WIP: perf(vk): a draw keeps its pipeline and dynamic state while the NVN state they are made from stands #2059

Draft
siantm wants to merge 4 commits from siantm/Longshot:perf/vk-draw-state-gen into main
Contributor

Summary

Each draw past pipe_fast put its pipeline key together and looked it up, and packed its dynamic state's inputs to compare them with the command buffer's. The replay now counts, on each thread, the changes to what those are made from (draw_state_gen, gpu/vk/vk_draw.h): gpu/vk/vk_replay.cpp moves it when a state record (render targets, viewports, scissor, depth range, the bound states, vertex attributes and streams, stencil, polygon offset, blend colour, primitive restart, depth clamp, rasterizer discard) writes another value, at any record not known to leave that state alone (op_moves_draw_state) and at each replay's start. While it stands, with the same state object, the same resolved targets (targets_gen) and the same program (object, key and variant) and topology, a draw takes the pipeline entry of the draw before (pipe_kept) and, with the command buffer's dynamic state valid, leaves its dynamic state as it is (dyn_kept), without packing or comparing. What is kept goes at each recording's begin. The result expected is less work for draws of the same state in a row.

Depends on #2049 (and through it #2048 and #2047: the switch, targets_gen, the word dynamic_state reads once). Their commits show in this diff until they merge. Open #1297 (a pipeline only with the program object it was built from) does not conflict: pipe_kept keys on the program object too.

Switch: RX_VK_BIND_CHANGED (kill, on). =0: every draw as on main.

From bd3ea307 on exp/x86-asm-sync.

Read first: draw_state_gen, kOpsDrawState and op_moves_draw_state in gpu/vk/vk_draw.h and gpu/vk/vk_replay.cpp; pipe_kept and dyn_kept in gpu/vk/vk_draw.cpp.

Testing

Tested: Windows 11, i7-9700, RTX 4060, the builder's llvm-mingw clang 23; head c27bd1f3 on #2049's head 3562fe6b (on main @ 75317e1f). Every check ran through tests/run_all.py --strict --exact in build jobs of the PC's job queue, in a hidden console (log t-dc4-vk-draw-state-gen):

  • Its own: tests/test_draw_state_gen.py (new: every case of replay() that writes a field dyn_pack or the key reads moves the generation; the records listed as leaving the state alone write none; the state records are exactly kOpsDrawState; any other record and each replay's start move it; pipe_kept and dyn_kept compare everything they were made from): pass.
  • The 278 checks that read a file this change touches (--changed 3562fe6b; its own are among them): 246 passed, 32 failed. Failed: tests/test_fsr_image_retirement.py, tests/test_fsr_uniform_ownership.py, tests/test_pipeline_play_cache.py, tests/test_sampler_admission.py, tests/test_draw_stream_visibility.py, tests/test_capture_readback_visibility.py, tests/test_crash_record.py, tests/test_device_lost_exit.py, tests/test_dev_packs.py, tests/test_draw_binds.py, tests/test_dev_ab.py, tests/test_crash_dialog.py, tests/test_flush_nothing_held.py, tests/test_frame_overlap.py, tests/test_gpu_wait_stats.py, tests/test_linux_pressure.py, tests/test_mesh_conv.py, tests/test_prepare_cache_save.py, tests/test_perf_report.py, tests/test_present_queue_default.py, tests/test_profiling_mode.py, tests/test_present_source_crop.py, tests/test_renderer_new_handler.py, tests/test_recorder_own_idle.py, tests/test_replay_write_order.py, tests/test_slow_frames.py, tests/test_sparse_mirror.py, tests/test_target_reuse_memory.py, tests/test_ub_update_batch.py, tests/test_upscaler_rows.py, tests/test_vk_occlusion_queries.py: each fails on main @ 75317e1f too (the same checks on main in the batch before, log t-dc3-base). tests/test_recording_admission.py fails on main @ 75317e1f too, now and then: its "worker slot ownership" case failed on main in 7 of 10 runs made alternately with this branch's (logs t-dc5-base-ra-*), with the same message.

