perf(vk): the presenter thread on by default with NVIDIA on Linux and AMD on Windows, with NVIDIA Reflex; after #1121 #1702

Closed
HumanBean wants to merge 6 commits from HumanBean/Longshot:perf/presenter-thread-nvidia-linux into main
Owner

Type: perf · Risk: medium · Tested on: CachyOS Linux, RTX 3090; the Test Farm: Windows RX 9070 XT (2), Windows RTX 3050 Ti and 3090, Linux RX 7900 XTX, Steam Deck · Needs: Intel (Windows and Linux; queued on the farm, no Linux Intel tester yet)

TL;DR

On Linux with NVIDIA's driver, a present blocks until the frame's copy to the screen is done, about 4.5 ms, and the render thread can't start the next frame meanwhile, so the GPU sits idle at each frame's start. This PR presents from a thread of its own by default with NVIDIA's driver on Linux and with AMD's driver on Windows (discrete cards), where the Test Farm measured it faster, and lets that thread work with NVIDIA Reflex on (until now Reflex kept presents on the game's thread). It builds on #1121, which replays the game's work as it comes instead of waiting for each frame's present. Together, on an RTX 3090 in Castle Town Market: about +7% fps walking and +4% turning (+8% for both with Reflex on), with no one-frame flash more than main in the frame log. On the Test Farm, uncapped: Windows RX 9070 XT Kokiri Forest +11%, Market +6% standing and +2% walking (presenter thread on); Linux RX 7900 XTX Kokiri +41%, Market 9 → 72 fps (main stalls ~1 s at a time there with V-Sync off, the PR doesn't); Windows NVIDIA even in fps with a lower p99; the Steam Deck +2% to +6%.

Breakdown

  • Who it helps: players with Threaded rendering on (Auto from 4 physical cores): #1121's part everyone measured (Linux AMD most, where main stalls), the presenter thread Linux NVIDIA and Windows AMD.
  • What was wrong: NVIDIA's Linux driver blocks vkQueuePresentKHR until the frame's copy is done (~4.5 ms), and with Reflex on, the presenter thread that avoids that never ran.
  • What changes: presents go to the presenter thread by default with NVIDIA's driver on Linux and AMD's on Windows with a discrete card, with Reflex's present id, and the replay doesn't wait for each frame's present (#1121's commit).
  • What does not change: Windows NVIDIA, RADV (the Steam Deck included), AMD integrated GPUs on Windows and Intel keep presents on the game's thread (measured even or a worse p99 with it, Intel not measured); frame pacing, V-Sync and frame generation choose as before.
  • How it was checked: interleaved runs in Castle Town Market at 2560x1440 with DLSS Quality: walking 78.2 → 84.0 fps (medians), turning 97.2 → 100.8; with Reflex on 76.9 → 83.1 and 94.8 → 102.5; the frame log's flash count over Kokiri Forest and the Market, standing, walking and turning: no one-frame dark or bright picture on either side (0 in 25,400 frames on main, 0 in 27,486 with this PR, Reflex on), and as many small one-frame block changes as main, all of them where the turning camera brushes a wall.
  • What is still open: Intel on the farm (queued); Reflex's latency with the presenter thread.
  • Risk: medium: a one-frame dark picture where the replay catches up with the game (#1121's risk), or a present problem on NVIDIA Linux or AMD Windows drivers not run here. RX_VK_FRAME_GATE=1 and RX_VK_PRESENT_THREAD=0 turn each part off.

Why

A profile of the Market on an RTX 3090 (DLSS Quality, 2560x1440) showed the render thread busy all frame and the GPU idle about 4 ms at each frame's start. NVIDIA's driver on Linux returns from vkQueuePresentKHR only once the frame's copy to the swapchain is done (the presenter thread's log: the copy's fence 4.5-4.6 ms in play, the present itself 0.23-0.24 ms), and the render thread was waiting on it. The presenter thread (#1043's work) makes the present elsewhere, but present_out handed nothing to it when the present carried Reflex's present id, and DLSS players have Reflex on. Without #1121, the render thread also waits for each frame's present before replaying its work, which keeps the same gap.

See #1121 (now its own PR, ready: this branch sits on it, so its commits show here until it merges; review only the top three, HumanBean's presenter commits and their docs), #1043.

What changed

The presenter thread is on by default with NVIDIA's driver on Linux and AMD's Windows driver on a discrete card, and takes Reflex's present id with each present. It sits on #1121 (the render thread replays jobs as they come), which merges first; the presenter thread's gain on Linux NVIDIA was measured with it.

  • render thread (#1121, nyannoying): gate_on() in gpu/vk/vk_replay.cpp is off unless RX_VK_FRAME_GATE=1; the present still waits for the main thread's signal (RX_VK_PRESENT_AFTER_SIGNAL).
  • presenter: present_thread_on() defaults to present_thread_default() (gpu/vk/presenter_queue.h: NVIDIA not on Windows, or AMD's proprietary driver on Windows on a discrete card), and create_device asks for the presenter's queue there too; RX_VK_PRESENT_THREAD=0/1 chooses over it. tests/presenter_queue_test.cpp checks the default on each platform. present_out hands a present with Reflex's id over too: present_hand_off(index, fence, reflex_id), and presenter_loop presents with that id, then marks PRESENT_END.
  • Reflex: reflex_present_handed_off() and reflex_present_end(id) in gpu/vk/vk_reflex.cpp: the game's thread clears presenting at the hand-off; the presenter thread marks the present's end.
  • docs: RX_VK_PRESENT_THREAD and RX_VK_FRAME_GATE in gpu/vk/switches.def and docs/development.md; docs/development/frame-pipeline.md; device_policy.h's presenter queue comment.

Measurements

Verdict: Faster on an RTX 3090 on Linux: Castle Town Market walking 78.2 → 84.0 fps (+7%) and turning 97.2 → 100.8 (+3.7%), medians of 3 and 3 sessions (the sides' runs don't overlap in either) with the defaults; with Reflex on, one session each, walking 76.9 → 83.1 and turning 94.8 → 102.5. The GPU's work a frame is the same (6.8-6.95 ms turning, 8.4-8.5 ms walking): it waits less between frames. The frame log: no one-frame dark or bright picture on either side (0 in 25,400 frames on main, 0 in 27,486 with this PR, Reflex on), and as many small one-frame block changes as main, all of them where the turning camera brushes a wall.

Hardware: CachyOS Linux (kernel 7.3.3), RTX 3090 24 GB, NVIDIA 620.70.06, Ryzen 9 7900X (12 cores, 24 threads; Threaded rendering's Auto: both threads), 32 GB
Scene: Castle Town Market (child, debug teleport from the Kokiri save), day; 5 s walking forward, then 20 s walking with the camera turning; 2560x1440 output, DLSS Quality (Preset K), no frame generation, HOS_FPS_MAX=1000, a private headless sway at 240 Hz, sound off
Method: the renderer built alone on one base (only longshot_vk.so differs), each side with its own NVIDIA shader cache. Warm-up then 2 timed sessions each, interleaved (main, PR, main, PR), on the PC's timing queue (one core complex to itself); the fps from the renderer's vk: <n> presents, <fps> fps lines inside each phase, frame times from RX_VK_FRAME_LOG, GPU time from the log's vk: GPU time <n> ms a frame lines. Reflex is off by default in a headless session: one more pair with RX_VK_REFLEX=1. Flashes: 3 more sessions each with RX_VK_REFLEX=1 and the frame log (RX_VK_FRAMELOG) on over Kokiri Forest and then the Market, in each 30 s standing, 5 s walking and 20 s walking with the camera turning (interleaved after a warm-up: main, PR, main, PR, on the shared queue, so their fps are not reported); scripts/framelog.py on each, and a whole-picture check: a frame whose mean brightness is 12+ levels below (or above) both neighbours that are within 6 of each other, and one where 3+ of the picture's 16x9 blocks are 20+ levels below (or above) both neighbours by more than those differ
How to reproduce: longshot_ctl.py teleport Market_Child, then hold forward 5 s, then forward and the right stick right 20 s; the log's vk: <n> presents, <fps> fps lines.

Baseline: both columns are renderers built alone on a base at main da91e770, measured before the rebase onto 09cbdd97. The rebase met main's present-wait bookkeeping in presenter_loop (the frame trace's present-to-shown times) and Threaded rendering's new Auto (#1664), which still turns both threads on for this CPU; it merged without a conflict in the code. The After column also had #1701's commit (the texture pipelines before the game), which doesn't run in play once the pipelines exist.

Before: main @ da91e770 After: this PR @ 1b6c78ae (on da91e770)
Market walking, fps (warm-up, 2 sessions; the median) 78.2, 78.5, 71.8 (78.2) 84.0, 83.6, 85.4 (84.0)
Market turning, fps (the same sessions) 96.5, 98.5, 97.2 (97.2) 100.8, 101.4, 99.1 (100.8)
Market walking, median frame / p99 (ms) 12.32 / 17.7, 12.19 / 17.2, 12.36 / 21.2 11.53 / 17.3, 11.53 / 17.7, 11.71 / 16.9
Market turning, median frame / p99 (ms) 10.06 / 15.9, 10.14 / 15.8, 10.06 / 16.0 9.85 / 15.5, 9.79 / 15.9, 9.97 / 16.0
GPU time a frame, walking / turning (ms) 8.5 / 6.8-6.9 8.4-8.5 / 6.8-6.95
with RX_VK_REFLEX=1, one session each: walking / turning fps 76.9 / 94.8 83.1 / 102.5
frame log, Reflex on (warm-up, 2 sessions): frames 8,048, 8,571, 8,781 8,953, 9,273, 9,260
one-frame whole-picture dark / bright, every window 0 / 0 in each 0 / 0 in each
one-frame changes of 3+ blocks standing and walking, Kokiri Forest and the Market 0 in each 0 in each
the same turning (the camera brushing walls), Kokiri Forest darker / brighter 4 / 2, 4 / 4, 5 / 6 6 / 1, 5 / 6, 6 / 3
the same turning, the Market darker / brighter 33 / 30, 36 / 27, 30 / 25 30 / 24, 28 / 27, 29 / 27
scripts/framelog.py events (all windows) 322, 324, 321 334, 269, 286
After: the presenter thread, and its times (a session with Reflex on):
vk: presenter thread: each present made on a thread and queue of its own once its copy is done (RX_VK_PRESENT_THREAD=0: off)
vk: the presenter thread's queue: family 0, queue 1 (the replay's family); waits for its presents to be shown: yes (VK_KHR_present_wait)
vk: presenter thread: the copy's fence 4.57 ms, the present 0.24 ms a present
vk: presenter thread: the copy's fence 4.49 ms, the present 0.23 ms a present
Frame log, main (fl-r1-main-1) and this PR (fl-r1-ahead-1), framelog.py:
events: 324 on the game's frames, 0 on made frames
events: 269 on the game's frames, 0 on made frames

The Test Farm

Runs 1-3 of @Beanstalk on this PR, main and the PR built and run on the same PC, ABBA, two game starts a side: Kokiri Forest and Castle Town Market, 15 s standing and 10 s after moving, V-Sync off and the frame rate uncapped (run 3; run 2 was at the 60 cap). Run 3's PR side was the head before the last commit, so its forced cell (RX_VK_PRESENT_THREAD=1) is what Windows AMD gets by default now. Medians of the reports, fps (p99 frame time in ms):

Target Scene main PR (run 3's default) PR, presenter thread forced on
Windows, RX 9070 XT (2 reports) Kokiri standing 85.2 (15.2) 94.9 (13.1) 94.5 (12.5)
Kokiri after moving 88.0 (14.3) 97.5 (13.8) 95.3 (13.4)
Market standing 62.1 (20.0) 62.5 (19.2) 67.3 (18.0)
Market after moving 80.9 (16.7) 76.5 (16.6) 84.0 (15.5)
Windows, RTX 3050 Ti and 3090 (2 reports) Kokiri standing 73.5 (23.3) 76.0 (16.7) 79.2 (20.5)
Market standing 62.0 (20.8) 64.0 (20.2) 63.9 (20.4)
Market after moving 66.6 (19.4) 67.6 (19.2) 64.8 (20.9)
Linux, RX 7900 XTX (1 report) Kokiri standing 71.0 (15.6) 100.1 (12.9) 99.6
Market standing 9.1 (1010) 71.6 (61.7) 72.2
Market after moving 63.6 (18.2) 91.9 (15.0) 89.9
Steam Deck (1 report) Kokiri standing 20.1 (96.5) 21.3 (83.9) 22.5 (54.7)
Kokiri after moving 21.5 (58.8) 21.9 (58.6) 22.5 (56.1)
Market after moving — 16.9 (102.9) 17.7 (96.1)

(The forced column's main differs a little from the default column's: each cell has its own main runs; the Steam Deck's forced cell against its own main was even, p99 +4% to +14% in the Market. The farm's second Linux AMD report was a Steam Deck's, left out of the Linux row. The picture checks "fail" on every target as main does against itself in these scenes: the fails are the farm's noise, not a picture change.)

Main on the RX 7900 XTX stalls about 1 s at a time with V-Sync off (frame max 1,000-1,040 ms in every scene, Market p99 1,010 ms); with #1121's part it doesn't (max 46-70 ms). Run 2 (60 cap) had the same: main 45.9 fps, the PR 60.

Per platform: #1121's part is on for everyone (faster or even everywhere). The presenter thread: on for Windows AMD (Market +8% standing and +10% after moving over the PR's default, p99 lower in all four), off for Windows NVIDIA (fps even, p99 +17% in Kokiri), off for RADV (even on the RX 7900 XTX; p99 up to +14% on the Steam Deck).

Flags and settings

One switch changes its default on NVIDIA Linux and Windows AMD; #1121's commit changes another for everyone.

Flag What it is Before this PR After this PR Effect Helps / doesn't help / untested Recommendation
RX_VK_PRESENT_THREAD Presents made on a thread (and queue, where there is a second) of their own once their copy is done off (=1 on) on with NVIDIA's driver on Linux and AMD's on Windows with a discrete card, off elsewhere; =0 / =1 choose the render thread no longer waits ~4.5 ms in each present (NVIDIA Linux); presents off the game's thread (AMD Windows) helps on an RTX 3090 on Linux and two RX 9070 XT on Windows; even or a worse p99 on Windows NVIDIA and RADV, where it stays off; Intel untested on with NVIDIA on Linux and AMD on Windows
RX_VK_FRAME_GATE (#1121) Whole frames: the render thread starts a frame's jobs at its present on (=0 off) off (=1 on) the replay no longer waits for each frame's present #1121: helps on an Arc B580 on Windows; the farm: faster or even on Windows AMD and NVIDIA, Linux AMD (main's 1 s stalls gone) and the Steam Deck off for everyone

Testing

Tested: CachyOS Linux, RTX 3090, NVIDIA 620.70.06: the renderer built alone on a base of main; 8 sessions to Castle Town Market walking and turning (above), and 6 sessions (3 each side, Reflex on) with the frame log over Kokiri Forest and the Market; no device loss, no failed present, the presenter thread on in every session of this PR. The rebased head (on main c4e8e2e) compiles (scripts/dev_build.py vk). The Test Farm, runs 1-3 (above): Windows AMD and NVIDIA, Linux AMD, the Steam Deck; no crash on any.

Not tested: Intel (Windows and Linux; queued on the farm); the last commit's Windows AMD default as a default (the farm ran it as RX_VK_PRESENT_THREAD=1, the same code path; run 4 checks it); Reflex's own latency numbers with the presenter thread (its markers are sent; the latency wasn't measured); a real display (the runs are in a headless compositor). mise run test: not run on this PC.

Must be tested:

  • linux, nvidia, on a screen: Kokiri Forest and the Market with DLSS and Reflex on, expecting presenter thread: each present made on a thread in the log, no tearing or stutter, and fps at least main's (Test Farm: @Beanstalk)
  • windows amd, the presenter thread on by default: vk: presenter thread: each present made in the log, fps at least main's (Test Farm: @Beanstalk, run 4)
  • #1121's items on Intel: linux intel and windows intel, Kokiri Forest and the Market standing 60 s each with RX_VK_FRAMELOG=<file>, then python -I scripts/framelog.py <file>, expecting no one-frame dark patch more than on main (Test Farm: @Beanstalk)

Risks

What could break: a one-frame dark picture where the replay catches up with the game (#1121); a present out of order or a stall on an NVIDIA Linux driver not run here; Reflex's latency readings with presents on another thread.

Turning it off: RX_VK_PRESENT_THREAD=0 (presents on the game's thread), RX_VK_FRAME_GATE=1 (whole frames); or revert.

Compatibility: Nothing changes: no option, cache or API.

Checklist

Everyone

  • One topic.
  • The title is a Conventional Commit (type(scope): description) of the status line's type.
  • Why gives the reason plainly and links the issues that fit (the tracker searched).
  • Tested on my own PC where it runs (in the game, for a change the game runs), as Testing's Tested says; what
    can't be run by hand is in Testing's Not testable by hand, with why.
  • Measurements has a verdict, or one line saying why there is nothing to measure.
  • Nothing gets worse that I know of: any cost (speed, latency, memory, a setup that worked before) is measured and
    in Risks. Not ticked: Reflex's latency with the presenter thread is not measured.
  • Testing names what was tested, what wasn't, and what must still be tested, where and how.
  • Rebased on current main.
  • python -I -B tests/run_all.py passes (any failure that also fails on main is named). Not run on this PC.
  • No game files, dumps, build output or generated files.
  • third_party/ untouched (a new folder with a PROVENANCE.md instead).
  • The license is OK: GPL-3.0-or-later, nothing incompatible and nothing decompiled.

When it applies

  • AI assistance recorded with Assisted-by: / Co-Authored-By: trailers.
  • Numbers from the same PC, scene and settings, at least 2 interleaved runs each, the median reported.
  • Switches documented (docs/development.md; the README for a menu row) and shipped at their recommended value.
  • A file in docs/tested/ for each new measured run (format in docs/tested-configurations.md): 14 (tests/test_tested_configurations.py not run on this PC).
  • Docs updated.

