perf(vk): the texture pipelines made before the game, through the pipeline cache #1701

Merged
HumanBean merged 2 commits from HumanBean/Longshot:perf/texture-pipelines-before-game into main 2026-11-19 06:20:05 +00:00
Owner

Type: perf · Risk: low · Tested on: CachyOS Linux, RTX 3090 · Needs: Windows, AMD and Intel (a first start's first ASTC texture)

TL;DR

On a first start, or after a new build or driver update empties the driver's shader cache, the first ASTC or BC texture the game showed held one frame for about a third of a second: the texture converters' GPU programs were compiled right then, with no cache. This PR builds them during the loading screen through the game's pipeline cache. On an RTX 3090 that 316 ms frame is gone. The loading screen pays 425 ms once, then 1 ms on later starts.

Breakdown

  • Who it helps: every player on a first start, after an update or after a driver update: no third-of-a-second freeze on the first ASTC texture.
  • What was wrong: the ASTC decoder, the BC3/BC7 encoders and the GPU unswizzle were compiled inside the first frame that needed one, without the pipeline cache.
  • What changes: they are built before the game, with the other prepared pipelines, and come from the pipeline cache on later starts.
  • What does not change: which textures are decoded or encoded, or how; the frame rate once playing; Intel's driver lock around module creation.
  • How it was checked: two first starts with empty NVIDIA caches on an RTX 3090, then warm starts: main has a 316.5 ms upload of the first ASTC texture, this PR none over 50 ms.
  • What is still open: Windows, AMD and Intel GPUs.
  • Risk: low: if the pipeline cache path fails, the pipelines are built as before.

Why

Most players use DLSS or FSR, and every update means a new renderer whose pipelines the driver has not seen. The texture converters (the ASTC decoder, the BC3/BC7 encoders, the GPU unswizzle) were the last compute pipelines made in play: in a profile of a first start on an RTX 3090, the ASTC decoder took 274 ms of a 283 ms frame and the BC encoder about 130 ms of a 494 ms frame.

What changed

The three converters' pipelines go through the same cached path as the game's own compute pipelines, and are built at the start of the pipeline preparation, before the title.

  • textures: texture_compute_pipeline() in gpu/vk/vk_texture.cpp makes a converter's pipeline through shared_compute_pipeline (the pipeline cache) and falls back to the uncached path as before. astc_ready(), bc_ready() and unswizzle_ready() hold IntelDriverGate for their shader modules only, since shared_compute_pipeline takes it too. texture_pipelines_warm() calls the three and logs the time.
  • start: precompile_run() in gpu/vk/vk_draw.cpp opens the pipeline cache and calls texture_pipelines_warm() first.

Measurements

Verdict: The first start's 316.5 ms frame on the first ASTC texture is gone. The pipelines take 425 ms during the loading screen on a first start and 1 ms after. Play's frame rate doesn't change (the Market numbers below are the same build as #1702, where they are reported).

Hardware: CachyOS Linux (kernel 7.3.3), RTX 3090 24 GB, NVIDIA 620.70.06, Ryzen 9 7900X, 32 GB
Scene: a new start from the title to Castle Town Market (debug teleport), then 5 s walking and 20 s turning; 2560x1440 output, DLSS Quality, no frame generation, HOS_FPS_MAX=1000; a private headless sway
Method: each side's first start with an empty NVIDIA shader cache of its own (__GL_SHADER_DISK_CACHE_PATH), then two more starts with it warm; the log's slow upload and slow submit lines (frames over 15 ms).
How to reproduce: empty the driver's shader cache, start the game, go to the Market; grep "slow upload" longshot_log.txt.

Baseline: both columns are renderers built alone on a base at main da91e770, measured before the rebase onto 09cbdd97. The renderer this PR changes is unchanged by the rebase (jj rebased it cleanly; the main commits in between don't touch the converters or precompile_run). The After column's renderer also had #1121 and #1702's commits, which don't touch the texture path.

