WIP: perf(build): optimize shared A64 helpers independently of cold chunks #756

Draft

siantm wants to merge 1 commit from siantm/Longshot:perf/shared-a64-helpers-o2 into main

pull from: siantm/Longshot:perf/shared-a64-helpers-o2

merge into: MagicBeanDev:main

MagicBeanDev:main

Conversation 0 Commits 1 Files changed 5 +155 -2

siantm commented 2026-11-15 10:02:01 +00:00

First-time contributor

• Copy link
• Copy Markdown

Type: perf · Risk: medium · Tested on: Windows 11 Pro 26300, game-free planning only · Needs: current-main build/gameplay A/B and full suite

Why

Shared instruction helpers can receive stronger optimization without imposing that compile cost on giant cold game chunks. This proposal changes only the two shared helpers, not hot-list coverage, runtime PGO, register localization or renderer settings.

What changed

nx2/build.py selects O2 for a64_rt.c and a64_suyu.c, preserving every other semantic flag. Cold chunks remain O1; RX_A64_RT_O2=0 restores the prior helper level.

• nx2/make_game.py: classify the existing rollback knob as compile-only, so it does not invalidate translation.
• A regression drives the real build planner and object keys, proving exact helper isolation, rollback and unchanged cold/hot jobs.
• Existing development documentation describes the switch.

Measurements

Verdict: compiler-job and cache isolation are proven game-free; actual performance benefit against current main is not measured. Keep WIP.
Hardware: Windows 11 Pro 26300, Intel Core i7-9700, 31.8 GiB usable RAM, Python 3.14.7; no GPU used.
Method: identical authored planning fixture against main and this staged branch. No compiler/game is launched by that fixture.

Check	Before: main @ 9e6f231d	After: this PR @ a9269637ec
Three planning tests	Fail in seven enabled-helper subcases: helpers remain O1	All three pass
Default helper level	O1	O2
Explicit rollback	O1	O1
Other jobs / semantic flags	Unchanged baseline	Unchanged; only two helper object keys change
Current-main gameplay/compile-time benefit	Not measured	Not measured

Observed: patched planner Ran 3 tests ... OK; build hash cache 9 tests, build times 19 tests, and kept translation 7 tests pass; lift-cache driver passes. Existing upstream file reads emit resource warnings. Older integrated-local FPS observations are not measurements of this branch and are not used to claim a current-main speedup.

Flags and settings

RX_A64_RT_O2: previous helpers O1; this proposal defaults to O2, 0 restores O1. Recommendation is provisional until isolated A/B validates the proposed default; do not mark ready without that evidence. No runtime quality/preferences change.

Testing

Tested: real build.main/plan_jobs/object-key consumer, rollback/flag isolation, lift-cache/hash-cache/build-times/kept-translation checks; catalogue renderer accepts the new record.
Not tested: full build, executable size, current-main FPS/frame times, Linux, or full suite. An existing game was running; it was not stopped or modified for benchmarking. Catalogue unit driver has a Windows CRLF-vs-LF fixture failure.
Must be tested: author or Test Farm builds main and this isolated branch, then performs at least two interleaved same-scene pairs with identical save/settings, reporting median FPS, 1% low, median/p99 frame time, executable size and compile timing. Complete game-free suite on Windows/Linux before readiness.

Risks

What could break: optimizer-sensitive helper behavior, larger code, compile cost, or no real performance gain.
Turning it off: RX_A64_RT_O2=0.
Compatibility: only helper compile keys should change. No intended save/settings/shader-cache-format, renderer ABI or required-tool changes.

Checklist

Everyone

• One topic.
• Conventional Commit title: perf(build): optimize shared A64 helpers independently of cold chunks.
• Issue search completed; related build/cache PRs reviewed, issue search pending.
• Measurements distinguish proven planning behavior from unmeasured FPS benefit.
• Testing names tested, untested and required work.
• Recheck current main before publishing; prepared on 9e6f231d.
• Complete game-free suite recorded; not run.
• No game files, dumps, generated game files or build output.
• Third-party sources untouched.
• Existing Longshot source and authored fixtures; GPL-3.0-or-later.

When it applies

• Source commit records Assisted-by: OpenAI Codex.
• Same-PC, same-scene interleaved performance measurements; pending.
• Proposed default backed by measurements before readiness; switch is documented.
• Game-free measured run recorded under docs/tested/.
• Planning regression fails on main and passes here.
• Development documentation updated.