🤖 Generated with Claude Code

https://claude.ai/code/session_016o1k1PazAdTJxQQWQBksW2

**Type:** perf · **Risk:** medium · **Tested on:** CachyOS Linux, RTX 3090; the Test Farm: Windows RX 9070 XT (2), Windows RTX 3050 Ti and 3090, Linux RX 7900 XTX, Steam Deck · **Needs:** Intel (Windows and Linux; queued on the farm, no Linux Intel tester yet) ## TL;DR On Linux with NVIDIA's driver, a present blocks until the frame's copy to the screen is done, about 4.5 ms, and the render thread can't start the next frame meanwhile, so the GPU sits idle at each frame's start. This PR presents from a thread of its own by default with NVIDIA's driver on Linux and with AMD's driver on Windows (discrete cards), where the Test Farm measured it faster, and lets that thread work with NVIDIA Reflex on (until now Reflex kept presents on the game's thread). It builds on #1121, which replays the game's work as it comes instead of waiting for each frame's present. Together, on an RTX 3090 in Castle Town Market: about +7% fps walking and +4% turning (+8% for both with Reflex on), with no one-frame flash more than main in the frame log. On the Test Farm, uncapped: Windows RX 9070 XT Kokiri Forest +11%, Market +6% standing and +2% walking (presenter thread on); Linux RX 7900 XTX Kokiri +41%, Market 9 → 72 fps (main stalls ~1 s at a time there with V-Sync off, the PR doesn't); Windows NVIDIA even in fps with a lower p99; the Steam Deck +2% to +6%. ## Breakdown - **Who it helps:** players with Threaded rendering on (Auto from 4 physical cores): #1121's part everyone measured (Linux AMD most, where main stalls), the presenter thread Linux NVIDIA and Windows AMD. - **What was wrong:** NVIDIA's Linux driver blocks `vkQueuePresentKHR` until the frame's copy is done (~4.5 ms), and with Reflex on, the presenter thread that avoids that never ran. - **What changes:** presents go to the presenter thread by default with NVIDIA's driver on Linux and AMD's on Windows with a discrete card, with Reflex's present id, and the replay doesn't wait for each frame's present (#1121's commit). - **What does not change:** Windows NVIDIA, RADV (the Steam Deck included), AMD integrated GPUs on Windows and Intel keep presents on the game's thread (measured even or a worse p99 with it, Intel not measured); frame pacing, V-Sync and frame generation choose as before. - **How it was checked:** interleaved runs in Castle Town Market at 2560x1440 with DLSS Quality: walking 78.2 → 84.0 fps (medians), turning 97.2 → 100.8; with Reflex on 76.9 → 83.1 and 94.8 → 102.5; the frame log's flash count over Kokiri Forest and the Market, standing, walking and turning: no one-frame dark or bright picture on either side (0 in 25,400 frames on main, 0 in 27,486 with this PR, Reflex on), and as many small one-frame block changes as main, all of them where the turning camera brushes a wall. - **What is still open:** Intel on the farm (queued); Reflex's latency with the presenter thread. - **Risk:** medium: a one-frame dark picture where the replay catches up with the game (#1121's risk), or a present problem on NVIDIA Linux or AMD Windows drivers not run here. `RX_VK_FRAME_GATE=1` and `RX_VK_PRESENT_THREAD=0` turn each part off. ## Why A profile of the Market on an RTX 3090 (DLSS Quality, 2560x1440) showed the render thread busy all frame and the GPU idle about 4 ms at each frame's start. NVIDIA's driver on Linux returns from `vkQueuePresentKHR` only once the frame's copy to the swapchain is done (the presenter thread's log: the copy's fence 4.5-4.6 ms in play, the present itself 0.23-0.24 ms), and the render thread was waiting on it. The presenter thread (#1043's work) makes the present elsewhere, but `present_out` handed nothing to it when the present carried Reflex's present id, and DLSS players have Reflex on. Without #1121, the render thread also waits for each frame's present before replaying its work, which keeps the same gap. See #1121 (now its own PR, ready: this branch sits on it, so its commits show here until it merges; review only the top three, HumanBean's presenter commits and their docs), #1043. ## What changed The presenter thread is on by default with NVIDIA's driver on Linux and AMD's Windows driver on a discrete card, and takes Reflex's present id with each present. It sits on #1121 (the render thread replays jobs as they come), which merges first; the presenter thread's gain on Linux NVIDIA was measured with it. - render thread (#1121, nyannoying): `gate_on()` in `gpu/vk/vk_replay.cpp` is off unless `RX_VK_FRAME_GATE=1`; the present still waits for the main thread's signal (`RX_VK_PRESENT_AFTER_SIGNAL`). - presenter: `present_thread_on()` defaults to `present_thread_default()` (`gpu/vk/presenter_queue.h`: NVIDIA not on Windows, or AMD's proprietary driver on Windows on a discrete card), and `create_device` asks for the presenter's queue there too; `RX_VK_PRESENT_THREAD=0/1` chooses over it. `tests/presenter_queue_test.cpp` checks the default on each platform. `present_out` hands a present with Reflex's id over too: `present_hand_off(index, fence, reflex_id)`, and `presenter_loop` presents with that id, then marks `PRESENT_END`. - Reflex: `reflex_present_handed_off()` and `reflex_present_end(id)` in `gpu/vk/vk_reflex.cpp`: the game's thread clears `presenting` at the hand-off; the presenter thread marks the present's end. - docs: `RX_VK_PRESENT_THREAD` and `RX_VK_FRAME_GATE` in `gpu/vk/switches.def` and `docs/development.md`; `docs/development/frame-pipeline.md`; `device_policy.h`'s presenter queue comment. ## Measurements **Verdict:** Faster on an RTX 3090 on Linux: Castle Town Market walking 78.2 → 84.0 fps (+7%) and turning 97.2 → 100.8 (+3.7%), medians of 3 and 3 sessions (the sides' runs don't overlap in either) with the defaults; with Reflex on, one session each, walking 76.9 → 83.1 and turning 94.8 → 102.5. The GPU's work a frame is the same (6.8-6.95 ms turning, 8.4-8.5 ms walking): it waits less between frames. The frame log: no one-frame dark or bright picture on either side (0 in 25,400 frames on main, 0 in 27,486 with this PR, Reflex on), and as many small one-frame block changes as main, all of them where the turning camera brushes a wall. Hardware: CachyOS Linux (kernel 7.3.3), RTX 3090 24 GB, NVIDIA 620.70.06, Ryzen 9 7900X (12 cores, 24 threads; Threaded rendering's Auto: both threads), 32 GB Scene: Castle Town Market (child, debug teleport from the Kokiri save), day; 5 s walking forward, then 20 s walking with the camera turning; 2560x1440 output, DLSS Quality (Preset K), no frame generation, `HOS_FPS_MAX=1000`, a private headless sway at 240 Hz, sound off Method: the renderer built alone on one base (only `longshot_vk.so` differs), each side with its own NVIDIA shader cache. Warm-up then 2 timed sessions each, interleaved (main, PR, main, PR), on the PC's timing queue (one core complex to itself); the fps from the renderer's `vk: <n> presents, <fps> fps` lines inside each phase, frame times from `RX_VK_FRAME_LOG`, GPU time from the log's `vk: GPU time <n> ms a frame` lines. Reflex is off by default in a headless session: one more pair with `RX_VK_REFLEX=1`. Flashes: 3 more sessions each with `RX_VK_REFLEX=1` and the frame log (`RX_VK_FRAMELOG`) on over Kokiri Forest and then the Market, in each 30 s standing, 5 s walking and 20 s walking with the camera turning (interleaved after a warm-up: main, PR, main, PR, on the shared queue, so their fps are not reported); `scripts/framelog.py` on each, and a whole-picture check: a frame whose mean brightness is 12+ levels below (or above) both neighbours that are within 6 of each other, and one where 3+ of the picture's 16x9 blocks are 20+ levels below (or above) both neighbours by more than those differ How to reproduce: `longshot_ctl.py teleport Market_Child`, then hold forward 5 s, then forward and the right stick right 20 s; the log's `vk: <n> presents, <fps> fps` lines. Baseline: both columns are renderers built alone on a base at main da91e770, measured before the rebase onto 09cbdd97. The rebase met main's present-wait bookkeeping in `presenter_loop` (the frame trace's present-to-shown times) and Threaded rendering's new Auto (#1664), which still turns both threads on for this CPU; it merged without a conflict in the code. The After column also had [#1701](https://git.magicbean.dev/MagicBeanDev/Longshot/pulls/1701)'s commit (the texture pipelines before the game), which doesn't run in play once the pipelines exist. | | Before: main @ da91e770 | After: this PR @ 1b6c78ae (on da91e770) | |---|---|---| | Market walking, fps (warm-up, 2 sessions; the median) | 78.2, 78.5, 71.8 (78.2) | 84.0, 83.6, 85.4 (84.0) | | Market turning, fps (the same sessions) | 96.5, 98.5, 97.2 (97.2) | 100.8, 101.4, 99.1 (100.8) | | Market walking, median frame / p99 (ms) | 12.32 / 17.7, 12.19 / 17.2, 12.36 / 21.2 | 11.53 / 17.3, 11.53 / 17.7, 11.71 / 16.9 | | Market turning, median frame / p99 (ms) | 10.06 / 15.9, 10.14 / 15.8, 10.06 / 16.0 | 9.85 / 15.5, 9.79 / 15.9, 9.97 / 16.0 | | GPU time a frame, walking / turning (ms) | 8.5 / 6.8-6.9 | 8.4-8.5 / 6.8-6.95 | | with `RX_VK_REFLEX=1`, one session each: walking / turning fps | 76.9 / 94.8 | 83.1 / 102.5 | | frame log, Reflex on (warm-up, 2 sessions): frames | 8,048, 8,571, 8,781 | 8,953, 9,273, 9,260 | | one-frame whole-picture dark / bright, every window | 0 / 0 in each | 0 / 0 in each | | one-frame changes of 3+ blocks standing and walking, Kokiri Forest and the Market | 0 in each | 0 in each | | the same turning (the camera brushing walls), Kokiri Forest darker / brighter | 4 / 2, 4 / 4, 5 / 6 | 6 / 1, 5 / 6, 6 / 3 | | the same turning, the Market darker / brighter | 33 / 30, 36 / 27, 30 / 25 | 30 / 24, 28 / 27, 29 / 27 | | `scripts/framelog.py` events (all windows) | 322, 324, 321 | 334, 269, 286 | ``` After: the presenter thread, and its times (a session with Reflex on): vk: presenter thread: each present made on a thread and queue of its own once its copy is done (RX_VK_PRESENT_THREAD=0: off) vk: the presenter thread's queue: family 0, queue 1 (the replay's family); waits for its presents to be shown: yes (VK_KHR_present_wait) vk: presenter thread: the copy's fence 4.57 ms, the present 0.24 ms a present vk: presenter thread: the copy's fence 4.49 ms, the present 0.23 ms a present Frame log, main (fl-r1-main-1) and this PR (fl-r1-ahead-1), framelog.py: events: 324 on the game's frames, 0 on made frames events: 269 on the game's frames, 0 on made frames ``` ### The Test Farm Runs 1-3 of `@Beanstalk` on this PR, main and the PR built and run on the same PC, ABBA, two game starts a side: Kokiri Forest and Castle Town Market, 15 s standing and 10 s after moving, V-Sync off and the frame rate uncapped (run 3; run 2 was at the 60 cap). Run 3's PR side was the head before the last commit, so its *forced* cell (`RX_VK_PRESENT_THREAD=1`) is what Windows AMD gets by default now. Medians of the reports, fps (p99 frame time in ms): | Target | Scene | main | PR (run 3's default) | PR, presenter thread forced on | |---|---|---|---|---| | Windows, RX 9070 XT (2 reports) | Kokiri standing | 85.2 (15.2) | 94.9 (13.1) | 94.5 (12.5) | | | Kokiri after moving | 88.0 (14.3) | 97.5 (13.8) | 95.3 (13.4) | | | Market standing | 62.1 (20.0) | 62.5 (19.2) | 67.3 (18.0) | | | Market after moving | 80.9 (16.7) | 76.5 (16.6) | 84.0 (15.5) | | Windows, RTX 3050 Ti and 3090 (2 reports) | Kokiri standing | 73.5 (23.3) | 76.0 (16.7) | 79.2 (20.5) | | | Market standing | 62.0 (20.8) | 64.0 (20.2) | 63.9 (20.4) | | | Market after moving | 66.6 (19.4) | 67.6 (19.2) | 64.8 (20.9) | | Linux, RX 7900 XTX (1 report) | Kokiri standing | 71.0 (15.6) | 100.1 (12.9) | 99.6 | | | Market standing | 9.1 (1010) | 71.6 (61.7) | 72.2 | | | Market after moving | 63.6 (18.2) | 91.9 (15.0) | 89.9 | | Steam Deck (1 report) | Kokiri standing | 20.1 (96.5) | 21.3 (83.9) | 22.5 (54.7) | | | Kokiri after moving | 21.5 (58.8) | 21.9 (58.6) | 22.5 (56.1) | | | Market after moving | — | 16.9 (102.9) | 17.7 (96.1) | (The forced column's main differs a little from the default column's: each cell has its own main runs; the Steam Deck's forced cell against its own main was even, p99 +4% to +14% in the Market. The farm's second Linux AMD report was a Steam Deck's, left out of the Linux row. The picture checks "fail" on every target as main does against itself in these scenes: the fails are the farm's noise, not a picture change.) Main on the RX 7900 XTX stalls about 1 s at a time with V-Sync off (frame max 1,000-1,040 ms in every scene, Market p99 1,010 ms); with #1121's part it doesn't (max 46-70 ms). Run 2 (60 cap) had the same: main 45.9 fps, the PR 60. Per platform: #1121's part is on for everyone (faster or even everywhere). The presenter thread: on for Windows AMD (Market +8% standing and +10% after moving over the PR's default, p99 lower in all four), off for Windows NVIDIA (fps even, p99 +17% in Kokiri), off for RADV (even on the RX 7900 XTX; p99 up to +14% on the Steam Deck). ### Flags and settings One switch changes its default on NVIDIA Linux and Windows AMD; #1121's commit changes another for everyone. | Flag | What it is | Before this PR | After this PR | Effect | Helps / doesn't help / untested | Recommendation | |---|---|---|---|---|---|---| | `RX_VK_PRESENT_THREAD` | Presents made on a thread (and queue, where there is a second) of their own once their copy is done | off (`=1` on) | on with NVIDIA's driver on Linux and AMD's on Windows with a discrete card, off elsewhere; `=0` / `=1` choose | the render thread no longer waits ~4.5 ms in each present (NVIDIA Linux); presents off the game's thread (AMD Windows) | helps on an RTX 3090 on Linux and two RX 9070 XT on Windows; even or a worse p99 on Windows NVIDIA and RADV, where it stays off; Intel untested | on with NVIDIA on Linux and AMD on Windows | | `RX_VK_FRAME_GATE` (#1121) | Whole frames: the render thread starts a frame's jobs at its present | on (`=0` off) | off (`=1` on) | the replay no longer waits for each frame's present | #1121: helps on an Arc B580 on Windows; the farm: faster or even on Windows AMD and NVIDIA, Linux AMD (main's 1 s stalls gone) and the Steam Deck | off for everyone | ## Testing **Tested:** CachyOS Linux, RTX 3090, NVIDIA 620.70.06: the renderer built alone on a base of main; 8 sessions to Castle Town Market walking and turning (above), and 6 sessions (3 each side, Reflex on) with the frame log over Kokiri Forest and the Market; no device loss, no failed present, the presenter thread on in every session of this PR. The rebased head (on main c4e8e2e) compiles (`scripts/dev_build.py vk`). The Test Farm, runs 1-3 (above): Windows AMD and NVIDIA, Linux AMD, the Steam Deck; no crash on any. **Not tested:** Intel (Windows and Linux; queued on the farm); the last commit's Windows AMD default as a default (the farm ran it as `RX_VK_PRESENT_THREAD=1`, the same code path; run 4 checks it); Reflex's own latency numbers with the presenter thread (its markers are sent; the latency wasn't measured); a real display (the runs are in a headless compositor). `mise run test`: not run on this PC. **Must be tested:** - linux, nvidia, on a screen: Kokiri Forest and the Market with DLSS and Reflex on, expecting `presenter thread: each present made on a thread` in the log, no tearing or stutter, and fps at least main's (Test Farm: @Beanstalk) - windows amd, the presenter thread on by default: `vk: presenter thread: each present made` in the log, fps at least main's (Test Farm: @Beanstalk, run 4) - #1121's items on Intel: linux intel and windows intel, Kokiri Forest and the Market standing 60 s each with `RX_VK_FRAMELOG=<file>`, then `python -I scripts/framelog.py <file>`, expecting no one-frame dark patch more than on main (Test Farm: @Beanstalk) ## Risks **What could break:** a one-frame dark picture where the replay catches up with the game (#1121); a present out of order or a stall on an NVIDIA Linux driver not run here; Reflex's latency readings with presents on another thread. **Turning it off:** `RX_VK_PRESENT_THREAD=0` (presents on the game's thread), `RX_VK_FRAME_GATE=1` (whole frames); or revert. **Compatibility:** Nothing changes: no option, cache or API. ## Checklist ### Everyone - [x] One topic. - [x] The title is a Conventional Commit (`type(scope): description`) of the status line's type. - [x] Why gives the reason plainly and links the issues that fit (the tracker searched). - [x] Tested on my own PC where it runs (in the game, for a change the game runs), as Testing's Tested says; what can't be run by hand is in Testing's Not testable by hand, with why. - [x] Measurements has a verdict, or one line saying why there is nothing to measure. - [ ] Nothing gets worse that I know of: any cost (speed, latency, memory, a setup that worked before) is measured and in Risks. Not ticked: Reflex's latency with the presenter thread is not measured. - [x] Testing names what was tested, what wasn't, and what must still be tested, where and how. - [x] Rebased on current `main`. - [ ] `python -I -B tests/run_all.py` passes (any failure that also fails on `main` is named). Not run on this PC. - [x] No game files, dumps, build output or generated files. - [x] `third_party/` untouched (a new folder with a `PROVENANCE.md` instead). - [x] The license is OK: GPL-3.0-or-later, nothing incompatible and nothing decompiled. ### When it applies - [x] AI assistance recorded with `Assisted-by:` / `Co-Authored-By:` trailers. - [x] Numbers from the same PC, scene and settings, at least 2 interleaved runs each, the median reported. - [x] Switches documented (docs/development.md; the README for a menu row) and shipped at their recommended value. - [x] A file in `docs/tested/` for each new measured run (format in `docs/tested-configurations.md`): 14 (`tests/test_tested_configurations.py` not run on this PC). - [x] Docs updated. 🤖 Generated with [Claude Code](https://claude.com/claude-code) https://claude.ai/code/session_016o1k1PazAdTJxQQWQBksW2
With Threaded rendering on, the render thread waited for each frame's present before it
replayed any of that frame's work (whole frames, PR 588), because replaying a frame's first
submits while the game was still writing the rest drew the lit scene black for one frame.
Those moments were also where a submit's capture missed the pages the replay's collection was
marking again, which #1083 fixes. With that fixed, jobs replayed as they come drew no such
frame in 23,400 frames on an Arc B580 (Kokiri Forest and the Market standing, four sessions
interleaved with four of whole frames), and the wait cost 86.95 -> 92.4 fps in Kokiri Forest
and 53.6 -> 58.0 in the Market (medians).

gate_on() is now off unless RX_VK_FRAME_GATE is on (=1: whole frames, a test). The present
is still handed over after the main thread's signal for its frame, as with whole frames,
which is what was measured (RX_VK_PRESENT_AFTER_SIGNAL=0, a test: at once).

Assisted-by: Claude Opus 5.5
Co-Authored-By: Claude Opus 5.5 <[email protected]>
With jobs replayed as they come, the render thread then starts the next frame's submits while the GPU still works
(3-5 % on an RTX 3090, docs/development/frame-pipeline.md). Reflex on kept every present on the game's thread before:
its present id now goes with the present, and the presenter thread marks the present's end.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_016o1k1PazAdTJxQQWQBksW2
docs(tested): the presenter thread and #1121 on an RTX 3090 on Linux, Castle Town Market and the frame log
Some checks failed
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Has been skipped
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Has been skipped
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Has been skipped
Third-party parts / The same as upstream (pull_request) Has been skipped
Website / Website on Cloudflare (pull_request) Has been skipped
CI / Conventional Commit title (pull_request) Successful in 7s
Guide screenshots / Guide images and local UI source review (pull_request) Failing after 10s
CI / Workflow lint (actionlint) (pull_request) Successful in 12s
Third-party parts / As their notes say (pull_request) Successful in 13s
Website / Website on Cloudflare (pull_request_target) Has been skipped
PR description / Description follows the template (pull_request_target) Failing after 8s
beanstalk/approval approved by HumanBean (reviewed)
beanstalk/windows+amd 2/1 fail
beanstalk/windows+nvidia 1/1 fail
beanstalk/linux+amd 2/1 fail
beanstalk/steamdeck 1/1 fail
beanstalk/windows+intel 0/1 pass, 0 running, 2 queued
beanstalk/linux+intel 0/1 pass, 0 running, 2 queued
3569b8da6a
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_016o1k1PazAdTJxQQWQBksW2
Author
Owner

Tested in game: RTX 3090, NVIDIA 620.70.06, CachyOS Linux (headless sway), 2560x1440 DLSS Quality: 8 sessions in Castle Town Market walking and turning (78.2 -> 84.0 fps walking, 97.2 -> 100.8 turning, medians) and 6 with Reflex on and the frame log over Kokiri Forest and the Market, standing, walking and turning: 0 one-frame dark or bright pictures on either side; the presenter thread on in every session of this PR; no device loss or failed present

Tested in game: RTX 3090, NVIDIA 620.70.06, CachyOS Linux (headless sway), 2560x1440 DLSS Quality: 8 sessions in Castle Town Market walking and turning (78.2 -> 84.0 fps walking, 97.2 -> 100.8 turning, medians) and 6 with Reflex on and the frame log over Kokiri Forest and the Market, standing, walking and turning: 0 one-frame dark or bright pictures on either side; the presenter thread on in every session of this PR; no device loss or failed present
Author
Owner

@Beanstalk test if this helps on windows/amd too

@Beanstalk test if this helps on windows/amd too
Member
Beanstalk test farm · an earlier run: commit 3569b8d (the newer results are in a comment below)

Commit 3569b8d · tier reviewed · approved by HumanBean · dashboard

What will be tested · AI plan (gpt-6.1-terra)

On Windows AMD, compare main and the PR in Kokiri Forest and the Market over about 23 minutes per tester. The plan measures frame times and FPS with threaded replay enabled, and compares sampled images for rendering regressions. Crashes, device loss, substantial frame-time or FPS regressions, or sufficiently different sampled images fail the plan; brief flashes between samples may be missed.

  • Where: windows+amd (1-2 reports).
  • forest-market: from the repository's save kokiri-start (settings vsync=2, frame_rate_cap=6, frame_generation=0; switches RX_VK_ASYNC=1), then teleport to Kokiri Forest, measure forest for 20 s (after 5 s warm-up), take the picture forest to compare with main, teleport to Market, move the stick, measure market for 20 s (after 5 s warm-up), take the picture market to compare with main; 2 runs on each side.
  • Measured: crashes, frame times, stutters and hitches, draws and frame rate, screenshots against main, the game's log.
  • The PR fails if: it crashes; or frame rate is more than 10% below main; or a picture differs from main by more than 10%; or frame time (p99) is more than 20% above main; or forbidden log lines is above 0.
  • Time: about 24 min of game runs per tester (4 game starts), plus the two builds.

Started at 06:45 UTC.

Target Reports Crash Frame p99 (ms) vs main VRAM peak (MB) vs main Result
windows+amd · 1: windows+amd+amd-proprietary+dgpu AMD Radeon RX 9070 XT, 2.0.416 1/1 1 none 14.1 vs 15.7 (−10%) — fail

Measurements · windows+amd

Verdict: fail on windows+amd (1/1 report): forest-market screenshot.max_diff failed.

Hardware: 1: windows+amd+amd-proprietary+dgpu AMD Radeon RX 9070 XT, 2.0.416 AMD Ryzen 9 5900X 12-Core Processor, 32 GB RAM
Scene: forest-market, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6, frame_generation=0, RX_VK_ASYNC=1); each cell's settings and switches as the table names them
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-market: 2 game starts a side, forest 20 s after 5 s warm-up, market 20 s after 5 s warm-up; each number the median of the runs, then of 1 report
How to reproduce: the farm's plan above (@Beanstalk on this PR runs it again)

Before: main @ 09cbdd9 After: this PR @ 3569b8d
forest-market · forest · frame rate 73.8 80.5 (+9%)
forest-market · market · frame rate 66.4 73.5 (+11%)
forest-market · forest · frame time (p99) (ms) 15.7 14.1 (−10%)
forest-market · market · frame time (p99) (ms) 19.9 17.5 (−12%)
forest-market · forbidden log lines 0.0 0.0

Flags and settings

None: the plan varied no setting, switch or build option.

