FileResourceMgr] vcores: 95073 takes, 16961 waits (mean 31 us, longest 2.0 ms), 8479 kicks, 8321 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 703 dirty pages from their submits' captures, 70309 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17348 in captures, 10 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vi: 25872 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (112 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.57, present 0.07, draw 0.85, descriptors 0.48, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.9 copies, 7.08 MB written back
[hos host] vk: 25920 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.2 ms a frame (the longest submission 4.1 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: replay reads of guest memory as submitted: 2980000 (2360898 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 590 dirty pages from their submits' captures, 69478 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16974 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: readback pages refreshed from guest memory: 1858923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 634 dirty pages from their submits' captures, 70372 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17051 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #190000: event 0x100d6c8008 mode 0 value 105688 (now 105685) (lr 0x806661f8)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.54, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.4 copies, 7.08 MB written back
[hos host] vk: 26040 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.8 ms a frame (the longest submission 4.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror syncs (600 submits): 695 dirty pages from their submits' captures, 69246 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17363 in captures, 12 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 639 dirty pages from their submits' captures, 70372 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17332 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] vcores: 95523 takes, 17090 waits (mean 29 us, longest 1.9 ms), 8548 kicks, 8362 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.52, present 0.06, draw 0.81, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.2 copies, 7.08 MB written back
[hos host] vk: 26160 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.3 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.1 ms a frame (the longest submission 4.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vi: 26173 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos host] vk: mirror syncs (600 submits): 635 dirty pages from their submits' captures, 70519 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17294 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 3000000 (2379576 pages from the captures)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 574 dirty pages from their submits' captures, 69441 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16979 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.55, present 0.06, draw 0.82, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.6 copies, 7.08 MB written back
[hos host] vk: 26280 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.2 ms a frame (the longest submission 4.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: readback pages refreshed from guest memory: 1870923 pages so far (0 held: may be written ahead in their submission)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1874474 packets run in 10.0 s (busy 0.32 s, spun idle 0.91 s, slept 4995 times, 663 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15906 times, 37.39 ms in all, the longest 0.09 ms; replay_mu unlock 4892/17.67 ms (max 0.05), vkEndCommandBuffer 5507/11.92 ms (max 0.09), vkResetDescriptorPool 5507/7.81 ms (max 0.09)
[hos host] vk: queues ordered by their events: 114000 submissions stopped at a wait, 113997 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 191746, not met 0; captures at a CPU event's wait 5359, 0 of them at a wait met on arrival
[hos host] vk: mirror syncs (600 submits): 675 dirty pages from their submits' captures, 70338 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17358 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: program picks: 5159896 kept (1807067 by the last picks' textures, a uniform buffer bound since), 849 new, 5839254 with other textures (of 11000000)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 639 dirty pages from their submits' captures, 69295 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17066 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10975 MB (peak 10996), private 18606 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 21408 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 21408 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 21408 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 21408 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 21408 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 23495 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 21888 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 21694 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 76 waited for it, 0.05 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.1 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.55, present 0.06, draw 0.84, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.18, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.1 copies, 7.08 MB written back
[hos host] vk: 26400 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.2 ms a frame (the longest submission 4.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.06 ms a frame (submits 1.55, presents 0.27, others 0.24), idle 14.61; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 88 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.06 ms after its hand-over (3.25 at most)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos rmbl::VibrationThread] hid: 81920 vibration values, strongest 0.00 since the last count
[hos ModuleSystemWorker1] vcores: 95171 takes, 17056 waits (mean 30 us, longest 2.0 ms), 8473 kicks, 8324 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 646 dirty pages from their submits' captures, 70362 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17312 in captures, 14 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vi: 26473 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.58, present 0.07, draw 0.86, descriptors 0.48, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.8 copies, 7.08 MB written back
[hos host] vk: 26520 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.3 ms a frame (the longest submission 5.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 531 dirty pages from their submits' captures, 69529 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16938 in captures, 20 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: replay reads of guest memory as submitted: 3020000 (2398254 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 538 dirty pages from their submits' captures, 69392 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16967 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos ModuleSystemWorker1] nvn: 1650000 recordings made, 29752 live copies (6.2 MB), 1211 texture copies; 4 command buffers' segments (2.2 MB)
[hos host] vk: readback pages refreshed from guest memory: 1882923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.53, present 0.06, draw 0.88, descriptors 0.50, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 732.7 copies, 7.08 MB written back
[hos host] vk: 26640 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.0 ms a frame (the longest submission 5.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 648 dirty pages from their submits' captures, 70358 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17320 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] nvn: QueueSubmitCommands #160000: queue 000010100D6BF020 (its #26666), 1 handles (lr 0x80666be0)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 629 dirty pages from their submits' captures, 69304 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17070 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos NavMeshCAStepDepWorker1] vcores: 94721 takes, 17187 waits (mean 30 us, longest 2.0 ms), 8525 kicks, 8375 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.49, present 0.06, draw 0.79, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.19, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.1 copies, 7.08 MB written back
[hos host] vk: 26760 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.3 ms a frame (the longest submission 5.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vi: 26773 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos ModuleSystemWorker2] vk: readbacks of GPU results: 0 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 598 dirty pages from their submits' captures, 70398 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17284 in captures, 17 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 715 dirty pages from their submits' captures, 70457 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17398 in captures, 9 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos ModuleSystemWorker3] nvn: CommandBufferWaitEvent #195000: event 0x100d6c8004 mode 0 value 108189 (now 108183) (lr 0x80a47c2c)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.51, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.3 copies, 7.08 MB written back
[hos host] vk: 26880 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.4 ms a frame (the longest submission 5.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 240 pages written, 240 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (112 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871301 packets run in 10.0 s (busy 0.32 s, spun idle 0.90 s, slept 4991 times, 661 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15854 times, 36.55 ms in all, the longest 0.18 ms; replay_mu unlock 4876/17.24 ms (max 0.05), vkEndCommandBuffer 5489/11.99 ms (max 0.18), vkResetDescriptorPool 5489/7.32 ms (max 0.07)
[hos host] vk: replay reads of guest memory as submitted: 3040000 (2416930 pages from the captures)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 681 dirty pages from their submits' captures, 70330 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17350 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: readback pages refreshed from guest memory: 1894923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: program picks: 5228321 kept (1812917 by the last picks' textures, a uniform buffer bound since), 849 new, 5970829 with other textures (of 11200000)
[hos host] vk: mirror syncs (600 submits): 599 dirty pages from their submits' captures, 69374 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17042 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10975 MB (peak 10996), private 18606 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 22008 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 22008 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 22008 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 22008 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 22008 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 24095 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 22488 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 22294 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 84 waited for it, 0.05 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 17.9 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.54, present 0.06, draw 0.85, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.22, dispatch 0.04, memory sync 0.18, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.4 copies, 7.08 MB written back
[hos host] vk: 27000 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.5 ms a frame (the longest submission 5.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.03 ms a frame (submits 1.52, presents 0.27, others 0.24), idle 14.63; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 92 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.04 ms after its hand-over (2.99 at most)
[hos Presentation Thread] vi: real-time step on: ratio 1.001, game's frame rate 60
[hos ModuleSystemWorker4] vcores: 94524 takes, 17066 waits (mean 30 us, longest 2.0 ms), 8468 kicks, 8308 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 515 dirty pages from their submits' captures, 69509 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16971 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vi: 27074 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 515 dirty pages from their submits' captures, 69721 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16980 in captures, 18 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.57, present 0.06, draw 0.84, descriptors 0.47, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.2 copies, 7.08 MB written back
[hos host] vk: 27120 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.8 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 4.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 589 dirty pages from their submits' captures, 69429 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16968 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.64, present 0.06, draw 0.88, descriptors 0.49, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.22, dispatch 0.05, memory sync 0.20, queue submit 0.20, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.9 copies, 7.08 MB written back
[hos host] vk: 27240 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.0 ms a frame (the longest submission 5.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror syncs (600 submits): 640 dirty pages from their submits' captures, 70455 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17325 in captures, 14 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 3060000 (2435610 pages from the captures)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (112 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: readback pages refreshed from guest memory: 1906923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 584 dirty pages from their submits' captures, 69446 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16998 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos ModuleSystemWorker1] vcores: 95185 takes, 17487 waits (mean 30 us, longest 2.0 ms), 8642 kicks, 8463 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.57, present 0.06, draw 0.86, descriptors 0.48, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.22, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.9 copies, 7.08 MB written back
[hos host] vk: 27360 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.8 ms a frame (the longest submission 5.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror syncs (600 submits): 614 dirty pages from their submits' captures, 70477 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17029 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vi: 27375 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 598 dirty pages from their submits' captures, 69568 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17270 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #110000: event 0x100d6c8008 mode 0 value 109999 (lr 0x80666598)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.54, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.8 copies, 7.08 MB written back
[hos host] vk: 27480 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.7 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.9 ms a frame (the longest submission 5.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] nvn: EventSignal (CPU) #55000: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos host] vk: mirror syncs (600 submits): 652 dirty pages from their submits' captures, 69371 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17083 in captures, 12 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871457 packets run in 10.0 s (busy 0.32 s, spun idle 0.92 s, slept 5000 times, 660 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15941 times, 38.18 ms in all, the longest 0.07 ms; replay_mu unlock 4902/18.37 ms (max 0.07), vkEndCommandBuffer 5520/12.52 ms (max 0.07), vkResetDescriptorPool 5519/7.29 ms (max 0.07)
[hos ModuleSystemWorker2] nvn: 1700000 recordings made, 29766 live copies (6.2 MB), 1211 texture copies; 2 command buffers' segments (2.1 MB)
[hos host] vk: program picks: 5296759 kept (1818767 by the last picks' textures, a uniform buffer bound since), 849 new, 6102391 with other textures (of 11400000)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 599 dirty pages from their submits' captures, 69426 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17017 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 3080000 (2454286 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10976 MB (peak 10996), private 18607 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 22608 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 22608 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 22608 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 22608 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 22608 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 24695 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 23088 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 22894 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 110 waited for it, 0.06 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.5 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.52, present 0.06, draw 0.80, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.4 copies, 7.08 MB written back
[hos host] vk: 27600 presents, 59.9 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.7 ms a frame (the longest submission 4.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.08 ms a frame (submits 1.49, presents 0.27, others 0.32), idle 14.59; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 122 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.09 ms after its hand-over (3.58 at most)
[hos host] vk: readback pages refreshed from guest memory: 1918923 pages so far (0 held: may be written ahead in their submission)
[hos rmbl::VibrationThread] hid: 86016 vibration values, strongest 0.00 since the last count
[hos host] vk: mirror syncs (600 submits): 654 dirty pages from their submits' captures, 70458 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17085 in captures, 11 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos ModuleSystemWorker1] vcores: 94342 takes, 17194 waits (mean 29 us, longest 2.1 ms), 8576 kicks, 8381 yields, 0 starved grants, 0 escapes in 5 s
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (112 MB), 5 spare buffers, 0 texture pages copied (0 MB)
[hos Presentation Thread] vi: 27676 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 298, 17.8-22 2, 22-30 0, 30-40 0, over 40 0
[hos sead::MainThread] nvn: CommandBufferWaitEvent #200000: event 0x100d6c8008 mode 0 value 110689 (now 110686) (lr 0x806661f8)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 610 dirty pages from their submits' captures, 69561 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17295 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.52, present 0.07, draw 0.82, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 735.3 copies, 7.08 MB written back
[hos host] vk: 27720 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.2 ms a frame (the longest submission 4.2 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: queues ordered by their events: 120000 submissions stopped at a wait, 119999 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 200374, not met 0; captures at a CPU event's wait 5609, 0 of them at a wait met on arrival
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 236 pages written, 236 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 738 dirty pages from their submits' captures, 70377 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17375 in captures, 10 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 554 dirty pages from their submits' captures, 68400 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16742 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.52, present 0.06, draw 0.84, descriptors 0.48, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.18, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.1 copies, 7.08 MB written back
[hos host] vk: 27840 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.7 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.5 ms a frame (the longest submission 6.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 515 dirty pages from their submits' captures, 69581 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16942 in captures, 18 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: replay reads of guest memory as submitted: 3100000 (2472965 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 1930923 pages so far (0 held: may be written ahead in their submission)
[hos ModuleSystemWorker1] vcores: 93833 takes, 16978 waits (mean 30 us, longest 2.3 ms), 8491 kicks, 8293 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.47, present 0.06, draw 0.77, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.19, dispatch 0.04, memory sync 0.17, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.1 copies, 7.08 MB written back
[hos host] vk: 27960 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.5 ms a frame (the longest submission 5.1 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 686 dirty pages from their submits' captures, 70415 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17369 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vi: 27977 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 594 dirty pages from their submits' captures, 69566 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17025 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 236 pages written, 236 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.49, present 0.06, draw 0.80, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 735.1 copies, 7.08 MB written back
[hos host] vk: 28080 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.1 ms a frame (the longest submission 4.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 687 dirty pages from their submits' captures, 70418 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17320 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871539 packets run in 10.0 s (busy 0.31 s, spun idle 0.90 s, slept 5023 times, 662 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15903 times, 35.92 ms in all, the longest 0.06 ms; replay_mu unlock 4883/17.06 ms (max 0.05), vkEndCommandBuffer 5510/11.84 ms (max 0.06), vkResetDescriptorPool 5510/7.02 ms (max 0.02)
