fix(vk): the presents on their own compute queue again by default with NVIDIA's driver 621.24 and newer on Windows #1476

Merged
HumanBean merged 3 commits from pmwork-personal/Longshot:fix/present-queue-default into main 2026-11-17 23:15:56 +00:00
Member

Type: fix · Risk: medium · Tested on: Windows 11, RTX 5090 (NVIDIA 621.24) · Needs: Windows with an RTX 40 (Test Farm), an RTX 4090 most of all

TL;DR

With frame generation, frames meant to reach the screen evenly still arrived in bunches: each one waited on the GPU behind
the game's next frame. This PR gives them a GPU queue of their own again, by default with NVIDIA's driver 621.24 or newer
on Windows. On an RTX 5090 at V-Sync Off and 3x, frames shown under 2 ms went from a third to none, and each frame reached
the screen about 5 ms sooner. The queue was turned off in v2.0.9 after one RTX 4090 on an older driver had a black screen
with it, so older drivers keep the old path, and the Test Farm checks RTX 40 cards before this merges.

Breakdown

  • Who it helps: players with frame generation on an NVIDIA card with driver 621.24 or newer on Windows, at any V-Sync
    setting.
  • What was wrong: a present on the game's own GPU queue waits behind the game's next frame (3 to 12 ms at 5120x2160),
    so frames that #1362 presents at their own times still reach the screen together.
  • What changes: with NVIDIA's driver 621.24 and newer on Windows, the presents go on a compute queue of their own, as
    before v2.0.9; the switch follows the yes/no rule; the device-lost message names the way back.
  • What does not change: other drivers, older NVIDIA drivers, AMD, Intel and Linux keep the game's queue; saves,
    settings and caches.
  • How it was checked: two interleaved runs a side against main on an RTX 5090: frames under 2 ms 33% to 0.0%, each
    present's call to the screen 6.6 to 1.3 ms; a new check that fails on main; the full suite as on main.
  • What is still open: RTX 40 cards (the Test Farm, with the queue forced on) and an RTX 4090 if anyone has one.
  • Risk: medium: on the one PC of Hookshot issue 1161 (RTX 4090, NVIDIA 621.14) the queue gave a black screen;
    RX_VK_PRESENT_QUEUE=0 turns it off.

Why

With a fixed frame generation multiplier, each made frame should stay on the screen for its share of the game's frame.
Since #1362, V-Sync Off presents them at those times, but each present still sits on the replay's queue behind the game's
next frame, so they leave the GPU together: a third of the frames are on the screen under 2 ms, which looks like no frame
generation at all. The same wait pairs the frames at 2x under FIFO (6 ms, then 11 ms). A queue of their own was the default
with NVIDIA's driver before v2.0.9; it was turned off for Hookshot issue 1161 (before the fork) and never turned back on.

See #1442, #315.

How to reproduce

Seen on: Windows 11 Pro build 26300, RTX 5090, NVIDIA 621.24
Settings and switches: V-Sync Off, Frame generation 3x by DLSS FG (Auto), Frame pacing Off; main 415a8944
Steps: in play, turn the camera at an even speed; for numbers, PresentMon on longshot.exe, the DisplayedTime column.
Expected: each frame on the screen about a third of the game's frame (5 to 7 ms at ~57 fps).
Actual: a third of the frames under 2 ms (p10 1.0 ms), others over 13 ms.

What changed

The presents' own compute queue is the default again with NVIDIA's proprietary driver on Windows, from driver 621.24 on,
where it was measured; anything else keeps the replay's queue unless RX_VK_PRESENT_QUEUE=1 asks for it.

  • gpu/vk/vk_main.cpp create_device: want is NVIDIA's proprietary driver with driverVersion at least 621.24
    (kPresentQueueNvidia); an older NVIDIA driver logs why it stays off. RX_VK_PRESENT_QUEUE follows the switches' yes/no
    rule (env_value_off: unset or empty is the default; 0, false, off or no is off; anything else on), so on no longer
    reads as off. The comment says why, with the history.
  • gpu/vk/vk_replay.cpp device_lost: while the presents are on their own queue, the fatal message names
    RX_VK_PRESENT_QUEUE=0 and asks for the GPU and driver.
  • gpu/vk/vk_dlss.cpp dlss_fg_close: the exit's 2 s wait also waits for the presents' own queues' locks: a present on
    them lets dev.present_mu go while it runs, so device_wait_idle_locked could wait on them with no end at the exit.
  • gpu/vk/switches.def: RX_VK_PRESENT_QUEUE is hw (it follows the driver); docs/development.md, design.md section 13
    rule 5 and the README say so, and what to do on a black screen or a lost GPU.
  • tests/test_present_queue_default.py (new, fails on main): the default, the version floor, the switch's rule, the rows,
    the device-lost text and the exit wait.

Measurements

Verdict: better. V-Sync Off 3x: frames on the screen under 2 ms 33.0-33.7% to 0.0%, their times' sd 4.7 to 1.05-1.30
ms, each present's call to the screen 6.5-6.7 to 1.3 ms. With #1442 at V-Sync Auto 2x, the 6/11 ms pairs go: 8.3-8.4 ms each.