It has NOT run in the game on this PC yet.

Still to test:

  • Windows 11, i7-9700, RTX 4060 (this PC): start in Kokiri Forest from the scene's save, play a minute (walking, turning the camera), then a dungeon room with moving lights: #2049's head, this PR with RX_VK_BIND_CHANGED=0 and this PR with it unset (on), each warmed a minute in the scene first, then interleaved (base, =0, unset, unset, =0, base), two runs each, expecting the same picture all three ways (no wrong blend, depth or stencil, no wrong-sized viewport) and unset the replay's time a frame the same as or lower than the base's (by hand)
  • Linux NVIDIA and AMD, Windows AMD and Intel, Steam Deck: start in Kokiri Forest from the scene's save, play a minute (walking, turning the camera), its base PR alone against this PR with RX_VK_BIND_CHANGED=0 and unset, warmed, in ABBA order, expecting the same picture every way and no crash or validation error (@Beanstalk linux+nvidia, linux+amd, windows+amd, windows+intel, steamdeck: Kokiri Forest a minute, its base PR alone against this PR with RX_VK_BIND_CHANGED=0 and unset, ABBA, the same picture)
  • Linux (any GPU): build the renderer and run tests/test_draw_state_gen.py with --cxx g++ and --cxx clang++, expecting PASS (by hand)

Measurements

Verdict: not measured: no micro-benchmark of this port and no run in the game on this PC yet; the in-game A/B is in Still to test. RX_VK_BIND_CHANGED ships on (kind kill), the branch's default; it is not measured on main.

Risks

A state record that changes what a pipeline or the dynamic state is made from but is missing from kOpsDrawState and listed as leaving it alone would let a draw keep the state of the draw before: a wrong blend, depth, stencil or viewport for that draw. The list is checked against replay()'s cases by the test; any record not listed moves the generation. The vk_replay.cpp hooks are fitted onto main's rewritten replay(). Turned off by RX_VK_BIND_CHANGED=0. The renderer is compiled again after updating.

Checklist

Ready for review

  • One topic, on current main; the title is a Conventional Commit.
  • Tested on my own PC, in the game for a change the game runs, as Testing says. Not yet: it has not run in the game.
  • mise run test passes (any failure that also fails on main is named). Not yet: only the checks in Testing ran.
  • Measured against main, or Measurements says why there is nothing to measure. Not yet (Measurements).
  • No game files, build output or hand-edited generated files; third_party/ untouched; nothing GPL-incompatible.