[hos host] vk: program picks: 5365199 kept (1824615 by the last picks' textures, a uniform buffer bound since), 849 new, 6233951 with other textures (of 11600000)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 671 dirty pages from their submits' captures, 70433 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17361 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10976 MB (peak 10996), private 18607 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 23208 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 23208 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 23208 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 23208 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 23208 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 25295 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 23688 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 23494 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 95 waited for it, 0.05 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.0 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.49, present 0.06, draw 0.79, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.19, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.4 copies, 7.08 MB written back
[hos host] vk: 28200 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.3 ms a frame (the longest submission 5.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 1.98 ms a frame (submits 1.47, presents 0.26, others 0.26), idle 14.68; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 103 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 1.99 ms after its hand-over (2.99 at most)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 715 dirty pages from their submits' captures, 69315 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17123 in captures, 9 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: replay reads of guest memory as submitted: 3120000 (
2491642pages from the captures)[hos ModuleSystemWorker1] vcores: 95049 takes, 17146 waits (mean 31 us, longest 2.0 ms), 8556 kicks, 8375 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: readback pages refreshed from guest memory: 1942923 pages so far (0 held: may be written ahead in their submission)
[hos Presentation Thread] vi: 28278 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos ModuleSystemWorker1] vk: readbacks of GPU results: 0 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: mirror syncs (600 submits): 576 dirty pages from their submits' captures, 70521 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17304 in captures, 14 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.49, present 0.06, draw 0.79, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.19, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 735.3 copies, 7.08 MB written back
[hos host] vk: 28320 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.4 ms a frame (the longest submission 5.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 236 pages written, 236 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 602 dirty pages from their submits' captures, 69559 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17042 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] nvn: 1750000 recordings made, 29779 live copies (5.9 MB), 1211 texture copies; 2 command buffers' segments (2.1 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 558 dirty pages from their submits' captures, 69453 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16995 in captures, 17 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.54, present 0.06, draw 0.79, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.19, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.7 copies, 7.08 MB written back
[hos host] vk: 28440 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.4 ms a frame (the longest submission 5.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 545 dirty pages from their submits' captures, 70564 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17243 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] nvn: CommandBufferWaitEvent #205000: event 0x100d6c8008 mode 0 value 113188 (now 113185) (lr 0x806661f8)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos NavMeshCAStepDepWorker1] vcores: 94876 takes, 17392 waits (mean 30 us, longest 1.9 ms), 8666 kicks, 8455 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: mirror syncs (600 submits): 734 dirty pages from their submits' captures, 69295 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17125 in captures, 11 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.52, present 0.06, draw 0.81, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.2 copies, 7.08 MB written back
[hos host] vk: 28560 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.4 ms a frame (the longest submission 4.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: replay reads of guest memory as submitted: 3140000 (2510318 pages from the captures)
[hos Presentation Thread] vi: 28578 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: readback pages refreshed from guest memory: 1954923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 648 dirty pages from their submits' captures, 70606 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17301 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.50, present 0.06, draw 0.79, descriptors 0.43, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.9 copies, 7.08 MB written back
[hos host] vk: 28680 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.4 ms a frame (the longest submission 5.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror syncs (600 submits): 671 dirty pages from their submits' captures, 70442 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17336 in captures, 10 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871425 packets run in 10.0 s (busy 0.31 s, spun idle 0.89 s, slept 5009 times, 662 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15880 times, 35.04 ms in all, the longest 0.07 ms; replay_mu unlock 4888/16.82 ms (max 0.04), vkEndCommandBuffer 5496/11.33 ms (max 0.07), vkResetDescriptorPool 5496/6.90 ms (max 0.02)
[hos host] vk: program picks: 5433611 kept (1830457 by the last picks' textures, a uniform buffer bound since), 849 new, 6365539 with other textures (of 11800000)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 553 dirty pages from their submits' captures, 69527 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16985 in captures, 20 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10976 MB (peak 10996), private 18607 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 23808 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 23808 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 23808 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 23808 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 23808 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 25895 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 24288 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 24094 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 88 waited for it, 0.04 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 17.9 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.53, present 0.06, draw 0.83, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.7 copies, 7.08 MB written back
[hos host] vk: 28800 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.4 ms a frame (the longest submission 5.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: queues ordered by their events: 124347 submissions stopped at a wait, 124347 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 206626, not met 0; captures at a CPU event's wait 5789, 0 of them at a wait met on arrival
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.01 ms a frame (submits 1.49, presents 0.27, others 0.26), idle 14.65; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 101 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.02 ms after its hand-over (2.74 at most)
[hos host] vk: mirror syncs (600 submits): 634 dirty pages from their submits' captures, 69380 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17050 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos NavMeshCAStepDepWorker1] vcores: 94193 takes, 16982 waits (mean 29 us, longest 2.0 ms), 8381 kicks, 8220 yields, 0 starved grants, 0 escapes in 5 s
[hos rmbl::VibrationThread] hid: 90112 vibration values, strongest 0.00 since the last count
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 626 dirty pages from their submits' captures, 70469 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17055 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vi: 28879 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 298, 17.8-22 2, 22-30 0, 30-40 0, over 40 0
[hos host] vk: replay reads of guest memory as submitted: 3160000 (2528998 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.46, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 735.2 copies, 7.08 MB written back
[hos host] vk: 28920 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.4 ms a frame (the longest submission 6.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: readback pages refreshed from guest memory: 1966923 pages so far (0 held: may be written ahead in their submission)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.02 over 745 ranges, 1580 MB), 236 pages written, 236 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 579 dirty pages from their submits' captures, 69597 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17295 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 556 dirty pages from their submits' captures, 69451 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16971 in captures, 17 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.60, present 0.06, draw 0.83, descriptors 0.46, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.20, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.6 copies, 7.08 MB written back
[hos host] vk: 29040 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.4 ms a frame (the longest submission 6.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 587 dirty pages from their submits' captures, 69432 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16998 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #115000: event 0x100d6c8004 mode 0 value 114999 (lr 0x80665068)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 644 dirty pages from their submits' captures, 70459 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17289 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos NavMeshCAStepDepWorker1] vcores: 93987 takes, 17345 waits (mean 29 us, longest 1.8 ms), 8612 kicks, 8437 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.60, present 0.06, draw 0.87, descriptors 0.49, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.22, dispatch 0.04, memory sync 0.19, queue submit 0.20, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.9 copies, 7.08 MB written back
[hos host] vk: 29160 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.9 ms a frame (the longest submission 4.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vi: 29180 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: queues ordered by their events: 126000 submissions stopped at a wait, 125999 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 208996, not met 0; captures at a CPU event's wait 5861, 0 of them at a wait met on arrival
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 659 dirty pages from their submits' captures, 69506 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17057 in captures, 14 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 236 pages written, 236 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 3180000 (2547674 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 1978923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 708 dirty pages from their submits' captures, 70408 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17375 in captures, 12 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.55, present 0.06, draw 0.86, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.22, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 735.2 copies, 7.08 MB written back
[hos host] vk: 29280 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.1 ms a frame (the longest submission 6.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos ModuleSystemWorker2] nvn: 1800000 recordings made, 29776 live copies (6.2 MB), 1211 texture copies; 5 command buffers' segments (2.3 MB)
[hos host] vk: program picks: 5501998 kept (1836307 by the last picks' textures, a uniform buffer bound since), 849 new, 6497152 with other textures (of 12000000)
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871408 packets run in 10.0 s (busy 0.32 s, spun idle 0.91 s, slept 4998 times, 661 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15895 times, 38.48 ms in all, the longest 0.08 ms; replay_mu unlock 4881/18.16 ms (max 0.04), vkEndCommandBuffer 5507/12.55 ms (max 0.08), vkResetDescriptorPool 5507/7.76 ms (max 0.06)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 545 dirty pages from their submits' captures, 69478 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16952 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] nvn: CommandBufferWaitEvent #210000: event 0x100d6c8004 mode 0 value 115689 (now 115683) (lr 0x80a47c2c)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10976 MB (peak 10996), private 18607 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 24408 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 24408 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 24408 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 24408 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 24408 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 26495 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 24888 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 24694 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 95 waited for it, 0.05 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 533 dirty pages from their submits' captures, 69486 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16956 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: status: 600 frames, the slowest 18.2 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.61, present 0.06, draw 0.88, descriptors 0.50, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.22, dispatch 0.04, memory sync 0.19, queue submit 0.20, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.5 copies, 7.08 MB written back
[hos host] vk: 29400 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.8 ms a frame (the longest submission 4.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.08 ms a frame (submits 1.53, presents 0.28, others 0.28), idle 14.59; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 108 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.09 ms after its hand-over (3.70 at most)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos BaseProcExecutor4] vcores: 94022 takes, 16890 waits (mean 31 us, longest 2.0 ms), 8328 kicks, 8152 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: mirror syncs (600 submits): 517 dirty pages from their submits' captures, 69509 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16898 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vi: 29480 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.69, present 0.07, draw 0.89, descriptors 0.49, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.23, dispatch 0.05, memory sync 0.20, queue submit 0.21, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.5 copies, 7.08 MB written back
[hos host] vk: 29520 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.7 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.3 ms a frame (the longest submission 5.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos ModuleSystemWorker2] hid: game window in front (foreground window: process 5076, class "Longshot")
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 636 dirty pages from their submits' captures, 70685 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16995 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: replay reads of guest memory as submitted: 3200000 (2566354 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 1990923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: mirror syncs (600 submits): 580 dirty pages from their submits' captures, 69437 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17273 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (112 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.49, present 0.06, draw 0.81, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.18, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.9 copies, 7.08 MB written back
[hos host] vk: 29640 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.1 ms a frame (the longest submission 3.4 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 661 dirty pages from their submits' captures, 70436 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17338 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 708 dirty pages from their submits' captures, 69320 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17093 in captures, 14 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos ModuleSystemWorker2] vcores: 93403 takes, 16919 waits (mean 32 us, longest 2.3 ms), 8366 kicks, 8185 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.46, present 0.06, draw 0.78, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.19, dispatch 0.04, memory sync 0.17, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.3 copies, 7.08 MB written back
[hos host] vk: 29760 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.4 ms a frame (the longest submission 3.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos ModuleSystemWorker1] vk: readbacks of GPU results: 0 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos Presentation Thread] vi: 29780 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 2, 15.5-17.8 297, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 564 dirty pages from their submits' captures, 69448 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17015 in captures, 20 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (78 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 707 dirty pages from their submits' captures, 70539 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17379 in captures, 8 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.45, present 0.06, draw 0.76, descriptors 0.42, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.19, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 735.2 copies, 7.08 MB written back
[hos host] vk: 29880 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.7 ms a frame (the longest submission 3.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: program picks: 5570428 kept (1842157 by the last picks' textures, a uniform buffer bound since), 849 new, 6628722 with other textures (of 12200000)
[hos host] vk: replay reads of guest memory as submitted: 3220000 (2585030 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: readback pages refreshed from guest memory: 2002923 pages so far (0 held: may be written ahead in their submission)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 242 pages written, 242 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871364 packets run in 10.0 s (busy 0.32 s, spun idle 0.90 s, slept 5009 times, 661 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15872 times, 38.74 ms in all, the longest 0.17 ms; replay_mu unlock 4873/17.53 ms (max 0.07), vkEndCommandBuffer 5500/12.93 ms (max 0.17), vkResetDescriptorPool 5499/8.27 ms (max 0.07)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 744 dirty pages from their submits' captures, 70366 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17396 in captures, 9 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: mirror syncs (600 submits): 554 dirty pages from their submits' captures, 69454 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17003 in captures, 18 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos Presentation Thread] nvn: QueueSubmitCommands #180000: queue 000010100D640020 (its #29999), 1 handles (lr 0x805282f4)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10976 MB (peak 10996), private 18607 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 25008 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 25008 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 25008 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 25008 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 25008 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 27095 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 25488 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 25294 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos sead::MainThread] nvn: EventSignal (CPU) #60000: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos Presentation Thread] vk: presents after the CPU's signal (600): 92 waited for it, 0.06 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.1 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.46, present 0.06, draw 0.79, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.17, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.0 copies, 7.08 MB written back
[hos host] vk: 30000 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.8 ms a frame (the longest submission 3.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.66 ms a frame): its jobs 2.14 ms a frame (submits 1.48, presents 0.40, others 0.27), idle 14.52; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 104 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.15 ms after its hand-over (10.77 at most)
[hos Presentation Thread] vi: real-time step on: ratio 1.006, game's frame rate 60
[hos BaseProcExecutor1] vcores: 93306 takes, 17088 waits (mean 30 us, longest 1.7 ms), 8564 kicks, 8387 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 599 dirty pages from their submits' captures, 69408 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17047 in captures, 17 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vi: 30080 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 299, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos rmbl::VibrationThread] hid: 94208 vibration values, strongest 0.00 since the last count
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.02 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 544 dirty pages from their submits' captures, 69637 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17012 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.50, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.9 copies, 7.08 MB written back