**Type:** perf · **Risk:** medium · **Tested on:** Windows 11 Pro 26300, game-free planning only · **Needs:** current-main build/gameplay A/B and full suite ## Why Shared instruction helpers can receive stronger optimization without imposing that compile cost on giant cold game chunks. This proposal changes only the two shared helpers, not hot-list coverage, runtime PGO, register localization or renderer settings. ## What changed `nx2/build.py` selects O2 for `a64_rt.c` and `a64_suyu.c`, preserving every other semantic flag. Cold chunks remain O1; `RX_A64_RT_O2=0` restores the prior helper level. - `nx2/make_game.py`: classify the existing rollback knob as compile-only, so it does not invalidate translation. - A regression drives the real build planner and object keys, proving exact helper isolation, rollback and unchanged cold/hot jobs. - Existing development documentation describes the switch. ## Measurements **Verdict:** compiler-job and cache isolation are proven game-free; actual performance benefit against current main is not measured. Keep WIP. Hardware: Windows 11 Pro 26300, Intel Core i7-9700, 31.8 GiB usable RAM, Python 3.14.7; no GPU used. Method: identical authored planning fixture against main and this staged branch. No compiler/game is launched by that fixture. | Check | Before: main @ 9e6f231d | After: this PR @ a9269637ec | |---|---|---| | Three planning tests | Fail in seven enabled-helper subcases: helpers remain O1 | All three pass | | Default helper level | O1 | O2 | | Explicit rollback | O1 | O1 | | Other jobs / semantic flags | Unchanged baseline | Unchanged; only two helper object keys change | | Current-main gameplay/compile-time benefit | Not measured | Not measured | Observed: patched planner `Ran 3 tests ... OK`; build hash cache 9 tests, build times 19 tests, and kept translation 7 tests pass; lift-cache driver passes. Existing upstream file reads emit resource warnings. Older integrated-local FPS observations are not measurements of this branch and are not used to claim a current-main speedup. ### Flags and settings `RX_A64_RT_O2`: previous helpers O1; this proposal defaults to O2, `0` restores O1. Recommendation is provisional until isolated A/B validates the proposed default; do not mark ready without that evidence. No runtime quality/preferences change. ## Testing **Tested:** real build.main/plan_jobs/object-key consumer, rollback/flag isolation, lift-cache/hash-cache/build-times/kept-translation checks; catalogue renderer accepts the new record. **Not tested:** full build, executable size, current-main FPS/frame times, Linux, or full suite. An existing game was running; it was not stopped or modified for benchmarking. Catalogue unit driver has a Windows CRLF-vs-LF fixture failure. **Must be tested:** author or Test Farm builds main and this isolated branch, then performs at least two interleaved same-scene pairs with identical save/settings, reporting median FPS, 1% low, median/p99 frame time, executable size and compile timing. Complete game-free suite on Windows/Linux before readiness. ## Risks **What could break:** optimizer-sensitive helper behavior, larger code, compile cost, or no real performance gain. **Turning it off:** `RX_A64_RT_O2=0`. **Compatibility:** only helper compile keys should change. No intended save/settings/shader-cache-format, renderer ABI or required-tool changes. ## Checklist ### Everyone - [x] One topic. - [x] Conventional Commit title: `perf(build): optimize shared A64 helpers independently of cold chunks`. - [ ] Issue search completed; related build/cache PRs reviewed, issue search pending. - [x] Measurements distinguish proven planning behavior from unmeasured FPS benefit. - [x] Testing names tested, untested and required work. - [ ] Recheck current main before publishing; prepared on 9e6f231d. - [ ] Complete game-free suite recorded; not run. - [x] No game files, dumps, generated game files or build output. - [x] Third-party sources untouched. - [x] Existing Longshot source and authored fixtures; GPL-3.0-or-later. ### When it applies - [x] Source commit records `Assisted-by: OpenAI Codex`. - [ ] Same-PC, same-scene interleaved performance measurements; pending. - [ ] Proposed default backed by measurements before readiness; switch is documented. - [x] Game-free measured run recorded under docs/tested/. - [x] Planning regression fails on main and passes here. - [x] Development documentation updated.

siantm added 1 commit 2026-11-15 10:02:02 +00:00

perf(build): optimize shared A64 helpers independently of cold chunks ... a9269637ec

Focused extraction of local Longshot changes: 0b9680a3. Authored tests and verification limits included; no game-derived artifacts.