When it applies

  • A switch added or changed: it ships at the default the measurements chose, with its row in gpu/vk/switches.def. Its row is in; not measured yet.
  • A check under tests/ that reads changed source is updated, not weakened.
  • Host code builds on Windows (llvm-mingw) and Linux, with UTF-8 paths. Not yet: only the checks' cuts compiled (Testing).
  • AI assistance recorded with Assisted-by: / Co-Authored-By: trailers.
## Summary Each draw past `pipe_fast` put its pipeline key together and looked it up, and packed its dynamic state's inputs to compare them with the command buffer's. The replay now counts, on each thread, the changes to what those are made from (`draw_state_gen`, `gpu/vk/vk_draw.h`): `gpu/vk/vk_replay.cpp` moves it when a state record (render targets, viewports, scissor, depth range, the bound states, vertex attributes and streams, stencil, polygon offset, blend colour, primitive restart, depth clamp, rasterizer discard) writes another value, at any record not known to leave that state alone (`op_moves_draw_state`) and at each replay's start. While it stands, with the same state object, the same resolved targets (`targets_gen`) and the same program (object, key and variant) and topology, a draw takes the pipeline entry of the draw before (`pipe_kept`) and, with the command buffer's dynamic state valid, leaves its dynamic state as it is (`dyn_kept`), without packing or comparing. What is kept goes at each recording's begin. The result expected is less work for draws of the same state in a row. Depends on #2049 (and through it #2048 and #2047: the switch, `targets_gen`, the word `dynamic_state` reads once). Their commits show in this diff until they merge. Open #1297 (a pipeline only with the program object it was built from) does not conflict: `pipe_kept` keys on the program object too. Switch: `RX_VK_BIND_CHANGED` (kill, on). `=0`: every draw as on main. From bd3ea307 on `exp/x86-asm-sync`. Read first: `draw_state_gen`, `kOpsDrawState` and `op_moves_draw_state` in `gpu/vk/vk_draw.h` and `gpu/vk/vk_replay.cpp`; `pipe_kept` and `dyn_kept` in `gpu/vk/vk_draw.cpp`. ## Testing **Tested:** Windows 11, i7-9700, RTX 4060, the builder's llvm-mingw clang 23; head c27bd1f3 on #2049's head 3562fe6b (on main @ 75317e1f). Every check ran through `tests/run_all.py --strict --exact` in build jobs of the PC's job queue, in a hidden console (log `t-dc4-vk-draw-state-gen`): - Its own: `tests/test_draw_state_gen.py` (new: every case of `replay()` that writes a field `dyn_pack` or the key reads moves the generation; the records listed as leaving the state alone write none; the state records are exactly `kOpsDrawState`; any other record and each replay's start move it; `pipe_kept` and `dyn_kept` compare everything they were made from): pass. - The 278 checks that read a file this change touches (`--changed 3562fe6b`; its own are among them): 246 passed, 32 failed. Failed: `tests/test_fsr_image_retirement.py`, `tests/test_fsr_uniform_ownership.py`, `tests/test_pipeline_play_cache.py`, `tests/test_sampler_admission.py`, `tests/test_draw_stream_visibility.py`, `tests/test_capture_readback_visibility.py`, `tests/test_crash_record.py`, `tests/test_device_lost_exit.py`, `tests/test_dev_packs.py`, `tests/test_draw_binds.py`, `tests/test_dev_ab.py`, `tests/test_crash_dialog.py`, `tests/test_flush_nothing_held.py`, `tests/test_frame_overlap.py`, `tests/test_gpu_wait_stats.py`, `tests/test_linux_pressure.py`, `tests/test_mesh_conv.py`, `tests/test_prepare_cache_save.py`, `tests/test_perf_report.py`, `tests/test_present_queue_default.py`, `tests/test_profiling_mode.py`, `tests/test_present_source_crop.py`, `tests/test_renderer_new_handler.py`, `tests/test_recorder_own_idle.py`, `tests/test_replay_write_order.py`, `tests/test_slow_frames.py`, `tests/test_sparse_mirror.py`, `tests/test_target_reuse_memory.py`, `tests/test_ub_update_batch.py`, `tests/test_upscaler_rows.py`, `tests/test_vk_occlusion_queries.py`: each fails on main @ 75317e1f too (the same checks on main in the batch before, log `t-dc3-base`). `tests/test_recording_admission.py` fails on main @ 75317e1f too, now and then: its "worker slot ownership" case failed on main in 7 of 10 runs made alternately with this branch's (logs `t-dc5-base-ra-*`), with the same message. It has NOT run in the game on this PC yet. **Still to test:** - Windows 11, i7-9700, RTX 4060 (this PC): start in Kokiri Forest from the scene's save, play a minute (walking, turning the camera), then a dungeon room with moving lights: #2049's head, this PR with `RX_VK_BIND_CHANGED=0` and this PR with it unset (on), each warmed a minute in the scene first, then interleaved (base, =0, unset, unset, =0, base), two runs each, expecting the same picture