[hos host] vk: 30120 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.7 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.9 ms a frame (the longest submission 5.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 630 dirty pages from their submits' captures, 70463 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17285 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 236 pages written, 236 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos ModuleSystemWorker1] nvn: 1850000 recordings made, 29769 live copies (6.2 MB), 1211 texture copies; 4 command buffers' segments (2.2 MB)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #215000: event 0x100d6c8008 mode 0 value 118189 (now 118186) (lr 0x806661f8)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: replay reads of guest memory as submitted: 3240000 (2603708 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 2014923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.53, present 0.06, draw 0.81, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.7 copies, 7.08 MB written back
[hos host] vk: 30240 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.7 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.0 ms a frame (the longest submission 4.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror syncs (600 submits): 520 dirty pages from their submits' captures, 68425 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16674 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 230 pages written, 230 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (86 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 433 dirty pages from their submits' captures, 68446 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16603 in captures, 16 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos BaseProcExecutor1] vcores: 93978 takes, 16949 waits (mean 28 us, longest 1.8 ms), 8395 kicks, 8238 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.52, present 0.06, draw 0.82, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 732.2 copies, 7.08 MB written back
[hos host] vk: 30360 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 645.1 full barriers recorded, 106.4 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.9 ms a frame (the longest submission 4.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 540 dirty pages from their submits' captures, 69459 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16977 in captures, 15 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vi: 30381 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 299, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.02 over 745 ranges, 1580 MB), 230 pages written, 230 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 716 dirty pages from their submits' captures, 69367 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17114 in captures, 10 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: program picks: 5638867 kept (1848007 by the last picks' textures, a uniform buffer bound since), 849 new, 6760283 with other textures (of 12400000)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.02 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 5 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.48, present 0.06, draw 0.81, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.2 copies, 7.08 MB written back
[hos host] vk: 30480 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.0 ms a frame (the longest submission 4.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 597 dirty pages from their submits' captures, 69332 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17004 in captures, 17 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871541 packets run in 10.0 s (busy 0.31 s, spun idle 0.89 s, slept 5001 times, 663 of them under 200 us), 0 calls made directly (no room); the replay waited for it 16022 times, 36.81 ms in all, the longest 0.09 ms; replay_mu unlock 4928/17.30 ms (max 0.06), vkEndCommandBuffer 5547/12.12 ms (max 0.09), vkResetDescriptorPool 5547/7.39 ms (max 0.08)
[hos host] vk: replay reads of guest memory as submitted: 3260000 (2622386 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 2026923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 593 dirty pages from their submits' captures, 70417 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17287 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (112 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10976 MB (peak 10996), private 18607 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 25608 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 25608 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 25608 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 25608 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 25608 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 27695 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 26088 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 25894 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 131 waited for it, 0.06 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.1 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.46, present 0.06, draw 0.74, descriptors 0.42, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.19, dispatch 0.04, memory sync 0.18, queue submit 0.17, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 732.7 copies, 7.08 MB written back
[hos host] vk: 30600 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.0 ms a frame (the longest submission 4.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.09 ms a frame (submits 1.38, presents 0.37, others 0.34), idle 14.58; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 141 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.10 ms after its hand-over (2.78 at most)
[hos host] vk: queues ordered by their events: 132000 submissions stopped at a wait, 131996 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 217564, not met 0; captures at a CPU event's wait 6146, 0 of them at a wait met on arrival
[hos host] vk: mirror syncs (600 submits): 594 dirty pages from their submits' captures, 69331 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17009 in captures, 17 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos tera::FileResourceMgr] vcores: 93123 takes, 16735 waits (mean 30 us, longest 1.8 ms), 8356 kicks, 8163 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos Presentation Thread] vi: 30682 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 589 dirty pages from their submits' captures, 69476 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17043 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.43, present 0.06, draw 0.78, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.19, dispatch 0.04, memory sync 0.17, queue submit 0.17, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.7 copies, 7.08 MB written back
[hos host] vk: 30720 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.8 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.0 ms a frame (the longest submission 4.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 230 pages written, 230 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 582 dirty pages from their submits' captures, 69350 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16748 in captures, 14 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] nvn: CommandBufferSignalEvent #120000: event 0x100d6c8000 mode 0 value 119999 (lr 0x80664f14)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 571 dirty pages from their submits' captures, 69357 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17246 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.52, present 0.06, draw 0.81, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 732.9 copies, 7.08 MB written back
[hos host] vk: 30840 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.7 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.0 ms a frame (the longest submission 4.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: readback pages refreshed from guest memory: 2038923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: replay reads of guest memory as submitted: 3280000 (2641062 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 571 dirty pages from their submits' captures, 68276 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16712 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos tera::FileResourceMgr] vcores: 92904 takes, 17316 waits (mean 29 us, longest 2.0 ms), 8604 kicks, 8432 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.56, present 0.06, draw 0.84, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 732.6 copies, 7.08 MB written back
[hos host] vk: 30960 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.8 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.8 ms a frame (the longest submission 4.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 544 dirty pages from their submits' captures, 69397 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16988 in captures, 18 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vi: 30982 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 684 dirty pages from their submits' captures, 70465 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17314 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] nvn: CommandBufferWaitEvent #220000: event 0x100d6c8008 mode 0 value 120688 (now 120685) (lr 0x806661f8)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: program picks: 5707305 kept (1853853 by the last picks' textures, a uniform buffer bound since), 849 new, 6891845 with other textures (of 12600000)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.49, present 0.06, draw 0.79, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.9 copies, 7.08 MB written back
[hos host] vk: 31080 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.8 ms a frame (the longest submission 3.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos ModuleSystemWorker2] nvn: 1900000 recordings made, 29761 live copies (6.2 MB), 1211 texture copies; 3 command buffers' segments (2.1 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 597 dirty pages from their submits' captures, 69348 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17044 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871504 packets run in 10.0 s (busy 0.31 s, spun idle 0.89 s, slept 5012 times, 664 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15979 times, 37.21 ms in all, the longest 0.14 ms; replay_mu unlock 4907/17.23 ms (max 0.06), vkEndCommandBuffer 5536/12.28 ms (max 0.14), vkResetDescriptorPool 5536/7.69 ms (max 0.08)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 541 dirty pages from their submits' captures, 69404 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16998 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10976 MB (peak 10996), private 18607 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 26208 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 26208 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 26208 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 26208 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 26208 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 28295 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 26688 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 26494 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 119 waited for it, 0.06 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 17.8 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.51, present 0.06, draw 0.81, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 732.7 copies, 7.08 MB written back
[hos host] vk: 31200 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.9 ms a frame (the longest submission 4.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.09 ms a frame (submits 1.40, presents 0.36, others 0.33), idle 14.58; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 136 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.10 ms after its hand-over (3.04 at most)
[hos host] vk: readback pages refreshed from guest memory: 2050923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: replay reads of guest memory as submitted: 3300000 (2659742 pages from the captures)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 585 dirty pages from their submits' captures, 69415 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17008 in captures, 16 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos nn.npln.Callback] vcores: 94598 takes, 17249 waits (mean 29 us, longest 2.1 ms), 8638 kicks, 8453 yields, 0 starved grants, 0 escapes in 5 s
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos ModuleSystemWorker3] vk: readbacks of GPU results: 0 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos Presentation Thread] vi: 31283 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: mirror syncs (600 submits): 527 dirty pages from their submits' captures, 68327 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16708 in captures, 15 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.52, present 0.06, draw 0.80, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.4 copies, 7.08 MB written back
[hos host] vk: 31320 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.9 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.9 ms a frame (the longest submission 4.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos rmbl::VibrationThread] hid: 98304 vibration values, strongest 0.00 since the last count
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 230 pages written, 230 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 602 dirty pages from their submits' captures, 69473 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17040 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 590 dirty pages from their submits' captures, 70420 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17262 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.46, present 0.06, draw 0.77, descriptors 0.43, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.0 copies, 7.08 MB written back
[hos host] vk: 31440 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.0 ms a frame (the longest submission 4.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 602 dirty pages from their submits' captures, 69324 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17032 in captures, 18 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: readback pages refreshed from guest memory: 2062923 pages so far (0 held: may be written ahead in their submission)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 3320000 (2678418 pages from the captures)
[hos ModuleSystemWorker1] vcores: 92686 takes, 16929 waits (mean 30 us, longest 1.8 ms), 8415 kicks, 8262 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: mirror syncs (600 submits): 594 dirty pages from their submits' captures, 69334 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17036 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.46, present 0.06, draw 0.78, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.0 copies, 7.08 MB written back
[hos host] vk: 31560 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.0 ms a frame (the longest submission 4.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vi: 31583 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 299, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 601 dirty pages from their submits' captures, 70550 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17300 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.02 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: program picks: 5775712 kept (1859697 by the last picks' textures, a uniform buffer bound since), 849 new, 7023438 with other textures (of 12800000)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 541 dirty pages from their submits' captures, 68307 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16713 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.44, present 0.06, draw 0.79, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.17, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.6 copies, 7.08 MB written back
[hos host] vk: 31680 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.7 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.1 ms a frame (the longest submission 4.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871475 packets run in 10.0 s (busy 0.31 s, spun idle 0.89 s, slept 5017 times, 659 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15946 times, 35.73 ms in all, the longest 0.09 ms; replay_mu unlock 4888/16.93 ms (max 0.09), vkEndCommandBuffer 5529/11.82 ms (max 0.08), vkResetDescriptorPool 5529/6.98 ms (max 0.02)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 682 dirty pages from their submits' captures, 70334 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17356 in captures, 14 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10976 MB (peak 10996), private 18606 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10797 allocations 4714 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 48 allocations 380 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 8 images 121 MB; 2 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (831 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 26808 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 26808 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 26808 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 26808 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 26808 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 28895 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 27288 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 27094 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 127 waited for it, 0.06 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.1 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.48, present 0.06, draw 0.79, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.1 copies, 7.08 MB written back
[hos host] vk: 31800 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.1 ms a frame (the longest submission 4.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.09 ms a frame (submits 1.38, presents 0.39, others 0.32), idle 14.58; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 134 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.10 ms after its hand-over (3.23 at most)
[hos host] vk: mirror syncs (600 submits): 573 dirty pages from their submits' captures, 69356 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16987 in captures, 14 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.02 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos tera::FileResourceMgr] vcores: 92529 takes, 16730 waits (mean 29 us, longest 2.1 ms), 8292 kicks, 8121 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: readback pages refreshed from guest memory: 2074923 pages so far (0 held: may be written ahead in their submission)
[hos ModuleSystemWorker3] nvn: CommandBufferWaitEvent #225000: event 0x100d6c8004 mode 0 value 123189 (now 123183) (lr 0x80a47c2c)
[hos host] vk: replay reads of guest memory as submitted: 3340000 (2697097 pages from the captures)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 605 dirty pages from their submits' captures, 69337 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17025 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vi: 31884 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.46, present 0.06, draw 0.81, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.9 copies, 7.08 MB written back
[hos host] vk: 31920 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.7 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.0 ms a frame (the longest submission 4.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 626 dirty pages from their submits' captures, 69455 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17062 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos ModuleSystemWorker3] nvn: 1950000 recordings made, 29753 live copies (6.2 MB), 1211 texture copies; 5 command buffers' segments (2.3 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 652 dirty pages from their submits' captures, 69361 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17077 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] menu: bug report asked for
[hos host] vk: present 32019 written to D:\Games\Longshot\bug-reports\2026-11-16_00-30-43\picture.png (the control bridge)
[hos host] menu: bug report written to bug-reports\2026-11-16_00-30-43: report.txt, longshot_log.txt (1.5 MB), longshot_log.1.txt (524 KB), picture.png
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.47, present 0.17, draw 0.78, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.3 copies, 7.08 MB written back
[hos host] vk: 32040 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.1 ms a frame (the longest submission 4.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: queues ordered by their events: 138000 submissions stopped at a wait, 137997 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 226090, not met 0; captures at a CPU event's wait 6463, 0 of them at a wait met on arrival
[hos host] vk: mirror syncs (600 submits): 678 dirty pages from their submits' captures, 69262 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17080 in captures, 10 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 613 dirty pages from their submits' captures, 70396 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17287 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos ModuleSystemWorker1] vcores: 93680 takes, 16809 waits (mean 29 us, longest 1.9 ms), 8290 kicks, 8122 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.47, present 0.06, draw 0.79, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 732.9 copies, 7.08 MB written back
[hos host] vk: 32160 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.1 ms a frame (the longest submission 4.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: readback pages refreshed from guest memory: 2086923 pages so far (0 held: may be written ahead in their submission)
[hos Presentation Thread] vi: 32185 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 549 dirty pages from their submits' captures, 69375 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16983 in captures, 19 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 3360000 (2715774 pages from the captures)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: program picks: 5844102 kept (1865547 by the last picks' textures, a uniform buffer bound since), 849 new, 7155048 with other textures (of 13000000)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 738 dirty pages from their submits' captures, 70415 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17114 in captures, 11 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.48, present 0.06, draw 0.82, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.1 copies, 7.08 MB written back