Assisted-by: OpenAI Codex

mooki added the

area/install

kind

performance

platform/linux

platform/windows

priority

high

labels 2026-11-15 13:59:27 +00:00

HumanBean force-pushed perf/shared-a64-helpers-o2 from a9269637ec to 16ea5060cc 2026-11-15 18:45:05 +00:00 Compare

BeanIssues added the

risk

medium

label 2026-11-15 20:27:44 +00:00

Some checks failed

Hide checks

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

Details

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

Details

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

Details

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

Details

Website / Website on Cloudflare (pull_request) Has been skipped

Details

PR description / Description follows the template (pull_request_target) Successful in 3s

Details

CI / Conventional Commit title (pull_request) Successful in 3s

Details

CI / Workflow lint (actionlint) (pull_request) Successful in 5s

Details

Guide screenshots / Guide images and local UI source review (pull_request) Failing after 5s

Details

Third-party parts / As their notes say (pull_request) Successful in 10s

Details

Website / Website on Cloudflare (pull_request_target) Has been skipped

Details

This pull request is marked as a work in progress.

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/shared-a64-helpers-o2:siantm-perf/shared-a64-helpers-o2'

git switch 'siantm-perf/shared-a64-helpers-o2'

Sign in to join this conversation.

Reviewers

No reviewers

Labels

Clear labels   

area/accessibility

Barriers for people with disabilities

  

area/audio

Sound and music

  

area/input

Controllers, keyboard, mouse

  

area/install

Installing, updating, building from your game

  

area/menu

In-game menu and settings

  

area/renderer

Vulkan renderer, shaders, effects

  

area/saves

Save files

  

area/tooling

Developer tools: scripts, CI, build and release tooling

  

area/upscaling

DLSS, FSR, frame generation

  

ci: approved

A maintainer approved CircleCI for this fork PR (sticky; removed after 14 quiet days)

  

good first issue

A good start for a new contributor

  

gpu/amd

AMD GPUs

  

gpu/igpu

Integrated GPUs

  

gpu/intel

Intel GPUs

  

gpu/nvidia

NVIDIA GPUs

  

help wanted

Extra hands or knowledge wanted

  

kind

bug

Something doesn't work as it should

  

kind

chore

Build, CI, dependencies, tidying

  

kind

docs

Documentation

  

kind

feature

A new feature or an improvement

  

kind

performance

Frame rate, frame time, loading, memory

  

kind

question

A question rather than a change

  

needs measurements

Waiting for before/after measurements

  

platform/linux

Affects Linux (a change for every system carries both Windows and Linux)

  

platform/macos

macOS (Apple silicon or Intel Macs)

  

platform/steam-deck

Steam Deck

  

platform/windows

Affects Windows (a change for every system carries both Windows and Linux)

  

preview

Maintainers: deploy a preview of this PR's website (read its changes first). Removed after the run.

  

priority

critical

Crashes, data loss, or blocks most players

  

priority

high

Important: next in line

  

priority

low

Nice to have

  

regression

Worked in an earlier build, broken in a newer one: highest priority, above other bugs

  

risk

high

Broad or core change: the renderer, defaults on many systems, saves, installs, security

  

risk

low

Small, contained change: little can break

  

risk

medium

Changes behaviour in one area, or a default on some systems

  

status

blocked

Waits on something else first

  

status

confirmed

Reproduced or agreed on

  

status

duplicate

Already reported or proposed

  

status

invalid

Not a problem in this project

  

status

needs-info

Waiting for more information from the reporter

  

status

wontfix

Will not be worked on

  

testing wanted

Wanted: a test on other hardware (posts a test request in #test-requests)

  

ci: approved

No labels

area/accessibility

area/audio

area/input

area/install

area/menu

area/renderer

area/saves

area/tooling

area/upscaling

ci: approved

good first issue

gpu/amd

gpu/igpu

gpu/intel

gpu/nvidia

help wanted

kind

bug

kind

chore

kind

docs

kind

feature

kind

performance

kind

question

needs measurements

platform/linux

platform/macos

platform/steam-deck

platform/windows

preview

priority

critical

priority

high

priority

low

regression

risk

high

risk

low

risk

medium

status

blocked

status

confirmed

status

duplicate

status

invalid

status

needs-info

status

wontfix

testing wanted

ci: approved

Milestone

Clear milestone

No items

No milestone

Projects

Clear projects

No items

No project

Assignees

Clear assignees

No assignees

2 participants

Notifications

Subscribe

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!756

No description provided.