all three ways (no wrong blend, depth or stencil, no wrong-sized viewport) and unset the replay's time a frame the same as or lower than the base's (by hand) - Linux NVIDIA and AMD, Windows AMD and Intel, Steam Deck: start in Kokiri Forest from the scene's save, play a minute (walking, turning the camera), its base PR alone against this PR with `RX_VK_BIND_CHANGED=0` and unset, warmed, in ABBA order, expecting the same picture every way and no crash or validation error (@Beanstalk linux+nvidia, linux+amd, windows+amd, windows+intel, steamdeck: Kokiri Forest a minute, its base PR alone against this PR with RX_VK_BIND_CHANGED=0 and unset, ABBA, the same picture) - Linux (any GPU): build the renderer and run `tests/test_draw_state_gen.py` with `--cxx g++` and `--cxx clang++`, expecting PASS (by hand) ## Measurements **Verdict:** not measured: no micro-benchmark of this port and no run in the game on this PC yet; the in-game A/B is in Still to test. `RX_VK_BIND_CHANGED` ships on (kind kill), the branch's default; it is not measured on main. ## Risks A state record that changes what a pipeline or the dynamic state is made from but is missing from `kOpsDrawState` and listed as leaving it alone would let a draw keep the state of the draw before: a wrong blend, depth, stencil or viewport for that draw. The list is checked against `replay()`'s cases by the test; any record not listed moves the generation. The `vk_replay.cpp` hooks are fitted onto main's rewritten `replay()`. Turned off by `RX_VK_BIND_CHANGED=0`. The renderer is compiled again after updating. ## Checklist ### Ready for review - [x] One topic, on current `main`; the title is a Conventional Commit. - [ ] Tested on my own PC, in the game for a change the game runs, as Testing says. Not yet: it has not run in the game. - [ ] `mise run test` passes (any failure that also fails on `main` is named). Not yet: only the checks in Testing ran. - [ ] Measured against `main`, or Measurements says why there is nothing to measure. Not yet (Measurements). - [x] No game files, build output or hand-edited generated files; `third_party/` untouched; nothing GPL-incompatible. ### When it applies - [ ] A switch added or changed: it ships at the default the measurements chose, with its row in `gpu/vk/switches.def`. Its row is in; not measured yet. - [x] A check under `tests/` that reads changed source is updated, not weakened. - [ ] Host code builds on Windows (llvm-mingw) and Linux, with UTF-8 paths. Not yet: only the checks' cuts compiled (Testing). - [x] AI assistance recorded with `Assisted-by:` / `Co-Authored-By:` trailers.
perf(vk): a draw leaves out a block of push constants its command buffer already has (RX_VK_BIND_CHANGED, on)
Some checks are pending
CI / Conventional Commit title (pull_request) Blocked by required conditions
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Blocked by required conditions
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Blocked by required conditions
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Blocked by required conditions
CI / Workflow lint (actionlint) (pull_request) Blocked by required conditions
CI / Website build and checks (pull_request) Blocked by required conditions
Guide screenshots / Guide images and local UI source review (pull_request) Blocked by required conditions
Third-party parts / As their notes say (pull_request) Blocked by required conditions
Third-party parts / The same as upstream (pull_request) Blocked by required conditions
PR description / Description follows the template (pull_request_target) Successful in 5s
Website / Website on Cloudflare (pull_request_target) Has been skipped
beanstalk/approval waiting for a BigBean's 👍 on the request
aebcf74638
push_constants pushed the program's whole block (page table, task first, render area, fallback addresses) at every
draw whose program reads it, though the draws of a pass push the same block one after another. It now leaves the
push out when the last block this thread recorded was the same bytes, for the same stages, into the same command
buffer (push_standing). vk_work.h counts every vkCmdPushConstants on the thread (push_epoch), so a push of anyone's
in between makes the next draw push again. The block is forgotten where the command buffer's may be something else:
at each recording's begin (binds_begin_recording), a masked clear, the temporal upscalers' stand-ins, each
dispatch's end (its stand-ins call NGX / FidelityFX, which push past vk_work.h), and (new here, beside the branch's
sites) in descriptors_disturbed, which every upscaler and library pass on main calls after recording its own
pipelines. A direct mesh draw no longer pushes entry 0's first a second time: it is in the block just sent or left
standing.