[hos host] vk: 32280 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.0 ms a frame (the longest submission 4.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871491 packets run in 10.0 s (busy 0.31 s, spun idle 0.88 s, slept 5047 times, 663 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15924 times, 35.36 ms in all, the longest 0.12 ms; replay_mu unlock 4890/16.62 ms (max 0.06), vkEndCommandBuffer 5517/11.81 ms (max 0.12), vkResetDescriptorPool 5517/6.94 ms (max 0.02)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 720 dirty pages from their submits' captures, 69210 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17396 in captures, 12 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 634 dirty pages from their submits' captures, 69304 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17040 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10976 MB (peak 10996), private 18607 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10798 allocations 4717 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 49 allocations 383 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 9 images 125 MB; 2 free ranges, the largest 2 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (828 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 27408 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 27408 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 27408 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 27408 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 27408 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 29495 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 27888 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 27694 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 102 waited for it, 0.06 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 17.9 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.45, present 0.06, draw 0.78, descriptors 0.44, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.20, dispatch 0.04, memory sync 0.17, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.4 copies, 7.08 MB written back
[hos host] vk: 32400 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.1 ms a frame (the longest submission 4.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: queues ordered by their events: 139486 submissions stopped at a wait, 139486 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 228226, not met 0; captures at a CPU event's wait 6528, 0 of them at a wait met on arrival
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.07 ms a frame (submits 1.42, presents 0.38, others 0.28), idle 14.59; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 116 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.08 ms after its hand-over (15.16 at most)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos Resource Memory] vcores: 93913 takes, 16948 waits (mean 30 us, longest 2.1 ms), 8364 kicks, 8187 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: mirror syncs (600 submits): 579 dirty pages from their submits' captures, 69353 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17009 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] nvn: CommandBufferSignalEvent #125000: event 0x100d6c8008 mode 0 value 124999 (lr 0x80666598)
[hos Presentation Thread] vi: 32486 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] nvn: EventSignal (CPU) #65000: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos host] vk: readback pages refreshed from guest memory: 2098923 pages so far (0 held: may be written ahead in their submission)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (112 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.46, present 0.06, draw 0.78, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.02, programs 0.05, commands 0.19, dispatch 0.04, memory sync 0.18, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.8 copies, 7.08 MB written back
[hos host] vk: 32520 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.1 ms a frame (the longest submission 4.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 625 dirty pages from their submits' captures, 69449 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17054 in captures, 11 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: replay reads of guest memory as submitted: 3380000 (2734452 pages from the captures)
[hos rmbl::VibrationThread] hid: 102400 vibration values, strongest 0.00 since the last count
[hos host] vk: mirror syncs (600 submits): 661 dirty pages from their submits' captures, 70371 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17314 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.52, present 0.06, draw 0.82, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.18, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 733.3 copies, 7.08 MB written back
[hos host] vk: 32640 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 5.0 ms a frame (the longest submission 4.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 661 dirty pages from their submits' captures, 70356 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17092 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] hid: game window not in front (foreground window: process 14560, class "Windows.UI.Core.CoreWindow")
[hos sead::MainThread] nvn: CommandBufferWaitEvent #230000: event 0x100d6c8008 mode 0 value 125689 (now 125686) (lr 0x806661f8)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 587 dirty pages from their submits' captures, 69351 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17261 in captures, 14 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos Resource Memory] vcores: 95396 takes, 17190 waits (mean 30 us, longest 2.0 ms), 8567 kicks, 8403 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.58, present 0.06, draw 0.85, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.22, dispatch 0.04, memory sync 0.19, queue submit 0.20, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.20 MB synced in 732.6 copies, 7.08 MB written back
[hos host] vk: 32760 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.7 ms a frame (the longest submission 5.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: readbacks of GPU results: 0 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos sead::MainThread] nvn: GPU waits in 5 s: 1 sync waits (1 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos Presentation Thread] vi: 32786 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 298, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 545 dirty pages from their submits' captures, 69399 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16944 in captures, 13 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: program picks: 5912534 kept (1871397 by the last picks' textures, a uniform buffer bound since), 849 new, 7286616 with other textures (of 13200000)
[hos host] vk: readback pages refreshed from guest memory: 2110923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: mirror syncs (600 submits): 645 dirty pages from their submits' captures, 69501 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17066 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 3400000 (2753130 pages from the captures)
[hos ModuleSystemWorker1] nvn: 2000000 recordings made, 29745 live copies (6.2 MB), 1211 texture copies; 4 command buffers' segments (2.2 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.62, present 0.06, draw 0.83, descriptors 0.46, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.21, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.0 copies, 7.08 MB written back
[hos host] vk: 32880 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.02 ms a frame (fences 0.01, timelines 0.01, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 3.5 ms a frame (the longest submission 11.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871505 packets run in 10.0 s (busy 0.32 s, spun idle 0.91 s, slept 4999 times, 665 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15907 times, 38.11 ms in all, the longest 0.20 ms; replay_mu unlock 4881/17.83 ms (max 0.20), vkEndCommandBuffer 5513/12.82 ms (max 0.10), vkResetDescriptorPool 5513/7.46 ms (max 0.07)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 654 dirty pages from their submits' captures, 70360 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17346 in captures, 15 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 654 dirty pages from their submits' captures, 69386 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17085 in captures, 10 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 238 pages written, 238 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (112 MB), 5 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10976 MB (peak 10996), private 18607 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10798 allocations 4717 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 49 allocations 383 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 9 images 125 MB; 2 free ranges, the largest 2 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (828 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 28008 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 28008 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 28008 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 28008 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 28008 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 30095 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 28488 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 28294 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 101 waited for it, 0.10 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.4 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.58, present 0.06, draw 0.85, descriptors 0.48, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.19, queue submit 0.21, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.0 copies, 7.08 MB written back
[hos host] vk: 33000 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 3.4 ms a frame (the longest submission 3.1 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.17 ms a frame (submits 1.52, presents 0.37, others 0.28), idle 14.50; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 108 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.18 ms after its hand-over (3.46 at most)
[hos Presentation Thread] vi: real-time step on: ratio 0.998, game's frame rate 60
[hos Resource Memory] vcores: 95848 takes, 16846 waits (mean 31 us, longest 1.9 ms), 8307 kicks, 8179 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 629 dirty pages from their submits' captures, 70471 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17309 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vi: 33087 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] hid: game window in front (foreground window: process 5076, class "Longshot")
[hos host] vk: mirror syncs (600 submits): 639 dirty pages from their submits' captures, 69527 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17014 in captures, 10 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.63, present 0.07, draw 0.87, descriptors 0.49, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.05, memory sync 0.19, queue submit 0.22, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.9 copies, 7.08 MB written back
[hos host] vk: 33120 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 3.4 ms a frame (the longest submission 3.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos ModuleSystemWorker3] hid: game window not in front (foreground window: process 2796, class "Chrome_WidgetWin_1")
[hos host] vk: readback pages refreshed from guest memory: 2122923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 326 dirty pages from their submits' captures, 69705 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16514 in captures, 12 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 230 pages written, 230 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 3420000 (2771806 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.94, present 0.07, draw 0.99, descriptors 0.55, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.07, commands 0.25, dispatch 0.05, memory sync 0.22, queue submit 0.25, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 732.8 copies, 7.08 MB written back
[hos host] vk: 33240 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.02 ms a frame (fences 0.02, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 645.0 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 3.0 ms a frame (the longest submission 3.2 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror syncs (600 submits): 446 dirty pages from their submits' captures, 68498 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16564 in captures, 13 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] vk: capture: a submit 0.09 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 230 pages written, 230 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 472 dirty pages from their submits' captures, 68458 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16907 in captures, 19 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] nvn: QueueSubmitCommands #200000: queue 0000101004133020 (its #33339), 1 handles (lr 0x80590358)
[hos NavMeshCAStepDepWorker1] vcores: 98870 takes, 18237 waits (mean 32 us, longest 2.2 ms), 9107 kicks, 8943 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.69, present 0.06, draw 0.91, descriptors 0.51, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.23, dispatch 0.05, memory sync 0.20, queue submit 0.22, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.2 copies, 7.08 MB written back
[hos host] vk: 33360 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.8 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 3.4 ms a frame (the longest submission 3.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror syncs (600 submits): 450 dirty pages from their submits' captures, 69578 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16887 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos Presentation Thread] vi: 33388 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: program picks: 5980975 kept (1877247 by the last picks' textures, a uniform buffer bound since), 849 new, 7418175 with other textures (of 13400000)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 490 dirty pages from their submits' captures, 69679 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16939 in captures, 17 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: queues ordered by their events: 144000 submissions stopped at a wait, 143998 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 234652, not met 0; captures at a CPU event's wait 6756, 0 of them at a wait met on arrival
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.80, present 0.06, draw 0.99, descriptors 0.55, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.07, commands 0.25, dispatch 0.05, memory sync 0.21, queue submit 0.23, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.0 copies, 7.08 MB written back
[hos host] vk: 33480 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.7 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 3.7 ms a frame (the longest submission 3.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: readback pages refreshed from guest memory: 2134923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 461 dirty pages from their submits' captures, 69566 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16846 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871523 packets run in 10.0 s (busy 0.36 s, spun idle 0.99 s, slept 4968 times, 665 of them under 200 us), 0 calls made directly (no room); the replay waited for it 16025 times, 46.93 ms in all, the longest 0.12 ms; replay_mu unlock 4931/21.60 ms (max 0.11), vkEndCommandBuffer 5547/15.78 ms (max 0.11), vkResetDescriptorPool 5547/9.55 ms (max 0.12)
[hos host] vk: replay reads of guest memory as submitted: 3440000 (2790486 pages from the captures)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #235000: event 0x100d6c8008 mode 0 value 128188 (now 128185) (lr 0x806661f8)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 599 dirty pages from their submits' captures, 69425 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17026 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10976 MB (peak 10996), private 18607 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10798 allocations 4717 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 49 allocations 383 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 9 images 125 MB; 2 free ranges, the largest 2 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (828 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 28608 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 28608 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 28608 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 28608 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 28608 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 30695 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 29088 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 28894 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 134 waited for it, 0.09 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 21.1 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.66, present 0.06, draw 0.89, descriptors 0.49, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.07, commands 0.23, dispatch 0.05, memory sync 0.20, queue submit 0.20, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.6 copies, 7.08 MB written back
[hos host] vk: 33600 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 3.4 ms a frame (the longest submission 3.1 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.45 ms a frame (submits 1.61, presents 0.42, others 0.42), idle 14.22; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 148 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.46 ms after its hand-over (11.71 at most)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 575 dirty pages from their submits' captures, 69512 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16962 in captures, 20 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos NavMeshCAStepDepWorker1] vcores: 96779 takes, 17455 waits (mean 31 us, longest 1.9 ms), 8588 kicks, 8440 yields, 0 starved grants, 0 escapes in 5 s
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos Presentation Thread] vi: 33688 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 2, 15.5-17.8 296, 17.8-22 2, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 559 dirty pages from their submits' captures, 70538 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17229 in captures, 14 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.64, present 0.07, draw 0.86, descriptors 0.47, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.07, commands 0.22, dispatch 0.05, memory sync 0.20, queue submit 0.21, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.22 MB synced in 734.6 copies, 7.08 MB written back
[hos host] vk: 33720 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.0 ms a frame (the longest submission 3.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 655 dirty pages from their submits' captures, 70590 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17064 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] nvn: 2050000 recordings made, 29758 live copies (6.2 MB), 1211 texture copies; 3 command buffers' segments (2.1 MB)
[hos rmbl::VibrationThread] hid: 106496 vibration values, strongest 0.00 since the last count
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: readback pages refreshed from guest memory: 2146923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 635 dirty pages from their submits' captures, 69383 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17331 in captures, 14 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.55, present 0.06, draw 0.81, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.20, dispatch 0.04, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.4 copies, 7.08 MB written back
[hos host] vk: 33840 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.2 ms a frame (the longest submission 4.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: replay reads of guest memory as submitted: 3460000 (2809162 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 581 dirty pages from their submits' captures, 70513 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17249 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos ModuleSystemWorker1] vcores: 96701 takes, 17336 waits (mean 29 us, longest 1.8 ms), 8675 kicks, 8533 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 234 pages written, 234 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.60, present 0.06, draw 0.84, descriptors 0.47, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.20, queue submit 0.20, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.7 copies, 7.08 MB written back
[hos host] vk: 33960 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.1 ms a frame (the longest submission 3.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 561 dirty pages from their submits' captures, 69463 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16983 in captures, 13 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: program picks: 6049412 kept (1883093 by the last picks' textures, a uniform buffer bound since), 849 new, 7549738 with other textures (of 13600000)
[hos Presentation Thread] vi: 33989 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 465 dirty pages from their submits' captures, 68605 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16626 in captures, 19 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 230 pages written, 230 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.65, present 0.06, draw 0.85, descriptors 0.47, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.05, memory sync 0.19, queue submit 0.21, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.4 copies, 7.08 MB written back
[hos host] vk: 34080 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.8 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.3 ms a frame (the longest submission 4.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 627 dirty pages from their submits' captures, 70472 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17288 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871371 packets run in 10.0 s (busy 0.33 s, spun idle 0.94 s, slept 5013 times, 663 of them under 200 us), 0 calls made directly (no room); the replay waited for it 15922 times, 40.27 ms in all, the longest 0.10 ms; replay_mu unlock 4896/18.98 ms (max 0.04), vkEndCommandBuffer 5513/13.18 ms (max 0.10), vkResetDescriptorPool 5513/8.11 ms (max 0.08)
[hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #130000: event 0x100d6c8004 mode 0 value 129999 (lr 0x80665068)