Hardware: Windows 11 Pro build 26300, RTX 5090, NVIDIA 621.24, AMD Ryzen 7 9800X3D, 64 GB
Scene: Hyrule Market (child), the tester's saved spot; 5120x2160 at 165 Hz with G-Sync, fullscreen, DLAA, DLSS Frame Gen
3x (DLSS-G made the frames), Reflex On + Boost, V-Sync Off, frame rate cap Uncapped
Method: main 415a8944 and this branch as it was first committed (b897bc79: the queue on with NVIDIA's driver; the review's
changes since, the 621.24 floor, the switch's rule, the exit wait and the device-lost text, change no frame on a 621.24
driver), each a dev_packs.py pack on one base (nightly-396 @ 7887c497); a warm-up of each, then main and the branch in
turn, two runs a side; the control bridge turns the camera with the right stick (60 degrees a second) for 30 s; PresentMon
2.3.0 on longshot.exe for 30 s. Each run's number shown. The D2 runs are #1442 (273f5d28) with RX_VK_PRESENT_QUEUE=1,
against the same build without it from earlier sessions that day. Main 7b229f66 is merged in since (6d0e72dc), without
new runs: of its commits after 415a8944 only #1442 changes the presents' path (vk_framegen.cpp, vk_replay.cpp,
vk_main.cpp, vk_dlss.cpp, vk_reflex.cpp), and it is the V-Sync On pacing the D2 runs already ran with, so the numbers hold.
How to reproduce: the settings above, a save at a spot to turn the camera, PresentMon 2.x --process_name longshot.exe --timed 30 --terminate_after_timed --output_file <csv>; frames under 2 ms and the sd from DisplayedTime, the call to
the screen as DisplayLatency less CPUBusy. Rows: docs/tested/2026-11-17-present-queue-default-*.md.

Before: main @ 415a8944 After: this PR @ b897bc79
V-Sync Off 3x: frames shown a second 165.5 / 163.2 166.7 / 171.8
V-Sync Off 3x: on the screen under 2 ms 33.7% / 33.0% 0.0% / 0.0%
V-Sync Off 3x: DisplayedTime p10 / p50 / p90, ms 1.0 / 5.4 / 13.2; 1.0 / 5.4 / 13.3 4.6 / 5.9 / 7.6; 4.8 / 5.7 / 6.9
V-Sync Off 3x: DisplayedTime sd, ms 4.72 / 4.78 1.30 / 1.05
V-Sync Off 3x: call to screen median, ms 6.5 / 6.7 1.3 / 1.3
#1442 at V-Sync Auto 2x, cap 60 Before: without the queue (3 runs, earlier that day) After: RX_VK_PRESENT_QUEUE=1
DisplayedTime p10 / p50, ms 5.9 / 7.3-7.8 7.2 / 8.3-8.4
DisplayedTime sd, ms 2.40-2.71 0.94 / 1.05
over 9 ms on the screen 36.5-38.5% 19.4% / 22.6%
call to screen median, ms 3.5-3.8 1.3 / 1.3
(this PR, lV-def2's log)
vk: presents on a queue of their own, of compute family 2 (RX_VK_PRESENT_QUEUE=0: off)

Flags and settings

One switch changes its default: RX_VK_PRESENT_QUEUE.

Flag What it is Before this PR After this PR Effect Helps / doesn't help / untested Recommendation
RX_VK_PRESENT_QUEUE env, renderer (hw) off on every PC (=1 on, by atoi) on with NVIDIA's driver 621.24+ on Windows, off elsewhere; the yes/no rule the presents on a compute family's queue of their own helps: the tables (RTX 5090, 621.24); untested: RTX 40, other drivers on where it is now default; =0 for a black screen or a lost GPU

Testing

Tested:

  • In the game on Windows 11, RTX 5090, NVIDIA 621.24: the runs above (V-Sync Off 3x, main and this branch in turn, two a
    side), the log's presents on a queue of their own, and, with #1442, V-Sync Auto 2x twice. The queue was also on (by
    switch) in 8 recorded runs and a play session on 2026-11-16 and 17 (docs/tested/*fg-pacing*present-queue*) and two
    latency runs for #1442: no lost device, no black screen.
  • python -I -B tests/run_all.py on 6d0e72dc (Windows, llvm-mingw): 653 passed, 52 failed, 48 skipped; main 7b229f66 on
    this PC: 650 passed, 54 failed. None fails here that fails not on main: the files that differed between the two runs
    (test_finish_output, test_longshot_ctl, test_memtour) pass alone on both, and test_fastfp_fma, test_fpx_sticky
    and test_spawn_emit fail alone on both. tests/test_present_queue_default.py passes here and fails on main. The game
    builds from 6d0e72dc (a dev_packs.py pack on nightly-396).

Not testable by hand: Hookshot issue 1161's black screen: I have no RTX 4090 and no 621.14. The device-lost message,
the 621.24 floor (older drivers stay off) and the Test Farm's RTX 40 run stand in for it.

Not tested: NVIDIA drivers between 621.14 and 621.24 (they stay off: the floor); AMD, Intel and Linux (unchanged).

Must be tested:

  • windows, nvidia, gpu-rtx-40xx: with RX_VK_PRESENT_QUEUE=1 (the queue on whatever the driver), Hyrule Market with
    frame generation 2x by DLSS FG, V-Sync Off and On, against main; expecting no lost device, crash or black screen and fps
    as main (Test Farm: @Beanstalk below)
  • An RTX 4090 on any driver, by hand: the same with RX_VK_PRESENT_QUEUE=1 for a few minutes, expecting no black screen
    and no lost GPU (either is issue 1161 back) (by hand: asked in #agent-updates; what to look at: the screen, and the log's
    device-lost line)

Risks

What could break: a black screen or a lost GPU with the presents on their own queue, as on Hookshot issue 1161's
RTX 4090 with NVIDIA's 621.14 (a driver now below the floor). Only NVIDIA's driver 621.24 and newer on Windows changes.

Turning it off: RX_VK_PRESENT_QUEUE=0 in longshot_env.txt; the device-lost message says so.

Compatibility: Nothing changes: saves, longshot_options.ini, caches and the vk ABI as before.

Issues

See #1442, #315

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.
  • 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).
  • 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).
  • A game-free test added for the fix, failing on main and passing here.
  • Docs updated.