Markdown for the PR description
## Measurements

**Verdict:** fail on windows+amd (1/1 report): `forest-market screenshot.max_diff` failed.

Hardware: 1: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416` `AMD Ryzen 9 5900X 12-Core Processor, 32 GB RAM`  
Scene: forest-market, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6, frame_generation=0, RX_VK_ASYNC=1); each cell's settings and switches as the table names them  
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-market: 2 game starts a side, forest 20 s after 5 s warm-up, market 20 s after 5 s warm-up; each number the median of the runs, then of 1 report  
How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again)

| | Before: main @ 09cbdd9 | After: this PR @ 3569b8d |
|---|---|---|
| forest-market · forest · frame rate | 73.8 | 80.5 (+9%) |
| forest-market · market · frame rate | 66.4 | 73.5 (+11%) |
| forest-market · forest · frame time (p99) (ms) | 15.7 | 14.1 (−10%) |
| forest-market · market · frame time (p99) (ms) | 19.9 | 17.5 (−12%) |
| forest-market · forbidden log lines | 0.0 | 0.0 |

### Flags and settings

None: the plan varied no setting, switch or build option.
<!-- beanstalk:previous --> <details><summary>Beanstalk test farm · an earlier run: commit <code>3569b8d</code> (the newer results are in a comment below)</summary> Commit `3569b8d` · tier **reviewed** · approved by HumanBean · [dashboard](https://beanstalk.magicbean.dev/prs/1702) **What will be tested** · AI plan (`gpt-6.1-terra`) On Windows AMD, compare main and the PR in Kokiri Forest and the Market over about 23 minutes per tester. The plan measures frame times and FPS with threaded replay enabled, and compares sampled images for rendering regressions. Crashes, device loss, substantial frame-time or FPS regressions, or sufficiently different sampled images fail the plan; brief flashes between samples may be missed. - **Where:** windows+amd (1-2 reports). - **forest-market:** from the repository's save `kokiri-start` (settings vsync=2, frame_rate_cap=6, frame_generation=0; switches `RX_VK_ASYNC=1`), then teleport to Kokiri Forest, measure forest for 20 s (after 5 s warm-up), take the picture forest to compare with main, teleport to Market, move the stick, measure market for 20 s (after 5 s warm-up), take the picture market to compare with main; 2 runs on each side. - **Measured:** crashes, frame times, stutters and hitches, draws and frame rate, screenshots against main, the game's log. - **The PR fails if:** it crashes; or frame rate is more than 10% below main; or a picture differs from main by more than 10%; or frame time (p99) is more than 20% above main; or forbidden log lines is above 0. - **Time:** about 24 min of game runs per tester (4 game starts), plus the two builds. Started at 06:45 UTC. | Target | Reports | Crash | Frame p99 (ms) vs main | VRAM peak (MB) vs main | Result | | --- | --- | --- | --- | --- | --- | | windows+amd · 1: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416` | 1/1 [1](https://beanstalk.magicbean.dev/reports/rp_a65df7e54289f5a3) | none | 14.1 vs 15.7 (−10%) | — | fail | #### Measurements · windows+amd **Verdict:** fail on windows+amd (1/1 report): `forest-market screenshot.max_diff` failed. Hardware: 1: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416` `AMD Ryzen 9 5900X 12-Core Processor, 32 GB RAM` Scene: forest-market, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6, frame_generation=0, RX_VK_ASYNC=1); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-market: 2 game starts a side, forest 20 s after 5 s warm-up, market 20 s after 5 s warm-up; each number the median of the runs, then of 1 report How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ 09cbdd9 | After: this PR @ 3569b8d | |---|---|---| | forest-market · forest · frame rate | 73.8 | 80.5 (+9%) | | forest-market · market · frame rate | 66.4 | 73.5 (+11%) | | forest-market · forest · frame time (p99) (ms) | 15.7 | 14.1 (−10%) | | forest-market · market · frame time (p99) (ms) | 19.9 | 17.5 (−12%) | | forest-market · forbidden log lines | 0.0 | 0.0 | ### Flags and settings None: the plan varied no setting, switch or build option. <details><summary>Markdown for the PR description</summary> ```markdown ## Measurements **Verdict:** fail on windows+amd (1/1 report): `forest-market screenshot.max_diff` failed. Hardware: 1: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416` `AMD Ryzen 9 5900X 12-Core Processor, 32 GB RAM` Scene: forest-market, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6, frame_generation=0, RX_VK_ASYNC=1); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-market: 2 game starts a side, forest 20 s after 5 s warm-up, market 20 s after 5 s warm-up; each number the median of the runs, then of 1 report How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ 09cbdd9 | After: this PR @ 3569b8d | |---|---|---| | forest-market · forest · frame rate | 73.8 | 80.5 (+9%) | | forest-market · market · frame rate | 66.4 | 73.5 (+11%) | | forest-market · forest · frame time (p99) (ms) | 15.7 | 14.1 (−10%) | | forest-market · market · frame time (p99) (ms) | 19.9 | 17.5 (−12%) | | forest-market · forbidden log lines | 0.0 | 0.0 | ### Flags and settings None: the plan varied no setting, switch or build option. ``` </details> </details>
HumanBean changed title from WIP: perf(vk): the presenter thread on by default with NVIDIA's driver on Linux, with NVIDIA Reflex; carries #1121 to perf(vk): the presenter thread on by default with NVIDIA's driver on Linux, with NVIDIA Reflex; carries #1121 2026-11-19 07:18:19 +00:00
Author
Owner

On the Windows AMD run (RX 9070 XT): the presenter thread was off there (this PR turns it on only with NVIDIA's driver on Linux), so what it measured is #1121's part, the replay taking a frame's jobs as they come. It helps there: Kokiri Forest 73.8 → 80.5 fps (+9%), the Market 66.4 → 73.5 (+11%), the Market's p99 19.9 → 17.5 ms.

The screenshot.max_diff fail is the Market picture rule, not a rendering difference: the two pictures of the failure have the same lighting and nothing missing or dark; Link and the camera are a little further along in one (the stick is held for a set time and the frames fall at other moments). Main against itself already differs by 0.37–0.39 in the Market, over the rule's 0.1, while Kokiri Forest's pictures differ from main no more than main from itself (0.015–0.035 against 0.026–0.040).

Next: the presenter thread for everyone. A farm run with RX_VK_PRESENT_THREAD=1 against this PR's default on the setups where it is off, below; if it helps or changes nothing there, the default becomes on for all.

🤖 Generated with Claude Code

https://claude.ai/code/session_016o1k1PazAdTJxQQWQBksW2

On the Windows AMD run (RX 9070 XT): the presenter thread was off there (this PR turns it on only with NVIDIA's driver on Linux), so what it measured is #1121's part, the replay taking a frame's jobs as they come. It helps there: Kokiri Forest 73.8 → 80.5 fps (+9%), the Market 66.4 → 73.5 (+11%), the Market's p99 19.9 → 17.5 ms. The `screenshot.max_diff` fail is the Market picture rule, not a rendering difference: the two pictures of the failure have the same lighting and nothing missing or dark; Link and the camera are a little further along in one (the stick is held for a set time and the frames fall at other moments). Main against itself already differs by 0.37–0.39 in the Market, over the rule's 0.1, while Kokiri Forest's pictures differ from main no more than main from itself (0.015–0.035 against 0.026–0.040). Next: the presenter thread for everyone. A farm run with `RX_VK_PRESENT_THREAD=1` against this PR's default on the setups where it is off, below; if it helps or changes nothing there, the default becomes on for all. 🤖 Generated with [Claude Code](https://claude.com/claude-code) https://claude.ai/code/session_016o1k1PazAdTJxQQWQBksW2
Author
Owner

@Beanstalk compare this PR with RX_VK_PRESENT_THREAD=1 against this PR with its default (the presenter thread off on these) on windows+amd, windows+nvidia and linux+amd: Kokiri Forest and the Market, fps, p99 frame time and the pictures

@Beanstalk compare this PR with `RX_VK_PRESENT_THREAD=1` against this PR with its default (the presenter thread off on these) on windows+amd, windows+nvidia and linux+amd: Kokiri Forest and the Market, fps, p99 frame time and the pictures
Member
Beanstalk test farm · an earlier run: commit 3569b8d, run 2 (the newer results are in a comment below)

Commit 3569b8d · tier reviewed · approved by HumanBean · dashboard

What will be tested · AI plan (gpt-6.1-terra)

On Windows AMD, Windows NVIDIA and Linux AMD, this plan measures FPS and p99 frame time and compares pictures in Kokiri Forest and the Market. It takes about 21 minutes per tester and tests the presenter thread both off and forced on. Each setting is compared with main, rather than with the PR’s default, because the PR also changes replay when the presenter thread is off. A crash, a frame-time increase over 15%, an FPS drop over 10%, or a picture difference over the threshold fails the plan; sampled pictures cannot reliably detect one-frame flashes.

  • Where: windows+amd (1-2 reports), windows+nvidia (1-2 reports), linux+amd (1-2 reports).
  • Matrix: 2 cells, each on main and the PR: RX_VK_PRESENT_THREAD 0 or 1.
  • forest-market: from the repository's save kokiri-start, then teleport to Kokiri Forest, measure forest for 20 s (after 5 s warm-up), take the picture forest to compare with main, teleport to Market, measure market for 20 s (after 5 s warm-up), take the picture market to compare with main; 1 run on each side for each of 2 cells (2 game starts a run).
  • Measured: crashes, frame times, stutters and hitches, draws and frame rate.
  • The PR fails if: it crashes; or frame rate is more than 10% below main; or a picture differs from main by more than 10%; or frame time (p99) is more than 15% above main.
  • Time: about 24 min of game runs per tester (4 game starts), plus the two builds.

Started at 07:21 UTC. Run 2: re-planned by HumanBean.

Estimate: done in about 1 h, from the queue and the testers online now.

Target Reports Crash Frame p99 (ms) vs main VRAM peak (MB) vs main Result
windows+amd · 1: windows+amd+amd-proprietary+dgpu AMD Radeon RX 9070 XT, 2.0.416; 2: windows+amd+amd-proprietary+dgpu AMD Radeon RX 9070 XT, 2.0.416 2/1 1 2 none 18.5 vs 19.3 (−4%) — fail
windows+nvidia · 1: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0; 2: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 3070, 621.24.0 2/1 1 2 none 19.0 vs 20.0 (−5%) — fail
linux+amd · 1: linux+amd+radv+dgpu AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7 1/1 1 none 17.8 vs 18.3 (−3%) — fail
Scenario · matrix cell Target Frame p99 (ms) vs main Result
forest-market · RX_VK_PRESENT_THREAD=0 windows+amd 18.5 vs 19.3 (−4%) fail
forest-market · RX_VK_PRESENT_THREAD=0 windows+nvidia 19.0 vs 20.0 (−5%) fail
forest-market · RX_VK_PRESENT_THREAD=0 linux+amd 17.8 vs 18.3 (−3%) fail
forest-market · RX_VK_PRESENT_THREAD=1 windows+amd 18.4 vs 18.8 (−2%) fail
forest-market · RX_VK_PRESENT_THREAD=1 windows+nvidia 19.6 vs 20.1 (−3%) fail
forest-market · RX_VK_PRESENT_THREAD=1 linux+amd 17.8 vs 18.4 (−3%) fail

Measurements · windows+amd

Verdict: fail on windows+amd (2/1 report): forest-market screenshot.max_diff failed.

Hardware: 1: windows+amd+amd-proprietary+dgpu AMD Radeon RX 9070 XT, 2.0.416 AMD Ryzen 9 5900X 12-Core Processor, 32 GB RAM; 2: windows+amd+amd-proprietary+dgpu AMD Radeon RX 9070 XT, 2.0.416 AMD Ryzen 7 5800X3D 8-Core Processor, 32 GB RAM
Scene: forest-market, from the repository's save kokiri-start; each cell's settings and switches as the table names them
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-market: 1 game start a side, forest 20 s after 5 s warm-up, market 20 s after 5 s warm-up; each number the median of the runs, then of 2 reports
How to reproduce: the farm's plan above (@Beanstalk on this PR runs it again)

Before: main @ 09cbdd9 After: this PR @ 3569b8d
forest-market · RX_VK_PRESENT_THREAD=0 · forest · frame rate 60.1 59.6 (−1%)
forest-market · RX_VK_PRESENT_THREAD=0 · market · frame rate 56.3 58.9 (+5%)
forest-market · RX_VK_PRESENT_THREAD=0 · forest · frame time (p99) (ms) 19.3 18.5 (−4%)
forest-market · RX_VK_PRESENT_THREAD=0 · market · frame time (p99) (ms) 21.8 20.4 (−6%)
forest-market · RX_VK_PRESENT_THREAD=1 · forest · frame rate 59.9 60.0 (+0%)
forest-market · RX_VK_PRESENT_THREAD=1 · market · frame rate 56.5 59.7 (+6%)
forest-market · RX_VK_PRESENT_THREAD=1 · forest · frame time (p99) (ms) 18.8 18.4 (−2%)
forest-market · RX_VK_PRESENT_THREAD=1 · market · frame time (p99) (ms) 21.7 20.5 (−5%)

Flags and settings

Flag What it is Values tried Before this PR After this PR Effect (frame rate) Helps / doesn't help / untested
RX_VK_PRESENT_THREAD switch 0, 1 main's default the PR's default forest-market, the PR at 0 → at 1: 59.6 → 60.0 (+1%) no clear effect
Markdown for the PR description
## Measurements

**Verdict:** fail on windows+amd (2/1 report): `forest-market screenshot.max_diff` failed.

Hardware: 1: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416` `AMD Ryzen 9 5900X 12-Core Processor, 32 GB RAM`; 2: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416` `AMD Ryzen 7 5800X3D 8-Core Processor, 32 GB RAM`  
Scene: forest-market, from the repository's save kokiri-start; each cell's settings and switches as the table names them  
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-market: 1 game start a side, forest 20 s after 5 s warm-up, market 20 s after 5 s warm-up; each number the median of the runs, then of 2 reports  
How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again)

| | Before: main @ 09cbdd9 | After: this PR @ 3569b8d |
|---|---|---|
| forest-market · `RX_VK_PRESENT_THREAD=0` · forest · frame rate | 60.1 | 59.6 (−1%) |
| forest-market · `RX_VK_PRESENT_THREAD=0` · market · frame rate | 56.3 | 58.9 (+5%) |
| forest-market · `RX_VK_PRESENT_THREAD=0` · forest · frame time (p99) (ms) | 19.3 | 18.5 (−4%) |
| forest-market · `RX_VK_PRESENT_THREAD=0` · market · frame time (p99) (ms) | 21.8 | 20.4 (−6%) |
| forest-market · `RX_VK_PRESENT_THREAD=1` · forest · frame rate | 59.9 | 60.0 (+0%) |
| forest-market · `RX_VK_PRESENT_THREAD=1` · market · frame rate | 56.5 | 59.7 (+6%) |
| forest-market · `RX_VK_PRESENT_THREAD=1` · forest · frame time (p99) (ms) | 18.8 | 18.4 (−2%) |
| forest-market · `RX_VK_PRESENT_THREAD=1` · market · frame time (p99) (ms) | 21.7 | 20.5 (−5%) |

### Flags and settings

| Flag | What it is | Values tried | Before this PR | After this PR | Effect (frame rate) | Helps / doesn't help / untested |
|---|---|---|---|---|---|---|
| `RX_VK_PRESENT_THREAD` | switch | `0`, `1` | main's default | the PR's default | forest-market, the PR at 0 → at 1: 59.6 → 60.0 (+1%) | no clear effect |

Measurements · windows+nvidia

Verdict: fail on windows+nvidia (2/1 report): forest-market screenshot.max_diff failed.

Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0 AMD Ryzen 7 5800H with Radeon Graphics, 16 GB RAM; 2: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 3070, 621.24.0 AMD Ryzen 5 5600X3D 6-Core Processor, 32 GB RAM
Scene: forest-market, from the repository's save kokiri-start; each cell's settings and switches as the table names them
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-market: 1 game start a side, forest 20 s after 5 s warm-up, market 20 s after 5 s warm-up; each number the median of the runs, then of 2 reports
How to reproduce: the farm's plan above (@Beanstalk on this PR runs it again)

Before: main @ 09cbdd9 After: this PR @ 3569b8d
forest-market · RX_VK_PRESENT_THREAD=0 · forest · frame rate 59.9 59.8 (−0%)
forest-market · RX_VK_PRESENT_THREAD=0 · market · frame rate 60.0 59.2 (−1%)
forest-market · RX_VK_PRESENT_THREAD=0 · forest · frame time (p99) (ms) 20.0 19.0 (−5%)
forest-market · RX_VK_PRESENT_THREAD=0 · market · frame time (p99) (ms) 21.2 23.4 (+10%)
forest-market · RX_VK_PRESENT_THREAD=1 · forest · frame rate 59.5 59.7 (+0%)
forest-market · RX_VK_PRESENT_THREAD=1 · market · frame rate 58.0 59.6 (+3%)
forest-market · RX_VK_PRESENT_THREAD=1 · forest · frame time (p99) (ms) 20.1 19.6 (−3%)
forest-market · RX_VK_PRESENT_THREAD=1 · market · frame time (p99) (ms) 21.8 21.9 (+0%)

Flags and settings

Flag What it is Values tried Before this PR After this PR Effect (frame rate) Helps / doesn't help / untested
RX_VK_PRESENT_THREAD switch 0, 1 main's default the PR's default forest-market, the PR at 0 → at 1: 59.8 → 59.7 (−0%) no clear effect
Markdown for the PR description
## Measurements

**Verdict:** fail on windows+nvidia (2/1 report): `forest-market screenshot.max_diff` failed.

Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0` `AMD Ryzen 7 5800H with Radeon Graphics, 16 GB RAM`; 2: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3070, 621.24.0` `AMD Ryzen 5 5600X3D 6-Core Processor, 32 GB RAM`  
Scene: forest-market, from the repository's save kokiri-start; each cell's settings and switches as the table names them  
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-market: 1 game start a side, forest 20 s after 5 s warm-up, market 20 s after 5 s warm-up; each number the median of the runs, then of 2 reports  
How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again)

| | Before: main @ 09cbdd9 | After: this PR @ 3569b8d |
|---|---|---|
| forest-market · `RX_VK_PRESENT_THREAD=0` · forest · frame rate | 59.9 | 59.8 (−0%) |
| forest-market · `RX_VK_PRESENT_THREAD=0` · market · frame rate | 60.0 | 59.2 (−1%) |
| forest-market · `RX_VK_PRESENT_THREAD=0` · forest · frame time (p99) (ms) | 20.0 | 19.0 (−5%) |
| forest-market · `RX_VK_PRESENT_THREAD=0` · market · frame time (p99) (ms) | 21.2 | 23.4 (+10%) |
| forest-market · `RX_VK_PRESENT_THREAD=1` · forest · frame rate | 59.5 | 59.7 (+0%) |
| forest-market · `RX_VK_PRESENT_THREAD=1` · market · frame rate | 58.0 | 59.6 (+3%) |
| forest-market · `RX_VK_PRESENT_THREAD=1` · forest · frame time (p99) (ms) | 20.1 | 19.6 (−3%) |
| forest-market · `RX_VK_PRESENT_THREAD=1` · market · frame time (p99) (ms) | 21.8 | 21.9 (+0%) |

### Flags and settings

| Flag | What it is | Values tried | Before this PR | After this PR | Effect (frame rate) | Helps / doesn't help / untested |
|---|---|---|---|---|---|---|
| `RX_VK_PRESENT_THREAD` | switch | `0`, `1` | main's default | the PR's default | forest-market, the PR at 0 → at 1: 59.8 → 59.7 (−0%) | no clear effect |

Measurements · linux+amd

Verdict: fail on linux+amd (1/1 report): forest-market screenshot.max_diff failed.