[hos host] vk: readback pages refreshed from guest memory: 2158923 pages so far (0 held: may be written ahead in their submission)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 432 dirty pages from their submits' captures, 68499 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16618 in captures, 17 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 3480000 (2827841 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10976 MB (peak 10996), private 18607 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10798 allocations 4717 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 49 allocations 383 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 9 images 125 MB; 2 free ranges, the largest 2 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (828 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 29208 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 29208 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 29208 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 29208 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 29208 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 31295 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 29688 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 29494 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 111 waited for it, 0.05 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.1 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.72, present 0.06, draw 0.90, descriptors 0.50, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.07, commands 0.23, dispatch 0.05, memory sync 0.21, queue submit 0.22, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.1 copies, 7.08 MB written back
[hos host] vk: 34200 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 645.0 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.5 ms a frame (the longest submission 4.4 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.27 ms a frame (submits 1.55, presents 0.37, others 0.35), idle 14.40; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 129 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.28 ms after its hand-over (3.50 at most)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 419 dirty pages from their submits' captures, 68533 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16611 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos NavMeshCAStepDepWorker1] vcores: 97216 takes, 17957 waits (mean 30 us, longest 2.4 ms), 8894 kicks, 8711 yields, 0 starved grants, 0 escapes in 5 s
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 230 pages written, 230 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos sead::MainThread] vk: readbacks of GPU results: 0 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 533 dirty pages from their submits' captures, 69499 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16938 in captures, 12 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vi: 34290 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 299, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.74, present 0.07, draw 0.92, descriptors 0.51, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.07, commands 0.23, dispatch 0.05, memory sync 0.21, queue submit 0.22, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.5 copies, 7.08 MB written back
[hos host] vk: 34320 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.7 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.4 ms a frame (the longest submission 4.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 563 dirty pages from their submits' captures, 70683 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16943 in captures, 14 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos ModuleSystemWorker1] nvn: CommandBufferWaitEvent #240000: event 0x100d6c8004 mode 0 value 130689 (now 130683) (lr 0x80a47c2c)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: mirror syncs (600 submits): 421 dirty pages from their submits' captures, 68517 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16903 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 6 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.65, present 0.06, draw 0.86, descriptors 0.48, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.04, memory sync 0.20, queue submit 0.21, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.2 copies, 7.08 MB written back
[hos host] vk: 34440 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.9 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.4 ms a frame (the longest submission 3.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: readback pages refreshed from guest memory: 2170923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 459 dirty pages from their submits' captures, 68548 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16642 in captures, 16 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: replay reads of guest memory as submitted: 3500000 (2846518 pages from the captures)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 230 pages written, 230 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 5 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: mirror syncs (600 submits): 481 dirty pages from their submits' captures, 69530 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16590 in captures, 19 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos aal::LowPrioWorkerThread] vcores: 95732 takes, 17209 waits (mean 32 us, longest 2.2 ms), 8367 kicks, 8205 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.76, present 0.06, draw 0.96, descriptors 0.52, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.07, commands 0.25, dispatch 0.05, memory sync 0.20, queue submit 0.23, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.0 copies, 7.08 MB written back
[hos host] vk: 34560 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 645.0 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.4 ms a frame (the longest submission 4.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: program picks: 6117814 kept (1888937 by the last picks' textures, a uniform buffer bound since), 849 new, 7681336 with other textures (of 13800000)
[hos Presentation Thread] vi: 34590 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 375 dirty pages from their submits' captures, 67494 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16615 in captures, 16 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 228 pages written, 228 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (84 MB), 5 spare buffers, 0 texture pages copied (0 MB)
[hos sead::MainThread] nvn: 2100000 recordings made, 29779 live copies (5.9 MB), 1211 texture copies; 2 command buffers' segments (2.1 MB)
[hos host] vk: mirror syncs (600 submits): 480 dirty pages from their submits' captures, 69685 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16907 in captures, 16 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.60, present 0.06, draw 0.89, descriptors 0.49, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.23, dispatch 0.04, memory sync 0.18, queue submit 0.21, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.9 copies, 7.08 MB written back
[hos host] vk: 34680 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 645.0 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.5 ms a frame (the longest submission 4.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: render targets drawn over from another start, let go: 1439 so far (3327 MB)
[hos host] vk: recorder: 1871832 packets run in 10.0 s (busy 0.35 s, spun idle 0.97 s, slept 5075 times, 661 of them under 200 us), 0 calls made directly (no room); the replay waited for it 16127 times, 43.37 ms in all, the longest 0.15 ms; replay_mu unlock 4968/20.55 ms (max 0.04), vkEndCommandBuffer 5580/14.12 ms (max 0.08), vkResetDescriptorPool 5579/8.70 ms (max 0.15)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (100 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 556 dirty pages from their submits' captures, 69464 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16991 in captures, 17 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: readback pages refreshed from guest memory: 2182923 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: memory: working set 10976 MB (peak 10996), private 18607 MB, staging 0 MB in 0 arenas
[hos host] vk: memory heaps: heap 0 (device): 101 blocks 5545 MB, 10798 allocations 4717 MB; used 6195 of 15280 MB; heap 1 (system): 10 blocks 400 MB, 49 allocations 383 MB; used 1615 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 9 images 125 MB; 2 free ranges, the largest 2 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 127 images 611 MB; 38 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1512 images 1998 MB; 466 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 772 made new, 645 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6195 MB used of 15280 MB allowed (828 MB of it free in the blocks); textures 3424 MB (budget 10928 MB), 1642 textures
[hos host] vk: textures: decoded ASTC 1819 MB, rendered 1016 MB (130 drawn in one frame, kept: 33391 KB), other 337 MB; used in the last 8 presents 301 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 29808 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 29808 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 29808 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 29808 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 29808 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 31895 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 30288 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 30094 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 19 (16170 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 134 waited for it, 0.05 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.6 ms; VRAM 6.0 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 719 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.62, present 0.06, draw 0.86, descriptors 0.48, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.21, dispatch 0.05, memory sync 0.19, queue submit 0.21, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.8 copies, 7.08 MB written back
[hos host] vk: 34800 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.5 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.8 ms a frame (the longest submission 4.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.34 ms a frame (submits 1.51, presents 0.39, others 0.43), idle 14.33; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 68.00 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 165 captures at a CPU signal; the submits' waits read in 0.009 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.35 ms after its hand-over (3.79 at most)
[hos host] vk: mirror syncs (600 submits): 523 dirty pages from their submits' captures, 69488 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16980 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (106 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos NavMeshCAStepDepWorker1] vcores: 97749 takes, 18395 waits (mean 28 us, longest 2.1 ms), 9231 kicks, 9046 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: replay reads of guest memory as submitted: 3520000 (2865194 pages from the captures)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 495 dirty pages from their submits' captures, 70597 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 330 runs, 467.4 MB compared; 66 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 17202 in captures, 15 only in the collection, 65 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: queues ordered by their events: 150000 submissions stopped at a wait, 149999 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 243142, not met 0; captures at a CPU event's wait 7097, 0 of them at a wait met on arrival
[hos Presentation Thread] vi: 34891 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (108 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.71, present 0.07, draw 0.93, descriptors 0.51, texture lookups 0.03, uploads 0.00, pipelines 0.03, programs 0.07, commands 0.24, dispatch 0.05, memory sync 0.19, queue submit 0.22, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 734.2 copies, 7.08 MB written back
[hos host] vk: 34920 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.6 full barriers recorded, 106.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.8 ms a frame (the longest submission 4.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 484 dirty pages from their submits' captures, 69670 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16900 in captures, 19 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos ModuleSystemWorker4] hid: game window in front (foreground window: process 5076, class "Longshot")
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 451 dirty pages from their submits' captures, 68499 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16675 in captures, 17 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] nvn: EventSignal (CPU) #70000: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos rmbl::VibrationThread] hid: 110592 vibration values, strongest 0.00 since the last count
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 745 ranges, 1580 MB), 230 pages written, 230 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (102 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.61, present 0.06, draw 0.85, descriptors 0.45, texture lookups 0.02, uploads 0.00, pipelines 0.03, programs 0.06, commands 0.23, dispatch 0.05, memory sync 0.18, queue submit 0.21, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 4.21 MB synced in 733.3 copies, 7.08 MB written back
[hos host] vk: 35040 presents, 60.0 fps; a frame: 340 draws (0 skipped), 2 dispatches, 139 passes, 84 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1642 textures (3424 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 644.9 full barriers recorded, 106.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 2.0; 0x12: 74.0; 0x13: 2.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 5.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror syncs (600 submits): 531 dirty pages from their submits' captures, 69488 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 16956 in captures, 16 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos sead::MainThread] nvn: GPU waits in 5 s: 1 sync waits (7 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: readback pages refreshed from guest memory: 2194923 pages so far (0 held: may be written ahead in their submission)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 746 ranges, 1813 MB), 230 pages written, 230 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (86 MB), 7 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: 3 textures retired (1642 left, 3402 MB): budget 0, drawn over 0, dead targets 3
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 381 dirty pages from their submits' captures, 65319 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 315 runs, 446.2 MB compared; 63 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 14672 in captures, 10 only in the collection, 64 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos ModuleSystemWorker5] vcores: 94890 takes, 17177 waits (mean 32 us, longest 2.3 ms), 8413 kicks, 8234 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: 7 textures retired (1724 left, 3437 MB): budget 0, drawn over 0, dead targets 7
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: program picks: 6185971 kept (1894517 by the last picks' textures, a uniform buffer bound since), 854 new, 7813174 with other textures (of 14000000)
[hos host] vk: a frame: 2 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.57, present 0.06, draw 0.78, descriptors 0.44, texture lookups 0.07, uploads 0.05, pipelines 0.02, programs 0.06, commands 0.19, dispatch 0.05, memory sync 0.18, queue submit 0.20, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 3.96 MB synced in 704.7 copies, 7.08 MB written back
[hos host] vk: 35160 presents, 60.0 fps; a frame: 339 draws (0 skipped), 2 dispatches, 136 passes, 83 barriers, 6 submits, 0.7 uploads (0.2 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1724 textures (3437 MB)
[hos host] vk: host time in GPU resource waits: 0.07 ms a frame (fences 0.01, timelines 0.06, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 643.4 full barriers recorded, 106.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 0.8; 0x10: 0.8; 0x11: 1.5; 0x12: 71.9; 0x13: 1.5; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.5 ms a frame (the longest submission 4.0 ms); 0.8 textures made a frame
[hos host] vk: a frame: 0.13 MB unswizzled on the CPU in 0.04 ms
[hos host] vk: mirror syncs (600 submits): 256 dirty pages from their submits' captures, 59762 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 320 runs, 453.3 MB compared; 64 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 11304 in captures, 0 only in the collection, 63 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vi: 35192 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 299, 17.8-22 0, 22-30 1, 30-40 0, over 40 0
[hos sead::MainThread] nvn: CommandBufferWaitEvent #245000: event 0x100d6c8008 mode 0 value 133189 (now 133186) (lr 0x806661f8)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.01, scan 0.03 over 746 ranges, 1813 MB), 230 pages written, 230 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (82 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: texture #3294 0x10000000000 138x96 x1 NVN 0x1 the GPU drew, finalized by the game, sampled again at frame 35228 (drawn at 35148)
[hos host] vk: texture #3290 0x10000000000 106x105 x1 NVN 0x1 the GPU drew, finalized by the game, sampled again at frame 35228 (drawn at 35148)
[hos host] vk: 9 textures retired (1725 left, 3436 MB): budget 0, drawn over 0, dead targets 9
[hos host] vk: 29 textures retired (1718 left, 3436 MB): budget 0, drawn over 0, dead targets 29
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 59 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 266 dirty pages from their submits' captures, 61946 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 325 runs, 460.3 MB compared; 65 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 11437 in captures, 0 only in the collection, 66 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: 4 textures retired (1714 left, 3435 MB): budget 0, drawn over 4, dead targets 0
[hos host] vk: 1 textures retired (1713 left, 3435 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: a frame: 12 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.46, present 0.07, draw 0.71, descriptors 0.40, texture lookups 0.04, uploads 0.02, pipelines 0.02, programs 0.05, commands 0.18, dispatch 0.06, memory sync 0.19, queue submit 0.19, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 3.73 MB synced in 674.6 copies, 7.08 MB written back
[hos host] vk: 35280 presents, 60.0 fps; a frame: 290 draws (0 skipped), 2 dispatches, 134 passes, 82 barriers, 6 submits, 0.3 uploads (0.1 MB), 461 ub updates (199 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1713 textures (3435 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 641.8 full barriers recorded, 106.6 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 1.8; 0x10: 1.8; 0x11: 1.0; 0x12: 70.7; 0x13: 1.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.8 ms a frame (the longest submission 4.2 ms); 0.3 textures made a frame
[hos host] vk: a frame: 0.08 MB unswizzled on the CPU in 0.01 ms
[hos Presentation Thread] vk: capture: a submit 0.16 ms (lock 0.07, scan 0.03 over 637 ranges, 1760 MB), 321 pages written, 321 copied (1.3 MB)
[hos host] vk: a capture taken (ms): all 0.004; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (142 MB), 11 spare buffers, 59 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.07
[hos OptimizeChangeBanc] nvn: 2150000 recordings made, 31113 live copies (6.2 MB), 1237 texture copies; 2 command buffers' segments (2.1 MB)
[hos host] vk: render targets drawn over from another start, let go: 1487 so far (3359 MB)
[hos host] vk: recorder: 1801153 packets run in 10.0 s (busy 0.33 s, spun idle 0.93 s, slept 5119 times, 693 of them under 200 us), 0 calls made directly (no room); the replay waited for it 16028 times, 42.04 ms in all, the longest 0.09 ms; replay_mu unlock 4950/20.15 ms (max 0.05), vkEndCommandBuffer 5539/14.07 ms (max 0.09), vkResetDescriptorPool 5539/7.82 ms (max 0.05)
[hos host] vk: mirror syncs (600 submits): 315 dirty pages from their submits' captures, 63909 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 345 runs, 488.7 MB compared; 69 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 10228 in captures, 837 only in the collection, 69 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 24 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: 4 textures retired (1713 left, 3433 MB): budget 0, drawn over 4, dead targets 0
[hos Presentation Thread] vk: capture: a submit 0.16 ms (lock 0.06, scan 0.03 over 1095 ranges, 2001 MB), 339 pages written, 339 copied (1.3 MB)
[hos host] vk: a capture taken (ms): all 0.004; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (90 MB), 9 spare buffers, 59 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 29, 563 MB with memory of 716 MB (152 MB spared); blocks given memory later 472, given back 1053; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 129 binds (14.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 276 dirty pages from their submits' captures, 67304 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 375 runs, 531.2 MB compared; 75 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 12754 in captures, 68 only in the collection, 75 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.08
[hos host] vk: memory: working set 11238 MB (peak 11239), private 18797 MB, staging 128 MB in 2 arenas
[hos host] vk: memory heaps: heap 0 (device): 103 blocks 5673 MB, 10871 allocations 4854 MB; used 6323 of 15280 MB; heap 1 (system): 12 blocks 448 MB, 50 allocations 429 MB; used 1663 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 9 images 125 MB; 2 free ranges, the largest 2 MB
[hos host] vk: image blocks (render targets): 7 blocks 896 MB, 124 images 588 MB; 37 free ranges, the largest 66 MB
[hos host] vk: image blocks (textures, compacted): 18 blocks 2304 MB, 1586 images 2029 MB; 483 free ranges, the largest 128 MB
[hos host] vk: render target images: 780 reused from the pool, 775 made new, 651 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6323 MB used of 15280 MB allowed (819 MB of it free in the blocks); textures 3433 MB (budget 10928 MB), 1713 textures
[hos host] vk: textures: decoded ASTC 1834 MB, rendered 1000 MB (110 drawn in one frame, kept: 33685 KB), other 344 MB; used in the last 8 presents 195 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 30408 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 30408 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 30408 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 30408 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 30408 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 32495 presents ago
[hos host] vk: 54 MB: 0x100022cda00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 30888 presents ago