Before: main @ da91e770 After: this PR @ 1b6c78ae (on da91e770)
first start, empty driver cache: the first ASTC texture's upload 316.5 ms (a 319.3 ms submit, a 323.4 ms frame) no upload over 15 ms
first start: texture pipelines made before the game (made in play) 425 ms
later starts: the same (made in play; no hitch once the driver's cache has them) 1 ms, 1 ms, 1 ms
Before, first start:
vk: slow upload 316.5 ms: #12 0x7fcd53d200 1664x1280x1 x1 levels 1 NVN 0x87 ASTC, 2496 of 2496 KB
vk: slow submit: 319.3 ms: draw 317.3 descriptors 316.9 texture lookups 318.0 uploads 317.7
vk: status: 600 frames, the slowest 323.4 ms; VRAM 1.4 of 20.2 GB
After, first start:
vk: driver shader cache at the start: 0 MB (~/.cache/hookshot-work/nvcache-fa-ahead/GLCache 0 MB)
vk: texture pipelines made before the game in 425 ms (ASTC decoder yes, BC encoder yes, GPU unswizzle yes)
After, a later start:
vk: texture pipelines made before the game in 1 ms (ASTC decoder yes, BC encoder yes, GPU unswizzle yes)

Flags and settings

None.

Testing

Tested: CachyOS Linux, RTX 3090, NVIDIA 620.70.06: the renderer built alone on a base of main, three starts (one with an empty driver cache) to Castle Town Market, walking and turning; no slow upload line over 15 ms, no device loss or failed pipeline. The rebased head compiles (scripts/dev_build.py vk).

Not tested: Windows; AMD (RADV, Adrenalin); Intel, where IntelDriverGate now covers only the modules. mise run test: not run on this PC (the team's checks run it on the forge).

Must be tested:

  • windows and linux, amd and intel: a first start after emptying the driver's shader cache, to any area with ASTC textures, expecting texture pipelines made before the game in <n> ms (ASTC decoder yes, ...) in the log and no slow upload of an ASTC texture over 50 ms (Test Farm: @Beanstalk)

Risks

What could break: a converter's pipeline failing to build through the cache. It then falls back to the old path, and the log's line says no for it. On Intel, IntelDriverGate now covers the module and the uncached fallback but not the cached build, which takes it itself.

Turning it off: revert the commit.

Compatibility: The pipeline cache gains three pipelines; nothing else changes.

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. (A first start's loading screen is 425 ms longer.)
  • 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.
  • A file in docs/tested/ for each new measured run (format in docs/tested-configurations.md). (tests/test_tested_configurations.py not run on this PC.)