The first of RX_VK_BIND_CHANGED's parts on the branch (bd3ea307, "draw-binds"); its other parts follow as their own
commits. Its index-buffer part (bind at the pool buffer's start, draw from the first index) is main's
RX_VK_INDEX_REBASE already and is not ported.

Switch: RX_VK_BIND_CHANGED, kill, on by default (the branch's default); =0 (or false, off, no) pushes at every draw as
before. Read once, at its first use. Row in gpu/vk/switches.def. Not measured on its own on the branch ("the saving is
not measured yet"); not measured in play.

Test: tests/test_push_changed.py runs push_standing (cut from the source) and reads the wiring: vk_work.h's count, the
check before the push, the block kept after it, every place it is forgotten, the mesh first; and the switch's reader
runs in fresh processes (unset, 0, off, false, 1, on and another value, twice each, set again after its first read).
The three fixtures that compile draw_begin_recording stand in binds_begin_recording.

Assisted-by: Claude Code
perf(vk): a draw takes its targets by reference and their colour types as worked out at their resolution
Some checks are pending
CI / Conventional Commit title (pull_request) Blocked by required conditions
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Blocked by required conditions
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Blocked by required conditions
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Blocked by required conditions
CI / Workflow lint (actionlint) (pull_request) Blocked by required conditions
CI / Website build and checks (pull_request) Blocked by required conditions
Guide screenshots / Guide images and local UI source review (pull_request) Blocked by required conditions
Third-party parts / As their notes say (pull_request) Blocked by required conditions
Third-party parts / The same as upstream (pull_request) Blocked by required conditions
PR description / Description follows the template (pull_request_target) Successful in 5s
Website / Website on Cloudflare (pull_request_target) Has been skipped
beanstalk/approval waiting for a BigBean's 👍 on the request
3432e729e7
draw() copied the thread's resolved targets twice a draw (targets(), then bare_targets()) and worked out their
colour types (color_types_of) at every draw. With RX_VK_BIND_CHANGED (on) it takes them by reference
(draw_targets: the thread's resolved ones, or the viewport's area in a scratch for a draw with no target) and the
colour types from a memo made again whenever targets() resolves anew (targets_gen). =0: copied and worked out at
every draw, as before.

Part of RX_VK_BIND_CHANGED on the branch (bd3ea307). Needs "perf(vk): a draw leaves out a block of push constants its
command buffer already has (RX_VK_BIND_CHANGED, on)" first (the switch). Not ported from the same part: the branch
also kept whether the targets can be the scene (colour 0 in B10G11R11) and asked once a recording whether an upscaler
wants the scene notes, then skipped temporal_note_scene_draw, fsr3_inputs::note_scene_draw and skin_check for other
draws. On main temporal_scene_format also takes R16G16B16A16_SFLOAT targets (PsychoV35 with the Upscaler Off or a
network that takes it), so that test would leave out draws main notes: those calls stay as main has them.

Not measured on its own on the branch; not measured in play.

Test: tests/test_targets_kept.py cuts draw_targets, draw_targets_copied, TargetsMemo and targets_memo_of and runs them
with stand-ins over 200,000 random target changes, viewports and new submissions against the copies and
color_types_of, and reads targets() and draw() for the generation and the switch.

RX_VK_BIND_CHANGED's row in gpu/vk/switches.def names this part too (what the switch keeps, what =0 gives back).