[hos host] vk: 54 MB: 0x10002121800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 30694 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 14 (8096 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 9 (1583 KB); 592x49x1 NVN 0x25: 1 (113 KB); 853x480x1 NVN 0x29: 1 (3198 KB); 853x480x1 NVN 0x34: 2 (3198 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 129 waited for it, 0.16 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 34.0 ms; VRAM 6.2 of 14.9 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 4898 queued, 4898 loaded (median 0.51 ms, 99th percentile 3.21 ms, worst 45.66 ms, 3743 ms and 1111.7 MB read in all); 6790 programs (1591 of them compute variants without their code, 0 graphics programs no note names), 9209 graphics pipelines (0 not in a cache), 680 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 726 pipelines made at create taken by draws; 2554 create calls with nothing kept for their stages, 0 before the index; units 7452 (4898 ready, 0 loading), 13767 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 680 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 1 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.79, present 0.06, draw 0.57, descriptors 0.35, texture lookups 0.02, uploads 0.00, pipelines 0.01, programs 0.04, commands 0.13, dispatch 0.06, memory sync 0.68, queue submit 0.17, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (563 MB): 3.53 MB synced in 674.8 copies, 7.08 MB written back
[hos host] vk: 35400 presents, 60.0 fps; a frame: 156 draws (0 skipped), 2 dispatches, 128 passes, 76 barriers, 6 submits, 0.0 uploads (0.0 MB), 459 ub updates (198 overlays), GPU-bound wait 0.0 ms (recording slots only); 9371 pipelines (1679 ms), 0 programs (0 failed), 1713 textures (3433 MB)
[hos host] vk: host time in GPU resource waits: 0.07 ms a frame (fences 0.01, timelines 0.06, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 628.4 full barriers recorded, 95.4 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 0.0; 0x10: 0.0; 0x11: 1.0; 0x12: 68.2; 0x13: 1.0; 0x21: 2.0; 0x92: 4.0;
[hos host] vk: GPU time 4.7 ms a frame (the longest submission 4.4 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 2.22 ms a frame (submits 1.51, presents 0.34, others 0.38), idle 14.44; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 66.24 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 147 captures at a CPU signal; the submits' waits read in 0.008 ms a frame; readbacks: 0 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 2.23 ms after its hand-over (8.22 at most)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos ModuleSystemWorker3] vcores: 108935 takes, 33863 waits (mean 45 us, longest 53.3 ms), 16706 kicks, 16458 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: readback pages refreshed from guest memory: 2207583 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: mirror syncs (600 submits): 119 dirty pages from their submits' captures, 39511 from earlier ones', 60 from guest memory as it was at the replay; 24 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 263 runs, 311.8 MB compared; 75 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 6046 in captures, 781 only in the collection, 44 only by the replay itself
[hos host] vk: read live, by pool: 0x1038400000 (4 MB, captured, state 2): 60;
[hos Presentation Thread] vk: capture: a submit 0.15 ms (lock 0.03, scan 0.03 over 816 ranges, 2023 MB), 302 pages written, 302 copied (1.2 MB)
[hos host] vk: a capture taken (ms): all 0.004; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (122 MB), 9 spare buffers, 59 texture pages copied (0 MB)
[hos host] vk: 1 textures retired (1712 left, 3429 MB): budget 0, drawn over 1, dead targets 0
[hos Presentation Thread] vi: 35492 frames presented (59.9 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 16, 15.5-17.8 272, 17.8-22 9, 22-30 1, 30-40 1, over 40 1
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.10
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 1.13, present 0.07, draw 0.19, descriptors 0.11, texture lookups 0.01, uploads 0.00, pipelines 0.01, programs 0.01, commands 0.05, dispatch 0.02, memory sync 0.63, queue submit 0.16, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (575 MB): 1.23 MB synced in 242.0 copies, 2.42 MB written back
[hos host] vk: 35520 presents, 59.7 fps; a frame: 47 draws (0 skipped), 1 dispatches, 44 passes, 26 barriers, 6 submits, 0.0 uploads (0.0 MB), 157 ub updates (68 overlays), GPU-bound wait 0.0 ms (recording slots only); 9603 pipelines (1733 ms), 0 programs (0 failed), 1712 textures (3429 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 236.6 full barriers recorded, 40.5 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x11: 0.3; 0x12: 23.2; 0x13: 0.3; 0x21: 0.7; 0x92: 1.4;
[hos host] vk: GPU time 2.0 ms a frame (the longest submission 4.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: sparse mirrors: 29, 575 MB with memory of 716 MB (140 MB spared); blocks given memory later 672, given back 1057; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 139 binds (15.7 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 60 dirty pages from their submits' captures, 1364 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 80 runs, 0.0 MB compared; 80 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 709 in captures, 3 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 76 live (1132 MB), 0 retired still imported (0 MB), 7 retired given back (264 MB)
[hos Presentation Thread] vk: capture: a submit 0.10 ms (lock 0.02, scan 0.03 over 915 ranges, 2031 MB), 249 pages written, 249 copied (1.0 MB)
[hos host] vk: a capture taken (ms): all 0.004; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (122 MB), 8 spare buffers, 59 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.04
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 120 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 32 dirty pages from their submits' captures, 1229 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 77 runs, 0.0 MB compared; 77 pages read into the shadows; 300 MB of shadows; pages the shadows knew that the CPU wrote: 322 in captures, 0 only in the collection, 0 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a frame: 0 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 0.47, present 0.07, draw 0.04, descriptors 0.01, texture lookups 0.00, uploads 0.00, pipelines 0.00, programs 0.00, commands 0.02, dispatch 0.00, memory sync 0.28, queue submit 0.15, slot wait 0.02
[hos host] vk: a frame: mirrors 98 (575 MB): 0.07 MB synced in 16.9 copies, 0.00 MB written back
[hos host] vk: 35640 presents, 60.0 fps; a frame: 5 draws (0 skipped), 0 dispatches, 2 passes, 1 barriers, 6 submits, 0.0 uploads (0.0 MB), 1 ub updates (1 overlays), GPU-bound wait 0.0 ms (recording slots only); 9790 pipelines (1774 ms), 0 programs (0 failed), 1712 textures (3429 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 34.2 full barriers recorded, 13.8 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x12: 1.0;
[hos host] vk: GPU time 0.4 ms a frame (the longest submission 0.5 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: capture: a submit 0.11 ms (lock 0.04, scan 0.03 over 1085 ranges, 2048 MB), 218 pages written, 218 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (122 MB), 7 spare buffers, 59 texture pages copied (0 MB)
[hos ModuleSystemWorker3] nvn: 2200000 recordings made, 33602 live copies (5.5 MB), 1237 texture copies; 5 command buffers' segments (2.3 MB)
[hos host] vk: import 3.3 ms: commit+properties 0.9, buffer 0.0, allocate 2.4, bind+address 0.0
[hos host] vk: pool 0x108c711000+0xe72e000 imported in 3.3 ms as 0x108c000000..0x109b000000 (84 imports, 68 ms in all)
[hos host] vk: pool 0x108c000000 remade larger (8 retired)
[hos host] vk: pool 0x108c000000..0x109b000000: 128716 KB the CPU wrote since retired pool 0x108c000000's last sync kept from guest memory, not its mirror
[hos host] vk: pool 0x108c000000..0x109b000000: mirror made with the GPU's contents of 1 retired pool(s)
[hos host] vk: import 4.3 ms: commit+properties 0.2, buffer 0.0, allocate 4.2, bind+address 0.0
[hos host] vk: pool 0x110ff1ea00+0x2685000 imported in 4.3 ms as 0x110fc00000..0x1112800000 (85 imports, 72 ms in all)
[hos host] vk: import 2.1 ms: commit+properties 0.1, buffer 0.0, allocate 2.0, bind+address 0.0
[hos host] vk: pool 0x7fd3bc4000+0x40700 imported in 2.1 ms as 0x7fd3400000..0x7fd4c00000 (87 imports, 75 ms in all)
[hos host] vk: pool 0x7fd3400000..0x7fd4c00000 took in 2 pools
[hos host] vk: slow submit: 71.0 ms: draw 54.6 descriptors 35.4 texture lookups 25.7 uploads 17.9 programs 8.5 commands 10.2
[hos host] vk: import 4.2 ms: commit+properties 0.6, buffer 0.0, allocate 3.6, bind+address 0.0
[hos host] vk: pool 0x1180eeab80+0x480 imported in 4.2 ms as 0x1178400000..0x1181c00000 (94 imports, 82 ms in all)
[hos host] vk: pool 0x1178400000..0x1181c00000: mirror made with the GPU's contents of 1 retired pool(s)
[hos host] vk: write-back diff: a shadow for pool 0x1178400000 (152 MB; 344 MB of shadows)
[hos host] vk: write-back diff: a shadow for pool 0x1038000000 (4 MB; 348 MB of shadows)
[hos host] vk: pool 0x7fb4000000..0x7fb5800000: mirror made with the GPU's contents of 1 retired pool(s)
[hos host] vk: pool 0x7fc0800000..0x7fc2400000 took in 2 pools
[hos host] vk: slow submit: 26.7 ms: draw 14.3 texture lookups 1.9 commands 13.6
[hos host] vk: sampler 542 is nearest: min filter 0, mag filter 0, wrap 5/5/5, lod 0..15 bias 0, aniso 1, compare 0
[hos host] vk: NVN2 program 55e5c68554e506d6 (stage 7) lowered with extended registers (291 REGMAP words)
[hos host] vk: texture #3053 0x10001ef0600 320x180 x1 NVN 0x3f the GPU drew, finalized by the game, sampled again at frame 35695 (drawn at 35441)
[hos host] vk: NVN2 program db295591c4c3f510 (stage 7) lowered with extended registers (331 REGMAP words)
[hos host] vk: NVN2 program db295591c4c3f510 (stage 7) lowered with extended registers (331 REGMAP words)
[hos host] vk: NVN2 program bd0ee311e887f8e4 (stage 0) lowered with extended registers (1132 REGMAP words)
[hos host] vk: texture 0x10cb1e5600 768x768x1 x1 levels 10 NVN 0x7b -> vk 37 (ASTC decoded) (2000 textures, 4307 MB)
[hos host] vk: NVN2 program 02a1c61f7738a6e8 (stage 0) lowered with extended registers (1142 REGMAP words)
[hos host] vk: NVN2 program 41becbf7e16bbd79 (stage 0) lowered with extended registers (1135 REGMAP words)
[hos host] vk: NVN2 program 5cecd4d153b207e0 (stage 0) lowered with extended registers (1134 REGMAP words)
[hos host] vk: NVN2 program 6e1680dab0c33f76 (stage 0) lowered with extended registers (1124 REGMAP words)
[hos host] vk: NVN2 program 41becbf7e16bbd79 (stage 0) lowered with extended registers (1135 REGMAP words)
[hos host] vk: NVN2 program 7d8136fe8a9978f0 (stage 0) lowered with extended registers (1148 REGMAP words)
[hos host] vk: slow submit: 125.7 ms: draw 67.3 descriptors 42.5 texture lookups 95.2 uploads 16.8 programs 23.4
[hos sead::MainThread] nvn: GPU waits in 5 s: 4 sync waits (377 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: slow submit: 18.5 ms: draw 2.0 descriptors 1.5 texture lookups 1.1
[hos host] vk: texture #3028 0x10000000000 256x256 x1 NVN 0x3f the GPU drew, finalized by the game, sampled again at frame 35696 (drawn at 35441)
[hos host] vk: replay reads of guest memory as submitted: 3540000 (2882196 pages from the captures)
[hos host] vk: mirror of pool 0x108c000000 (132 MB) given back: retired, 281357 submissions since its sync, GPU-only data, GPU-written
[hos host] vk: mirror of pool 0x1178400000 (108 MB) given back: retired, 52 submissions since its sync, GPU-only data, GPU-written
[hos host] vk: mirror of pool 0x7fb4800000 (4 MB) given back: retired, 50 submissions since its sync
[hos host] vk: slow submit: 24.9 ms:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.10
[hos ModuleSystemWorker1] vk: readbacks of GPU results: 7 of 3000 waited for their write-back, 0.31 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: texture #3497 0x10001410600 1707x960 NVN 0xa: the GPU wrote its storage (submission 34945): uploaded again
[hos host] vk: upload over a drawn image: #3497 0x10001410600 1707x960x1 x1 NVN 0xa at present 35698 (texture frame 35699), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos host] vk: texture 0x10001410600 1707x960x1 x1 levels 1 NVN 0xa (6848 KB of storage) re-uploaded (its memory was written; flags 0x8): a GPU write into its storage, 6848 KB of it, over what the GPU wrote (finalized since)
[hos host] vk: NVN2 program a1eb212ddaf83e1f (stage 0) lowered with extended registers (1135 REGMAP words)
[hos host] vk: sparse mirrors: 57, 1000 MB with memory of 1264 MB (263 MB spared); blocks given memory later 683, given back 1058; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 176 binds (22.6 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 11122 dirty pages from their submits' captures, 11589 from earlier ones', 5482 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 945 runs, 334.3 MB compared; 26190 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 2023 in captures, 184 only in the collection, 3 only by the replay itself
[hos host] vk: read live, by pool: 0x1178400000 (152 MB, captured, state 2): 2283; 0x104e000000 (24 MB, captured, state 2): 1406; 0x113b400000 (24 MB, captured, state 2): 625; 0x103d000000 (8 MB, captured, state 2): 373; 0x1137000000 (8 MB, captured, state 2): 271; 0x1038000000 (4 MB, captured, state 2): 261; 0x1159c00000 (36 MB, captured, state 2): 142; 0x1163400000 (8 MB, captured, state 2): 106;
[hos host] vk: imports: 90 live (1592 MB), 0 retired still imported (0 MB), 15 retired given back (532 MB)
[hos host] vk: 38 textures retired (2091 left, 4247 MB): budget 0, drawn over 10, dead targets 28
[hos host] vk: NVN2 program 40d0c0768e874600 (stage 7) lowered with extended registers (331 REGMAP words)
[hos BaseProcExecutor0] map: HyruleField_Adult (adult)
[hos host] vk: pool 0x7fbf000000..0x7fbfc00000: mirror made with the GPU's contents of 1 retired pool(s)
[hos host] vk: pool 0x7fbcfc5e00+0x14a0 imported in 2.4 ms as 0x7fb8800000..0x7fbdc00000 (110 imports, 94 ms in all)
[hos host] vk: pool 0x7fb8800000..0x7fbdc00000 took in 2 pools
[hos host] vk: pool 0x7fb8800000..0x7fbdc00000: mirror made with the GPU's contents of 2 retired pool(s)
[hos host] vk: pool 0x7fd260ce00+0x16488 imported in 2.1 ms as 0x7fd2400000..0x7fd2800000 (111 imports, 96 ms in all)
[hos host] vk: pool 0x7fa7ca9300+0x117c8 imported in 2.0 ms as 0x7fa7c00000..0x7fa8400000 (112 imports, 98 ms in all)
[hos host] vk: slow submit: 30.8 ms: draw 3.0 descriptors 1.5 texture lookups 1.7
[hos host] vk: upload over a drawn image: #1088 0x10000e38800 427x240x1 x1 NVN 0x14 at present 35708 (texture frame 35709), finalized, 370 KB dirty in 1 ranges
[hos host] vk: slow submit: 57.4 ms: draw 55.0 descriptors 32.3 texture lookups 30.1 uploads 23.7 programs 15.6 commands 6.7
[hos host] vk: 41 textures retired (2453 left, 5021 MB): budget 0, drawn over 1, dead targets 40
[hos host] vk: mirror of pool 0x7fbf800000 (4 MB) given back: retired, 44 submissions since its sync
[hos host] vk: mirror of pool 0x7fbd800000 (4 MB) given back: retired, 36 submissions since its sync
[hos host] vk: mirror of pool 0x7fb8800000 (60 MB) given back: retired, 37 submissions since its sync
[hos host] vk: texture 0x1169f59000 260x260x1 x1 levels 1 NVN 0x4b -> vk 141 (2500 textures, 5047 MB)
[hos] guest backtrace: lr 0x804fc1ec 0x83b6f194 0x83b6f080
[hos] guest backtrace: lr 0x8348c5e0 0x83b6f08c
[hos] guest backtrace: lr 0x804fc1ec 0x83b6f194 0x83b6f080
[hos] guest backtrace: lr 0x8348c5e0 0x83b6f08c
[hos] guest backtrace: lr 0x804fc1ec 0x83b6f194 0x83b6f080
[hos] guest backtrace: lr 0x8348c5e0 0x83b6f08c
[hos host] vk: texture #4320 0x1169d9f000 260x260 x1 NVN 0x4b (compressed) over storage render targets took: uploaded from the game's memory all the same
[hos host] vk: pool 0x7fdc000000..0x7fdd800000 took in 2 pools
[hos host] vk: pool 0x7fdc000000..0x7fdd800000: 4096 KB the CPU wrote since retired pool 0x7fdc800000's last sync kept from guest memory, not its mirror
[hos host] vk: pool 0x7fdc000000..0x7fdd800000: mirror made with the GPU's contents of 2 retired pool(s)
[hos host] vk: upload over a drawn image: #1088 0x10000e38800 427x240x1 x1 NVN 0x14 at present 35710 (texture frame 35711), finalized, 370 KB dirty in 1 ranges
[hos sead::MainThread] nvn: the game sets present interval 1 -> 2
[hos sead::MainThread] nvn: the game sets present interval 2 -> 1
[hos host] vk: mirror of pool 0x7fdc800000 (4 MB) given back: retired, 5284 submissions since its sync
[hos host] vk: mirror of pool 0x7fdc000000 (8 MB) given back: retired, 25 submissions since its sync
[hos ModuleSystemWorker4] vcores: 171990 takes, 82373 waits (mean 157 us, longest 1001.2 ms), 39882 kicks, 38802 yields, 2 starved grants, 0 escapes in 5 s
[hos host] vk: texture #1088 0x10000e38800 427x240 NVN 0x14: the GPU wrote its storage (submission 249977): uploaded again
[hos host] vk: upload over a drawn image: #1088 0x10000e38800 427x240x1 x1 NVN 0x14 at present 35711 (texture frame 35712), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos sead::MainThread] nvn: the game sets present interval 1 -> 2
[hos sead::MainThread] nvn: the game sets present interval 2 -> 1
[hos host] vk: replay reads of guest memory as submitted: 3560000 (2895070 pages from the captures)
[hos sead::MainThread] nvn: the game sets present interval 1 -> 2
[hos sead::MainThread] nvn: the game sets present interval 2 -> 1
[hos host] vk: slow submit: 21.2 ms: draw 17.9 descriptors 6.1 texture lookups 4.4 uploads 3.3 programs 10.1 commands 1.1
[hos host] vk: 43 textures retired (2753 left, 5392 MB): budget 0, drawn over 0, dead targets 43
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 2416 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: mirror syncs (600 submits): 1931 dirty pages from their submits' captures, 42244 from earlier ones', 1206 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4446 runs, 1453.8 MB compared; 237 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 11050 in captures, 72 only in the collection, 20 only by the replay itself
[hos host] vk: read live, by pool: 0x1051800000 (4 MB, captured, state 2): 830; 0x1038400000 (4 MB, captured, state 2): 376;
[hos host] vk: replay reads of guest memory as submitted: 3580000 (2909873 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 2239736 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: replay reads of guest memory as submitted: 3600000 (2923060 pages from the captures)
[hos host] vk: sparse mirrors: 83, 1112 MB with memory of 1468 MB (355 MB spared); blocks given memory later 882, given back 1058; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 221 binds (26.8 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 1461 dirty pages from their submits' captures, 34009 from earlier ones', 7 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3833 runs, 1103.6 MB compared; 30 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 8826 in captures, 14 only in the collection, 13 only by the replay itself
[hos host] vk: read live, by pool: 0x7fd2400000 (4 MB, captured, state 2): 4; 0x7fd9400000 (4 MB, captured, state 2): 3;
[hos host] vk: imports: 104 live (1720 MB), 0 retired still imported (0 MB), 21 retired given back (616 MB)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #135000: event 0x100d6c8014 mode 0 value 135000 (lr 0x80660bcc)
[hos host] vk: program picks: 6328828 kept (1954102 by the last picks' textures, a uniform buffer bound since), 1505 new, 7869666 with other textures (of 14200000)
[hos host] vk: replay reads of guest memory as submitted: 3620000 (2935309 pages from the captures)
[hos host] vk: 23 textures retired (2744 left, 5398 MB): budget 0, drawn over 0, dead targets 23
[hos host] vk: mirror syncs (600 submits): 300 dirty pages from their submits' captures, 32817 from earlier ones', 133 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3699 runs, 1116.7 MB compared; 28 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9320 in captures, 8 only in the collection, 15 only by the replay itself
[hos host] vk: read live, by pool: 0x1065800000 (8 MB, captured, state 2): 123; 0x7fd9400000 (4 MB, captured, state 2): 9; 0x7fd2400000 (4 MB, captured, state 2): 1;
[hos host] vk: replay reads of guest memory as submitted: 3640000 (2948177 pages from the captures)
[hos Presentation Thread] vi: 35759 frames presented (53.3 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 27, 15.5-17.8 216, 17.8-22 13, 22-30 4, 30-40 3, over 40 4
[hos host] vk: 2 textures retired (2775 left, 5404 MB): budget 0, drawn over 0, dead targets 2
[hos Presentation Thread] vk: capture: a submit 0.17 ms (lock 0.06, scan 0.03 over 468 ranges, 3189 MB), 385 pages written, 385 copied (1.5 MB)
[hos host] vk: a capture taken (ms): all 0.014; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.007, bytes copied 0.000; 25 kept (146 MB), 8 spare buffers, 2430 texture pages copied (9 MB)
[hos host] vk: 5870 programs from the program cache
[hos host] vk: a frame: 161 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 9.83, present 0.17, draw 5.39, descriptors 2.34, texture lookups 1.67, uploads 0.71, pipelines 0.14, programs 1.20, commands 1.34, dispatch 0.65, memory sync 0.67, queue submit 0.47, slot wait 0.04
[hos host] vk: a frame: mirrors 160 (1114 MB): 12.04 MB synced in 725.4 copies, 38.04 MB written back
[hos host] vk: 35760 presents, 46.8 fps; a frame: 1625 draws (0 skipped), 114 dispatches, 99 passes, 87 barriers, 6 submits, 8.9 uploads (5.5 MB), 57 ub updates (42 overlays), GPU-bound wait 0.0 ms (recording slots only); 10175 pipelines (1895 ms), 0 programs (0 failed), 2775 textures (5404 MB)
[hos host] vk: host time in GPU resource waits: 5.91 ms a frame (fences 0.03, timelines 5.89, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 399.5 full barriers recorded, 132.4 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.2; 0x8: 1.5; 0x9: 0.6; 0x10: 1.1; 0x11: 21.8; 0x12: 44.9; 0x13: 1.1; 0x21: 2.1; 0x28: 8.8; 0x92: 1.6; 0x97: 0.6; 0x9b: 0.3;
[hos host] vk: GPU time 5.0 ms a frame (the longest submission 7.3 ms); 10.1 textures made a frame
[hos host] vk: a frame: 2.83 MB unswizzled on the CPU in 0.36 ms
[hos host] vk: replay reads of guest memory as submitted: 3660000 (2961420 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 145 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 83, 1117 MB with memory of 1468 MB (350 MB spared); blocks given memory later 967, given back 1058; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 226 binds (27.4 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 2456 dirty pages from their submits' captures, 34232 from earlier ones', 21 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3720 runs, 1036.0 MB compared; 26 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 8878 in captures, 9 only in the collection, 13 only by the replay itself