Hardware: 1: linux+amd+radv+dgpu AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7 AMD Ryzen 7 5800X3D 8-Core Processor, 64 GB RAM
Scene: forest-market, from the repository's save kokiri-start; each cell's settings and switches as the table names them
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-market: 1 game start a side, forest 20 s after 5 s warm-up, market 20 s after 5 s warm-up; each number the median of the runs, then of 1 report
How to reproduce: the farm's plan above (@Beanstalk on this PR runs it again)

Before: main @ 09cbdd9 After: this PR @ 3569b8d
forest-market · RX_VK_PRESENT_THREAD=0 · forest · frame rate 60.0 59.6 (−1%)
forest-market · RX_VK_PRESENT_THREAD=0 · market · frame rate 45.9 60.0 (+31%)
forest-market · RX_VK_PRESENT_THREAD=0 · forest · frame time (p99) (ms) 18.3 17.8 (−3%)
forest-market · RX_VK_PRESENT_THREAD=0 · market · frame time (p99) (ms) 21.2 20.2 (−5%)
forest-market · RX_VK_PRESENT_THREAD=1 · forest · frame rate 60.0 60.0 (−0%)
forest-market · RX_VK_PRESENT_THREAD=1 · market · frame rate 17.6 59.5 (+239%)
forest-market · RX_VK_PRESENT_THREAD=1 · forest · frame time (p99) (ms) 18.4 17.8 (−3%)
forest-market · RX_VK_PRESENT_THREAD=1 · market · frame time (p99) (ms) 1,011 23.5 (−98%)

Flags and settings

Flag What it is Values tried Before this PR After this PR Effect (frame rate) Helps / doesn't help / untested
RX_VK_PRESENT_THREAD switch 0, 1 main's default the PR's default forest-market, the PR at 0 → at 1: 59.6 → 60.0 (+1%) no clear effect
Markdown for the PR description
## Measurements

**Verdict:** fail on linux+amd (1/1 report): `forest-market screenshot.max_diff` failed.

Hardware: 1: linux+amd+radv+dgpu `AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7` `AMD Ryzen 7 5800X3D 8-Core Processor, 64 GB RAM`  
Scene: forest-market, from the repository's save kokiri-start; each cell's settings and switches as the table names them  
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-market: 1 game start a side, forest 20 s after 5 s warm-up, market 20 s after 5 s warm-up; each number the median of the runs, then of 1 report  
How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again)

| | Before: main @ 09cbdd9 | After: this PR @ 3569b8d |
|---|---|---|
| forest-market · `RX_VK_PRESENT_THREAD=0` · forest · frame rate | 60.0 | 59.6 (−1%) |
| forest-market · `RX_VK_PRESENT_THREAD=0` · market · frame rate | 45.9 | 60.0 (+31%) |
| forest-market · `RX_VK_PRESENT_THREAD=0` · forest · frame time (p99) (ms) | 18.3 | 17.8 (−3%) |
| forest-market · `RX_VK_PRESENT_THREAD=0` · market · frame time (p99) (ms) | 21.2 | 20.2 (−5%) |
| forest-market · `RX_VK_PRESENT_THREAD=1` · forest · frame rate | 60.0 | 60.0 (−0%) |
| forest-market · `RX_VK_PRESENT_THREAD=1` · market · frame rate | 17.6 | 59.5 (+239%) |
| forest-market · `RX_VK_PRESENT_THREAD=1` · forest · frame time (p99) (ms) | 18.4 | 17.8 (−3%) |
| forest-market · `RX_VK_PRESENT_THREAD=1` · market · frame time (p99) (ms) | 1,011 | 23.5 (−98%) |

### Flags and settings

| Flag | What it is | Values tried | Before this PR | After this PR | Effect (frame rate) | Helps / doesn't help / untested |
|---|---|---|---|---|---|---|
| `RX_VK_PRESENT_THREAD` | switch | `0`, `1` | main's default | the PR's default | forest-market, the PR at 0 → at 1: 59.6 → 60.0 (+1%) | no clear effect |
<!-- beanstalk:previous --> <details><summary>Beanstalk test farm · an earlier run: commit <code>3569b8d</code>, run 2 (the newer results are in a comment below)</summary> Commit `3569b8d` · tier **reviewed** · approved by HumanBean · [dashboard](https://beanstalk.magicbean.dev/prs/1702) **What will be tested** · AI plan (`gpt-6.1-terra`) On Windows AMD, Windows NVIDIA and Linux AMD, this plan measures FPS and p99 frame time and compares pictures in Kokiri Forest and the Market. It takes about 21 minutes per tester and tests the presenter thread both off and forced on. Each setting is compared with main, rather than with the PR’s default, because the PR also changes replay when the presenter thread is off. A crash, a frame-time increase over 15%, an FPS drop over 10%, or a picture difference over the threshold fails the plan; sampled pictures cannot reliably detect one-frame flashes. - **Where:** windows+amd (1-2 reports), windows+nvidia (1-2 reports), linux+amd (1-2 reports). - **Matrix:** 2 cells, each on main and the PR: RX_VK_PRESENT_THREAD `0` or `1`. - **forest-market:** from the repository's save `kokiri-start`, then teleport to Kokiri Forest, measure forest for 20 s (after 5 s warm-up), take the picture forest to compare with main, teleport to Market, measure market for 20 s (after 5 s warm-up), take the picture market to compare with main; 1 run on each side for each of 2 cells (2 game starts a run). - **Measured:** crashes, frame times, stutters and hitches, draws and frame rate. - **The PR fails if:** it crashes; or frame rate is more than 10% below main; or a picture differs from main by more than 10%; or frame time (p99) is more than 15% above main. - **Time:** about 24 min of game runs per tester (4 game starts), plus the two builds. Started at 07:21 UTC. Run 2: re-planned by HumanBean. **Estimate:** done in about 1 h, from the queue and the testers online now. | Target | Reports | Crash | Frame p99 (ms) vs main | VRAM peak (MB) vs main | Result | | --- | --- | --- | --- | --- | --- | | windows+amd · 1: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416`; 2: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416` | 2/1 [1](https://beanstalk.magicbean.dev/reports/rp_5009f0f683143955) [2](https://beanstalk.magicbean.dev/reports/rp_c45a1107923a365f) | none | 18.5 vs 19.3 (−4%) | — | fail | | windows+nvidia · 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0`; 2: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3070, 621.24.0` | 2/1 [1](https://beanstalk.magicbean.dev/reports/rp_3bdfd674e0a16009) [2](https://beanstalk.magicbean.dev/reports/rp_dabcf9c0a1af5264) | none | 19.0 vs 20.0 (−5%) | — | fail | | linux+amd · 1: linux+amd+radv+dgpu `AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7` | 1/1 [1](https://beanstalk.magicbean.dev/reports/rp_446ffb6b133f1a62) | none | 17.8 vs 18.3 (−3%) | — | fail | | Scenario · matrix cell | Target | Frame p99 (ms) vs main | Result | | --- | --- | --- | --- | | forest-market · `RX_VK_PRESENT_THREAD=0` | windows+amd | 18.5 vs 19.3 (−4%) | fail | | forest-market · `RX_VK_PRESENT_THREAD=0` | windows+nvidia | 19.0 vs 20.0 (−5%) | fail | | forest-market · `RX_VK_PRESENT_THREAD=0` | linux+amd | 17.8 vs 18.3 (−3%) | fail | | forest-market · `RX_VK_PRESENT_THREAD=1` | windows+amd | 18.4 vs 18.8 (−2%) | fail | | forest-market · `RX_VK_PRESENT_THREAD=1` | windows+nvidia | 19.6 vs 20.1 (−3%) | fail | | forest-market · `RX_VK_PRESENT_THREAD=1` | linux+amd | 17.8 vs 18.4 (−3%) | fail | #### Measurements · windows+amd **Verdict:** fail on windows+amd (2/1 report): `forest-market screenshot.max_diff` failed. Hardware: 1: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416` `AMD Ryzen 9 5900X 12-Core Processor, 32 GB RAM`; 2: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416` `AMD Ryzen 7 5800X3D 8-Core Processor, 32 GB RAM` Scene: forest-market, from the repository's save kokiri-start; each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-market: 1 game start a side, forest 20 s after 5 s warm-up, market 20 s after 5 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ 09cbdd9 | After: this PR @ 3569b8d | |---|---|---| | forest-market · `RX_VK_PRESENT_THREAD=0` · forest · frame rate | 60.1 | 59.6 (−1%) | | forest-market · `RX_VK_PRESENT_THREAD=0` · market · frame rate | 56.3 | 58.9 (+5%) | | forest-market · `RX_VK_PRESENT_THREAD=0` · forest · frame time (p99) (ms) | 19.3 | 18.5 (−4%) | | forest-market · `RX_VK_PRESENT_THREAD=0` · market · frame time (p99) (ms) | 21.8 | 20.4 (−6%) | | forest-market · `RX_VK_PRESENT_THREAD=1` · forest · frame rate | 59.9 | 60.0 (+0%) | | forest-market · `RX_VK_PRESENT_THREAD=1` · market · frame rate | 56.5 | 59.7 (+6%) | | forest-market · `RX_VK_PRESENT_THREAD=1` · forest · frame time (p99) (ms) | 18.8 | 18.4 (−2%) | | forest-market · `RX_VK_PRESENT_THREAD=1` · market · frame time (p99) (ms) | 21.7 | 20.5 (−5%) | ### Flags and settings | Flag | What it is | Values tried | Before this PR | After this PR | Effect (frame rate) | Helps / doesn't help / untested | |---|---|---|---|---|---|---| | `RX_VK_PRESENT_THREAD` | switch | `0`, `1` | main's default | the PR's default | forest-market, the PR at 0 → at 1: 59.6 → 60.0 (+1%) | no clear effect | <details><summary>Markdown for the PR description</summary> ```markdown ## Measurements **Verdict:** fail on windows+amd (2/1 report): `forest-market screenshot.max_diff` failed. Hardware: 1: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416` `AMD Ryzen 9 5900X 12-Core Processor, 32 GB RAM`; 2: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416` `AMD Ryzen 7 5800X3D 8-Core Processor, 32 GB RAM` Scene: forest-market, from the repository's save kokiri-start; each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-market: 1 game start a side, forest 20 s after 5 s warm-up, market 20 s after 5 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ 09cbdd9 | After: this PR @ 3569b8d | |---|---|---| | forest-market · `RX_VK_PRESENT_THREAD=0` · forest · frame rate | 60.1 | 59.6 (−1%) | | forest-market · `RX_VK_PRESENT_THREAD=0` · market · frame rate | 56.3 | 58.9 (+5%) | | forest-market · `RX_VK_PRESENT_THREAD=0` · forest · frame time (p99) (ms) | 19.3 | 18.5 (−4%) | | forest-market · `RX_VK_PRESENT_THREAD=0` · market · frame time (p99) (ms) | 21.8 | 20.4 (−6%) | | forest-market · `RX_VK_PRESENT_THREAD=1` · forest · frame rate | 59.9 | 60.0 (+0%) | | forest-market · `RX_VK_PRESENT_THREAD=1` · market · frame rate | 56.5 | 59.7 (+6%) | | forest-market · `RX_VK_PRESENT_THREAD=1` · forest · frame time (p99) (ms) | 18.8 | 18.4 (−2%) | | forest-market · `RX_VK_PRESENT_THREAD=1` · market · frame time (p99) (ms) | 21.7 | 20.5 (−5%) | ### Flags and settings | Flag | What it is | Values tried | Before this PR | After this PR | Effect (frame rate) | Helps / doesn't help / untested | |---|---|---|---|---|---|---| | `RX_VK_PRESENT_THREAD` | switch | `0`, `1` | main's default | the PR's default | forest-market, the PR at 0 → at 1: 59.6 → 60.0 (+1%) | no clear effect | ``` </details> #### Measurements · windows+nvidia **Verdict:** fail on windows+nvidia (2/1 report): `forest-market screenshot.max_diff` failed. Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0` `AMD Ryzen 7 5800H with Radeon Graphics, 16 GB RAM`; 2: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3070, 621.24.0` `AMD Ryzen 5 5600X3D 6-Core Processor, 32 GB RAM` Scene: forest-market, from the repository's save kokiri-start; each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-market: 1 game start a side, forest 20 s after 5 s warm-up, market 20 s after 5 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ 09cbdd9 | After: this PR @ 3569b8d | |---|---|---| | forest-market · `RX_VK_PRESENT_THREAD=0` · forest · frame rate | 59.9 | 59.8 (−0%) | | forest-market · `RX_VK_PRESENT_THREAD=0` · market · frame rate | 60.0 | 59.2 (−1%) | | forest-market · `RX_VK_PRESENT_THREAD=0` · forest · frame time (p99) (ms) | 20.0 | 19.0 (−5%) | | forest-market · `RX_VK_PRESENT_THREAD=0` · market · frame time (p99) (ms) | 21.2 | 23.4 (+10%) | | forest-market · `RX_VK_PRESENT_THREAD=1` · forest · frame rate | 59.5 | 59.7 (+0%) | | forest-market · `RX_VK_PRESENT_THREAD=1` · market · frame rate | 58.0 | 59.6 (+3%) | | forest-market · `RX_VK_PRESENT_THREAD=1` · forest · frame time (p99) (ms) | 20.1 | 19.6 (−3%) | | forest-market · `RX_VK_PRESENT_THREAD=1` · market · frame time (p99) (ms) | 21.8 | 21.9 (+0%) | ### Flags and settings | Flag | What it is | Values tried | Before this PR | After this PR | Effect (frame rate) | Helps / doesn't help / untested | |---|---|---|---|---|---|---| | `RX_VK_PRESENT_THREAD` | switch | `0`, `1` | main's default | the PR's default | forest-market, the PR at 0 → at 1: 59.8 → 59.7 (−0%) | no clear effect | <details><summary>Markdown for the PR description</summary> ```markdown ## Measurements **Verdict:** fail on windows+nvidia (2/1 report): `forest-market screenshot.max_diff` failed. Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0` `AMD Ryzen 7 5800H with Radeon Graphics, 16 GB RAM`; 2: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3070, 621.24.0` `AMD Ryzen 5 5600X3D 6-Core Processor, 32 GB RAM` Scene: forest-market, from the repository's save kokiri-start; each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-market: 1 game start a side, forest 20 s after 5 s warm-up, market 20 s after 5 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ 09cbdd9 | After: this PR @ 3569b8d | |---|---|---| | forest-market · `RX_VK_PRESENT_THREAD=0` · forest · frame rate | 59.9 | 59.8 (−0%) | | forest-market · `RX_VK_PRESENT_THREAD=0` · market · frame rate | 60.0 | 59.2 (−1%) | | forest-market · `RX_VK_PRESENT_THREAD=0` · forest · frame time (p99) (ms) | 20.0 | 19.0 (−5%) | | forest-market · `RX_VK_PRESENT_THREAD=0` · market · frame time (p99) (ms) | 21.2 | 23.4 (+10%) | | forest-market · `RX_VK_PRESENT_THREAD=1` · forest · frame rate | 59.5 | 59.7 (+0%) | | forest-market · `RX_VK_PRESENT_THREAD=1` · market · frame rate | 58.0 | 59.6 (+3%) | | forest-market · `RX_VK_PRESENT_THREAD=1` · forest · frame time (p99) (ms) | 20.1 | 19.6 (−3%) | | forest-market · `RX_VK_PRESENT_THREAD=1` · market · frame time (p99) (ms) | 21.8 | 21.9 (+0%) | ### Flags and settings | Flag | What it is | Values tried | Before this PR | After this PR | Effect (frame rate) | Helps / doesn't help / untested | |---|---|---|---|---|---|---| | `RX_VK_PRESENT_THREAD` | switch | `0`, `1` | main's default | the PR's default | forest-market, the PR at 0 → at 1: 59.8 → 59.7 (−0%) | no clear effect | ``` </details> #### Measurements · linux+amd **Verdict:** fail on linux+amd (1/1 report): `forest-market screenshot.max_diff` failed. Hardware: 1: linux+amd+radv+dgpu `AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7` `AMD Ryzen 7 5800X3D 8-Core Processor, 64 GB RAM` Scene: forest-market, from the repository's save kokiri-start; each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-market: 1 game start a side, forest 20 s after 5 s warm-up, market 20 s after 5 s warm-up; each number the median of the runs, then of 1 report How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ 09cbdd9 | After: this PR @ 3569b8d | |---|---|---| | forest-market · `RX_VK_PRESENT_THREAD=0` · forest · frame rate | 60.0 | 59.6 (−1%) | | forest-market · `RX_VK_PRESENT_THREAD=0` · market · frame rate | 45.9 | 60.0 (+31%) | | forest-market · `RX_VK_PRESENT_THREAD=0` · forest · frame time (p99) (ms) | 18.3 | 17.8 (−3%) | | forest-market · `RX_VK_PRESENT_THREAD=0` · market · frame time (p99) (ms) | 21.2 | 20.2 (−5%) | | forest-market · `RX_VK_PRESENT_THREAD=1` · forest · frame rate | 60.0 | 60.0 (−0%) | | forest-market · `RX_VK_PRESENT_THREAD=1` · market · frame rate | 17.6 | 59.5 (+239%) | | forest-market · `RX_VK_PRESENT_THREAD=1` · forest · frame time (p99) (ms) | 18.4 | 17.8 (−3%) | | forest-market · `RX_VK_PRESENT_THREAD=1` · market · frame time (p99) (ms) | 1,011 | 23.5 (−98%) | ### Flags and settings | Flag | What it is | Values tried | Before this PR | After this PR | Effect (frame rate) | Helps / doesn't help / untested | |---|---|---|---|---|---|---| | `RX_VK_PRESENT_THREAD` | switch | `0`, `1` | main's default | the PR's default | forest-market, the PR at 0 → at 1: 59.6 → 60.0 (+1%) | no clear effect | <details><summary>Markdown for the PR description</summary> ```markdown ## Measurements **Verdict:** fail on linux+amd (1/1 report): `forest-market screenshot.max_diff` failed. Hardware: 1: linux+amd+radv+dgpu `AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7` `AMD Ryzen 7 5800X3D 8-Core Processor, 64 GB RAM` Scene: forest-market, from the repository's save kokiri-start; each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-market: 1 game start a side, forest 20 s after 5 s warm-up, market 20 s after 5 s warm-up; each number the median of the runs, then of 1 report How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ 09cbdd9 | After: this PR @ 3569b8d | |---|---|---| | forest-market · `RX_VK_PRESENT_THREAD=0` · forest · frame rate | 60.0 | 59.6 (−1%) | | forest-market · `RX_VK_PRESENT_THREAD=0` · market · frame rate | 45.9 | 60.0 (+31%) | | forest-market · `RX_VK_PRESENT_THREAD=0` · forest · frame time (p99) (ms) | 18.3 | 17.8 (−3%) | | forest-market · `RX_VK_PRESENT_THREAD=0` · market · frame time (p99) (ms) | 21.2 | 20.2 (−5%) | | forest-market · `RX_VK_PRESENT_THREAD=1` · forest · frame rate | 60.0 | 60.0 (−0%) | | forest-market · `RX_VK_PRESENT_THREAD=1` · market · frame rate | 17.6 | 59.5 (+239%) | | forest-market · `RX_VK_PRESENT_THREAD=1` · forest · frame time (p99) (ms) | 18.4 | 17.8 (−3%) | | forest-market · `RX_VK_PRESENT_THREAD=1` · market · frame time (p99) (ms) | 1,011 | 23.5 (−98%) | ### Flags and settings | Flag | What it is | Values tried | Before this PR | After this PR | Effect (frame rate) | Helps / doesn't help / untested | |---|---|---|---|---|---|---| | `RX_VK_PRESENT_THREAD` | switch | `0`, `1` | main's default | the PR's default | forest-market, the PR at 0 → at 1: 59.6 → 60.0 (+1%) | no clear effect | ``` </details> </details>
Author
Owner

@Beanstalk compare main, this PR with its default, and this PR with RX_VK_PRESENT_THREAD=1, on windows+amd, windows+nvidia, linux+amd, steamdeck, windows+intel and linux+intel: Kokiri Forest and the Market, standing and walking with the camera turning; fps, p99 frame time, the pictures against main, and the frame log (RX_VK_FRAMELOG) for one-frame dark pictures and pictures that go dark and stay dark (this replaces the request above: Steam Deck and Intel added, Intel being where #1121 saw dark pictures)

@Beanstalk compare main, this PR with its default, and this PR with `RX_VK_PRESENT_THREAD=1`, on windows+amd, windows+nvidia, linux+amd, steamdeck, windows+intel and linux+intel: Kokiri Forest and the Market, standing and walking with the camera turning; fps, p99 frame time, the pictures against main, and the frame log (`RX_VK_FRAMELOG`) for one-frame dark pictures and pictures that go dark and stay dark (this replaces the request above: Steam Deck and Intel added, Intel being where #1121 saw dark pictures)
Author
Owner

@Beanstalk with the frame rate uncapped (settings frame_rate_cap=0, vsync=0: the last run sat at the 60 cap on every side), compare main, this PR with its default, and this PR with RX_VK_PRESENT_THREAD=1, on windows+amd, windows+nvidia, linux+amd, steamdeck, windows+intel and linux+intel: Kokiri Forest and the Market, standing and walking with the camera turning, 2 runs a side; fps, p99 frame time, the pictures against main, and the frame log (RX_VK_FRAMELOG) for one-frame dark pictures and pictures that go dark and stay dark

@Beanstalk with the frame rate uncapped (settings frame_rate_cap=0, vsync=0: the last run sat at the 60 cap on every side), compare main, this PR with its default, and this PR with `RX_VK_PRESENT_THREAD=1`, on windows+amd, windows+nvidia, linux+amd, steamdeck, windows+intel and linux+intel: Kokiri Forest and the Market, standing and walking with the camera turning, 2 runs a side; fps, p99 frame time, the pictures against main, and the frame log (`RX_VK_FRAMELOG`) for one-frame dark pictures and pictures that go dark and stay dark
Member
Beanstalk test farm · an earlier run: commit 3569b8d, run 3 (the newer results are in a comment below)

Commit 3569b8d · tier reviewed · approved by HumanBean · dashboard

What will be tested · AI plan (gpt-6.1-terra)

Two runs per side visit Kokiri Forest and the Market on the six requested hardware targets, comparing main with the PR default and with the presenter thread forced on; Intel targets wait for matching testers. The presenter-thread axis isolates the forced-on configuration, and the settings use the actual uncapped frame-rate and V-Sync-off values rather than the requested numeric values, which select 60 FPS and Auto. The runs take about 45 minutes per tester and measure FPS and p99 frame time, with pictures compared against main; crashes, substantial performance regressions, or picture differences fail. The farm cannot use the requested frame log, so sampled pictures cannot reliably detect single-frame flashes or every persistent darkening; walking and camera turning are exercised separately. No tester online now matches windows+intel, linux+intel: those targets wait for one.