Assisted-by: Claude Code
perf(vk): a draw's write masks from its program's word, not its stages walked for each target
Some checks are pending
CI / Conventional Commit title (pull_request) Blocked by required conditions
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Blocked by required conditions
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Blocked by required conditions
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Blocked by required conditions
CI / Workflow lint (actionlint) (pull_request) Blocked by required conditions
CI / Website build and checks (pull_request) Blocked by required conditions
Guide screenshots / Guide images and local UI source review (pull_request) Blocked by required conditions
Third-party parts / As their notes say (pull_request) Blocked by required conditions
Third-party parts / The same as upstream (pull_request) Blocked by required conditions
PR description / Description follows the template (pull_request_target) Successful in 5s
Website / Website on Cloudflare (pull_request_target) Has been skipped
beanstalk/approval waiting for a BigBean's 👍 on the request
3562fe6b59
target_write_mask walked the program's stages for its fragment stage at every target of every draw that worked out
its dynamic state, and at every target in draw_hazards. program_wm_sig already keeps all that function reads of a
program as one word (6 bits a target), read by dyn_pack; write_mask_of makes each mask from that word and the
channel mask. dynamic_state reads the word once for dyn_pack and the masks. =0 (RX_VK_BIND_CHANGED): the stages
walked, as before.

Part of RX_VK_BIND_CHANGED on the branch (bd3ea307). Needs "perf(vk): a draw leaves out a block of push constants its
command buffer already has (RX_VK_BIND_CHANGED, on)" first (the switch); it goes after "perf(vk): a draw takes its
targets by reference ..." only so that the next commit, which needs both, has one base. Not measured on its own on the branch; not
measured in play.

Test: tests/test_write_mask_word.py cuts target_write_mask, program_wm_sig and write_mask_of and checks write_mask_of
of the word is target_write_mask for every target, stored or not, components and channel masks; and reads
dynamic_state and draw_hazards for the switch. test_same_dyn.py reads the word as dynamic_state now takes it.

RX_VK_BIND_CHANGED's row in gpu/vk/switches.def names this part too (what the switch keeps, what =0 gives back).

Assisted-by: Claude Code
perf(vk): a draw keeps its pipeline and dynamic state while the NVN state they are made from stands
Some checks are pending
CI / Conventional Commit title (pull_request) Blocked by required conditions
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Blocked by required conditions
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Blocked by required conditions
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Blocked by required conditions
CI / Workflow lint (actionlint) (pull_request) Blocked by required conditions
CI / Website build and checks (pull_request) Blocked by required conditions
Guide screenshots / Guide images and local UI source review (pull_request) Blocked by required conditions
Third-party parts / As their notes say (pull_request) Blocked by required conditions
Third-party parts / The same as upstream (pull_request) Blocked by required conditions
PR description / Description follows the template (pull_request_target) Successful in 5s
Website / Website on Cloudflare (pull_request_target) Has been skipped
beanstalk/approval waiting for a BigBean's 👍 on the request
c27bd1f34e
Each draw past pipe_fast put its pipeline key together and looked it up, and packed its dynamic state's inputs to
compare them with the command buffer's. The replay now counts, on each thread, the changes to what those are made
from (vk_draw.h draw_state_gen): vk_replay.cpp moves it when a state record (render targets, viewports, scissor,
depth range, the six bound states, vertex attributes and streams, stencil, polygon offset, blend colour, primitive
restart, depth clamp, rasterizer discard) writes another value, at any record not known to leave that state alone
(op_moves_draw_state: dispatches, clears, copies, events, anything new) and at each replay's start. While it stands,
with the same state object, the same resolved targets (targets_gen) and the same program (object, key and variant)
and topology, a draw takes the pipeline entry of the draw before (pipe_kept) and, with the command buffer's dynamic
state valid, leaves its dynamic state as it is (dyn_kept), without packing or comparing. What is kept goes at each
recording's begin. =0 (RX_VK_BIND_CHANGED): every draw as before.

Part of RX_VK_BIND_CHANGED on the branch (bd3ea307). Needs "a draw leaves out a block of push constants ...
(RX_VK_BIND_CHANGED, on)" (the switch), "a draw takes its targets by reference ..." (targets_gen) and "a draw's
write masks from its program's word ..." (the word dynamic_state reads once) first. Open #1297 (TrashPanda: a
pipeline only with the program object it was built from) does not conflict: pipe_kept keys on the program object
too. Not measured on its own on the branch; not measured in play.