[hos host] vk: read live, by pool: 0x7fd9400000 (4 MB, captured, state 2): 21;
[hos host] vk: imports: 104 live (1720 MB), 0 retired still imported (0 MB), 21 retired given back (616 MB)
[hos host] vk: replay reads of guest memory as submitted: 3680000 (2973856 pages from the captures)
[hos host] vk: 1 textures retired (2774 left, 5404 MB): budget 0, drawn over 0, dead targets 1
[hos host] vk: mirror syncs (600 submits): 395 dirty pages from their submits' captures, 35295 from earlier ones', 8 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3841 runs, 1106.7 MB compared; 25 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9430 in captures, 11 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool: 0x7fd9400000 (4 MB, captured, state 2): 5; 0x7fd2400000 (4 MB, captured, state 2): 3;
[hos host] vk: replay reads of guest memory as submitted: 3700000 (2986300 pages from the captures)
[hos ModuleSystemWorker5] nvn: CommandBufferWaitEvent #250000: event 0x100d6c8034 mode 0 value 136091 (now 136072) (lr 0x80662a68)
[hos host] vk: replay reads of guest memory as submitted: 3720000 (2998773 pages from the captures)
[hos host] vk: program picks: 6490089 kept (2041506 by the last picks' textures, a uniform buffer bound since), 1509 new, 7908401 with other textures (of 14400000)
[hos host] vk: a submit's memory work (ms): maps 0.01, capture taken 0.01, writes collected 0.11
[hos host] vk: sparse mirrors: 83, 1153 MB with memory of 1468 MB (314 MB spared); blocks given memory later 1599, given back 1110; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 254 binds (30.1 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 279 dirty pages from their submits' captures, 34092 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3608 runs, 1032.0 MB compared; 25 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9394 in captures, 9 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 104 live (1720 MB), 0 retired still imported (0 MB), 21 retired given back (616 MB)
[hos host] vk: mirror of pool 0x1043c00000 (4 MB) given back: idle, 6017 submissions since its sync
[hos host] vk: replay reads of guest memory as submitted: 3740000 (3011172 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 2306221 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 113 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: mirror syncs (600 submits): 287 dirty pages from their submits' captures, 31492 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 3729 runs, 1104.8 MB compared; 23 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 8754 in captures, 9 only in the collection, 15 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 3760000 (3023992 pages from the captures)
[hos host] vk: 1 textures retired (2774 left, 5404 MB): budget 0, drawn over 0, dead targets 1
[hos host] vk: replay reads of guest memory as submitted: 3780000 (3037241 pages from the captures)
[hos OptimizeChangeBanc] nvn: 2250000 recordings made, 38994 live copies (17.4 MB), 1350 texture copies; 2 command buffers' segments (4.1 MB)
[hos host] vk: 1 textures retired (2774 left, 5404 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: sparse mirrors: 82, 1176 MB with memory of 1464 MB (287 MB spared); blocks given memory later 1984, given back 1110; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 281 binds (32.7 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 187 dirty pages from their submits' captures, 32546 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2840 runs, 1089.4 MB compared; 20 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9289 in captures, 5 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 104 live (1720 MB), 0 retired still imported (0 MB), 21 retired given back (616 MB)
[hos host] vk: replay reads of guest memory as submitted: 3800000 (3050666 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 145 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 259 dirty pages from their submits' captures, 32240 from earlier ones', 4 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2826 runs, 1084.1 MB compared; 21 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9240 in captures, 7 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool: 0x7fd9400000 (4 MB, captured, state 2): 4;
[hos host] vk: 1 textures retired (2773 left, 5403 MB): budget 0, drawn over 0, dead targets 1
[hos host] vk: replay reads of guest memory as submitted: 3820000 (3063944 pages from the captures)
[hos host] vk: program picks: 6649979 kept (2129182 by the last picks' textures, a uniform buffer bound since), 1509 new, 7948511 with other textures (of 14600000)
[hos Presentation Thread] vk: capture: a submit 0.23 ms (lock 0.12, scan 0.03 over 574 ranges, 3277 MB), 395 pages written, 395 copied (1.5 MB)
[hos host] vk: a capture taken (ms): all 0.010; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 25 kept (160 MB), 12 spare buffers, 2904 texture pages copied (11 MB)
[hos host] vk: 1 textures retired (2776 left, 5406 MB): budget 0, drawn over 0, dead targets 1
[hos host] vk: sparse mirrors: 82, 1181 MB with memory of 1464 MB (282 MB spared); blocks given memory later 2060, given back 1110; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 294 binds (33.7 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 256 dirty pages from their submits' captures, 30691 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2666 runs, 1036.6 MB compared; 24 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9254 in captures, 4 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 104 live (1720 MB), 0 retired still imported (0 MB), 21 retired given back (616 MB)
[hos host] vk: replay reads of guest memory as submitted: 3840000 (3077317 pages from the captures)
[hos sead::MainThread] vk: readbacks of GPU results: 1374 of 3000 waited for their write-back, 0.10 ms each; 0 looked at the stopped queues first, 9 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: (its written part: 1 of 1 KB readable, 269 bytes not zero; levels L0)
[hos host] vk: texture 0x110b62c200 2064x2064x1 x1 levels 1 NVN 0x4b (4192 KB of storage) re-uploaded (its memory was written; flags 0): what the CPU wrote, 1 KB of it
[hos host] vk: replay reads of guest memory as submitted: 3860000 (3090470 pages from the captures)
[hos host] vk: (its written part: 1 of 1 KB readable, 269 bytes not zero; levels L0)
[hos host] vk: texture 0x110b62c200 2064x2064x1 x1 levels 1 NVN 0x4b (4192 KB of storage) re-uploaded (its memory was written; flags 0): what the CPU wrote, 1 KB of it
[hos host] vk: mirror syncs (600 submits): 165 dirty pages from their submits' captures, 30660 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2809 runs, 1083.3 MB compared; 23 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 8683 in captures, 2 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: mirror of pool 0x7fc2400000 (4 MB) given back: idle, 6060 submissions since its sync
[hos host] vk: recorder: 3986823 packets run in 10.0 s (busy 0.52 s, spun idle 2.03 s, slept 5013 times, 1003 of them under 200 us), 0 calls made directly (no room); the replay waited for it 24952 times, 51.33 ms in all, the longest 0.13 ms; vkEndCommandBuffer 9730/28.42 ms (max 0.13), replay_mu unlock 5237/12.08 ms (max 0.10), vkResetDescriptorPool 9730/10.07 ms (max 0.04), direct recording 183/0.42 ms (max 0.03), vkQueueBindSparse 57/0.32 ms (max 0.01), vkDestroyImageView 12/0.02 ms (max 0.00)
[hos host] vk: 4 textures retired (2781 left, 5434 MB): budget 0, drawn over 4, dead targets 0
[hos host] vk: a frame: 350 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 11.17, present 0.12, draw 6.25, descriptors 2.27, texture lookups 0.11, uploads 0.02, pipelines 0.27, programs 1.05, commands 2.02, dispatch 0.85, memory sync 0.93, queue submit 0.74, slot wait 0.07
[hos host] vk: a frame: mirrors 160 (1177 MB): 8.17 MB synced in 1289.4 copies, 68.50 MB written back
[hos host] vk: 35880 presents, 60.2 fps; a frame: 3459 draws (0 skipped), 185 dispatches, 182 passes, 153 barriers, 6 submits, 0.1 uploads (0.2 MB), 84 ub updates (58 overlays), GPU-bound wait 0.1 ms (recording slots only); 10597 pipelines (2012 ms), 0 programs (0 failed), 2781 textures (5434 MB)
[hos host] vk: host time in GPU resource waits: 1.12 ms a frame (fences 0.04, timelines 1.07, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 630.5 full barriers recorded, 236.0 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 7.1; 0x8: 3.0; 0x9: 1.0; 0x10: 5.1; 0x11: 38.0; 0x12: 72.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 9.0 ms a frame (the longest submission 3.3 ms); 0.1 textures made a frame
[hos host] vk: a frame: 0.21 MB unswizzled on the CPU in 0.02 ms
[hos host] vk: replay reads of guest memory as submitted: 3880000 (3103828 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 2372707 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: 1 textures retired (2780 left, 5434 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: sparse mirrors: 81, 1177 MB with memory of 1460 MB (282 MB spared); blocks given memory later 2060, given back 1110; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 294 binds (33.7 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 179 dirty pages from their submits' captures, 31625 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2815 runs, 1082.6 MB compared; 23 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9224 in captures, 5 only in the collection, 15 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 104 live (1720 MB), 0 retired still imported (0 MB), 21 retired given back (616 MB)
[hos host] vk: replay reads of guest memory as submitted: 3900000 (3117106 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.11
[hos host] vk: 1 textures retired (2779 left, 5434 MB): budget 0, drawn over 0, dead targets 1
[hos host] vk: replay reads of guest memory as submitted: 3920000 (3130442 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 209 dirty pages from their submits' captures, 31239 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2814 runs, 1083.3 MB compared; 24 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9235 in captures, 1 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: render targets drawn over from another start, let go: 1628 so far (3697 MB)
[hos host] vk: mirror of pool 0x1065800000 (8 MB) given back: idle, 6003 submissions since its sync
[hos host] vk: 80 mirrors given back (870 MB in all); 1174 MB of mirrors now, 108 MB of them idle and kept for what the GPU wrote there alone
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 27835 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: program picks: 6809594 kept (2216523 by the last picks' textures, a uniform buffer bound since), 1511 new, 7988894 with other textures (of 14800000)
[hos host] vk: replay reads of guest memory as submitted: 3940000 (3143755 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 145 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 80, 1174 MB with memory of 1452 MB (277 MB spared); blocks given memory later 2060, given back 1110; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 294 binds (33.7 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 180 dirty pages from their submits' captures, 31032 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2664 runs, 1016.6 MB compared; 24 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9235 in captures, 4 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 104 live (1720 MB), 0 retired still imported (0 MB), 21 retired given back (616 MB)
[hos host] vk: replay reads of guest memory as submitted: 3960000 (3157029 pages from the captures)
[hos host] vk: 2 textures retired (2778 left, 5434 MB): budget 0, drawn over 1, dead targets 1
[hos host] vk: mirror syncs (600 submits): 240 dirty pages from their submits' captures, 30205 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2810 runs, 1083.4 MB compared; 23 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 8627 in captures, 1 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 3980000 (3170345 pages from the captures)
[hos host] vk: replay reads of guest memory as submitted: 4000000 (3183499 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.14 ms (lock 0.01, scan 0.04 over 577 ranges, 3309 MB), 488 pages written, 488 copied (1.9 MB)
[hos host] vk: a capture taken (ms): all 0.035; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.032, bytes copied 0.000; 25 kept (138 MB), 9 spare buffers, 7575 texture pages copied (29 MB)
[hos host] vk: sparse mirrors: 80, 1174 MB with memory of 1452 MB (277 MB spared); blocks given memory later 2060, given back 1110; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 294 binds (33.7 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 244 dirty pages from their submits' captures, 31463 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2830 runs, 1103.3 MB compared; 23 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9234 in captures, 2 only in the collection, 15 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 104 live (1720 MB), 0 retired still imported (0 MB), 21 retired given back (616 MB)
[hos host] vk: replay reads of guest memory as submitted: 4020000 (3196938 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 2439337 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: program picks: 6970160 kept (2304608 by the last picks' textures, a uniform buffer bound since), 1511 new, 8028328 with other textures (of 15000000)
[hos host] vk: mirror syncs (600 submits): 254 dirty pages from their submits' captures, 31509 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2826 runs, 1103.6 MB compared; 24 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9242 in captures, 3 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 4040000 (3210282 pages from the captures)
[hos host] vk: 1 textures retired (2778 left, 5434 MB): budget 0, drawn over 0, dead targets 1
[hos host] vk: replay reads of guest memory as submitted: 4060000 (3223462 pages from the captures)
[hos host] vk: sparse mirrors: 80, 1174 MB with memory of 1452 MB (277 MB spared); blocks given memory later 2060, given back 1110; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 294 binds (33.7 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 226 dirty pages from their submits' captures, 31185 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2837 runs, 1087.4 MB compared; 24 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9242 in captures, 2 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 104 live (1720 MB), 0 retired still imported (0 MB), 21 retired given back (616 MB)
[hos ModuleSystemWorker1] nvn: CommandBufferWaitEvent #255000: event 0x100d6c8034 mode 0 value 139891 (now 139872) (lr 0x80662a68)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.03, writes collected 0.03
[hos host] vk: replay reads of guest memory as submitted: 4080000 (3236828 pages from the captures)
[hos host] vk: memory: working set 12868 MB (peak 12873), private 22855 MB, staging 256 MB in 4 arenas
[hos host] vk: memory heaps: heap 0 (device): 126 blocks 8085 MB, 21720 allocations 7643 MB; used 8738 of 15280 MB; heap 1 (system): 13 blocks 640 MB, 50 allocations 617 MB; used 2447 of 15215 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 9 images 125 MB; 2 free ranges, the largest 2 MB
[hos host] vk: image blocks (render targets): 8 blocks 1024 MB, 174 images 692 MB; 52 free ranges, the largest 101 MB
[hos host] vk: image blocks (textures, compacted): 31 blocks 3968 MB, 2604 images 3928 MB; 823 free ranges, the largest 37 MB
[hos host] vk: render target images: 800 reused from the pool, 933 made new, 759 destroyed from it; it holds 2 (0 MB)
[hos host] vk: VRAM: 8738 MB used of 15280 MB allowed (442 MB of it free in the blocks); textures 5434 MB (budget 10928 MB), 2779 textures
[hos host] vk: textures: decoded ASTC 3216 MB, rendered 1144 MB (123 drawn in one frame, kept: 48516 KB), other 727 MB; used in the last 8 presents 2314 MB
[hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 31008 presents ago
[hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 1 presents ago
[hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 1 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 33095 presents ago
[hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk: 54 MB: 0x1000262e400 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk: 54 MB: 0x1000247e200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 31008 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 41 (6977 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 39 (6862 KB); 592x49x1 NVN 0x25: 1 (113 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 202 waited for it, 3.53 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos ModuleSystemWorker2] nvn: CommandBufferSignalEvent #140000: event 0x100d6c8020 mode 0 value 140000 (lr 0x80664f14)
[hos host] vk: status: 600 frames, the slowest 256.1 ms; VRAM 8.5 of 14.9 GB; NVIDIA DLSS: 498 frames drawn, 1 made, jitter +0.219 -0.426 px, actor motion 31429 draws in 478 frames (0.722 ms CPU a frame; poses 31602 read at the draw, 0 copied later), its images 98 MB, its own 143 MB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 22 program records loaded (1.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 4, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 5809 queued, 5809 loaded (median 0.53 ms, 99th percentile 3.40 ms, worst 45.66 ms, 4599 ms and 1289.7 MB read in all); 7918 programs (1799 of them compute variants without their code, 0 graphics programs no note names), 10420 graphics pipelines (0 not in a cache), 810 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 1197 pipelines made at create taken by draws; 2984 create calls with nothing kept for their stages, 0 before the index; units 8793 (5809 ready, 0 loading), 15837 programs alive
[hos host] vk: module identifiers (play): 882 known, 0 learned in this run; 810 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 361 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 9.59, present 0.08, draw 5.88, descriptors 2.13, texture lookups 0.07, uploads 0.00, pipelines 0.25, programs 1.02, commands 1.86, dispatch 0.74, memory sync 0.38, queue submit 0.64, slot wait 0.06
[hos host] vk: a frame: mirrors 160 (1174 MB): 7.74 MB synced in 1236.7 copies, 68.14 MB written back
[hos host] vk: 36000 presents, 60.0 fps; a frame: 3488 draws (0 skipped), 154 dispatches, 181 passes, 144 barriers, 6 submits, 0.0 uploads (0.0 MB), 84 ub updates (58 overlays), GPU-bound wait 0.1 ms (recording slots only); 10597 pipelines (2012 ms), 0 programs (0 failed), 2779 textures (5434 MB)
[hos host] vk: host time in GPU resource waits: 0.23 ms a frame (fences 0.04, timelines 0.19, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 596.6 full barriers recorded, 227.0 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 6.7; 0x8: 3.0; 0x9: 1.0; 0x10: 4.7; 0x11: 30.3; 0x12: 72.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 8.8 ms a frame (the longest submission 3.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: queues ordered by their events: 155482 submissions stopped at a wait, 155482 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 255134, not met 0; captures at a CPU event's wait 7459, 0 of them at a wait met on arrival
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 2 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 17.61 ms a frame): its jobs 7.40 ms a frame (submits 5.51, presents 0.65, others 1.25), idle 10.21; the game waited for room at 3 presents, 0.95 ms each (0.00 a frame; 105.67 jobs queued at a present); 2 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 7.87 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 234 captures at a CPU signal; the submits' waits read in 0.024 ms a frame; readbacks: 1525 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 7.43 ms after its hand-over (388.53 at most)
[hos Presentation Thread] vi: real-time step on: ratio 1.003, game's frame rate 60
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 145 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 252 dirty pages from their submits' captures, 30922 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2682 runs, 1026.8 MB compared; 23 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9259 in captures, 3 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 4100000 (3250123 pages from the captures)
[hos AudioUserTaskThread] vcores: 299788 takes, 119811 waits (mean 72 us, longest 73.6 ms), 61361 kicks, 60363 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 72884 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos ModuleSystemWorker2] nvn: DrawMeshTasksIndirect: 120000 so far (x1 0x117c952000 x2 0 x3 0x117c952000 x4 0x168040)
[hos host] vk: 1 textures retired (2778 left, 5434 MB): budget 0, drawn over 0, dead targets 1
[hos host] vk: sparse mirrors: 80, 1174 MB with memory of 1452 MB (277 MB spared); blocks given memory later 2060, given back 1110; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 294 binds (33.7 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 184 dirty pages from their submits' captures, 30173 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2540 runs, 1100.1 MB compared; 19 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 8637 in captures, 1 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 104 live (1720 MB), 0 retired still imported (0 MB), 21 retired given back (616 MB)
[hos host] vk: replay reads of guest memory as submitted: 4120000 (3263338 pages from the captures)
[hos host] vk: program picks: 7130000 kept (2392746 by the last picks' textures, a uniform buffer bound since), 1512 new, 8068487 with other textures (of 15200000)
[hos host] vk: replay reads of guest memory as submitted: 4140000 (3276670 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 249 dirty pages from their submits' captures, 31342 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2545 runs, 1080.6 MB compared; 20 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9210 in captures, 1 only in the collection, 15 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] vk: readbacks of GPU results: 1548 of 3000 waited for their write-back, 0.02 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: replay reads of guest memory as submitted: 4160000 (3289954 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 2505545 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 80, 1174 MB with memory of 1452 MB (277 MB spared); blocks given memory later 2060, given back 1110; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 294 binds (33.7 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 195 dirty pages from their submits' captures, 31660 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2549 runs, 1080.0 MB compared; 23 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9216 in captures, 3 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 104 live (1720 MB), 0 retired still imported (0 MB), 21 retired given back (616 MB)