🤖 Generated with Claude Code

**Type:** fix · **Risk:** medium · **Tested on:** Windows 11, RTX 5090 (NVIDIA 621.24) · **Needs:** Windows with an RTX 40 (Test Farm), an RTX 4090 most of all ## TL;DR With frame generation, frames meant to reach the screen evenly still arrived in bunches: each one waited on the GPU behind the game's next frame. This PR gives them a GPU queue of their own again, by default with NVIDIA's driver 621.24 or newer on Windows. On an RTX 5090 at V-Sync Off and 3x, frames shown under 2 ms went from a third to none, and each frame reached the screen about 5 ms sooner. The queue was turned off in v2.0.9 after one RTX 4090 on an older driver had a black screen with it, so older drivers keep the old path, and the Test Farm checks RTX 40 cards before this merges. ## Breakdown - **Who it helps:** players with frame generation on an NVIDIA card with driver 621.24 or newer on Windows, at any V-Sync setting. - **What was wrong:** a present on the game's own GPU queue waits behind the game's next frame (3 to 12 ms at 5120x2160), so frames that #1362 presents at their own times still reach the screen together. - **What changes:** with NVIDIA's driver 621.24 and newer on Windows, the presents go on a compute queue of their own, as before v2.0.9; the switch follows the yes/no rule; the device-lost message names the way back. - **What does not change:** other drivers, older NVIDIA drivers, AMD, Intel and Linux keep the game's queue; saves, settings and caches. - **How it was checked:** two interleaved runs a side against main on an RTX 5090: frames under 2 ms 33% to 0.0%, each present's call to the screen 6.6 to 1.3 ms; a new check that fails on main; the full suite as on main. - **What is still open:** RTX 40 cards (the Test Farm, with the queue forced on) and an RTX 4090 if anyone has one. - **Risk:** medium: on the one PC of Hookshot issue 1161 (RTX 4090, NVIDIA 621.14) the queue gave a black screen; `RX_VK_PRESENT_QUEUE=0` turns it off. ## Why With a fixed frame generation multiplier, each made frame should stay on the screen for its share of the game's frame. Since #1362, V-Sync Off presents them at those times, but each present still sits on the replay's queue behind the game's next frame, so they leave the GPU together: a third of the frames are on the screen under 2 ms, which looks like no frame generation at all. The same wait pairs the frames at 2x under FIFO (6 ms, then 11 ms). A queue of their own was the default with NVIDIA's driver before v2.0.9; it was turned off for Hookshot issue 1161 (before the fork) and never turned back on. See #1442, #315. ## How to reproduce **Seen on:** Windows 11 Pro build 26300, RTX 5090, NVIDIA 621.24 **Settings and switches:** V-Sync Off, Frame generation 3x by DLSS FG (Auto), Frame pacing Off; main 415a8944 **Steps:** in play, turn the camera at an even speed; for numbers, PresentMon on `longshot.exe`, the `DisplayedTime` column. **Expected:** each frame on the screen about a third of the game's frame (5 to 7 ms at ~57 fps). **Actual:** a third of the frames under 2 ms (p10 1.0 ms), others over 13 ms. ## What changed The presents' own compute queue is the default again with NVIDIA's proprietary driver on Windows, from driver 621.24 on, where it was measured; anything else keeps the replay's queue unless `RX_VK_PRESENT_QUEUE=1` asks for it. - `gpu/vk/vk_main.cpp` `create_device`: `want` is NVIDIA's proprietary driver with `driverVersion` at least 621.24 (`kPresentQueueNvidia`); an older NVIDIA driver logs why it stays off. `RX_VK_PRESENT_QUEUE` follows the switches' yes/no rule (`env_value_off`: unset or empty is the default; 0, false, off or no is off; anything else on), so `on` no longer reads as off. The comment says why, with the history. - `gpu/vk/vk_replay.cpp` `device_lost`: while the presents are on their own queue, the fatal message names `RX_VK_PRESENT_QUEUE=0` and asks for the GPU and driver. - `gpu/vk/vk_dlss.cpp` `dlss_fg_close`: the exit's 2 s wait also waits for the presents' own queues' locks: a present on them lets `dev.present_mu` go while it runs, so `device_wait_idle_locked` could wait on them with no end at the exit. - `gpu/vk/switches.def`: `RX_VK_PRESENT_QUEUE` is `hw` (it follows the driver); docs/development.md, design.md section 13 rule 5 and the README say so, and what to do on a black screen or a lost GPU. - `tests/test_present_queue_default.py` (new, fails on main): the default, the version floor, the switch's rule, the rows, the device-lost text and the exit wait. ## Measurements **Verdict:** better. V-Sync Off 3x: frames on the screen under 2 ms 33.0-33.7% to 0.0%, their times' sd 4.7 to 1.05-1.30 ms, each present's call to the screen 6.5-6.7 to 1.3 ms. With #1442 at V-Sync Auto 2x, the 6/11 ms pairs go: 8.3-8.4 ms each. Hardware: Windows 11 Pro build 26300, RTX 5090, NVIDIA 621.24, AMD Ryzen 7 9800X3D, 64 GB Scene: Hyrule Market (child), the tester's saved spot; 5120x2160 at 165 Hz with G-Sync, fullscreen, DLAA, DLSS Frame Gen 3x (DLSS-G made the frames), Reflex On + Boost, V-Sync Off, frame rate cap Uncapped Method: main 415a8944 and this branch as it was first committed (b897bc79: the queue on with NVIDIA's driver; the review's changes since, the 621.24 floor, the switch's rule, the exit wait and the device-lost text, change no frame on a 621.24 driver), each a `dev_packs.py` pack on one base (nightly-396 @ 7887c497); a warm-up of each, then main and the branch in turn, two runs a side; the control bridge turns the camera with the right stick (60 degrees a second) for 30 s; PresentMon 2.3.0 on `longshot.exe` for 30 s. Each run's number shown. The D2 runs are #1442 (273f5d28) with `RX_VK_PRESENT_QUEUE=1`, against the same build without it from earlier sessions that day. Main 7b229f66 is merged in since (6d0e72dc), without new runs: of its commits after 415a8944 only #1442 changes the presents' path (vk_framegen.cpp, vk_replay.cpp, vk_main.cpp, vk_dlss.cpp, vk_reflex.cpp), and it is the V-Sync On pacing the D2 runs already ran with, so the numbers hold. How to reproduce: the settings above, a save at a spot to turn the camera, PresentMon 2.x `--process_name longshot.exe --timed 30 --terminate_after_timed --output_file <csv>`; frames