🤖 Generated with Claude Code

https://claude.ai/code/session_016o1k1PazAdTJxQQWQBksW2

**Type:** perf · **Risk:** low · **Tested on:** CachyOS Linux, RTX 3090 · **Needs:** Windows, AMD and Intel (a first start's first ASTC texture) ## TL;DR On a first start, or after a new build or driver update empties the driver's shader cache, the first ASTC or BC texture the game showed held one frame for about a third of a second: the texture converters' GPU programs were compiled right then, with no cache. This PR builds them during the loading screen through the game's pipeline cache. On an RTX 3090 that 316 ms frame is gone. The loading screen pays 425 ms once, then 1 ms on later starts. ## Breakdown - **Who it helps:** every player on a first start, after an update or after a driver update: no third-of-a-second freeze on the first ASTC texture. - **What was wrong:** the ASTC decoder, the BC3/BC7 encoders and the GPU unswizzle were compiled inside the first frame that needed one, without the pipeline cache. - **What changes:** they are built before the game, with the other prepared pipelines, and come from the pipeline cache on later starts. - **What does not change:** which textures are decoded or encoded, or how; the frame rate once playing; Intel's driver lock around module creation. - **How it was checked:** two first starts with empty NVIDIA caches on an RTX 3090, then warm starts: main has a 316.5 ms upload of the first ASTC texture, this PR none over 50 ms. - **What is still open:** Windows, AMD and Intel GPUs. - **Risk:** low: if the pipeline cache path fails, the pipelines are built as before. ## Why Most players use DLSS or FSR, and every update means a new renderer whose pipelines the driver has not seen. The texture converters (the ASTC decoder, the BC3/BC7 encoders, the GPU unswizzle) were the last compute pipelines made in play: in a profile of a first start on an RTX 3090, the ASTC decoder took 274 ms of a 283 ms frame and the BC encoder about 130 ms of a 494 ms frame. ## What changed The three converters' pipelines go through the same cached path as the game's own compute pipelines, and are built at the start of the pipeline preparation, before the title. - textures: `texture_compute_pipeline()` in `gpu/vk/vk_texture.cpp` makes a converter's pipeline through `shared_compute_pipeline` (the pipeline cache) and falls back to the uncached path as before. `astc_ready()`, `bc_ready()` and `unswizzle_ready()` hold `IntelDriverGate` for their shader modules only, since `shared_compute_pipeline` takes it too. `texture_pipelines_warm()` calls the three and logs the time. - start: `precompile_run()` in `gpu/vk/vk_draw.cpp` opens the pipeline cache and calls `texture_pipelines_warm()` first. ## Measurements **Verdict:** The first start's 316.5 ms frame on the first ASTC texture is gone. The pipelines take 425 ms during the loading screen on a first start and 1 ms after. Play's frame rate doesn't change (the Market numbers below are the same build as [#1702](https://git.magicbean.dev/MagicBeanDev/Longshot/pulls/1702), where they are reported). Hardware: CachyOS Linux (kernel 7.3.3), RTX 3090 24 GB, NVIDIA 620.70.06, Ryzen 9 7900X, 32 GB Scene: a new start from the title to Castle Town Market (debug teleport), then 5 s walking and 20 s turning; 2560x1440 output, DLSS Quality, no frame generation, `HOS_FPS_MAX=1000`; a private headless sway Method: each side's first start with an empty NVIDIA shader cache of its own (`__GL_SHADER_DISK_CACHE_PATH`), then two more starts with it warm; the log's `slow upload` and `slow submit` lines (frames over 15 ms). How to reproduce: empty the driver's shader cache, start the game, go to the Market; `grep "slow upload" longshot_log.txt`. Baseline: both columns are renderers built alone on a base at main da91e770, measured before the rebase onto 09cbdd97. The renderer this PR changes is unchanged by the rebase (`jj` rebased it cleanly; the main commits in between don't touch the converters or `precompile_run`). The After column's renderer also had #1121 and [#1702](https://git.magicbean.dev/MagicBeanDev/Longshot/pulls/1702)'s commits, which don't touch the texture path. | | Before: main @ da91e770 | After: this PR @ 1b6c78ae (on da91e770) | |---|---|---| | first start, empty driver cache: the first ASTC texture's upload | 316.5 ms (a 319.3 ms submit, a 323.4 ms frame) | no upload over 15 ms | | first start: texture pipelines made before the game | (made in play) | 425 ms | | later starts: the same | (made in play; no hitch once the driver's cache has them) | 1 ms, 1 ms, 1 ms | ``` Before, first start: vk: slow upload 316.5 ms: #12 0x7fcd53d200 1664x1280x1 x1 levels 1 NVN 0x87 ASTC, 2496 of 2496 KB vk: slow submit: 319.3 ms: draw 317.3 descriptors 316.9 texture lookups 318.0 uploads 317.7 vk: status: 600 frames, the slowest 323.4 ms; VRAM 1.4 of 20.2 GB After, first start: vk: driver shader cache at the start: 0 MB (~/.cache/hookshot-work/nvcache-fa-ahead/GLCache 0 MB) vk: texture pipelines made before the game in 425 ms (ASTC decoder yes, BC encoder yes, GPU unswizzle yes) After, a later start: vk: texture pipelines made before the game in 1 ms (ASTC decoder yes, BC encoder yes, GPU unswizzle yes) ``` ### Flags and settings None. ## Testing **Tested:** CachyOS Linux, RTX 3090, NVIDIA 620.70.06: the renderer built alone on a base of main, three starts (one with an empty driver cache) to Castle Town Market, walking and turning; no `slow upload` line over 15 ms, no device loss or failed pipeline. The rebased head compiles (`scripts/dev_build.py vk`). **Not tested:** Windows; AMD (RADV, Adrenalin); Intel, where `IntelDriverGate` now covers only the modules. `mise run test`: not run on this PC (the team's checks run it on the forge). **Must be tested:** - windows and linux, amd and intel: a first start after emptying the driver's shader cache, to any area with ASTC textures, expecting `texture pipelines made before the game in <n> ms (ASTC decoder yes, ...)` in the log and no `slow upload` of an ASTC texture over 50 ms (Test Farm: @Beanstalk) ## Risks **What could break:** a converter's pipeline failing to build through the cache. It then falls back to the old path, and the log's line says `no` for it. On Intel, `IntelDriverGate` now covers the module and the uncached fallback but not the cached build, which takes it itself. **Turning it off:** revert the commit. **Compatibility:** The pipeline cache gains three pipelines; nothing else changes. ## 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. (A first start's loading screen is 425 ms longer.) - [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] A file in `docs/tested/` for each new measured run (format in `docs/tested-configurations.md`). (`tests/test_tested_configurations.py` not run on this PC.) 🤖 Generated with [Claude Code](https://claude.com/claude-code) https://claude.ai/code/session_016o1k1PazAdTJxQQWQBksW2
The ASTC decoder, the BC encoders and the GPU unswizzle were compiled with no cache inside the frame of the first
texture that needed them: 274 ms for the ASTC decoder (a 283 ms frame) and ~130 ms of a 494 ms frame for the BC
encoder on an RTX 3090. precompile_run makes them first, into the start's pipeline cache.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_016o1k1PazAdTJxQQWQBksW2
docs(tested): the texture pipelines before the game, two first starts on an RTX 3090
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
Website / Website on Cloudflare (pull_request_target) Has been skipped
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 13s
beanstalk/approval approved by HumanBean (reviewed)
beanstalk/any 0/1 pass, 2 error
PR description / Description follows the template (pull_request_target) Failing after 4s
d60f91bffa
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): three starts to Castle Town Market at 2560x1440 with DLSS Quality, one with an empty driver cache: the texture pipelines were made before the game (425 ms, then 1 ms), no slow upload of an ASTC texture in play (main: 316.5 ms on the first start), no device loss