[hos host] vk: replay reads of guest memory as submitted: 4180000 (3303795 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.14 ms (lock 0.01, scan 0.04 over 577 ranges, 3309 MB), 498 pages written, 498 copied (1.9 MB)
[hos host] vk: a capture taken (ms): all 0.031; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.029, bytes copied 0.000; 25 kept (156 MB), 9 spare buffers, 7576 texture pages copied (29 MB)
[hos host] vk: 1 textures retired (2778 left, 5434 MB): budget 0, drawn over 0, dead targets 1
[hos Presentation Thread] vi: 36060 frames presented (60.1 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 15, 15.5-17.8 282, 17.8-22 4, 22-30 0, 30-40 0, over 40 0
[hos host] vk: replay reads of guest memory as submitted: 4200000 (3317269 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 260 dirty pages from their submits' captures, 31418 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2544 runs, 1085.1 MB compared; 24 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9229 in captures, 1 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: queues ordered by their events: 156000 submissions stopped at a wait, 155998 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 256978, not met 0; captures at a CPU event's wait 7459, 0 of them at a wait met on arrival
[hos host] vk: replay reads of guest memory as submitted: 4220000 (3330562 pages from the captures)
[hos host] vk: program picks: 7290361 kept (2480853 by the last picks' textures, a uniform buffer bound since), 1513 new, 8108125 with other textures (of 15400000)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 145 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 81, 1177 MB with memory of 1460 MB (282 MB spared); blocks given memory later 2060, given back 1110; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 295 binds (33.8 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 239 dirty pages from their submits' captures, 30804 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2424 runs, 1037.0 MB compared; 24 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9233 in captures, 2 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 104 live (1720 MB), 0 retired still imported (0 MB), 21 retired given back (616 MB)
[hos host] vk: replay reads of guest memory as submitted: 4240000 (3343712 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 243 dirty pages from their submits' captures, 30913 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2557 runs, 1103.2 MB compared; 23 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 8624 in captures, 2 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.04, writes collected 0.03
[hos host] vk: 1 textures retired (2778 left, 5434 MB): budget 0, drawn over 0, dead targets 1
[hos host] vk: replay reads of guest memory as submitted: 4260000 (3357129 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 90356 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 4280000 (3370394 pages from the captures)
[hos host] vk: sparse mirrors: 81, 1177 MB with memory of 1460 MB (282 MB spared); blocks given memory later 2060, given back 1110; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 295 binds (33.8 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 211 dirty pages from their submits' captures, 31565 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2556 runs, 1102.9 MB compared; 24 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9221 in captures, 5 only in the collection, 15 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 104 live (1720 MB), 0 retired still imported (0 MB), 21 retired given back (616 MB)
[hos host] vk: a frame: 370 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 9.78, present 0.09, draw 5.97, descriptors 2.16, texture lookups 0.07, uploads 0.00, pipelines 0.25, programs 1.04, commands 1.88, dispatch 0.71, memory sync 0.40, queue submit 0.66, slot wait 0.07
[hos host] vk: a frame: mirrors 161 (1177 MB): 7.80 MB synced in 1236.4 copies, 68.34 MB written back
[hos host] vk: 36120 presents, 60.0 fps; a frame: 3502 draws (0 skipped), 133 dispatches, 181 passes, 139 barriers, 6 submits, 0.0 uploads (0.0 MB), 84 ub updates (58 overlays), GPU-bound wait 0.1 ms (recording slots only); 10597 pipelines (2012 ms), 0 programs (0 failed), 2779 textures (5434 MB)
[hos host] vk: host time in GPU resource waits: 0.15 ms a frame (fences 0.04, timelines 0.11, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 576.1 full barriers recorded, 221.9 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 6.7; 0x8: 3.0; 0x9: 1.0; 0x10: 4.7; 0x11: 25.0; 0x12: 72.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 8.7 ms a frame (the longest submission 1.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: replay reads of guest memory as submitted: 4300000 (3383710 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 2571823 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: mirror syncs (600 submits): 189 dirty pages from their submits' captures, 31919 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2541 runs, 1098.5 MB compared; 24 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9188 in captures, 0 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 4320000 (3397080 pages from the captures)
[hos host] vk: program picks: 7450980 kept (2569276 by the last picks' textures, a uniform buffer bound since), 1513 new, 8147506 with other textures (of 15600000)
[hos host] vk: 1 textures retired (2778 left, 5434 MB): budget 0, drawn over 0, dead targets 1
[hos host] vk: sparse mirrors: 81, 1177 MB with memory of 1460 MB (282 MB spared); blocks given memory later 2060, given back 1110; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 295 binds (33.8 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 183 dirty pages from their submits' captures, 31567 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2529 runs, 1119.7 MB compared; 24 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9209 in captures, 2 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 104 live (1720 MB), 0 retired still imported (0 MB), 21 retired given back (616 MB)
[hos host] vk: replay reads of guest memory as submitted: 4340000 (3410357 pages from the captures)
[hos sead::MainThread] vk: capture: a submit 0.15 ms (lock 0.01, scan 0.04 over 577 ranges, 3309 MB), 504 pages written, 504 copied (2.0 MB)
[hos host] vk: a capture taken (ms): all 0.035; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.032, bytes copied 0.000; 25 kept (146 MB), 7 spare buffers, 7575 texture pages copied (29 MB)
[hos host] vk: replay reads of guest memory as submitted: 4360000 (3423724 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 145 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 223 dirty pages from their submits' captures, 30759 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2409 runs, 1011.5 MB compared; 24 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9204 in captures, 0 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 4380000 (3436804 pages from the captures)
[hos host] vk: sparse mirrors: 81, 1177 MB with memory of 1460 MB (282 MB spared); blocks given memory later 2060, given back 1110; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 295 binds (33.8 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 189 dirty pages from their submits' captures, 31064 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2522 runs, 1076.2 MB compared; 22 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 8657 in captures, 2 only in the collection, 15 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 104 live (1720 MB), 0 retired still imported (0 MB), 21 retired given back (616 MB)
[hos host] vk: 1 textures retired (2778 left, 5434 MB): budget 0, drawn over 0, dead targets 1
[hos host] vk: replay reads of guest memory as submitted: 4400000 (3450166 pages from the captures)
[hos ModuleSystemWorker4] nvn: 2300000 recordings made, 39993 live copies (15.5 MB), 1350 texture copies; 6 command buffers' segments (4.3 MB)
[hos host] vk: replay reads of guest memory as submitted: 4420000 (3463372 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 222 dirty pages from their submits' captures, 31584 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2532 runs, 1077.1 MB compared; 24 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9197 in captures, 1 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] nvn: CommandBufferWaitEvent #260000: event 0x100d6c8034 mode 0 value 143691 (now 143672) (lr 0x80662a68)
[hos host] vk: program picks: 7611186 kept (2657643 by the last picks' textures, a uniform buffer bound since), 1514 new, 8187299 with other textures (of 15800000)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.03, writes collected 0.03
[hos rmbl::VibrationThread] hid: 114688 vibration values, strongest 0.00 since the last count
[hos host] vk: readback pages refreshed from guest memory: 2638309 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: replay reads of guest memory as submitted: 4440000 (3476709 pages from the captures)
[hos host] vk: sparse mirrors: 81, 1177 MB with memory of 1460 MB (282 MB spared); blocks given memory later 2060, given back 1110; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 295 binds (33.8 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 182 dirty pages from their submits' captures, 32011 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2523 runs, 1077.0 MB compared; 24 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9201 in captures, 2 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 104 live (1720 MB), 0 retired still imported (0 MB), 21 retired given back (616 MB)
[hos host] vk: 3 textures retired (2776 left, 5434 MB): budget 0, drawn over 0, dead targets 3
[hos host] vk: mirror of pool 0x1066000000 (4 MB) given back: idle, 6031 submissions since its sync
[hos ModuleSystemWorker3] vk: readbacks of GPU results: 1548 of 3000 waited for their write-back, 0.01 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 53776 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 4460000 (3490033 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 204 dirty pages from their submits' captures, 30699 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2390 runs, 1010.6 MB compared; 24 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9198 in captures, 6 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 4480000 (3503288 pages from the captures)
[hos host] vk: replay reads of guest memory as submitted: 4500000 (3516736 pages from the captures)
[hos host] vk: a frame: 369 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 9.65, present 0.08, draw 6.02, descriptors 2.16, texture lookups 0.06, uploads 0.00, pipelines 0.25, programs 1.03, commands 1.94, dispatch 0.72, memory sync 0.32, queue submit 0.66, slot wait 0.07
[hos host] vk: a frame: mirrors 161 (1174 MB): 7.80 MB synced in 1236.2 copies, 67.86 MB written back
[hos host] vk: 36240 presents, 60.0 fps; a frame: 3502 draws (0 skipped), 133 dispatches, 181 passes, 137 barriers, 6 submits, 0.0 uploads (0.0 MB), 83 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 10597 pipelines (2012 ms), 0 programs (0 failed), 2776 textures (5434 MB)
[hos host] vk: host time in GPU resource waits: 0.06 ms a frame (fences 0.04, timelines 0.02, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 573.2 full barriers recorded, 219.8 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 6.2; 0x8: 3.0; 0x9: 1.0; 0x10: 4.2; 0x11: 25.0; 0x12: 71.7; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 8.7 ms a frame (the longest submission 1.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 145 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 80, 1174 MB with memory of 1456 MB (281 MB spared); blocks given memory later 2060, given back 1110; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 295 binds (33.8 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 180 dirty pages from their submits' captures, 30685 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2534 runs, 1077.1 MB compared; 23 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 8615 in captures, 1 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 104 live (1720 MB), 0 retired still imported (0 MB), 21 retired given back (616 MB)
[hos host] vk: replay reads of guest memory as submitted: 4520000 (3529876 pages from the captures)
[hos host] vk: program picks: 7771859 kept (2746580 by the last picks' textures, a uniform buffer bound since), 1514 new, 8226626 with other textures (of 16000000)
[hos Presentation Thread] vk: capture: a submit 0.13 ms (lock 0.01, scan 0.04 over 577 ranges, 3309 MB), 461 pages written, 461 copied (1.8 MB)
[hos host] vk: a capture taken (ms): all 0.024; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.022, bytes copied 0.000; 25 kept (162 MB), 11 spare buffers, 7576 texture pages copied (29 MB)
[hos host] vk: mirror syncs (600 submits): 190 dirty pages from their submits' captures, 31776 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2525 runs, 1076.3 MB compared; 23 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9203 in captures, 1 only in the collection, 15 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 4540000 (3543180 pages from the captures)
[hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #145000: event 0x100d6c8028 mode 0 value 144999 (lr 0x80667410)
[hos host] vk: sparse mirrors: 80, 1174 MB with memory of 1456 MB (281 MB spared); blocks given memory later 2060, given back 1110; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 295 binds (33.8 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 185 dirty pages from their submits' captures, 31448 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2526 runs, 1077.1 MB compared; 24 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9212 in captures, 2 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 104 live (1720 MB), 0 retired still imported (0 MB), 21 retired given back (616 MB)
[hos host] vk: replay reads of guest memory as submitted: 4560000 (3556582 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 2704795 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: replay reads of guest memory as submitted: 4580000 (3569828 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 213 dirty pages from their submits' captures, 31991 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2531 runs, 1077.1 MB compared; 24 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9217 in captures, 2 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 4600000 (3583188 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.03, writes collected 0.03
[hos host] vk: sparse mirrors: 80, 1174 MB with memory of 1456 MB (281 MB spared); blocks given memory later 2060, given back 1110; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 295 binds (33.8 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 191 dirty pages from their submits' captures, 30682 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2400 runs, 1011.2 MB compared; 24 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9201 in captures, 1 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 104 live (1720 MB), 0 retired still imported (0 MB), 21 retired given back (616 MB)
[hos host] vk: replay reads of guest memory as submitted: 4620000 (3596400 pages from the captures)
[hos host] vk: program picks: 7932333 kept (2835441 by the last picks' textures, a uniform buffer bound since), 1514 new, 8266152 with other textures (of 16200000)
[hos BaseProcExecutor0] vcores: 207620 takes, 31936 waits (mean 43 us, longest 5.8 ms), 16425 kicks, 16088 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 62325 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 4640000 (3609782 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 454 KB; 0 made on demand (0 MB kept now); c1 stages: at most 145 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 248 dirty pages from their submits' captures, 30569 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2535 runs, 1077.7 MB compared; 23 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 8660 in captures, 2 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 4660000 (3622980 pages from the captures)
[hos host] vk: 1 textures retired (2775 left, 5434 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: sparse mirrors: 80, 1174 MB with memory of 1456 MB (281 MB spared); blocks given memory later 2060, given back 1110; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 295 binds (33.8 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 226 dirty pages from their submits' captures, 31808 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2521 runs, 1076.3 MB compared; 24 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9209 in captures, 1 only in the collection, 15 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 104 live (1720 MB), 0 retired still imported (0 MB), 21 retired given back (616 MB)
[hos host] vk: replay reads of guest memory as submitted: 4680000 (3636349 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 200 dirty pages from their submits' captures, 31413 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2535 runs, 1077.1 MB compared; 24 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9196 in captures, 2 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 4700000 (3649668 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.14 ms (lock 0.01, scan 0.04 over 577 ranges, 3309 MB), 474 pages written, 474 copied (1.8 MB)
[hos host] vk: a capture taken (ms): all 0.027; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.024, bytes copied 0.000; 25 kept (144 MB), 11 spare buffers, 7576 texture pages copied (29 MB)
[hos host] vk: a frame: 365 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 9.55, present 0.08, draw 5.88, descriptors 2.10, texture lookups 0.06, uploads 0.00, pipelines 0.25, programs 1.01, commands 1.89, dispatch 0.72, memory sync 0.33, queue submit 0.65, slot wait 0.06
[hos host] vk: a frame: mirrors 162 (1177 MB): 7.81 MB synced in 1236.0 copies, 67.33 MB written back
[hos host] vk: 36360 presents, 60.0 fps; a frame: 3494 draws (0 skipped), 133 dispatches, 178 passes, 133 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.1 ms (recording slots only); 10597 pipelines (2012 ms), 0 programs (0 failed), 2775 textures (5434 MB)
[hos host] vk: host time in GPU resource waits: 0.06 ms a frame (fences 0.04, timelines 0.02, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 566.4 full barriers recorded, 215.6 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 5.0; 0x8: 3.0; 0x9: 1.0; 0x10: 3.0; 0x11: 25.0; 0x12: 69.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 8.7 ms a frame (the longest submission 1.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vi: 36361 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 297, 17.8-22 3, 22-30 0, 30-40 0, over 40 0
[hos host] vk: readback pages refreshed from guest memory: 2771463 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: replay reads of guest memory as submitted: 4720000 (3663765 pages from the captures)
[hos host] vk: program picks: 8092675 kept (2924086 by the last picks' textures, a uniform buffer bound since), 1514 new, 8305810 with other textures (of 16400000)
[hos host] vk: sparse mirrors: 81, 1177 MB with memory of 1460 MB (282 MB spared); blocks given memory later 2060, given back 1110; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 296 binds (33.9 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 194 dirty pages from their submits' captures, 31871 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 2466 runs, 1075.9 MB compared; 24 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 9209 in captures, 2 only in the collection, 16 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 104 live (1720 MB), 0 retired still imported (0 MB), 21 retired given back (616 MB)
[hos host] vk: replay reads of guest memory as submitted: 4740000 (3677047 pages from the captures)
Screenshots or video
No response
Before you send it
From Discord:
Further testing suggests GPU timing/frame-rate stability is involved: the issue worsens when timing is unstable and is hard to reproduce when timing is smooth.
Root cause found (and a save fix): a scripted flag freezes the clock
Confirmed on v3.0.0-rc.5 and tracked down with the help of an AI coding assistant (Claude Code). The clock isn't wrong. The game's own "fixed time" rule is engaged because one story flag is stuck on.
Cause
The Bool
HrlField_isFirstNightTime_Adult(murmur3 hash0x8592aa82) is still1in the save. It holds time at 20:00 for the first night as adult Link in Hyrule Field, and an event should clear it afterwards. That never happened on my save.In the lifted code (lift-store
b32e1c90…):f_803edf70is the per-frame clock update (clock object =*(world+0x510): +0x28 seconds of day, +0x3C per-frame step, +0x48/+0x4C pending time request). Each frame it callsf_8347c020. When that returns true, it writes0to the step and forces the time, which also overwrites any pending request.f_8347c020is the "is time fixed?" check. Unless theHyruleField_ArriveEntrancecondition skips it, it returns true when quest0x4dbca27fis not in stateReadyandHrlField_isFirstNightTime_Adultis true.So the clock step is zeroed every frame. The Sun's Song (request 06:00 / 21600 s) and Set time are both accepted and then overwritten on the next update, which explains the ~2 s flicker.
How I verified it
Parsed
progress.sav: header0x01020304, then(u32 hash, u32 value)pairs and a data section, with no checksum. I named the hashes usingromfs/GameData/GameDataList.Product.110.byml.zs(big-endian BYML v7, zstd with the dictionary fromPack/ZsDic.pack.zs, murmur3_32 with seed 0). The flag was1in every slot, which fits "every save" in this issue.Watched it live on a copy of the save, using Longshot's control bridge (
HOS_CONTROL+HOS_CONTROL_MEM=ro,scripts/longshot_ctl.py) to read the clock object and the inputs tof_8347c020every frame:The clock and frame-whole step code behave correctly once the flag is off, so the clock itself isn't broken. The open question is why the event that should clear the flag didn't fire. That would fit the Discord note above: unstable frame timing could make the game miss the event that resets the flag.
Save fix (one byte per slot)
Back up first: copy
~/.local/share/longshot/save/somewhere safe and close the game. Then run this on eachprogress.sav:On my save the pair sits at offset
0xe738, and the patched file differs from the original by exactly one byte. I've since played and saved normally: the day/night cycle works, the Sun's Song sticks, and the flag stays at 0.Caveats:
Suggestion for the devs: check the event or flow that is supposed to reset
HrlField_isFirstNightTime_Adultafter the first adult night in Hyrule Field, and why it doesn't run here. A timing or ordering difference in the recomp would be my first guess, since this flag never gets stuck on hardware.