under 2 ms and the sd from `DisplayedTime`, the call to the screen as `DisplayLatency` less `CPUBusy`. Rows: `docs/tested/2026-11-17-present-queue-default-*.md`. | | Before: main @ 415a8944 | After: this PR @ b897bc79 | |---|---|---| | V-Sync Off 3x: frames shown a second | 165.5 / 163.2 | 166.7 / 171.8 | | V-Sync Off 3x: on the screen under 2 ms | 33.7% / 33.0% | 0.0% / 0.0% | | V-Sync Off 3x: `DisplayedTime` p10 / p50 / p90, ms | 1.0 / 5.4 / 13.2; 1.0 / 5.4 / 13.3 | 4.6 / 5.9 / 7.6; 4.8 / 5.7 / 6.9 | | V-Sync Off 3x: `DisplayedTime` sd, ms | 4.72 / 4.78 | 1.30 / 1.05 | | V-Sync Off 3x: call to screen median, ms | 6.5 / 6.7 | 1.3 / 1.3 | | #1442 at V-Sync Auto 2x, cap 60 | Before: without the queue (3 runs, earlier that day) | After: `RX_VK_PRESENT_QUEUE=1` | |---|---|---| | `DisplayedTime` p10 / p50, ms | 5.9 / 7.3-7.8 | 7.2 / 8.3-8.4 | | `DisplayedTime` sd, ms | 2.40-2.71 | 0.94 / 1.05 | | over 9 ms on the screen | 36.5-38.5% | 19.4% / 22.6% | | call to screen median, ms | 3.5-3.8 | 1.3 / 1.3 | ``` (this PR, lV-def2's log) vk: presents on a queue of their own, of compute family 2 (RX_VK_PRESENT_QUEUE=0: off) ``` ### Flags and settings One switch changes its default: `RX_VK_PRESENT_QUEUE`. | Flag | What it is | Before this PR | After this PR | Effect | Helps / doesn't help / untested | Recommendation | |---|---|---|---|---|---|---| | `RX_VK_PRESENT_QUEUE` | env, renderer (hw) | off on every PC (`=1` on, by `atoi`) | on with NVIDIA's driver 621.24+ on Windows, off elsewhere; the yes/no rule | the presents on a compute family's queue of their own | helps: the tables (RTX 5090, 621.24); untested: RTX 40, other drivers | on where it is now default; `=0` for a black screen or a lost GPU | ## Testing **Tested:** - In the game on Windows 11, RTX 5090, NVIDIA 621.24: the runs above (V-Sync Off 3x, main and this branch in turn, two a side), the log's `presents on a queue of their own`, and, with #1442, V-Sync Auto 2x twice. The queue was also on (by switch) in 8 recorded runs and a play session on 2026-11-16 and 17 (`docs/tested/*fg-pacing*present-queue*`) and two latency runs for #1442: no lost device, no black screen. - `python -I -B tests/run_all.py` on 6d0e72dc (Windows, llvm-mingw): 653 passed, 52 failed, 48 skipped; main 7b229f66 on this PC: 650 passed, 54 failed. None fails here that fails not on main: the files that differed between the two runs (`test_finish_output`, `test_longshot_ctl`, `test_memtour`) pass alone on both, and `test_fastfp_fma`, `test_fpx_sticky` and `test_spawn_emit` fail alone on both. `tests/test_present_queue_default.py` passes here and fails on main. The game builds from 6d0e72dc (a `dev_packs.py` pack on nightly-396). **Not testable by hand:** Hookshot issue 1161's black screen: I have no RTX 4090 and no 621.14. The device-lost message, the 621.24 floor (older drivers stay off) and the Test Farm's RTX 40 run stand in for it. **Not tested:** NVIDIA drivers between 621.14 and 621.24 (they stay off: the floor); AMD, Intel and Linux (unchanged). **Must be tested:** - windows, nvidia, gpu-rtx-40xx: with `RX_VK_PRESENT_QUEUE=1` (the queue on whatever the driver), Hyrule Market with frame generation 2x by DLSS FG, V-Sync Off and On, against main; expecting no lost device, crash or black screen and fps as main (Test Farm: @Beanstalk below) - An RTX 4090 on any driver, by hand: the same with `RX_VK_PRESENT_QUEUE=1` for a few minutes, expecting no black screen and no lost GPU (either is issue 1161 back) (by hand: asked in #agent-updates; what to look at: the screen, and the log's device-lost line) ## Risks **What could break:** a black screen or a lost GPU with the presents on their own queue, as on Hookshot issue 1161's RTX 4090 with NVIDIA's 621.14 (a driver now below the floor). Only NVIDIA's driver 621.24 and newer on Windows changes. **Turning it off:** `RX_VK_PRESENT_QUEUE=0` in `longshot_env.txt`; the device-lost message says so. **Compatibility:** Nothing changes: saves, longshot_options.ini, caches and the vk ABI as before. ## Issues See #1442, #315 ## 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. - [x] Nothing gets worse that I know of: any cost (speed, latency, memory, a setup that worked before) is measured and in Risks. - [x] Testing names what was tested, what wasn't, and what must still be tested, where and how. - [x] Rebased on current `main`. - [x] `python -I -B tests/run_all.py` passes (any failure that also fails on `main` is named). - [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`). - [x] A game-free test added for the fix, failing on `main` and passing here. - [x] Docs updated. 🤖 Generated with [Claude Code](https://claude.com/claude-code)
fix(vk): the presents on their own compute queue again by default with NVIDIA's driver 621.24 and newer on Windows
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
PR description / Description follows the template (pull_request_target) Successful in 18s
CI / Conventional Commit title (pull_request) Successful in 14s
Website / Website on Cloudflare (pull_request_target) Has been skipped
CI / Workflow lint (actionlint) (pull_request) Successful in 27s
Guide screenshots / Guide images and local UI source review (pull_request) Successful in 27s
Third-party parts / As their notes say (pull_request) Successful in 49s
beanstalk/approval approved by futondestroyer (reviewed)
beanstalk/windows+nvidia+gpu-rtx-40xx 0/1 pass, 0 running, 2 queued
beanstalk/windows+amd 0/1 pass, 2 running, 0 queued
beanstalk/linux+amd 1/1 fail
a2d0d3b6c5
On the replay's queue a present waits behind the game's next frame (3 to 12 ms at 5120x2160), so frame generation's frames,
each presented at its own time since #1362, still reach the screen together. An RTX 5090 on 621.24, 165 Hz G-Sync, DLSS
Frame Gen 3x, V-Sync Off, main 415a8944 against this branch, two runs a side (PresentMon): frames on the screen under 2 ms
after the one before 33.0-33.7% -> 0.0%, the sd of their times on the screen 4.7 -> 1.05-1.30 ms, each present's call to
the screen (DisplayLatency less CPUBusy) 6.5-6.7 -> 1.3 ms. With #1442 and V-Sync Auto at 2x (120 a second on 165 Hz)
the made frame and the game frame stop coming in pairs: 8.3-8.4 ms each (p10 7.2), sd 2.4-2.7 -> 0.94-1.05 ms.

