MagicBeanDev/Longshot

Watch

Fork 98

WIP: docs(tested): RTX 5090 on Windows, Kokiri Forest: main against v2.1.0, `49f75dc8` and the last main before #2602 #220

Closed

dukenheimer wants to merge 3 commits from dukenheimer/Longshot:docs/tested-rtx5090-kokiri into main

dukenheimer commented

2026-11-13 15:28:39 +00:00

Contributor

Why

The tested configurations had no RTX 40/50 Windows run of Kokiri Forest, and no single-PC comparison of main against the builds before https://github.com/NotRexed/Hookshot/pull/2125 / https://github.com/NotRexed/Hookshot/pull/2419 and https://github.com/NotRexed/Hookshot/pull/2602. Moved from https://github.com/NotRexed/Hookshot/pull/2840.

What changed

docs: nine rows near the top of docs/tested-configurations.md, from an RTX 5090 + i7-13700K on Windows:
- main 46780503 at the Kokiri village autosave: 2048x1152 uncapped 65.7 ± 1.7 fps (GPU 7.1 ms, no GPU-bound wait), 5120x2160 57.2 ± 0.4, and DLSS + DLSS Frame Generation 2x capped at 165: game 61.9 / shown 123.9, each with the critical path from HOS_CHAIN + scripts/chain.py (of 15.9 ms a frame, the Presentation thread's inline replay ~12.0, sead::MainThread ~2.8);
- main 9776c36d 61.9 fps against 55b976c0 (the last main before #2602) 47.6, 49f75dc8 (before #2125/#2419) 61.9 and v2.1.0 61.2, alternated in rounds, with readback waits per game frame;
- main 46780503 on a moving route (running and panning through Kokiri), at 2048x1152 and with DLSS + frame generation.

Flags and settings

None.

Measurements

main: Hookshot main 46780503 (2026-11-12), the builds the rows name
this PR: docs only, no code
Hardware: RTX 5090 (driver in the rows), i7-13700K, Windows 11
Scene: Kokiri Forest, village autosave and the moving route; settings per row
Method: builds from source with the Hookshot Builder's toolchain and v2.1.0's profile and hot list; the autosave loaded by scripted input, a warm-up run first, frames measured 40-70 s after the first present (HOS_PRESENT_TRACE); rounds alternated
How to reproduce: the rows give each build, setting and switch

	main @ `46780503`	this PR @ docs only
rows	in the table	nothing to measure

The numbers are in the rows themselves; the summary on Hookshot: https://github.com/NotRexed/Hookshot/pull/2602#issuecomment-6817467208

Testing

Tested: docs only; the table renders, and the rows' Hookshot pull request numbers link by full URL.

Not tested: these are Hookshot main builds, not Longshot main; Longshot's 26 commits since the fork point are not measured here.

Needs other testers:

None.

Screenshots

Nothing on screen

Risk and rollback

None: documentation. Reverting the commits removes the rows.

Reviewer notes

Ported by cherry-pick from the Hookshot PR; the rows go after Longshot's newest rows, and the moving-route rows stay directly above the rows they say "as below" of.

Issues

See https://github.com/NotRexed/Hookshot/pull/2602

Checklist

For everyone

One topic.
The title is a Conventional Commit (type(scope): description).
Rebased on current main.
python -I -B tests/run_all.py run and passing (any failure that also fails on main is named above).
Tested in the game, or what wasn't is named under Testing.
Testing filled in: what was tested, what wasn't, and what needs other testers (with test requests).
Measured: main and this PR at named commits, on the same PC, scene and settings, at least 2 interleaved runs each, the median reported.
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.

If applicable

AI assistance recorded with Assisted-by: / Co-Authored-By: trailers.
A row in docs/tested-configurations.md for each measured run.