  • Where: windows+amd (1-2 reports), windows+nvidia (1-2 reports), linux+amd (1-2 reports), steamdeck (1-2 reports), windows+intel (1-2 reports), linux+intel (1-2 reports).
  • Matrix: 1 cell, each on main and the PR: RX_VK_PRESENT_THREAD 1 (PR only).
  • default-presenter: from the repository's save kokiri-start (settings vsync=2, frame_rate_cap=6), then teleport to Kokiri Forest, measure kokiri-standing for 15 s (after 5 s warm-up), take the picture kokiri-standing to compare with main, move the stick, measure kokiri-after-motion for 10 s (after 0 s warm-up), take the picture kokiri-after-motion to compare with main, teleport to Market, measure market-standing for 15 s (after 5 s warm-up), take the picture market-standing to compare with main, measure market-after-motion for 10 s (after 0 s warm-up), take the picture market-after-motion to compare with main; 2 runs on each side.
  • forced-presenter: from the repository's save kokiri-start (settings vsync=2, frame_rate_cap=6), then teleport to Kokiri Forest, measure kokiri-standing for 15 s (after 5 s warm-up), take the picture kokiri-standing to compare with main, move the stick, measure kokiri-after-motion for 10 s (after 0 s warm-up), take the picture kokiri-after-motion to compare with main, teleport to Market, measure market-standing for 15 s (after 5 s warm-up), take the picture market-standing to compare with main, measure market-after-motion for 10 s (after 0 s warm-up), take the picture market-after-motion to compare with main; 2 runs on each side.
  • Measured: crashes, frame times, stutters and hitches, draws and frame rate, screenshots against main, the game's log.
  • The PR fails if: it crashes; or frame rate is more than 15% below main; or a picture differs from main by more than 40%; or frame time (p99) is more than 20% above main; or forbidden log lines is above 0.
  • Time: about 48 min of game runs per tester (8 game starts), plus the two builds.

Started at 08:41 UTC. Run 3: re-planned by HumanBean.

⚠ No tester has a PC for linux+intel (none seen in 14 days): it waits until one signs in.

Target Reports Crash Frame p99 (ms) vs main VRAM peak (MB) vs main Result
windows+amd · 1: windows+amd+amd-proprietary+dgpu AMD Radeon RX 9070 XT, 2.0.416; 2: windows+amd+amd-proprietary+dgpu AMD Radeon RX 9070 XT, 2.0.416 2/1 1 2 none 13.1 vs 15.2 (−14%) — fail ⚠ outlier
windows+nvidia · 1: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0; 2: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 3090, 621.24.0 2/1 1 2 none 16.7 vs 23.3 (−29%) — fail
linux+amd · 1: linux+amd+radv+dgpu AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7; 2: linux+amd+radv+igpu+handheld AMD Custom GPU 0405 (RADV VANGOGH), 26.1.99 2/1 1 2 none 34.1 vs 43.0 (−21%) — fail ⚠ outlier
steamdeck · 1: linux+amd+radv+igpu+handheld AMD Custom GPU 0405 (RADV VANGOGH), 26.1.99 1/1 1 none 83.9 vs 96.5 (−13%) — fail
windows+intel 0/1 — — — queued
linux+intel 0/1 — — — queued

Measurements · windows+amd

Verdict: fail on windows+amd (2/1 report): forced-presenter screenshot.max_diff; default-presenter screenshot.max_diff failed.

Hardware: 1: windows+amd+amd-proprietary+dgpu AMD Radeon RX 9070 XT, 2.0.416 AMD Ryzen 7 5800X3D 8-Core Processor, 32 GB RAM; 2: windows+amd+amd-proprietary+dgpu AMD Radeon RX 9070 XT, 2.0.416 AMD Ryzen 9 5900X 12-Core Processor, 32 GB RAM
Scene: default-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); forced-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); default-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; forced-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports
How to reproduce: the farm's plan above (@Beanstalk on this PR runs it again)

Before: main @ 09cbdd9 After: this PR @ 3569b8d
default-presenter · kokiri-standing · frame rate 85.2 94.9 (+11%)
default-presenter · market-standing · frame rate 62.1 62.5 (+1%)
default-presenter · kokiri-after-motion · frame rate 88.0 97.5 (+11%)
default-presenter · market-after-motion · frame rate 80.9 76.5 (−5%)
default-presenter · kokiri-standing · frame time (p99) (ms) 15.2 13.1 (−14%)
default-presenter · market-standing · frame time (p99) (ms) 20.0 19.2 (−4%)
default-presenter · kokiri-after-motion · frame time (p99) (ms) 14.3 13.8 (−4%)
default-presenter · market-after-motion · frame time (p99) (ms) 16.7 16.6 (−1%)
default-presenter · forbidden log lines 0.0 0.0
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · kokiri-standing · frame rate 86.3 94.5 (+9%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · market-standing · frame rate 63.3 67.3 (+6%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · kokiri-after-motion · frame rate 85.0 95.3 (+12%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · market-after-motion · frame rate 82.2 84.0 (+2%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · kokiri-standing · frame time (p99) (ms) 13.5 12.5 (−7%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · market-standing · frame time (p99) (ms) 19.5 18.0 (−7%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · kokiri-after-motion · frame time (p99) (ms) 14.0 13.4 (−4%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · market-after-motion · frame time (p99) (ms) 16.2 15.5 (−4%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · forbidden log lines 0.0 0.0

Flags and settings

Flag What it is Values tried Before this PR After this PR Effect (frame rate) Helps / doesn't help / untested
RX_VK_PRESENT_THREAD switch the PR adds (set on the PR side only) 1 not in main the PR's default forced-presenter, main without it → the PR with 1: 86.3 → 94.5 (+9%) helps
Markdown for the PR description
## Measurements

**Verdict:** fail on windows+amd (2/1 report): `forced-presenter screenshot.max_diff`; `default-presenter screenshot.max_diff` failed.

Hardware: 1: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416` `AMD Ryzen 7 5800X3D 8-Core Processor, 32 GB RAM`; 2: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416` `AMD Ryzen 9 5900X 12-Core Processor, 32 GB RAM`  
Scene: default-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); forced-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them  
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); default-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; forced-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports  
How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again)

| | Before: main @ 09cbdd9 | After: this PR @ 3569b8d |
|---|---|---|
| default-presenter · kokiri-standing · frame rate | 85.2 | 94.9 (+11%) |
| default-presenter · market-standing · frame rate | 62.1 | 62.5 (+1%) |
| default-presenter · kokiri-after-motion · frame rate | 88.0 | 97.5 (+11%) |
| default-presenter · market-after-motion · frame rate | 80.9 | 76.5 (−5%) |
| default-presenter · kokiri-standing · frame time (p99) (ms) | 15.2 | 13.1 (−14%) |
| default-presenter · market-standing · frame time (p99) (ms) | 20.0 | 19.2 (−4%) |
| default-presenter · kokiri-after-motion · frame time (p99) (ms) | 14.3 | 13.8 (−4%) |
| default-presenter · market-after-motion · frame time (p99) (ms) | 16.7 | 16.6 (−1%) |
| default-presenter · forbidden log lines | 0.0 | 0.0 |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-standing · frame rate | 86.3 | 94.5 (+9%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-standing · frame rate | 63.3 | 67.3 (+6%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-after-motion · frame rate | 85.0 | 95.3 (+12%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-after-motion · frame rate | 82.2 | 84.0 (+2%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-standing · frame time (p99) (ms) | 13.5 | 12.5 (−7%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-standing · frame time (p99) (ms) | 19.5 | 18.0 (−7%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-after-motion · frame time (p99) (ms) | 14.0 | 13.4 (−4%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-after-motion · frame time (p99) (ms) | 16.2 | 15.5 (−4%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · forbidden log lines | 0.0 | 0.0 |

### Flags and settings

| Flag | What it is | Values tried | Before this PR | After this PR | Effect (frame rate) | Helps / doesn't help / untested |
|---|---|---|---|---|---|---|
| `RX_VK_PRESENT_THREAD` | switch the PR adds (set on the PR side only) | `1` | not in main | the PR's default | forced-presenter, main without it → the PR with 1: 86.3 → 94.5 (+9%) | helps |

Measurements · windows+nvidia

Verdict: fail on windows+nvidia (2/1 report): default-presenter screenshot.max_diff; forced-presenter screenshot.max_diff failed.

Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0 AMD Ryzen 7 5800H with Radeon Graphics, 16 GB RAM; 2: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 3090, 621.24.0 AMD Ryzen 9 5900X 12-Core Processor, 128 GB RAM
Scene: default-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); forced-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); default-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; forced-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports
How to reproduce: the farm's plan above (@Beanstalk on this PR runs it again)

Before: main @ 09cbdd9 After: this PR @ 3569b8d
default-presenter · kokiri-standing · frame rate 73.5 76.0 (+3%)
default-presenter · market-standing · frame rate 62.0 64.0 (+3%)
default-presenter · kokiri-after-motion · frame rate 79.7 77.6 (−3%)
default-presenter · market-after-motion · frame rate 66.6 67.6 (+1%)
default-presenter · kokiri-standing · frame time (p99) (ms) 23.3 16.7 (−29%)
default-presenter · market-standing · frame time (p99) (ms) 20.8 20.2 (−3%)
default-presenter · kokiri-after-motion · frame time (p99) (ms) 17.3 15.6 (−9%)
default-presenter · market-after-motion · frame time (p99) (ms) 19.4 19.2 (−1%)
default-presenter · forbidden log lines 0.0 0.0
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · kokiri-standing · frame rate 78.1 79.2 (+1%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · market-standing · frame rate 62.8 63.9 (+2%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · kokiri-after-motion · frame rate 79.7 80.7 (+1%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · market-after-motion · frame rate 68.2 64.8 (−5%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · kokiri-standing · frame time (p99) (ms) 17.5 20.5 (+17%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · market-standing · frame time (p99) (ms) 20.7 20.4 (−1%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · kokiri-after-motion · frame time (p99) (ms) 17.3 17.1 (−2%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · market-after-motion · frame time (p99) (ms) 18.8 20.9 (+11%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · forbidden log lines 0.0 0.0

Flags and settings

Flag What it is Values tried Before this PR After this PR Effect (frame rate) Helps / doesn't help / untested
RX_VK_PRESENT_THREAD switch the PR adds (set on the PR side only) 1 not in main the PR's default forced-presenter, main without it → the PR with 1: 78.1 → 79.2 (+1%) no clear effect
Markdown for the PR description
## Measurements

**Verdict:** fail on windows+nvidia (2/1 report): `default-presenter screenshot.max_diff`; `forced-presenter screenshot.max_diff` failed.

Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0` `AMD Ryzen 7 5800H with Radeon Graphics, 16 GB RAM`; 2: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3090, 621.24.0` `AMD Ryzen 9 5900X 12-Core Processor, 128 GB RAM`  
Scene: default-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); forced-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them  
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); default-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; forced-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports  
How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again)

| | Before: main @ 09cbdd9 | After: this PR @ 3569b8d |
|---|---|---|
| default-presenter · kokiri-standing · frame rate | 73.5 | 76.0 (+3%) |
| default-presenter · market-standing · frame rate | 62.0 | 64.0 (+3%) |
| default-presenter · kokiri-after-motion · frame rate | 79.7 | 77.6 (−3%) |
| default-presenter · market-after-motion · frame rate | 66.6 | 67.6 (+1%) |
| default-presenter · kokiri-standing · frame time (p99) (ms) | 23.3 | 16.7 (−29%) |
| default-presenter · market-standing · frame time (p99) (ms) | 20.8 | 20.2 (−3%) |
| default-presenter · kokiri-after-motion · frame time (p99) (ms) | 17.3 | 15.6 (−9%) |
| default-presenter · market-after-motion · frame time (p99) (ms) | 19.4 | 19.2 (−1%) |
| default-presenter · forbidden log lines | 0.0 | 0.0 |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-standing · frame rate | 78.1 | 79.2 (+1%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-standing · frame rate | 62.8 | 63.9 (+2%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-after-motion · frame rate | 79.7 | 80.7 (+1%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-after-motion · frame rate | 68.2 | 64.8 (−5%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-standing · frame time (p99) (ms) | 17.5 | 20.5 (+17%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-standing · frame time (p99) (ms) | 20.7 | 20.4 (−1%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-after-motion · frame time (p99) (ms) | 17.3 | 17.1 (−2%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-after-motion · frame time (p99) (ms) | 18.8 | 20.9 (+11%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · forbidden log lines | 0.0 | 0.0 |

### Flags and settings

| Flag | What it is | Values tried | Before this PR | After this PR | Effect (frame rate) | Helps / doesn't help / untested |
|---|---|---|---|---|---|---|
| `RX_VK_PRESENT_THREAD` | switch the PR adds (set on the PR side only) | `1` | not in main | the PR's default | forced-presenter, main without it → the PR with 1: 78.1 → 79.2 (+1%) | no clear effect |

Measurements · linux+amd

Verdict: fail on linux+amd (2/1 report): default-presenter screenshot.max_diff; forced-presenter screenshot.max_diff; forced-presenter kokiri-standing.frametime_p99_ms.max_delta_pct (+50.2%) failed.

Hardware: 1: linux+amd+radv+dgpu AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7 AMD Ryzen 7 5800X3D 8-Core Processor, 64 GB RAM; 2: linux+amd+radv+igpu+handheld AMD Custom GPU 0405 (RADV VANGOGH), 26.1.99 AMD Custom APU 0405, 12 GB RAM
Scene: default-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); forced-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); default-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; forced-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports
How to reproduce: the farm's plan above (@Beanstalk on this PR runs it again)

Before: main @ 09cbdd9 After: this PR @ 3569b8d
default-presenter · kokiri-standing · frame rate 46.2 61.3 (+33%)
default-presenter · market-standing · frame rate 13.7 45.0 (+228%)
default-presenter · kokiri-after-motion · frame rate 49.1 61.1 (+25%)
default-presenter · market-after-motion · frame rate 40.5 54.9 (+36%)
default-presenter · kokiri-standing · frame time (p99) (ms) 43.0 34.1 (−21%)
default-presenter · market-standing · frame time (p99) (ms) 549.9 71.6 (−87%)
default-presenter · kokiri-after-motion · frame time (p99) (ms) 40.0 33.4 (−17%)
default-presenter · market-after-motion · frame time (p99) (ms) 65.3 50.7 (−22%)
default-presenter · forbidden log lines 0.0 0.0
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · kokiri-standing · frame rate 49.5 59.9 (+21%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · market-standing · frame rate 14.5 72.2 (+397%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · kokiri-after-motion · frame rate 49.5 60.6 (+22%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · market-after-motion · frame rate 45.7 89.9 (+97%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · kokiri-standing · frame time (p99) (ms) 35.8 48.8 (+36%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · market-standing · frame time (p99) (ms) 546.7 61.3 (−89%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · kokiri-after-motion · frame time (p99) (ms) 36.4 36.9 (+1%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · market-after-motion · frame time (p99) (ms) 58.7 14.8 (−75%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · forbidden log lines 0.0 0.0

Flags and settings

Flag What it is Values tried Before this PR After this PR Effect (frame rate) Helps / doesn't help / untested
RX_VK_PRESENT_THREAD switch the PR adds (set on the PR side only) 1 not in main the PR's default forced-presenter, main without it → the PR with 1: 49.5 → 59.9 (+21%) helps
Markdown for the PR description
## Measurements

**Verdict:** fail on linux+amd (2/1 report): `default-presenter screenshot.max_diff`; `forced-presenter screenshot.max_diff`; `forced-presenter kokiri-standing.frametime_p99_ms.max_delta_pct (+50.2%)` failed.

Hardware: 1: linux+amd+radv+dgpu `AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7` `AMD Ryzen 7 5800X3D 8-Core Processor, 64 GB RAM`; 2: linux+amd+radv+igpu+handheld `AMD Custom GPU 0405 (RADV VANGOGH), 26.1.99` `AMD Custom APU 0405, 12 GB RAM`  
Scene: default-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); forced-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them  
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); default-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; forced-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports  
How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again)

| | Before: main @ 09cbdd9 | After: this PR @ 3569b8d |
|---|---|---|
| default-presenter · kokiri-standing · frame rate | 46.2 | 61.3 (+33%) |
| default-presenter · market-standing · frame rate | 13.7 | 45.0 (+228%) |
| default-presenter · kokiri-after-motion · frame rate | 49.1 | 61.1 (+25%) |
| default-presenter · market-after-motion · frame rate | 40.5 | 54.9 (+36%) |
| default-presenter · kokiri-standing · frame time (p99) (ms) | 43.0 | 34.1 (−21%) |
| default-presenter · market-standing · frame time (p99) (ms) | 549.9 | 71.6 (−87%) |
| default-presenter · kokiri-after-motion · frame time (p99) (ms) | 40.0 | 33.4 (−17%) |
| default-presenter · market-after-motion · frame time (p99) (ms) | 65.3 | 50.7 (−22%) |
| default-presenter · forbidden log lines | 0.0 | 0.0 |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-standing · frame rate | 49.5 | 59.9 (+21%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-standing · frame rate | 14.5 | 72.2 (+397%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-after-motion · frame rate | 49.5 | 60.6 (+22%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-after-motion · frame rate | 45.7 | 89.9 (+97%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-standing · frame time (p99) (ms) | 35.8 | 48.8 (+36%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-standing · frame time (p99) (ms) | 546.7 | 61.3 (−89%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-after-motion · frame time (p99) (ms) | 36.4 | 36.9 (+1%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-after-motion · frame time (p99) (ms) | 58.7 | 14.8 (−75%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · forbidden log lines | 0.0 | 0.0 |

### Flags and settings

| Flag | What it is | Values tried | Before this PR | After this PR | Effect (frame rate) | Helps / doesn't help / untested |
|---|---|---|---|---|---|---|
| `RX_VK_PRESENT_THREAD` | switch the PR adds (set on the PR side only) | `1` | not in main | the PR's default | forced-presenter, main without it → the PR with 1: 49.5 → 59.9 (+21%) | helps |

Measurements · steamdeck

Verdict: fail on steamdeck (1/1 report): default-presenter screenshot.max_diff failed.