Test: tests/test_draw_state_gen.py (the branch's test_bind_changed, its write-mask part in test_write_mask_word.py):
every case of replay() that writes a field dyn_pack or key_inputs reads moves the generation, the records listed as
leaving the state alone write none, the state records are exactly kOpsDrawState, any other record and each replay's
start move it, and pipe_kept / dyn_kept compare everything they were made from.

RX_VK_BIND_CHANGED's row in gpu/vk/switches.def names this part too (what the switch keeps, what =0 gives back); the
switch's reader is run by tests/test_push_changed.py, so this check no longer reads its source.
tests/test_draw_side_effects.py (it compiles draw()'s readiness block) stands in pipe_kept and pipe_keep with no
pipeline kept, so each of its cases looks its pipeline up as before.

Assisted-by: Claude Code
Author
Contributor

@Beanstalk This makes the renderer track every draw's pipeline and dynamic state with a generation count (gpu/vk), behind RX_VK_BIND_CHANGED, a kill switch on by default; RX_VK_BIND_CHANGED=0 is main's way. It is on #2049, #2048 and #2047, whose commits are in its diff. It has not run in the game on these PCs yet. Please play Kokiri Forest and Hyrule Field, two minutes each, the PR against main on the same PC, on the PR's side with the switch unset and with RX_VK_BIND_CHANGED=0, with a picture in each compared with main's, on Linux with NVIDIA, Linux with AMD (RADV), Windows with Intel and the Steam Deck. The same picture as main, no crash, device lost, validation error or FATAL line; unset, frame time p99 equal to main's or better and to the switch off.

@Beanstalk This makes the renderer track every draw's pipeline and dynamic state with a generation count (gpu/vk), behind RX_VK_BIND_CHANGED, a kill switch on by default; RX_VK_BIND_CHANGED=0 is main's way. It is on #2049, #2048 and #2047, whose commits are in its diff. It has not run in the game on these PCs yet. Please play Kokiri Forest and Hyrule Field, two minutes each, the PR against main on the same PC, on the PR's side with the switch unset and with RX_VK_BIND_CHANGED=0, with a picture in each compared with main's, on Linux with NVIDIA, Linux with AMD (RADV), Windows with Intel and the Steam Deck. The same picture as main, no crash, device lost, validation error or FATAL line; unset, frame time p99 equal to main's or better and to the switch off.
Member

@siantm only members of BigBeans can start the farm. One of them can approve this request by reacting 👍 to it or to this comment.

@siantm only members of `BigBeans` can start the farm. One of them can approve this request by reacting 👍 to it or to this comment.
Some checks are pending
CI / Conventional Commit title (pull_request) Blocked by required conditions
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Blocked by required conditions
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Blocked by required conditions
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Blocked by required conditions
CI / Workflow lint (actionlint) (pull_request) Blocked by required conditions
CI / Website build and checks (pull_request) Blocked by required conditions
Guide screenshots / Guide images and local UI source review (pull_request) Blocked by required conditions
Third-party parts / As their notes say (pull_request) Blocked by required conditions
Third-party parts / The same as upstream (pull_request) Blocked by required conditions
PR description / Description follows the template (pull_request_target) Successful in 5s
Website / Website on Cloudflare (pull_request_target) Has been skipped
beanstalk/approval waiting for a BigBean's 👍 on the request
This pull request is marked as a work in progress.
Some workflows are waiting to be reviewed.
This branch is out-of-date with the base branch
View command line instructions

Checkout

From your project repository, check out a new branch and test the changes.
git fetch -u 'perf/vk-draw-state-gen:siantm-perf/vk-draw-state-gen'
git switch 'siantm-perf/vk-draw-state-gen'
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!2059
No description provided.