Tested in game: RTX 3090, NVIDIA 620.70.06, CachyOS Linux (headless sway): three starts to Castle Town Market at 2560x1440 with DLSS Quality, one with an empty driver cache: the texture pipelines were made before the game (425 ms, then 1 ms), no slow upload of an ASTC texture in play (main: 316.5 ms on the first start), no device loss
Author
Owner

Description: links #1702, the presenter-thread PR whose Market numbers were measured on the same build.

Description: links #1702, the presenter-thread PR whose Market numbers were measured on the same build.
Author
Owner

@HumanBean

@HumanBean
Author
Owner

/beanstalk

/beanstalk
Member

Beanstalk test farm

Commit d60f91b · tier reviewed · approved by HumanBean · dashboard

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

The plan compares startup and Market gameplay on main and the PR, including texture appearance, shader preparation, load time and frame pacing. It takes about 20 minutes per tester and fails on crashes, converter failure logs, large ASTC upload stalls, visible differences or specified performance regressions. Driver caches are not cleared by the plan, so it cannot guarantee a cold-cache first-start test.

  • Where: any (any PC, 1-2 reports).
  • market-textures: from the repository's save kokiri-start, then teleport to Market, take the picture market to compare with main, move the stick, measure market for 20 s (after 5 s warm-up); 2 runs on each side.
  • Measured: crashes, boot time, load times, shader preparation at start, frame times, stutters and hitches, the game's log.
  • The PR fails if: it crashes; or a picture differs from main by more than 5%; or boot time is more than 25% above main; or longest load is more than 25% above main; or frame time (p99) is more than 20% above main; or forbidden log lines is above 0.
  • Time: about 22 min of game runs per tester (4 game starts), plus the two builds.