Hardware: 1: linux+amd+radv+igpu+handheld AMD Custom GPU 0405 (RADV VANGOGH), 26.1.99 AMD Custom APU 0405, 12 GB RAM
Scene: default-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); forced-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); default-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; forced-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; each number the median of the runs, then of 1 report
How to reproduce: the farm's plan above (@Beanstalk on this PR runs it again)

Before: main @ 09cbdd9 After: this PR @ 3569b8d
default-presenter · kokiri-standing · frame rate 20.1 21.3 (+6%)
default-presenter · kokiri-after-motion · frame rate 21.5 21.9 (+2%)
default-presenter · market-standing · frame rate — 18.1
default-presenter · market-after-motion · frame rate — 16.9
default-presenter · kokiri-standing · frame time (p99) (ms) 96.5 83.9 (−13%)
default-presenter · kokiri-after-motion · frame time (p99) (ms) 58.8 58.6 (−0%)
default-presenter · market-standing · frame time (p99) (ms) — 90.6
default-presenter · market-after-motion · frame time (p99) (ms) — 102.9
default-presenter · forbidden log lines 0.0 0.0
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · kokiri-standing · frame rate 22.4 22.5 (+1%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · market-standing · frame rate 18.3 18.4 (+0%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · kokiri-after-motion · frame rate 22.6 22.5 (−0%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · market-after-motion · frame rate 18.5 17.7 (−4%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · kokiri-standing · frame time (p99) (ms) 58.5 54.7 (−7%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · market-standing · frame time (p99) (ms) 80.7 86.8 (+8%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · kokiri-after-motion · frame time (p99) (ms) 54.1 56.1 (+4%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · market-after-motion · frame time (p99) (ms) 84.4 96.1 (+14%)
forced-presenter · RX_VK_PRESENT_THREAD=1 (PR only) · forbidden log lines 0.0 0.0

Flags and settings

Flag What it is Values tried Before this PR After this PR Effect (frame rate) Helps / doesn't help / untested
RX_VK_PRESENT_THREAD switch the PR adds (set on the PR side only) 1 not in main the PR's default forced-presenter, main without it → the PR with 1: 22.4 → 22.5 (+1%) no clear effect
Markdown for the PR description
## Measurements

**Verdict:** fail on steamdeck (1/1 report): `default-presenter screenshot.max_diff` failed.

Hardware: 1: linux+amd+radv+igpu+handheld `AMD Custom GPU 0405 (RADV VANGOGH), 26.1.99` `AMD Custom APU 0405, 12 GB RAM`  
Scene: default-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); forced-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them  
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); default-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; forced-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; each number the median of the runs, then of 1 report  
How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again)

| | Before: main @ 09cbdd9 | After: this PR @ 3569b8d |
|---|---|---|
| default-presenter · kokiri-standing · frame rate | 20.1 | 21.3 (+6%) |
| default-presenter · kokiri-after-motion · frame rate | 21.5 | 21.9 (+2%) |
| default-presenter · market-standing · frame rate | — | 18.1 |
| default-presenter · market-after-motion · frame rate | — | 16.9 |
| default-presenter · kokiri-standing · frame time (p99) (ms) | 96.5 | 83.9 (−13%) |
| default-presenter · kokiri-after-motion · frame time (p99) (ms) | 58.8 | 58.6 (−0%) |
| default-presenter · market-standing · frame time (p99) (ms) | — | 90.6 |
| default-presenter · market-after-motion · frame time (p99) (ms) | — | 102.9 |
| default-presenter · forbidden log lines | 0.0 | 0.0 |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-standing · frame rate | 22.4 | 22.5 (+1%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-standing · frame rate | 18.3 | 18.4 (+0%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-after-motion · frame rate | 22.6 | 22.5 (−0%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-after-motion · frame rate | 18.5 | 17.7 (−4%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-standing · frame time (p99) (ms) | 58.5 | 54.7 (−7%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-standing · frame time (p99) (ms) | 80.7 | 86.8 (+8%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-after-motion · frame time (p99) (ms) | 54.1 | 56.1 (+4%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-after-motion · frame time (p99) (ms) | 84.4 | 96.1 (+14%) |
| forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · forbidden log lines | 0.0 | 0.0 |

### Flags and settings

| Flag | What it is | Values tried | Before this PR | After this PR | Effect (frame rate) | Helps / doesn't help / untested |
|---|---|---|---|---|---|---|
| `RX_VK_PRESENT_THREAD` | switch the PR adds (set on the PR side only) | `1` | not in main | the PR's default | forced-presenter, main without it → the PR with 1: 22.4 → 22.5 (+1%) | no clear effect |
<!-- beanstalk:previous --> <details><summary>Beanstalk test farm · an earlier run: commit <code>3569b8d</code>, run 3 (the newer results are in a comment below)</summary> Commit `3569b8d` · tier **reviewed** · approved by HumanBean · [dashboard](https://beanstalk.magicbean.dev/prs/1702) **What will be tested** · AI plan (`gpt-6.1-terra`) Two runs per side visit Kokiri Forest and the Market on the six requested hardware targets, comparing main with the PR default and with the presenter thread forced on; Intel targets wait for matching testers. The presenter-thread axis isolates the forced-on configuration, and the settings use the actual uncapped frame-rate and V-Sync-off values rather than the requested numeric values, which select 60 FPS and Auto. The runs take about 45 minutes per tester and measure FPS and p99 frame time, with pictures compared against main; crashes, substantial performance regressions, or picture differences fail. The farm cannot use the requested frame log, so sampled pictures cannot reliably detect single-frame flashes or every persistent darkening; walking and camera turning are exercised separately. No tester online now matches windows+intel, linux+intel: those targets wait for one. - **Where:** windows+amd (1-2 reports), windows+nvidia (1-2 reports), linux+amd (1-2 reports), steamdeck (1-2 reports), windows+intel (1-2 reports), linux+intel (1-2 reports). - **Matrix:** 1 cell, each on main and the PR: RX_VK_PRESENT_THREAD `1` (PR only). - **default-presenter:** from the repository's save `kokiri-start` (settings vsync=2, frame_rate_cap=6), then teleport to Kokiri Forest, measure kokiri-standing for 15 s (after 5 s warm-up), take the picture kokiri-standing to compare with main, move the stick, measure kokiri-after-motion for 10 s (after 0 s warm-up), take the picture kokiri-after-motion to compare with main, teleport to Market, measure market-standing for 15 s (after 5 s warm-up), take the picture market-standing to compare with main, measure market-after-motion for 10 s (after 0 s warm-up), take the picture market-after-motion to compare with main; 2 runs on each side. - **forced-presenter:** from the repository's save `kokiri-start` (settings vsync=2, frame_rate_cap=6), then teleport to Kokiri Forest, measure kokiri-standing for 15 s (after 5 s warm-up), take the picture kokiri-standing to compare with main, move the stick, measure kokiri-after-motion for 10 s (after 0 s warm-up), take the picture kokiri-after-motion to compare with main, teleport to Market, measure market-standing for 15 s (after 5 s warm-up), take the picture market-standing to compare with main, measure market-after-motion for 10 s (after 0 s warm-up), take the picture market-after-motion to compare with main; 2 runs on each side. - **Measured:** crashes, frame times, stutters and hitches, draws and frame rate, screenshots against main, the game's log. - **The PR fails if:** it crashes; or frame rate is more than 15% below main; or a picture differs from main by more than 40%; or frame time (p99) is more than 20% above main; or forbidden log lines is above 0. - **Time:** about 48 min of game runs per tester (8 game starts), plus the two builds. Started at 08:41 UTC. Run 3: re-planned by HumanBean. ⚠ No tester has a PC for `linux+intel` (none seen in 14 days): it waits until one signs in. | Target | Reports | Crash | Frame p99 (ms) vs main | VRAM peak (MB) vs main | Result | | --- | --- | --- | --- | --- | --- | | windows+amd · 1: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416`; 2: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416` | 2/1 [1](https://beanstalk.magicbean.dev/reports/rp_4af36d408d9304cf) [2](https://beanstalk.magicbean.dev/reports/rp_01c20b8226d7940d) | none | 13.1 vs 15.2 (−14%) | — | fail ⚠ outlier | | windows+nvidia · 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0`; 2: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3090, 621.24.0` | 2/1 [1](https://beanstalk.magicbean.dev/reports/rp_89160c60ed6b579c) [2](https://beanstalk.magicbean.dev/reports/rp_6f75df0f318b29e5) | none | 16.7 vs 23.3 (−29%) | — | fail | | linux+amd · 1: linux+amd+radv+dgpu `AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7`; 2: linux+amd+radv+igpu+handheld `AMD Custom GPU 0405 (RADV VANGOGH), 26.1.99` | 2/1 [1](https://beanstalk.magicbean.dev/reports/rp_8fdadaaac118fe30) [2](https://beanstalk.magicbean.dev/reports/rp_531e9a2b3e65ed16) | none | 34.1 vs 43.0 (−21%) | — | fail ⚠ outlier | | steamdeck · 1: linux+amd+radv+igpu+handheld `AMD Custom GPU 0405 (RADV VANGOGH), 26.1.99` | 1/1 [1](https://beanstalk.magicbean.dev/reports/rp_d5204a53a6df6657) | none | 83.9 vs 96.5 (−13%) | — | fail | | windows+intel | 0/1 | — | — | — | queued | | linux+intel | 0/1 | — | — | — | queued | #### Measurements · windows+amd **Verdict:** fail on windows+amd (2/1 report): `forced-presenter screenshot.max_diff`; `default-presenter screenshot.max_diff` failed. Hardware: 1: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416` `AMD Ryzen 7 5800X3D 8-Core Processor, 32 GB RAM`; 2: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416` `AMD Ryzen 9 5900X 12-Core Processor, 32 GB RAM` Scene: default-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); forced-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); default-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; forced-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ 09cbdd9 | After: this PR @ 3569b8d | |---|---|---| | default-presenter · kokiri-standing · frame rate | 85.2 | 94.9 (+11%) | | default-presenter · market-standing · frame rate | 62.1 | 62.5 (+1%) | | default-presenter · kokiri-after-motion · frame rate | 88.0 | 97.5 (+11%) | | default-presenter · market-after-motion · frame rate | 80.9 | 76.5 (−5%) | | default-presenter · kokiri-standing · frame time (p99) (ms) | 15.2 | 13.1 (−14%) | | default-presenter · market-standing · frame time (p99) (ms) | 20.0 | 19.2 (−4%) | | default-presenter · kokiri-after-motion · frame time (p99) (ms) | 14.3 | 13.8 (−4%) | | default-presenter · market-after-motion · frame time (p99) (ms) | 16.7 | 16.6 (−1%) | | default-presenter · forbidden log lines | 0.0 | 0.0 | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-standing · frame rate | 86.3 | 94.5 (+9%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-standing · frame rate | 63.3 | 67.3 (+6%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-after-motion · frame rate | 85.0 | 95.3 (+12%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-after-motion · frame rate | 82.2 | 84.0 (+2%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-standing · frame time (p99) (ms) | 13.5 | 12.5 (−7%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-standing · frame time (p99) (ms) | 19.5 | 18.0 (−7%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-after-motion · frame time (p99) (ms) | 14.0 | 13.4 (−4%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-after-motion · frame time (p99) (ms) | 16.2 | 15.5 (−4%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · forbidden log lines | 0.0 | 0.0 | ### Flags and settings | Flag | What it is | Values tried | Before this PR | After this PR | Effect (frame rate) | Helps / doesn't help / untested | |---|---|---|---|---|---|---| | `RX_VK_PRESENT_THREAD` | switch the PR adds (set on the PR side only) | `1` | not in main | the PR's default | forced-presenter, main without it → the PR with 1: 86.3 → 94.5 (+9%) | helps | <details><summary>Markdown for the PR description</summary> ```markdown ## Measurements **Verdict:** fail on windows+amd (2/1 report): `forced-presenter screenshot.max_diff`; `default-presenter screenshot.max_diff` failed. Hardware: 1: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416` `AMD Ryzen 7 5800X3D 8-Core Processor, 32 GB RAM`; 2: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416` `AMD Ryzen 9 5900X 12-Core Processor, 32 GB RAM` Scene: default-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); forced-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); default-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; forced-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ 09cbdd9 | After: this PR @ 3569b8d | |---|---|---| | default-presenter · kokiri-standing · frame rate | 85.2 | 94.9 (+11%) | | default-presenter · market-standing · frame rate | 62.1 | 62.5 (+1%) | | default-presenter · kokiri-after-motion · frame rate | 88.0 | 97.5 (+11%) | | default-presenter · market-after-motion · frame rate | 80.9 | 76.5 (−5%) | | default-presenter · kokiri-standing · frame time (p99) (ms) | 15.2 | 13.1 (−14%) | | default-presenter · market-standing · frame time (p99) (ms) | 20.0 | 19.2 (−4%) | | default-presenter · kokiri-after-motion · frame time (p99) (ms) | 14.3 | 13.8 (−4%) | | default-presenter · market-after-motion · frame time (p99) (ms) | 16.7 | 16.6 (−1%) | | default-presenter · forbidden log lines | 0.0 | 0.0 | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-standing · frame rate | 86.3 | 94.5 (+9%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-standing · frame rate | 63.3 | 67.3 (+6%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-after-motion · frame rate | 85.0 | 95.3 (+12%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-after-motion · frame rate | 82.2 | 84.0 (+2%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-standing · frame time (p99) (ms) | 13.5 | 12.5 (−7%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-standing · frame time (p99) (ms) | 19.5 | 18.0 (−7%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-after-motion · frame time (p99) (ms) | 14.0 | 13.4 (−4%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-after-motion · frame time (p99) (ms) | 16.2 | 15.5 (−4%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · forbidden log lines | 0.0 | 0.0 | ### Flags and settings | Flag | What it is | Values tried | Before this PR | After this PR | Effect (frame rate) | Helps / doesn't help / untested | |---|---|---|---|---|---|---| | `RX_VK_PRESENT_THREAD` | switch the PR adds (set on the PR side only) | `1` | not in main | the PR's default | forced-presenter, main without it → the PR with 1: 86.3 → 94.5 (+9%) | helps | ``` </details> #### Measurements · windows+nvidia **Verdict:** fail on windows+nvidia (2/1 report): `default-presenter screenshot.max_diff`; `forced-presenter screenshot.max_diff` failed. Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0` `AMD Ryzen 7 5800H with Radeon Graphics, 16 GB RAM`; 2: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3090, 621.24.0` `AMD Ryzen 9 5900X 12-Core Processor, 128 GB RAM` Scene: default-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); forced-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); default-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; forced-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ 09cbdd9 | After: this PR @ 3569b8d | |---|---|---| | default-presenter · kokiri-standing · frame rate | 73.5 | 76.0 (+3%) | | default-presenter · market-standing · frame rate | 62.0 | 64.0 (+3%) | | default-presenter · kokiri-after-motion · frame rate | 79.7 | 77.6 (−3%) | | default-presenter · market-after-motion · frame rate | 66.6 | 67.6 (+1%) | | default-presenter · kokiri-standing · frame time (p99) (ms) | 23.3 | 16.7 (−29%) | | default-presenter · market-standing · frame time (p99) (ms) | 20.8 | 20.2 (−3%) | | default-presenter · kokiri-after-motion · frame time (p99) (ms) | 17.3 | 15.6 (−9%) | | default-presenter · market-after-motion · frame time (p99) (ms) | 19.4 | 19.2 (−1%) | | default-presenter · forbidden log lines | 0.0 | 0.0 | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-standing · frame rate | 78.1 | 79.2 (+1%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-standing · frame rate | 62.8 | 63.9 (+2%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-after-motion · frame rate | 79.7 | 80.7 (+1%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-after-motion · frame rate | 68.2 | 64.8 (−5%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-standing · frame time (p99) (ms) | 17.5 | 20.5 (+17%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-standing · frame time (p99) (ms) | 20.7 | 20.4 (−1%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-after-motion · frame time (p99) (ms) | 17.3 | 17.1 (−2%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-after-motion · frame time (p99) (ms) | 18.8 | 20.9 (+11%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · forbidden log lines | 0.0 | 0.0 | ### Flags and settings | Flag | What it is | Values tried | Before this PR | After this PR | Effect (frame rate) | Helps / doesn't help / untested | |---|---|---|---|---|---|---| | `RX_VK_PRESENT_THREAD` | switch the PR adds (set on the PR side only) | `1` | not in main | the PR's default | forced-presenter, main without it → the PR with 1: 78.1 → 79.2 (+1%) | no clear effect | <details><summary>Markdown for the PR description</summary> ```markdown ## Measurements **Verdict:** fail on windows+nvidia (2/1 report): `default-presenter screenshot.max_diff`; `forced-presenter screenshot.max_diff` failed. Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0` `AMD Ryzen 7 5800H with Radeon Graphics, 16 GB RAM`; 2: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3090, 621.24.0` `AMD Ryzen 9 5900X 12-Core Processor, 128 GB RAM` Scene: default-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); forced-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); default-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; forced-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ 09cbdd9 | After: this PR @ 3569b8d | |---|---|---| | default-presenter · kokiri-standing · frame rate | 73.5 | 76.0 (+3%) | | default-presenter · market-standing · frame rate | 62.0 | 64.0 (+3%) | | default-presenter · kokiri-after-motion · frame rate | 79.7 | 77.6 (−3%) | | default-presenter · market-after-motion · frame rate | 66.6 | 67.6 (+1%) | | default-presenter · kokiri-standing · frame time (p99) (ms) | 23.3 | 16.7 (−29%) | | default-presenter · market-standing · frame time (p99) (ms) | 20.8 | 20.2 (−3%) | | default-presenter · kokiri-after-motion · frame time (p99) (ms) | 17.3 | 15.6 (−9%) | | default-presenter · market-after-motion · frame time (p99) (ms) | 19.4 | 19.2 (−1%) | | default-presenter · forbidden log lines | 0.0 | 0.0 | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-standing · frame rate | 78.1 | 79.2 (+1%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-standing · frame rate | 62.8 | 63.9 (+2%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-after-motion · frame rate | 79.7 | 80.7 (+1%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-after-motion · frame rate | 68.2 | 64.8 (−5%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-standing · frame time (p99) (ms) | 17.5 | 20.5 (+17%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-standing · frame time (p99) (ms) | 20.7 | 20.4 (−1%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-after-motion · frame time (p99) (ms) | 17.3 | 17.1 (−2%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-after-motion · frame time (p99) (ms) | 18.8 | 20.9 (+11%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · forbidden log lines | 0.0 | 0.0 | ### Flags and settings | Flag | What it is | Values tried | Before this PR | After this PR | Effect (frame rate) | Helps / doesn't help / untested | |---|---|---|---|---|---|---| | `RX_VK_PRESENT_THREAD` | switch the PR adds (set on the PR side only) | `1` | not in main | the PR's default | forced-presenter, main without it → the PR with 1: 78.1 → 79.2 (+1%) | no clear effect | ``` </details> #### Measurements · linux+amd **Verdict:** fail on linux+amd (2/1 report): `default-presenter screenshot.max_diff`; `forced-presenter screenshot.max_diff`; `forced-presenter kokiri-standing.frametime_p99_ms.max_delta_pct (+50.2%)` failed. Hardware: 1: linux+amd+radv+dgpu `AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7` `AMD Ryzen 7 5800X3D 8-Core Processor, 64 GB RAM`; 2: linux+amd+radv+igpu+handheld `AMD Custom GPU 0405 (RADV VANGOGH), 26.1.99` `AMD Custom APU 0405, 12 GB RAM` Scene: default-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); forced-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); default-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; forced-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ 09cbdd9 | After: this PR @ 3569b8d | |---|---|---| | default-presenter · kokiri-standing · frame rate | 46.2 | 61.3 (+33%) | | default-presenter · market-standing · frame rate | 13.7 | 45.0 (+228%) | | default-presenter · kokiri-after-motion · frame rate | 49.1 | 61.1 (+25%) | | default-presenter · market-after-motion · frame rate | 40.5 | 54.9 (+36%) | | default-presenter · kokiri-standing · frame time (p99) (ms) | 43.0 | 34.1 (−21%) | | default-presenter · market-standing · frame time (p99) (ms) | 549.9 | 71.6 (−87%) | | default-presenter · kokiri-after-motion · frame time (p99) (ms) | 40.0 | 33.4 (−17%) | | default-presenter · market-after-motion · frame time (p99) (ms) | 65.3 | 50.7 (−22%) | | default-presenter · forbidden log lines | 0.0 | 0.0 | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-standing · frame rate | 49.5 | 59.9 (+21%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-standing · frame rate | 14.5 | 72.2 (+397%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-after-motion · frame rate | 49.5 | 60.6 (+22%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-after-motion · frame rate | 45.7 | 89.9 (+97%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-standing · frame time (p99) (ms) | 35.8 | 48.8 (+36%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-standing · frame time (p99) (ms) | 546.7 | 61.3 (−89%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-after-motion · frame time (p99) (ms) | 36.4 | 36.9 (+1%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-after-motion · frame time (p99) (ms) | 58.7 | 14.8 (−75%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · forbidden log lines | 0.0 | 0.0 | ### Flags and settings | Flag | What it is | Values tried | Before this PR | After this PR | Effect (frame rate) | Helps / doesn't help / untested | |---|---|---|---|---|---|---| | `RX_VK_PRESENT_THREAD` | switch the PR adds (set on the PR side only) | `1` | not in main | the PR's default | forced-presenter, main without it → the PR with 1: 49.5 → 59.9 (+21%) | helps | <details><summary>Markdown for the PR description</summary> ```markdown ## Measurements **Verdict:** fail on linux+amd (2/1 report): `default-presenter screenshot.max_diff`; `forced-presenter screenshot.max_diff`; `forced-presenter kokiri-standing.frametime_p99_ms.max_delta_pct (+50.2%)` failed. Hardware: 1: linux+amd+radv+dgpu `AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7` `AMD Ryzen 7 5800X3D 8-Core Processor, 64 GB RAM`; 2: linux+amd+radv+igpu+handheld `AMD Custom GPU 0405 (RADV VANGOGH), 26.1.99` `AMD Custom APU 0405, 12 GB RAM` Scene: default-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); forced-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); default-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; forced-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ 09cbdd9 | After: this PR @ 3569b8d | |---|---|---| | default-presenter · kokiri-standing · frame rate | 46.2 | 61.3 (+33%) | | default-presenter · market-standing · frame rate | 13.7 | 45.0 (+228%) | | default-presenter · kokiri-after-motion · frame rate | 49.1 | 61.1 (+25%) | | default-presenter · market-after-motion · frame rate | 40.5 | 54.9 (+36%) | | default-presenter · kokiri-standing · frame time (p99) (ms) | 43.0 | 34.1 (−21%) | | default-presenter · market-standing · frame time (p99) (ms) | 549.9 | 71.6 (−87%) | | default-presenter · kokiri-after-motion · frame time (p99) (ms) | 40.0 | 33.4 (−17%) | | default-presenter · market-after-motion · frame time (p99) (ms) | 65.3 | 50.7 (−22%) | | default-presenter · forbidden log lines | 0.0 | 0.0 | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-standing · frame rate | 49.5 | 59.9 (+21%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-standing · frame rate | 14.5 | 72.2 (+397%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-after-motion · frame rate | 49.5 | 60.6 (+22%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-after-motion · frame rate | 45.7 | 89.9 (+97%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-standing · frame time (p99) (ms) | 35.8 | 48.8 (+36%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-standing · frame time (p99) (ms) | 546.7 | 61.3 (−89%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-after-motion · frame time (p99) (ms) | 36.4 | 36.9 (+1%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-after-motion · frame time (p99) (ms) | 58.7 | 14.8 (−75%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · forbidden log lines | 0.0 | 0.0 | ### Flags and settings | Flag | What it is | Values tried | Before this PR | After this PR | Effect (frame rate) | Helps / doesn't help / untested | |---|---|---|---|---|---|---| | `RX_VK_PRESENT_THREAD` | switch the PR adds (set on the PR side only) | `1` | not in main | the PR's default | forced-presenter, main without it → the PR with 1: 49.5 → 59.9 (+21%) | helps | ``` </details> #### Measurements · steamdeck **Verdict:** fail on steamdeck (1/1 report): `default-presenter screenshot.max_diff` failed. Hardware: 1: linux+amd+radv+igpu+handheld `AMD Custom GPU 0405 (RADV VANGOGH), 26.1.99` `AMD Custom APU 0405, 12 GB RAM` Scene: default-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); forced-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); default-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; forced-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; each number the median of the runs, then of 1 report How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ 09cbdd9 | After: this PR @ 3569b8d | |---|---|---| | default-presenter · kokiri-standing · frame rate | 20.1 | 21.3 (+6%) | | default-presenter · kokiri-after-motion · frame rate | 21.5 | 21.9 (+2%) | | default-presenter · market-standing · frame rate | — | 18.1 | | default-presenter · market-after-motion · frame rate | — | 16.9 | | default-presenter · kokiri-standing · frame time (p99) (ms) | 96.5 | 83.9 (−13%) | | default-presenter · kokiri-after-motion · frame time (p99) (ms) | 58.8 | 58.6 (−0%) | | default-presenter · market-standing · frame time (p99) (ms) | — | 90.6 | | default-presenter · market-after-motion · frame time (p99) (ms) | — | 102.9 | | default-presenter · forbidden log lines | 0.0 | 0.0 | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-standing · frame rate | 22.4 | 22.5 (+1%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-standing · frame rate | 18.3 | 18.4 (+0%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-after-motion · frame rate | 22.6 | 22.5 (−0%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-after-motion · frame rate | 18.5 | 17.7 (−4%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-standing · frame time (p99) (ms) | 58.5 | 54.7 (−7%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-standing · frame time (p99) (ms) | 80.7 | 86.8 (+8%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-after-motion · frame time (p99) (ms) | 54.1 | 56.1 (+4%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-after-motion · frame time (p99) (ms) | 84.4 | 96.1 (+14%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · forbidden log lines | 0.0 | 0.0 | ### Flags and settings | Flag | What it is | Values tried | Before this PR | After this PR | Effect (frame rate) | Helps / doesn't help / untested | |---|---|---|---|---|---|---| | `RX_VK_PRESENT_THREAD` | switch the PR adds (set on the PR side only) | `1` | not in main | the PR's default | forced-presenter, main without it → the PR with 1: 22.4 → 22.5 (+1%) | no clear effect | <details><summary>Markdown for the PR description</summary> ```markdown ## Measurements **Verdict:** fail on steamdeck (1/1 report): `default-presenter screenshot.max_diff` failed. Hardware: 1: linux+amd+radv+igpu+handheld `AMD Custom GPU 0405 (RADV VANGOGH), 26.1.99` `AMD Custom APU 0405, 12 GB RAM` Scene: default-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); forced-presenter, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); default-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; forced-presenter: 2 game starts a side, kokiri-standing 15 s after 5 s warm-up, kokiri-after-motion 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-motion 10 s after 0 s warm-up; each number the median of the runs, then of 1 report How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ 09cbdd9 | After: this PR @ 3569b8d | |---|---|---| | default-presenter · kokiri-standing · frame rate | 20.1 | 21.3 (+6%) | | default-presenter · kokiri-after-motion · frame rate | 21.5 | 21.9 (+2%) | | default-presenter · market-standing · frame rate | — | 18.1 | | default-presenter · market-after-motion · frame rate | — | 16.9 | | default-presenter · kokiri-standing · frame time (p99) (ms) | 96.5 | 83.9 (−13%) | | default-presenter · kokiri-after-motion · frame time (p99) (ms) | 58.8 | 58.6 (−0%) | | default-presenter · market-standing · frame time (p99) (ms) | — | 90.6 | | default-presenter · market-after-motion · frame time (p99) (ms) | — | 102.9 | | default-presenter · forbidden log lines | 0.0 | 0.0 | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-standing · frame rate | 22.4 | 22.5 (+1%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-standing · frame rate | 18.3 | 18.4 (+0%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-after-motion · frame rate | 22.6 | 22.5 (−0%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-after-motion · frame rate | 18.5 | 17.7 (−4%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-standing · frame time (p99) (ms) | 58.5 | 54.7 (−7%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-standing · frame time (p99) (ms) | 80.7 | 86.8 (+8%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · kokiri-after-motion · frame time (p99) (ms) | 54.1 | 56.1 (+4%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · market-after-motion · frame time (p99) (ms) | 84.4 | 96.1 (+14%) | | forced-presenter · `RX_VK_PRESENT_THREAD=1 (PR only)` · forbidden log lines | 0.0 | 0.0 | ### Flags and settings | Flag | What it is | Values tried | Before this PR | After this PR | Effect (frame rate) | Helps / doesn't help / untested | |---|---|---|---|---|---|---| | `RX_VK_PRESENT_THREAD` | switch the PR adds (set on the PR side only) | `1` | not in main | the PR's default | forced-presenter, main without it → the PR with 1: 22.4 → 22.5 (+1%) | no clear effect | ``` </details> </details>
HumanBean force-pushed perf/presenter-thread-nvidia-linux from 3569b8da6a
Some checks failed
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Has been skipped
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Has been skipped
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Has been skipped
Third-party parts / The same as upstream (pull_request) Has been skipped
Website / Website on Cloudflare (pull_request) Has been skipped
CI / Conventional Commit title (pull_request) Successful in 7s
Guide screenshots / Guide images and local UI source review (pull_request) Failing after 10s
CI / Workflow lint (actionlint) (pull_request) Successful in 12s
Third-party parts / As their notes say (pull_request) Successful in 13s
Website / Website on Cloudflare (pull_request_target) Has been skipped
PR description / Description follows the template (pull_request_target) Failing after 8s
beanstalk/approval approved by HumanBean (reviewed)
beanstalk/windows+amd 2/1 fail
beanstalk/windows+nvidia 1/1 fail
beanstalk/linux+amd 2/1 fail
beanstalk/steamdeck 1/1 fail
beanstalk/windows+intel 0/1 pass, 0 running, 2 queued
beanstalk/linux+intel 0/1 pass, 0 running, 2 queued
to 0c3808483c
Some checks reported errors
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Has been skipped
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Has been skipped
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Has been skipped
Third-party parts / The same as upstream (pull_request) Has been skipped
Website / Website on Cloudflare (pull_request) Has been skipped
CI / Conventional Commit title (pull_request) Successful in 8s
Guide screenshots / Guide images and local UI source review (pull_request) Failing after 13s
CI / Workflow lint (actionlint) (pull_request) Successful in 14s
Third-party parts / As their notes say (pull_request) Successful in 14s
PR description / Description follows the template (pull_request_target) Failing after 9s
Website / Website on Cloudflare (pull_request_target) Has been skipped
beanstalk/approval approved by HumanBean (reviewed)
beanstalk/windows+amd 0/1 pass, 2 error
beanstalk/windows+nvidia 0/1 pass, 2 error
beanstalk/windows+intel 0/1 pass, 0 running, 2 queued
beanstalk/linux+intel 0/1 pass, 0 running, 2 queued
2026-11-19 11:55:57 +00:00
Compare
Member
Beanstalk test farm · an earlier run: commit 0c38084 (the newer results are in a comment below)