v2.0.9 turned the queue off for Hookshot issue 1161, before the fork: an RTX 4090 on NVIDIA's 621.14, whose GPU v2.0.8 lost
in the write-back diff (b784c68a), had a black screen with the present queue alone (4e24bd4d). That fault was never placed.
So the default is NVIDIA's proprietary driver from 621.24 on, where it ran in 12 recorded runs and a tester's play; older
NVIDIA drivers (the log says so), other drivers and Linux keep the replay's queue. RX_VK_PRESENT_QUEUE follows the switches'
yes/no rule now (unset or empty: the default; 0, false, off, no: off; else on), and the device-lost message names =0 while
the queue is in use. dlss_fg_close's 2 s exit wait also waits for the presents' own queues' locks, which a present on them
holds while dev.present_mu is let go (the cold review): device_wait_idle_locked waited there with no end.

The switch's row is hw; create_device's comment, design.md section 13 rule 5, development.md and the README say so; six
docs/tested rows (2026-11-17-present-queue-default-*). tests/test_present_queue_default.py checks the default, the version,
the switch's rule, the rows, the device-lost text and the exit wait (it fails on main).

Co-Authored-By: Claude Opus 5.5 <[email protected]>
Author
Member

Tested in game: Windows 11, RTX 5090, NVIDIA 621.24: Hyrule Market, V-Sync Off, Frame generation 3x by DLSS FG, main 415a8944 and this branch in turn, two 30 s camera turns a side: the log says presents on a queue of their own; frames on the screen under 2 ms 33% on main, 0.0% here (PresentMon); no lost device or black screen

Tested in game: Windows 11, RTX 5090, NVIDIA 621.24: Hyrule Market, V-Sync Off, Frame generation 3x by DLSS FG, main 415a8944 and this branch in turn, two 30 s camera turns a side: the log says presents on a queue of their own; frames on the screen under 2 ms 33% on main, 0.0% here (PresentMon); no lost device or black screen
Author
Member

@Beanstalk windows, nvidia, gpu-rtx-40xx: compare main with this PR in child Hyrule Market, Frame generation 2x by DLSS FG, V-Sync Off and V-Sync On, about 30 s each, with RX_VK_PRESENT_QUEUE=1 on the PR's side (so the presents' own queue is used whatever the driver: the PR's default starts at NVIDIA 621.24). The PR fails on a lost device, a crash, a black screen, or fps more than 10% under main. Please take the picture after the stick is let go, with the camera still. Also windows amd and linux amd: the PR changes nothing there (the default stays off), one short run each as a crash check.

@Beanstalk windows, nvidia, gpu-rtx-40xx: compare main with this PR in child Hyrule Market, Frame generation 2x by DLSS FG, V-Sync Off and V-Sync On, about 30 s each, with RX_VK_PRESENT_QUEUE=1 on the PR's side (so the presents' own queue is used whatever the driver: the PR's default starts at NVIDIA 621.24). The PR fails on a lost device, a crash, a black screen, or fps more than 10% under main. Please take the picture after the stick is let go, with the camera still. Also windows amd and linux amd: the PR changes nothing there (the default stays off), one short run each as a crash check.
Member

@Beanstalk Please compare main and this PR on Windows with an NVIDIA RTX 40-series GPU, preferably an RTX 4090. In child Hyrule Market, run DLSS Frame Generation at 2x with V-Sync Off and again with V-Sync On, about 30 seconds for each setting. Set RX_VK_PRESENT_QUEUE=1 on the PR side so the dedicated queue is exercised on every driver. Flag device loss, a crash, a black screen, or FPS more than 10% below main. Also run a short crash check at default settings on Windows AMD and Linux AMD. Report pass/fail and summary metrics only.

@Beanstalk Please compare main and this PR on Windows with an NVIDIA RTX 40-series GPU, preferably an RTX 4090. In child Hyrule Market, run DLSS Frame Generation at 2x with V-Sync Off and again with V-Sync On, about 30 seconds for each setting. Set RX_VK_PRESENT_QUEUE=1 on the PR side so the dedicated queue is exercised on every driver. Flag device loss, a crash, a black screen, or FPS more than 10% below main. Also run a short crash check at default settings on Windows AMD and Linux AMD. Report pass/fail and summary metrics only.
Member
Beanstalk test farm · an earlier run: commit a2d0d3b (the newer results are in a comment below)

Commit a2d0d3b · tier reviewed · approved by futondestroyer · dashboard

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

The plan compares main and the PR in child Hyrule Market with 2x frame generation for 30 seconds each with V-Sync off and on, then runs a short default-settings crash check. All scenarios run on each target, and the present-queue switch is forced on both sides because the plan cannot set this existing switch on the PR side alone. Crashes, device-loss logs, major screenshot differences, or FPS more than 10% below main fail; the screenshots check for a black screen. The RTX 40-series target must wait for a matching Windows tester, and DLSS is not built on the farm, so the requested DLSS-specific coverage cannot be guaranteed. No tester online now matches windows+nvidia+gpu-rtx-40xx: that target waits for one.