## Why The tested configurations had no RTX 40/50 Windows run of Kokiri Forest, and no single-PC comparison of main against the builds before https://github.com/NotRexed/Hookshot/pull/2125 / https://github.com/NotRexed/Hookshot/pull/2419 and https://github.com/NotRexed/Hookshot/pull/2602. Moved from https://github.com/NotRexed/Hookshot/pull/2840. ## What changed - docs: nine rows near the top of `docs/tested-configurations.md`, from an RTX 5090 + i7-13700K on Windows: - main `46780503` at the Kokiri village autosave: 2048x1152 uncapped 65.7 ± 1.7 fps (GPU 7.1 ms, no GPU-bound wait), 5120x2160 57.2 ± 0.4, and DLSS + DLSS Frame Generation 2x capped at 165: game 61.9 / shown 123.9, each with the critical path from `HOS_CHAIN` + `scripts/chain.py` (of 15.9 ms a frame, the Presentation thread's inline replay ~12.0, sead::MainThread ~2.8); - main `9776c36d` 61.9 fps against `55b976c0` (the last main before #2602) 47.6, `49f75dc8` (before #2125/#2419) 61.9 and v2.1.0 61.2, alternated in rounds, with readback waits per game frame; - main `46780503` on a moving route (running and panning through Kokiri), at 2048x1152 and with DLSS + frame generation. ## Flags and settings None. ## Measurements main: Hookshot main `46780503` (2026-11-12), the builds the rows name this PR: docs only, no code Hardware: RTX 5090 (driver in the rows), i7-13700K, Windows 11 Scene: Kokiri Forest, village autosave and the moving route; settings per row Method: builds from source with the Hookshot Builder's toolchain and v2.1.0's profile and hot list; the autosave loaded by scripted input, a warm-up run first, frames measured 40-70 s after the first present (`HOS_PRESENT_TRACE`); rounds alternated How to reproduce: the rows give each build, setting and switch | | main @ 46780503 | this PR @ docs only | |---|---|---| | rows | in the table | nothing to measure | ``` The numbers are in the rows themselves; the summary on Hookshot: https://github.com/NotRexed/Hookshot/pull/2602#issuecomment-6817467208 ``` ## Testing **Tested:** docs only; the table renders, and the rows' Hookshot pull request numbers link by full URL. **Not tested:** these are Hookshot main builds, not Longshot main; Longshot's 26 commits since the fork point are not measured here. **Needs other testers:** - None. ## Screenshots Nothing on screen ## Risk and rollback None: documentation. Reverting the commits removes the rows. ## Reviewer notes Ported by cherry-pick from the Hookshot PR; the rows go after Longshot's newest rows, and the moving-route rows stay directly above the rows they say "as below" of. ## Issues See https://github.com/NotRexed/Hookshot/pull/2602 ## Checklist ### For everyone - [x] One topic. - [x] The title is a Conventional Commit (`type(scope): description`). - [x] Rebased on current `main`. - [ ] `python -I -B tests/run_all.py` run and passing (any failure that also fails on `main` is named above). - [x] Tested in the game, or what wasn't is named under Testing. - [x] Testing filled in: what was tested, what wasn't, and what needs other testers (with test requests). - [x] Measured: main and this PR at named commits, on the same PC, scene and settings, at least 2 interleaved runs each, the median reported. - [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. ### If applicable - [x] AI assistance recorded with `Assisted-by:` / `Co-Authored-By:` trailers. - [x] A row in `docs/tested-configurations.md` for each measured run.

dukenheimer added 3 commits

2026-11-13 15:28:39 +00:00

docs(tested): RTX 5090 on Windows, Kokiri Forest: main against v2.1.0, 49f75dc8 and the last main before #2602 2fd6327b02

The tested configurations had no RTX 40/50 Windows run of Kokiri Forest, and none comparing main against the builds
before #2125/#2419 and #2602 on one PC. This adds seven rows from one RTX 5090 + i7-13700K, all built from source with
the Hookshot Builder's toolchain:

- main 46780503 at 2048x1152, at 5120x2160, and with DLSS + DLSS Frame Generation 2x capped at 165, standing at the
  village autosave, each with the frame's critical path from HOS_CHAIN (the Presentation thread's replay is ~12 of 15.9 ms);
- main 9776c36d against 55b976c0 (before #2602), 49f75dc8 (before #2125/#2419) and v2.1.0, alternated in rounds.

Readback waits per frame are per game frame in play. Runs, logs and summaries stay on the tester's PC.

Tests: docs only; no check reads this file. Nothing on screen.

See #2602

Co-authored-by: Copilot App <[email protected]>
(cherry picked from commit ed373577759bbad54756eaa862244629f1fc416c)

docs(tested): RTX 5090, Kokiri Forest on a moving route (main 46780503) 1f686a38d6

Co-authored-by: Copilot App <[email protected]>
(cherry picked from commit 86f99d93e59b4111715f8653e55556d7200f9e5c)

docs(tested): link the Hookshot pull requests these rows name by their full URL

PR description / Description follows the template (pull_request_target) Successful in 4s

Details

Website / Website on Cloudflare (pull_request_target) Has been skipped

Details

CI / Conventional Commit title (pull_request) Has been cancelled

Details

CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Has been cancelled

Details

CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Has been cancelled

Details

CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Has been cancelled

Details

CI / Workflow lint (actionlint) (pull_request) Has been cancelled

Details

Third-party parts / As their notes say (pull_request) Has been cancelled

Details

Third-party parts / The same as upstream (pull_request) Has been cancelled

Details

bc18e11fb4

Co-authored-by: Copilot App <[email protected]>

mooki added the

kind

docs

label

2026-11-14 01:45:13 +00:00

mooki added the

priority

low

label

2026-11-14 04:18:14 +00:00

mooki added the

gpu/nvidia

platform/windows

labels

2026-11-14 16:27:34 +00:00

dukenheimer commented

2026-11-15 06:13:08 +00:00

Author

Contributor

Closing: these tested rows are from the Hookshot-era builds (main against v2.1.0) and are out of date for Longshot's current main. Newer runs are recorded on the individual PRs.

dukenheimer closed this pull request

2026-11-15 06:13:09 +00:00