Done (started 05:01 UTC, last report 05:13 UTC). Comment @Beanstalk to run it again.

Target Reports Crash Frame p99 (ms) vs main VRAM peak (MB) vs main Result
any · 1: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0; 2: linux+amd+radv+dgpu AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7 2/1 1 2 none — — error

Measurements · any

Verdict: could not be judged on any (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: 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-textures, 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); market-textures: 2 game starts a side, 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 @ d60f91b
market-textures · boot time (s) 54.5 48.8 (−10%)
market-textures · forbidden log lines 1.0 0.0 (−100%)

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 any (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: 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-textures, 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); market-textures: 2 game starts a side, 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 @ d60f91b |
|---|---|---|
| market-textures · boot time (s) | 54.5 | 48.8 (−10%) |
| market-textures · forbidden log lines | 1.0 | 0.0 (−100%) |

### Flags and settings

None: the plan varied no setting, switch or build option.
<!-- beanstalk:sticky --> ### Beanstalk test farm Commit `d60f91b` · tier **reviewed** · approved by HumanBean · [dashboard](https://beanstalk.magicbean.dev/prs/1701) **What will be tested** · AI plan (`gpt-6.1-terra`) The plan compares startup and Market gameplay on main and the PR, including texture appearance, shader preparation, load time and frame pacing. It takes about 20 minutes per tester and fails on crashes, converter failure logs, large ASTC upload stalls, visible differences or specified performance regressions. Driver caches are not cleared by the plan, so it cannot guarantee a cold-cache first-start test. - **Where:** any (any PC, 1-2 reports). - **market-textures:** from the repository's save `kokiri-start`, then teleport to Market, take the picture market to compare with main, move the stick, measure market for 20 s (after 5 s warm-up); 2 runs on each side. - **Measured:** crashes, boot time, load times, shader preparation at start, frame times, stutters and hitches, the game's log. - **The PR fails if:** it crashes; or a picture differs from main by more than 5%; or boot time is more than 25% above main; or longest load is more than 25% above main; or frame time (p99) is more than 20% above main; or forbidden log lines is above 0. - **Time:** about 22 min of game runs per tester (4 game starts), plus the two builds. Done (started 05:01 UTC, last report 05:13 UTC). Comment `@Beanstalk` to run it again. | Target | Reports | Crash | Frame p99 (ms) vs main | VRAM peak (MB) vs main | Result | | --- | --- | --- | --- | --- | --- | | any · 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0`; 2: linux+amd+radv+dgpu `AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7` | 2/1 [1](https://beanstalk.magicbean.dev/reports/rp_5a8152a6aa30630a) [2](https://beanstalk.magicbean.dev/reports/rp_c1c3e5dd82109ba3) | none | — | — | error | #### Measurements · any **Verdict:** could not be judged on any (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: 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-textures, 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); market-textures: 2 game starts a side, 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 @ d60f91b | |---|---|---| | market-textures · boot time (s) | 54.5 | 48.8 (−10%) | | market-textures · forbidden log lines | 1.0 | 0.0 (−100%) | ### 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 any (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: 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-textures, 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); market-textures: 2 game starts a side, 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 @ d60f91b | |---|---|---| | market-textures · boot time (s) | 54.5 | 48.8 (−10%) | | market-textures · forbidden log lines | 1.0 | 0.0 (−100%) | ### Flags and settings None: the plan varied no setting, switch or build option. ``` </details>
HumanBean changed title from WIP: perf(vk): the texture pipelines made before the game, through the pipeline cache to perf(vk): the texture pipelines made before the game, through the pipeline cache 2026-11-19 06:20:00 +00:00
HumanBean deleted branch perf/texture-pipelines-before-game 2026-11-19 06:20:05 +00:00
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!1701
No description provided.