  • Where: windows+nvidia+gpu-rtx-40xx (GPU "rtx 40xx", 1-2 reports), windows+amd (1-2 reports), linux+amd (1-2 reports).
  • Matrix: 2 cells, each on main and the PR: vsync 2 or 1.
  • market-frame-generation: from a new save (settings frame_pacing=0, frame_generation=2, frame_generation_by=0; switches RX_VK_PRESENT_QUEUE=1), then teleport to Market, measure market for 30 s (after 5 s warm-up), take the picture market to compare with main; 1 run on each side for each of 2 cells (1 game start a run).
  • default-crash-check: from a new save, then measure forest for 10 s (after 5 s warm-up); 1 run on each side.
  • Measured: crashes, 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 15%; or forbidden log lines is above 0.
  • Time: about 27 min of game runs per tester (4 game starts), plus the two builds.

Started at 22:49 UTC.

Estimate: done in about 25 min, from the queue and the testers online now; some jobs can't start yet.

Target Reports Crash Frame p99 (ms) vs main VRAM peak (MB) vs main Result
windows+nvidia+gpu-rtx-40xx 0/1 — — — queued
windows+amd 0/1 — — — running
linux+amd · 1: linux+amd+radv+dgpu AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7 1/1 1 none — — fail
Scenario · matrix cell Target Frame p99 (ms) vs main Result
market-frame-generation · vsync=2 windows+nvidia+gpu-rtx-40xx — —
market-frame-generation · vsync=2 windows+amd — —
market-frame-generation · vsync=2 linux+amd — pass
market-frame-generation · vsync=1 windows+nvidia+gpu-rtx-40xx — —
market-frame-generation · vsync=1 windows+amd — —
market-frame-generation · vsync=1 linux+amd — fail

Measurements · linux+amd

Verdict: fail on linux+amd (1/1 report): market-frame-generation market.fps_mean.min_delta_pct (-15.2%) 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
Scene: market-frame-generation, from a new save (frame_pacing=0, frame_generation=2, frame_generation_by=0, RX_VK_PRESENT_QUEUE=1); default-crash-check, from a new save; 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); market-frame-generation: 1 game start a side, market 30 s after 5 s warm-up; default-crash-check: 1 game start a side, forest 10 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 @ 415a894 After: this PR @ a2d0d3b
market-frame-generation · vsync=2 · market · frame rate 2.9 3.1 (+6%)
market-frame-generation · vsync=2 · forbidden log lines 0.0 0.0
market-frame-generation · vsync=1 · market · frame rate 13.3 11.2 (−15%)
market-frame-generation · vsync=1 · forbidden log lines 0.0 0.0
default-crash-check · forest · frame rate 52.7 56.6 (+8%)
default-crash-check · 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
vsync menu setting 2, 1 main's default the PR's default market-frame-generation, the PR at 2 → at 1: 3.1 → 11.2 (+262%) helps
Markdown for the PR description
## Measurements