Commit 0c38084 · tier reviewed · approved by HumanBean · dashboard

What will be tested · AI plan (gpt-6.1-terra)

Compare the PR with main on Windows AMD and NVIDIA PCs, with Windows and Linux Intel targets also queued; no Intel tester is currently online. Two starts per side visit Kokiri Forest and Castle Town Market with V-Sync off and the frame rate uncapped, measuring standing and post-movement performance over roughly 22 minutes per tester. Crashes, device loss, missing presenter-mode logs, substantial FPS or frame-time regressions, and large picture differences fail the plan. The shared log rule accepts either presenter mode, so it cannot independently enforce AMD-on and NVIDIA-off; the reported logs show which mode was selected. Snapshot comparisons also cannot reliably catch one-frame flashes. No tester online now matches windows+intel, linux+intel: those targets wait for one.

  • Where: windows+amd (1-2 reports), windows+nvidia (1-2 reports), windows+intel (1-2 reports), linux+intel (1-2 reports).
  • forest-market: from the repository's save kokiri-start (settings vsync=2, frame_rate_cap=6), then teleport to Kokiri Forest, measure forest-standing for 15 s (after 5 s warm-up), take the picture forest-standing to compare with main, move the stick, measure forest-after-moving for 10 s (after 0 s warm-up), take the picture forest-after-moving to compare with main, teleport to Market, measure market-standing for 15 s (after 5 s warm-up), take the picture market-standing to compare with main, measure market-after-moving for 10 s (after 0 s warm-up), take the picture market-after-moving to compare with main; 2 runs on each side.
  • Measured: crashes, frame times, stutters and hitches, draws and frame rate, the game's log.
  • The PR fails if: it crashes; or frame rate is more than 10% below main; or a picture differs from main by more than 40%; or frame time (p99) is more than 15% above main; or forbidden log lines is above 0; or expected log lines missing is above 0.
  • Time: about 24 min of game runs per tester (4 game starts), plus the two builds.

Started at 11:56 UTC.

⚠ No tester has a PC for linux+intel (none seen in 14 days): it waits until one signs in.

Target Reports Crash Frame p99 (ms) vs main VRAM peak (MB) vs main Result
windows+amd · 1: windows+amd+amd-proprietary+dgpu AMD Radeon RX 9070 XT, 2.0.416; 2: windows+amd+amd-proprietary+dgpu AMD Radeon RX 9070 XT, 2.0.416 2/1 1 2 none — — error
windows+nvidia · 1: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0; 2: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 3090, 621.24.0 2/1 1 2 none — — error
windows+intel 0/1 — — — queued
linux+intel 0/1 — — — queued

Measurements · windows+amd

Verdict: could not be judged on windows+amd (2/1 report).

Hardware: 1: windows+amd+amd-proprietary+dgpu AMD Radeon RX 9070 XT, 2.0.416 AMD Ryzen 9 5900X 12-Core Processor, 32 GB RAM; 2: windows+amd+amd-proprietary+dgpu AMD Radeon RX 9070 XT, 2.0.416 AMD Ryzen 7 5800X3D 8-Core Processor, 32 GB RAM
Scene: forest-market, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-market: 2 game starts a side, forest-standing 15 s after 5 s warm-up, forest-after-moving 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-moving 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports
How to reproduce: the farm's plan above (@Beanstalk on this PR runs it again)

Nothing was measured: no metric came back.

Flags and settings

None: the plan varied no setting, switch or build option.

Markdown for the PR description
## Measurements

**Verdict:** could not be judged on windows+amd (2/1 report).

Hardware: 1: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416` `AMD Ryzen 9 5900X 12-Core Processor, 32 GB RAM`; 2: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416` `AMD Ryzen 7 5800X3D 8-Core Processor, 32 GB RAM`  
Scene: forest-market, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them  
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-market: 2 game starts a side, forest-standing 15 s after 5 s warm-up, forest-after-moving 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-moving 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports  
How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again)

Nothing was measured: no metric came back.

### Flags and settings

None: the plan varied no setting, switch or build option.

Measurements · windows+nvidia

Verdict: could not be judged on windows+nvidia (2/1 report).

Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0 AMD Ryzen 7 5800H with Radeon Graphics, 16 GB RAM; 2: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 3090, 621.24.0 AMD Ryzen 9 5900X 12-Core Processor, 128 GB RAM
Scene: forest-market, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-market: 2 game starts a side, forest-standing 15 s after 5 s warm-up, forest-after-moving 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-moving 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports
How to reproduce: the farm's plan above (@Beanstalk on this PR runs it again)

Nothing was measured: no metric came back.

Flags and settings

None: the plan varied no setting, switch or build option.

Markdown for the PR description
## Measurements

**Verdict:** could not be judged on windows+nvidia (2/1 report).

Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0` `AMD Ryzen 7 5800H with Radeon Graphics, 16 GB RAM`; 2: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3090, 621.24.0` `AMD Ryzen 9 5900X 12-Core Processor, 128 GB RAM`  
Scene: forest-market, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them  
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-market: 2 game starts a side, forest-standing 15 s after 5 s warm-up, forest-after-moving 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-moving 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports  
How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again)

Nothing was measured: no metric came back.

### Flags and settings

None: the plan varied no setting, switch or build option.
<!-- beanstalk:previous --> <details><summary>Beanstalk test farm · an earlier run: commit <code>0c38084</code> (the newer results are in a comment below)</summary> Commit `0c38084` · tier **reviewed** · approved by HumanBean · [dashboard](https://beanstalk.magicbean.dev/prs/1702) **What will be tested** · AI plan (`gpt-6.1-terra`) Compare the PR with main on Windows AMD and NVIDIA PCs, with Windows and Linux Intel targets also queued; no Intel tester is currently online. Two starts per side visit Kokiri Forest and Castle Town Market with V-Sync off and the frame rate uncapped, measuring standing and post-movement performance over roughly 22 minutes per tester. Crashes, device loss, missing presenter-mode logs, substantial FPS or frame-time regressions, and large picture differences fail the plan. The shared log rule accepts either presenter mode, so it cannot independently enforce AMD-on and NVIDIA-off; the reported logs show which mode was selected. Snapshot comparisons also cannot reliably catch one-frame flashes. No tester online now matches windows+intel, linux+intel: those targets wait for one. - **Where:** windows+amd (1-2 reports), windows+nvidia (1-2 reports), windows+intel (1-2 reports), linux+intel (1-2 reports). - **forest-market:** from the repository's save `kokiri-start` (settings vsync=2, frame_rate_cap=6), then teleport to Kokiri Forest, measure forest-standing for 15 s (after 5 s warm-up), take the picture forest-standing to compare with main, move the stick, measure forest-after-moving for 10 s (after 0 s warm-up), take the picture forest-after-moving to compare with main, teleport to Market, measure market-standing for 15 s (after 5 s warm-up), take the picture market-standing to compare with main, measure market-after-moving for 10 s (after 0 s warm-up), take the picture market-after-moving to compare with main; 2 runs on each side. - **Measured:** crashes, frame times, stutters and hitches, draws and frame rate, the game's log. - **The PR fails if:** it crashes; or frame rate is more than 10% below main; or a picture differs from main by more than 40%; or frame time (p99) is more than 15% above main; or forbidden log lines is above 0; or expected log lines missing is above 0. - **Time:** about 24 min of game runs per tester (4 game starts), plus the two builds. Started at 11:56 UTC. ⚠ No tester has a PC for `linux+intel` (none seen in 14 days): it waits until one signs in. | Target | Reports | Crash | Frame p99 (ms) vs main | VRAM peak (MB) vs main | Result | | --- | --- | --- | --- | --- | --- | | windows+amd · 1: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416`; 2: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416` | 2/1 [1](https://beanstalk.magicbean.dev/reports/rp_4bc7ec755cfe900b) [2](https://beanstalk.magicbean.dev/reports/rp_a9eacb65ac1b432d) | none | — | — | error | | windows+nvidia · 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0`; 2: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3090, 621.24.0` | 2/1 [1](https://beanstalk.magicbean.dev/reports/rp_2481870588f0935e) [2](https://beanstalk.magicbean.dev/reports/rp_ac9de19fc07f2198) | none | — | — | error | | windows+intel | 0/1 | — | — | — | queued | | linux+intel | 0/1 | — | — | — | queued | #### Measurements · windows+amd **Verdict:** could not be judged on windows+amd (2/1 report). Hardware: 1: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416` `AMD Ryzen 9 5900X 12-Core Processor, 32 GB RAM`; 2: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416` `AMD Ryzen 7 5800X3D 8-Core Processor, 32 GB RAM` Scene: forest-market, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-market: 2 game starts a side, forest-standing 15 s after 5 s warm-up, forest-after-moving 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-moving 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) Nothing was measured: no metric came back. ### Flags and settings None: the plan varied no setting, switch or build option. <details><summary>Markdown for the PR description</summary> ```markdown ## Measurements **Verdict:** could not be judged on windows+amd (2/1 report). Hardware: 1: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416` `AMD Ryzen 9 5900X 12-Core Processor, 32 GB RAM`; 2: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 9070 XT, 2.0.416` `AMD Ryzen 7 5800X3D 8-Core Processor, 32 GB RAM` Scene: forest-market, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-market: 2 game starts a side, forest-standing 15 s after 5 s warm-up, forest-after-moving 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-moving 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) Nothing was measured: no metric came back. ### Flags and settings None: the plan varied no setting, switch or build option. ``` </details> #### Measurements · windows+nvidia **Verdict:** could not be judged on windows+nvidia (2/1 report). Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0` `AMD Ryzen 7 5800H with Radeon Graphics, 16 GB RAM`; 2: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3090, 621.24.0` `AMD Ryzen 9 5900X 12-Core Processor, 128 GB RAM` Scene: forest-market, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-market: 2 game starts a side, forest-standing 15 s after 5 s warm-up, forest-after-moving 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-moving 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) Nothing was measured: no metric came back. ### Flags and settings None: the plan varied no setting, switch or build option. <details><summary>Markdown for the PR description</summary> ```markdown ## Measurements **Verdict:** could not be judged on windows+nvidia (2/1 report). Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0` `AMD Ryzen 7 5800H with Radeon Graphics, 16 GB RAM`; 2: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3090, 621.24.0` `AMD Ryzen 9 5900X 12-Core Processor, 128 GB RAM` Scene: forest-market, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-market: 2 game starts a side, forest-standing 15 s after 5 s warm-up, forest-after-moving 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-moving 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) Nothing was measured: no metric came back. ### Flags and settings None: the plan varied no setting, switch or build option. ``` </details> </details>
HumanBean changed title from perf(vk): the presenter thread on by default with NVIDIA's driver on Linux, with NVIDIA Reflex; carries #1121 to perf(vk): the presenter thread on by default with NVIDIA on Linux and AMD on Windows, with NVIDIA Reflex; carries #1121 2026-11-19 11:56:04 +00:00
Author
Owner

@Beanstalk run 4: the last commit turns the presenter thread on by default with AMD's Windows driver on a discrete card (run 3's forced cell). Please test this PR against main on windows+amd and windows+nvidia (NVIDIA should be unchanged from run 3: presenter thread off there), with the settings vsync=2 (Off) and frame_rate_cap=6 (Uncapped): Kokiri Forest and Castle Town Market, standing 15 s and 10 s after moving, two game starts a side. No switches: the defaults only. Expect vk: presenter thread: each present made on a thread in the log on AMD and off (RX_VK_PRESENT_THREAD=1: on) on NVIDIA. Intel targets from run 3 can stay queued.

@Beanstalk run 4: the last commit turns the presenter thread on by default with AMD's Windows driver on a discrete card (run 3's forced cell). Please test this PR against main on windows+amd and windows+nvidia (NVIDIA should be unchanged from run 3: presenter thread off there), with the settings vsync=2 (Off) and frame_rate_cap=6 (Uncapped): Kokiri Forest and Castle Town Market, standing 15 s and 10 s after moving, two game starts a side. No switches: the defaults only. Expect `vk: presenter thread: each present made on a thread` in the log on AMD and `off (RX_VK_PRESENT_THREAD=1: on)` on NVIDIA. Intel targets from run 3 can stay queued.
HumanBean force-pushed perf/presenter-thread-nvidia-linux from 0c3808483c
Some checks reported errors
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Has been skipped
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Has been skipped
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Has been skipped
Third-party parts / The same as upstream (pull_request) Has been skipped
Website / Website on Cloudflare (pull_request) Has been skipped
CI / Conventional Commit title (pull_request) Successful in 8s
Guide screenshots / Guide images and local UI source review (pull_request) Failing after 13s
CI / Workflow lint (actionlint) (pull_request) Successful in 14s
Third-party parts / As their notes say (pull_request) Successful in 14s
PR description / Description follows the template (pull_request_target) Failing after 9s
Website / Website on Cloudflare (pull_request_target) Has been skipped
beanstalk/approval approved by HumanBean (reviewed)
beanstalk/windows+amd 0/1 pass, 2 error
beanstalk/windows+nvidia 0/1 pass, 2 error
beanstalk/windows+intel 0/1 pass, 0 running, 2 queued
beanstalk/linux+intel 0/1 pass, 0 running, 2 queued
to a93a983fba
Some checks failed
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Has been skipped
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Has been skipped
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Has been skipped
Third-party parts / The same as upstream (pull_request) Has been skipped
Website / Website on Cloudflare (pull_request) Has been skipped
CI / Conventional Commit title (pull_request) Successful in 7s
PR description / Description follows the template (pull_request_target) Failing after 9s
Guide screenshots / Guide images and local UI source review (pull_request) Failing after 10s
CI / Workflow lint (actionlint) (pull_request) Successful in 11s
Third-party parts / As their notes say (pull_request) Successful in 11s
beanstalk/approval planning the tests
2026-11-19 14:40:13 +00:00
Compare
Member

Beanstalk test farm

Commit 28f5fb2 · tier reviewed · approved by HumanBean · dashboard

What will be tested · AI plan (gpt-6.1-terra)

Compare the PR with main on Windows AMD and NVIDIA PCs, with V-Sync off and the frame rate uncapped. Each of two starts per side visits Kokiri Forest and Castle Town Market, measuring 15 seconds standing and 10 seconds after moving at each location; the run takes about 22 minutes per tester. The PR fails on a crash, device loss, a sampled picture difference, or FPS below main in any segment. The log check accepts either requested presenter-thread message, but cannot enforce the AMD and NVIDIA expectations separately in one shared plan.