**Verdict:** fail on linux+amd (1/1 report): `market-frame-generation market.fps_mean.min_delta_pct (-15.2%)` 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`  
Scene: market-frame-generation, from a new save (frame_pacing=0, frame_generation=2, frame_generation_by=0, RX_VK_PRESENT_QUEUE=1); default-crash-check, from a new save; 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); market-frame-generation: 1 game start a side, market 30 s after 5 s warm-up; default-crash-check: 1 game start a side, forest 10 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 @ 415a894 | After: this PR @ a2d0d3b |
|---|---|---|
| market-frame-generation · `vsync=2` · market · frame rate | 2.9 | 3.1 (+6%) |
| market-frame-generation · `vsync=2` · forbidden log lines | 0.0 | 0.0 |
| market-frame-generation · `vsync=1` · market · frame rate | 13.3 | 11.2 (−15%) |
| market-frame-generation · `vsync=1` · forbidden log lines | 0.0 | 0.0 |
| default-crash-check · forest · frame rate | 52.7 | 56.6 (+8%) |
| default-crash-check · 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 |
|---|---|---|---|---|---|---|
| `vsync` | menu setting | `2`, `1` | main's default | the PR's default | market-frame-generation, the PR at 2 → at 1: 3.1 → 11.2 (+262%) | helps |
<!-- beanstalk:previous --> <details><summary>Beanstalk test farm · an earlier run: commit <code>a2d0d3b</code> (the newer results are in a comment below)</summary> Commit `a2d0d3b` · tier **reviewed** · approved by futondestroyer · [dashboard](https://beanstalk.magicbean.dev/prs/1476) **What will be tested** · AI plan (`gpt-6.1-terra`) The plan compares main and the PR in child Hyrule Market with 2x frame generation for 30 seconds each with V-Sync off and on, then runs a short default-settings crash check. All scenarios run on each target, and the present-queue switch is forced on both sides because the plan cannot set this existing switch on the PR side alone. Crashes, device-loss logs, major screenshot differences, or FPS more than 10% below main fail; the screenshots check for a black screen. The RTX 40-series target must wait for a matching Windows tester, and DLSS is not built on the farm, so the requested DLSS-specific coverage cannot be guaranteed. No tester online now matches windows+nvidia+gpu-rtx-40xx: that target waits for one. - **Where:** windows+nvidia+gpu-rtx-40xx (GPU "rtx 40xx", 1-2 reports), windows+amd (1-2 reports), linux+amd (1-2 reports). - **Matrix:** 2 cells, each on main and the PR: vsync `2` or `1`. - **market-frame-generation:** from a new save (settings frame_pacing=0, frame_generation=2, frame_generation_by=0; switches `RX_VK_PRESENT_QUEUE=1`), then teleport to Market, measure market for 30 s (after 5 s warm-up), take the picture market to compare with main; 1 run on each side for each of 2 cells (1 game start a run). - **default-crash-check:** from a new save, then measure forest for 10 s (after 5 s warm-up); 1 run on each side. - **Measured:** crashes, 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 15%; or forbidden log lines is above 0. - **Time:** about 27 min of game runs per tester (4 game starts), plus the two builds. Started at 22:49 UTC. **Estimate:** done in about 25 min, from the queue and the testers online now; some jobs can't start yet. | Target | Reports | Crash | Frame p99 (ms) vs main | VRAM peak (MB) vs main | Result | | --- | --- | --- | --- | --- | --- | | windows+nvidia+gpu-rtx-40xx | 0/1 | — | — | — | queued | | windows+amd | 0/1 | — | — | — | running | | 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_380a91419781d088) | none | — | — | fail | | Scenario · matrix cell | Target | Frame p99 (ms) vs main | Result | | --- | --- | --- | --- | | market-frame-generation · `vsync=2` | windows+nvidia+gpu-rtx-40xx | — | — | | market-frame-generation · `vsync=2` | windows+amd | — | — | | market-frame-generation · `vsync=2` | linux+amd | — | pass | | market-frame-generation · `vsync=1` | windows+nvidia+gpu-rtx-40xx | — | — | | market-frame-generation · `vsync=1` | windows+amd | — | — | | market-frame-generation · `vsync=1` | linux+amd | — | fail | #### Measurements · linux+amd **Verdict:** fail on linux+amd (1/1 report): `market-frame-generation market.fps_mean.min_delta_pct (-15.2%)` 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` Scene: market-frame-generation, from a new save (frame_pacing=0, frame_generation=2, frame_generation_by=0, RX_VK_PRESENT_QUEUE=1); default-crash-check, from a new save; 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); market-frame-generation: 1 game start a side, market 30 s after 5 s warm-up; default-crash-check: 1 game start a side, forest 10 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 @ 415a894 | After: this PR @ a2d0d3b | |---|---|---| | market-frame-generation · `vsync=2` · market · frame rate | 2.9 | 3.1 (+6%) | | market-frame-generation · `vsync=2` · forbidden log lines | 0.0 | 0.0 | | market-frame-generation · `vsync=1` · market · frame rate | 13.3 | 11.2 (−15%) | | market-frame-generation · `vsync=1` · forbidden log lines | 0.0 | 0.0 | | default-crash-check · forest · frame rate | 52.7 | 56.6 (+8%) | | default-crash-check · 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 | |---|---|---|---|---|---|---| | `vsync` | menu setting | `2`, `1` | main's default | the PR's default | market-frame-generation, the PR at 2 → at 1: 3.1 → 11.2 (+262%) | helps | <details><summary>Markdown for the PR description</summary> ```markdown ## Measurements **Verdict:** fail on linux+amd (1/1 report): `market-frame-generation market.fps_mean.min_delta_pct (-15.2%)` 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` Scene: market-frame-generation, from a new save (frame_pacing=0, frame_generation=2, frame_generation_by=0, RX_VK_PRESENT_QUEUE=1); default-crash-check, from a new save; 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); market-frame-generation: 1 game start a side, market 30 s after 5 s warm-up; default-crash-check: 1 game start a side, forest 10 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 @ 415a894 | After: this PR @ a2d0d3b | |---|---|---| | market-frame-generation · `vsync=2` · market · frame rate | 2.9 | 3.1 (+6%) | | market-frame-generation · `vsync=2` · forbidden log lines | 0.0 | 0.0 | | market-frame-generation · `vsync=1` · market · frame rate | 13.3 | 11.2 (−15%) | | market-frame-generation · `vsync=1` · forbidden log lines | 0.0 | 0.0 | | default-crash-check · forest · frame rate | 52.7 | 56.6 (+8%) | | default-crash-check · 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 | |---|---|---|---|---|---|---| | `vsync` | menu setting | `2`, `1` | main's default | the PR's default | market-frame-generation, the PR at 2 → at 1: 3.1 → 11.2 (+262%) | helps | ``` </details> </details>
Conflicts with #1442 (merged): vk_main.cpp keeps this PR's default (NVIDIA 621.24+ on Windows) and adds #1442's V-Sync On
numbers to its comment; README and docs/development.md keep #1442's FIFO text for the timeline and this PR's present-queue
default, with main's 4x figure.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
fix(vk): the older-driver line only when the switch is unset; device_lost's text in a local array
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 8s
CI / Workflow lint (actionlint) (pull_request) Successful in 13s
Guide screenshots / Guide images and local UI source review (pull_request) Failing after 13s
Third-party parts / As their notes say (pull_request) Successful in 21s
PR description / Description follows the template (pull_request_target) Successful in 5s
Website / Website on Cloudflare (pull_request_target) Has been skipped
beanstalk/approval approved by llun (reviewed)
beanstalk/windows+nvidia+gpu-rtx-40xx 0/1 pass, 0 running, 0 queued
6d0e72dcd5
From a cold review of the PR at the merge: with RX_VK_PRESENT_QUEUE=1 on an NVIDIA driver older than 621.24 the log said
"presents on the replay's queue" and then "presents on a queue of their own"; the line now comes only when the switch is
unset. device_lost can run on several threads at once, so its text goes in a local array, not a static one.
docs/development.md says which case logs why not.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
Member

Beanstalk test farm

Commit 6d0e72d · tier reviewed · approved by llun · dashboard

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

The plan compares main and the PR in child Hyrule Market with 2x built-in frame generation, forcing the dedicated present queue on the PR. It tests V-Sync on and off because both presentation paths can be affected, measuring FPS and frametime and comparing still images for black screens. Crashes, device loss, a substantial image difference, or FPS more than 10% below main fail the plan. It takes about 25 minutes per tester and waits for a Windows RTX 40-series PC; DLSS Frame Generation and display-level pacing cannot be tested on the farm. No tester online now matches windows+nvidia+gpu-rtx-40xx: that target waits for one.