  • Where: windows+amd (1-2 reports), windows+nvidia (1-2 reports).
  • forest-and-market: from the repository's save kokiri-start (settings vsync=2, frame_rate_cap=6), then teleport to Kokiri Forest, measure forest-standing for 15 s (after 5 s warm-up), take the picture forest to compare with main, move the stick, measure forest-after-moving for 10 s (after 0 s warm-up), teleport to Market, measure market-standing for 15 s (after 5 s warm-up), take the picture market to compare with main, measure market-after-moving for 10 s (after 0 s warm-up); 2 runs on each side.
  • Measured: crashes, draws and frame rate, frame times, stutters and hitches, the game's log.
  • The PR fails if: it crashes; or frame rate is more than 0% below main; or a picture differs from main by more than 20%; or forbidden log lines is above 0; or expected log lines missing is above 0.
  • Time: about 24 min of game runs per tester (4 game starts), plus the two builds.

Done (started 16:18 UTC, last report 18:55 UTC). Comment @Beanstalk to run it again.

Target Reports Crash Frame p99 (ms) vs main VRAM peak (MB) vs main Result
windows+amd · 1: windows+amd+amd-proprietary+dgpu AMD Radeon RX 7900 XTX, 2.0.416; 2: windows+amd+amd-proprietary+igpu AMD Radeon(TM) 880M Graphics, 2.0.416 2/1 1 2 none — — error
windows+nvidia · 1: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0; 2: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 3090, 621.24.0 2/1 1 2 none 19.4 vs 20.9 (−7%) — fail

Measurements · windows+amd

Verdict: could not be judged on windows+amd (2/1 report).

Hardware: 1: windows+amd+amd-proprietary+dgpu AMD Radeon RX 7900 XTX, 2.0.416 AMD Ryzen 7 5800X3D 8-Core Processor, 32 GB RAM; 2: windows+amd+amd-proprietary+igpu AMD Radeon(TM) 880M Graphics, 2.0.416 AMD Ryzen AI 9 365 w/ Radeon 880M, 32 GB RAM
Scene: forest-and-market, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-and-market: 2 game starts a side, forest-standing 15 s after 5 s warm-up, forest-after-moving 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-moving 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports
How to reproduce: the farm's plan above (@Beanstalk on this PR runs it again)

Nothing was measured: no metric came back.

Flags and settings

None: the plan varied no setting, switch or build option.

Markdown for the PR description
## Measurements

**Verdict:** could not be judged on windows+amd (2/1 report).

Hardware: 1: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 7900 XTX, 2.0.416` `AMD Ryzen 7 5800X3D 8-Core Processor, 32 GB RAM`; 2: windows+amd+amd-proprietary+igpu `AMD Radeon(TM) 880M Graphics, 2.0.416` `AMD Ryzen AI 9 365 w/ Radeon 880M, 32 GB RAM`  
Scene: forest-and-market, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them  
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-and-market: 2 game starts a side, forest-standing 15 s after 5 s warm-up, forest-after-moving 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-moving 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports  
How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again)

Nothing was measured: no metric came back.

### Flags and settings

None: the plan varied no setting, switch or build option.

Measurements · windows+nvidia

Verdict: fail on windows+nvidia (2/1 report): forest-and-market log_expected_missing.max failed.

Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0 AMD Ryzen 7 5800H with Radeon Graphics, 16 GB RAM; 2: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 3090, 621.24.0 AMD Ryzen 9 5900X 12-Core Processor, 128 GB RAM
Scene: forest-and-market, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-and-market: 2 game starts a side, forest-standing 15 s after 5 s warm-up, forest-after-moving 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-moving 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports
How to reproduce: the farm's plan above (@Beanstalk on this PR runs it again)

Before: main @ d5794c8 After: this PR @ 28f5fb2
forest-and-market · forest-standing · frame rate 73.5 79.9 (+9%)
forest-and-market · market-standing · frame rate 62.7 63.1 (+1%)
forest-and-market · forest-after-moving · frame rate 77.4 80.5 (+4%)
forest-and-market · market-after-moving · frame rate 60.4 60.6 (+0%)
forest-and-market · forbidden log lines 0.0 0.0
forest-and-market · expected log lines missing 1.0 1.0 (+0%)
forest-and-market · forest-standing · frame time (p99) (ms) 20.9 19.4 (−7%)
forest-and-market · market-standing · frame time (p99) (ms) 20.5 21.1 (+3%)
forest-and-market · forest-after-moving · frame time (p99) (ms) 18.8 17.3 (−8%)
forest-and-market · market-after-moving · frame time (p99) (ms) 22.8 22.8 (−0%)

Flags and settings

None: the plan varied no setting, switch or build option.

Markdown for the PR description
## Measurements

**Verdict:** fail on windows+nvidia (2/1 report): `forest-and-market log_expected_missing.max` failed.

Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0` `AMD Ryzen 7 5800H with Radeon Graphics, 16 GB RAM`; 2: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3090, 621.24.0` `AMD Ryzen 9 5900X 12-Core Processor, 128 GB RAM`  
Scene: forest-and-market, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them  
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-and-market: 2 game starts a side, forest-standing 15 s after 5 s warm-up, forest-after-moving 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-moving 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports  
How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again)

| | Before: main @ d5794c8 | After: this PR @ 28f5fb2 |
|---|---|---|
| forest-and-market · forest-standing · frame rate | 73.5 | 79.9 (+9%) |
| forest-and-market · market-standing · frame rate | 62.7 | 63.1 (+1%) |
| forest-and-market · forest-after-moving · frame rate | 77.4 | 80.5 (+4%) |
| forest-and-market · market-after-moving · frame rate | 60.4 | 60.6 (+0%) |
| forest-and-market · forbidden log lines | 0.0 | 0.0 |
| forest-and-market · expected log lines missing | 1.0 | 1.0 (+0%) |
| forest-and-market · forest-standing · frame time (p99) (ms) | 20.9 | 19.4 (−7%) |
| forest-and-market · market-standing · frame time (p99) (ms) | 20.5 | 21.1 (+3%) |
| forest-and-market · forest-after-moving · frame time (p99) (ms) | 18.8 | 17.3 (−8%) |
| forest-and-market · market-after-moving · frame time (p99) (ms) | 22.8 | 22.8 (−0%) |

### Flags and settings

None: the plan varied no setting, switch or build option.
<!-- beanstalk:sticky --> ### Beanstalk test farm Commit `28f5fb2` · tier **reviewed** · approved by HumanBean · [dashboard](https://beanstalk.magicbean.dev/prs/1702) **What will be tested** · AI plan (`gpt-6.1-terra`) Compare the PR with main on Windows AMD and NVIDIA PCs, with V-Sync off and the frame rate uncapped. Each of two starts per side visits Kokiri Forest and Castle Town Market, measuring 15 seconds standing and 10 seconds after moving at each location; the run takes about 22 minutes per tester. The PR fails on a crash, device loss, a sampled picture difference, or FPS below main in any segment. The log check accepts either requested presenter-thread message, but cannot enforce the AMD and NVIDIA expectations separately in one shared plan. - **Where:** windows+amd (1-2 reports), windows+nvidia (1-2 reports). - **forest-and-market:** from the repository's save `kokiri-start` (settings vsync=2, frame_rate_cap=6), then teleport to Kokiri Forest, measure forest-standing for 15 s (after 5 s warm-up), take the picture forest to compare with main, move the stick, measure forest-after-moving for 10 s (after 0 s warm-up), teleport to Market, measure market-standing for 15 s (after 5 s warm-up), take the picture market to compare with main, measure market-after-moving for 10 s (after 0 s warm-up); 2 runs on each side. - **Measured:** crashes, draws and frame rate, frame times, stutters and hitches, the game's log. - **The PR fails if:** it crashes; or frame rate is more than 0% below main; or a picture differs from main by more than 20%; or forbidden log lines is above 0; or expected log lines missing is above 0. - **Time:** about 24 min of game runs per tester (4 game starts), plus the two builds. Done (started 16:18 UTC, last report 18:55 UTC). Comment `@Beanstalk` to run it again. | Target | Reports | Crash | Frame p99 (ms) vs main | VRAM peak (MB) vs main | Result | | --- | --- | --- | --- | --- | --- | | windows+amd · 1: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 7900 XTX, 2.0.416`; 2: windows+amd+amd-proprietary+igpu `AMD Radeon(TM) 880M Graphics, 2.0.416` | 2/1 [1](https://beanstalk.magicbean.dev/reports/rp_62086cc2465d0a52) [2](https://beanstalk.magicbean.dev/reports/rp_5708eb072282d275) | none | — | — | error | | windows+nvidia · 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0`; 2: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3090, 621.24.0` | 2/1 [1](https://beanstalk.magicbean.dev/reports/rp_a48e5b8e6cc573a3) [2](https://beanstalk.magicbean.dev/reports/rp_2eacdc0f799b5a3f) | none | 19.4 vs 20.9 (−7%) | — | fail | #### Measurements · windows+amd **Verdict:** could not be judged on windows+amd (2/1 report). Hardware: 1: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 7900 XTX, 2.0.416` `AMD Ryzen 7 5800X3D 8-Core Processor, 32 GB RAM`; 2: windows+amd+amd-proprietary+igpu `AMD Radeon(TM) 880M Graphics, 2.0.416` `AMD Ryzen AI 9 365 w/ Radeon 880M, 32 GB RAM` Scene: forest-and-market, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-and-market: 2 game starts a side, forest-standing 15 s after 5 s warm-up, forest-after-moving 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-moving 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) Nothing was measured: no metric came back. ### Flags and settings None: the plan varied no setting, switch or build option. <details><summary>Markdown for the PR description</summary> ```markdown ## Measurements **Verdict:** could not be judged on windows+amd (2/1 report). Hardware: 1: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 7900 XTX, 2.0.416` `AMD Ryzen 7 5800X3D 8-Core Processor, 32 GB RAM`; 2: windows+amd+amd-proprietary+igpu `AMD Radeon(TM) 880M Graphics, 2.0.416` `AMD Ryzen AI 9 365 w/ Radeon 880M, 32 GB RAM` Scene: forest-and-market, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-and-market: 2 game starts a side, forest-standing 15 s after 5 s warm-up, forest-after-moving 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-moving 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) Nothing was measured: no metric came back. ### Flags and settings None: the plan varied no setting, switch or build option. ``` </details> #### Measurements · windows+nvidia **Verdict:** fail on windows+nvidia (2/1 report): `forest-and-market log_expected_missing.max` failed. Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0` `AMD Ryzen 7 5800H with Radeon Graphics, 16 GB RAM`; 2: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3090, 621.24.0` `AMD Ryzen 9 5900X 12-Core Processor, 128 GB RAM` Scene: forest-and-market, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-and-market: 2 game starts a side, forest-standing 15 s after 5 s warm-up, forest-after-moving 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-moving 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ d5794c8 | After: this PR @ 28f5fb2 | |---|---|---| | forest-and-market · forest-standing · frame rate | 73.5 | 79.9 (+9%) | | forest-and-market · market-standing · frame rate | 62.7 | 63.1 (+1%) | | forest-and-market · forest-after-moving · frame rate | 77.4 | 80.5 (+4%) | | forest-and-market · market-after-moving · frame rate | 60.4 | 60.6 (+0%) | | forest-and-market · forbidden log lines | 0.0 | 0.0 | | forest-and-market · expected log lines missing | 1.0 | 1.0 (+0%) | | forest-and-market · forest-standing · frame time (p99) (ms) | 20.9 | 19.4 (−7%) | | forest-and-market · market-standing · frame time (p99) (ms) | 20.5 | 21.1 (+3%) | | forest-and-market · forest-after-moving · frame time (p99) (ms) | 18.8 | 17.3 (−8%) | | forest-and-market · market-after-moving · frame time (p99) (ms) | 22.8 | 22.8 (−0%) | ### Flags and settings None: the plan varied no setting, switch or build option. <details><summary>Markdown for the PR description</summary> ```markdown ## Measurements **Verdict:** fail on windows+nvidia (2/1 report): `forest-and-market log_expected_missing.max` failed. Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0` `AMD Ryzen 7 5800H with Radeon Graphics, 16 GB RAM`; 2: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3090, 621.24.0` `AMD Ryzen 9 5900X 12-Core Processor, 128 GB RAM` Scene: forest-and-market, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); forest-and-market: 2 game starts a side, forest-standing 15 s after 5 s warm-up, forest-after-moving 10 s after 0 s warm-up, market-standing 15 s after 5 s warm-up, market-after-moving 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ d5794c8 | After: this PR @ 28f5fb2 | |---|---|---| | forest-and-market · forest-standing · frame rate | 73.5 | 79.9 (+9%) | | forest-and-market · market-standing · frame rate | 62.7 | 63.1 (+1%) | | forest-and-market · forest-after-moving · frame rate | 77.4 | 80.5 (+4%) | | forest-and-market · market-after-moving · frame rate | 60.4 | 60.6 (+0%) | | forest-and-market · forbidden log lines | 0.0 | 0.0 | | forest-and-market · expected log lines missing | 1.0 | 1.0 (+0%) | | forest-and-market · forest-standing · frame time (p99) (ms) | 20.9 | 19.4 (−7%) | | forest-and-market · market-standing · frame time (p99) (ms) | 20.5 | 21.1 (+3%) | | forest-and-market · forest-after-moving · frame time (p99) (ms) | 18.8 | 17.3 (−8%) | | forest-and-market · market-after-moving · frame time (p99) (ms) | 22.8 | 22.8 (−0%) | ### Flags and settings None: the plan varied no setting, switch or build option. ``` </details>
Author
Owner

Run 4 measured nothing: main's base failed to build on Windows on every tester (gpu/vk/descriptor_array_census.h: a member named near, which the Windows headers define away, since #475). #1729 fixes it. This PR is rebased on main 868f6be (still without that fix); the Windows AMD default goes back to the farm once #1729 is in.

Run 4 measured nothing: main's base failed to build on Windows on every tester (`gpu/vk/descriptor_array_census.h`: a member named `near`, which the Windows headers define away, since #475). [#1729](https://git.magicbean.dev/MagicBeanDev/Longshot/pulls/1729) fixes it. This PR is rebased on main 868f6be (still without that fix); the Windows AMD default goes back to the farm once #1729 is in.
Author
Owner

@Beanstalk run 5 (run 4 failed: main didn't build on Windows; #1729 is merged and this PR is rebased on it). The last commit turns the presenter thread on by default with AMD's Windows driver on a discrete card. Please test this PR against main on windows+amd and windows+nvidia, settings vsync=2 (Off) and frame_rate_cap=6 (Uncapped), no switches: Kokiri Forest and Castle Town Market, standing 15 s and 10 s after moving, two game starts a side. Expect vk: presenter thread: each present made on a thread in the log on AMD and off (RX_VK_PRESENT_THREAD=1: on) on NVIDIA, and fps at least main's on both.

@Beanstalk run 5 (run 4 failed: main didn't build on Windows; #1729 is merged and this PR is rebased on it). The last commit turns the presenter thread on by default with AMD's Windows driver on a discrete card. Please test this PR against main on windows+amd and windows+nvidia, settings vsync=2 (Off) and frame_rate_cap=6 (Uncapped), no switches: Kokiri Forest and Castle Town Market, standing 15 s and 10 s after moving, two game starts a side. Expect `vk: presenter thread: each present made on a thread` in the log on AMD and `off (RX_VK_PRESENT_THREAD=1: on)` on NVIDIA, and fps at least main's on both.
HumanBean force-pushed perf/presenter-thread-nvidia-linux from a93a983fba
Some checks failed
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Has been skipped
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Has been skipped
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Has been skipped
Third-party parts / The same as upstream (pull_request) Has been skipped
Website / Website on Cloudflare (pull_request) Has been skipped
CI / Conventional Commit title (pull_request) Successful in 7s
PR description / Description follows the template (pull_request_target) Failing after 9s
Guide screenshots / Guide images and local UI source review (pull_request) Failing after 10s
CI / Workflow lint (actionlint) (pull_request) Successful in 11s
Third-party parts / As their notes say (pull_request) Successful in 11s
beanstalk/approval planning the tests
to 08ef67ccd3
Some checks failed
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Has been skipped
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Has been skipped
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Has been skipped
Third-party parts / The same as upstream (pull_request) Has been skipped
Website / Website on Cloudflare (pull_request) Has been skipped
CI / Conventional Commit title (pull_request) Successful in 9s
PR description / Description follows the template (pull_request_target) Failing after 11s
Guide screenshots / Guide images and local UI source review (pull_request) Failing after 12s
CI / Workflow lint (actionlint) (pull_request) Successful in 13s
Third-party parts / As their notes say (pull_request) Successful in 14s
beanstalk/approval not approved yet
2026-11-19 15:04:13 +00:00
Compare
HumanBean force-pushed perf/presenter-thread-nvidia-linux from 08ef67ccd3
Some checks failed
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Has been skipped
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Has been skipped
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Has been skipped
Third-party parts / The same as upstream (pull_request) Has been skipped
Website / Website on Cloudflare (pull_request) Has been skipped
CI / Conventional Commit title (pull_request) Successful in 9s
PR description / Description follows the template (pull_request_target) Failing after 11s
Guide screenshots / Guide images and local UI source review (pull_request) Failing after 12s
CI / Workflow lint (actionlint) (pull_request) Successful in 13s
Third-party parts / As their notes say (pull_request) Successful in 14s
beanstalk/approval not approved yet
to 28f5fb2b1e
Some checks reported errors
beanstalk/windows+nvidia 1/1 fail
beanstalk/approval approved by HumanBean (reviewed)
beanstalk/windows+amd 0/1 pass, 2 error
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Has been skipped
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Has been skipped
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Has been skipped
Third-party parts / The same as upstream (pull_request) Has been skipped
Website / Website on Cloudflare (pull_request) Has been skipped
CI / Conventional Commit title (pull_request) Successful in 12s
Guide screenshots / Guide images and local UI source review (pull_request) Failing after 19s
CI / Workflow lint (actionlint) (pull_request) Successful in 19s
Third-party parts / As their notes say (pull_request) Successful in 13s
PR description / Description follows the template (pull_request_target) Failing after 5s
Website / Website on Cloudflare (pull_request_target) Has been skipped
2026-11-19 15:17:07 +00:00
Compare
HumanBean changed title from perf(vk): the presenter thread on by default with NVIDIA on Linux and AMD on Windows, with NVIDIA Reflex; carries #1121 to perf(vk): the presenter thread on by default with NVIDIA on Linux and AMD on Windows, with NVIDIA Reflex; after #1121 2026-11-19 15:18:17 +00:00
Author
Owner

@Beanstalk run 5, again for the new head 28f5fb2 (the same code: #1121 now sits under it as its own PR; run 4 failed because main did not build on Windows, fixed by #1729). The last commit turns the presenter thread on by default with AMD's Windows driver on a discrete card. Please test this PR against main on windows+amd and windows+nvidia, settings vsync=2 (Off) and frame_rate_cap=6 (Uncapped), no switches: Kokiri Forest and Castle Town Market, standing 15 s and 10 s after moving, two game starts a side. Expect vk: presenter thread: each present made on a thread in the log on AMD and off (RX_VK_PRESENT_THREAD=1: on) on NVIDIA, and fps at least main's on both.

@Beanstalk run 5, again for the new head 28f5fb2 (the same code: #1121 now sits under it as its own PR; run 4 failed because main did not build on Windows, fixed by #1729). The last commit turns the presenter thread on by default with AMD's Windows driver on a discrete card. Please test this PR against main on windows+amd and windows+nvidia, settings vsync=2 (Off) and frame_rate_cap=6 (Uncapped), no switches: Kokiri Forest and Castle Town Market, standing 15 s and 10 s after moving, two game starts a side. Expect `vk: presenter thread: each present made on a thread` in the log on AMD and `off (RX_VK_PRESENT_THREAD=1: on)` on NVIDIA, and fps at least main's on both.
Author
Owner

Replaced by #1763, which carries this PR's presenter thread (and its Reflex present id) as part of one rewrite of the renderer's threads: the presenter on every PC, on the device's own present queue, with the recorder thread and the parallel replay removed. Its farm run decides the presenter per platform from there; closing this one so there is a single PR.

Replaced by [#1763](https://git.magicbean.dev/MagicBeanDev/Longshot/pulls/1763), which carries this PR's presenter thread (and its Reflex present id) as part of one rewrite of the renderer's threads: the presenter on every PC, on the device's own present queue, with the recorder thread and the parallel replay removed. Its farm run decides the presenter per platform from there; closing this one so there is a single PR.
HumanBean closed this pull request 2026-11-19 22:12:52 +00:00
Some checks reported errors
beanstalk/windows+nvidia 1/1 fail
beanstalk/approval approved by HumanBean (reviewed)
beanstalk/windows+amd 0/1 pass, 2 error
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Has been skipped
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Has been skipped
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Has been skipped
Third-party parts / The same as upstream (pull_request) Has been skipped
Website / Website on Cloudflare (pull_request) Has been skipped
CI / Conventional Commit title (pull_request) Successful in 12s
Guide screenshots / Guide images and local UI source review (pull_request) Failing after 19s
CI / Workflow lint (actionlint) (pull_request) Successful in 19s
Third-party parts / As their notes say (pull_request) Successful in 13s
PR description / Description follows the template (pull_request_target) Failing after 5s
Website / Website on Cloudflare (pull_request_target) Has been skipped

Pull request closed

Sign in to join this conversation.
No reviewers
No milestone
No project
No assignees
2 participants
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set

Reference
MagicBeanDev/Longshot!1702
No description provided.