  • Where: windows+nvidia+gpu-rtx-40xx (GPU "rtx 40xx", 1-2 reports).
  • Matrix: 2 cells, each on main and the PR: vsync 1 or 2; RX_VK_PRESENT_QUEUE 1 (PR only).
  • market-present: from a new save (settings frame_pacing=0, frame_generation=2, frame_generation_by=1), then teleport to Market, move the stick, take the picture market-still to compare with main, measure market for 30 s (after 5 s warm-up); 1 run on each side for each of 2 cells (1 game start a run).
  • 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 15%; or forbidden log lines is above 0.
  • Time: about 15 min of game runs per tester (2 game starts), plus the two builds.

Done (started 16:07 UTC). Comment @Beanstalk to run it again.

Target Reports Crash Frame p99 (ms) vs main VRAM peak (MB) vs main Result
windows+nvidia+gpu-rtx-40xx 0/1 — — — queued
Scenario · matrix cell Target Frame p99 (ms) vs main Result
market-present · vsync=1, RX_VK_PRESENT_QUEUE=1 (PR only) windows+nvidia+gpu-rtx-40xx — —
market-present · vsync=2, RX_VK_PRESENT_QUEUE=1 (PR only) windows+nvidia+gpu-rtx-40xx — —
<!-- beanstalk:sticky --> ### Beanstalk test farm Commit `6d0e72d` · tier **reviewed** · approved by llun · [dashboard](https://beanstalk.magicbean.dev/prs/1476) **What will be tested** · AI plan (`gpt-6.1-terra`) The plan compares main and the PR in child Hyrule Market with 2x built-in frame generation, forcing the dedicated present queue on the PR. It tests V-Sync on and off because both presentation paths can be affected, measuring FPS and frametime and comparing still images for black screens. Crashes, device loss, a substantial image difference, or FPS more than 10% below main fail the plan. It takes about 25 minutes per tester and waits for a Windows RTX 40-series PC; DLSS Frame Generation and display-level pacing cannot be tested on the farm. No tester online now matches windows+nvidia+gpu-rtx-40xx: that target waits for one. - **Where:** windows+nvidia+gpu-rtx-40xx (GPU "rtx 40xx", 1-2 reports). - **Matrix:** 2 cells, each on main and the PR: vsync `1` or `2`; RX_VK_PRESENT_QUEUE `1` (PR only). - **market-present:** from a new save (settings frame_pacing=0, frame_generation=2, frame_generation_by=1), then teleport to Market, move the stick, take the picture market-still to compare with main, measure market for 30 s (after 5 s warm-up); 1 run on each side for each of 2 cells (1 game start a run). - **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 15%; or forbidden log lines is above 0. - **Time:** about 15 min of game runs per tester (2 game starts), plus the two builds. Done (started 16:07 UTC). Comment `@Beanstalk` to run it again. | Target | Reports | Crash | Frame p99 (ms) vs main | VRAM peak (MB) vs main | Result | | --- | --- | --- | --- | --- | --- | | windows+nvidia+gpu-rtx-40xx | 0/1 | — | — | — | queued | | Scenario · matrix cell | Target | Frame p99 (ms) vs main | Result | | --- | --- | --- | --- | | market-present · `vsync=1, RX_VK_PRESENT_QUEUE=1 (PR only)` | windows+nvidia+gpu-rtx-40xx | — | — | | market-present · `vsync=2, RX_VK_PRESENT_QUEUE=1 (PR only)` | windows+nvidia+gpu-rtx-40xx | — | — |
Author
Member

Main 7b229f66 merged in (fb057a1f, a merge, no force-push), plus three small fixes from a cold review (6d0e72dc):

  • The conflict: #1442 changed the same present-queue comment in vk_main.cpp and the same lines in the README and
    docs/development.md. The code is this PR's; the comment keeps #1442's V-Sync On numbers for the queue; the docs keep
    #1442's FIFO text for the timeline and main's 4x figure.
  • The older-driver log line came even when RX_VK_PRESENT_QUEUE=1 turned the queue on (then the log said both "on the
    replay's queue" and "on a queue of their own"). It now comes only with the switch unset.
  • device_lost's text is in a local array: it can run on several threads at once, and a static buffer could mix two
    messages.
  • docs/development.md says which case logs why the queue is off (an NVIDIA driver older than 621.24).

Checks: the full suite on 6d0e72dc fails nothing that main 7b229f66 does not fail (the differing files pass alone on
both), test_present_queue_default passes, and the game builds. The measurements hold: of main's commits since
415a8944 only #1442 changes the presents' path, and the D2 runs already had it.

Main 7b229f66 merged in (fb057a1f, a merge, no force-push), plus three small fixes from a cold review (6d0e72dc): - **The conflict:** #1442 changed the same present-queue comment in `vk_main.cpp` and the same lines in the README and `docs/development.md`. The code is this PR's; the comment keeps #1442's V-Sync On numbers for the queue; the docs keep #1442's FIFO text for the timeline and main's 4x figure. - **The older-driver log line** came even when `RX_VK_PRESENT_QUEUE=1` turned the queue on (then the log said both "on the replay's queue" and "on a queue of their own"). It now comes only with the switch unset. - **`device_lost`'s text** is in a local array: it can run on several threads at once, and a static buffer could mix two messages. - **`docs/development.md`** says which case logs why the queue is off (an NVIDIA driver older than 621.24). Checks: the full suite on 6d0e72dc fails nothing that main 7b229f66 does not fail (the differing files pass alone on both), `test_present_queue_default` passes, and the game builds. The measurements hold: of main's commits since 415a8944 only #1442 changes the presents' path, and the D2 runs already had it.
Member

@Beanstalk

@Beanstalk
HumanBean deleted branch fix/present-queue-default 2026-11-17 23:15:57 +00:00
Sign in to join this conversation.
No reviewers
No milestone
No project
No assignees
4 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!1476
No description provided.