Vibe Coded 5-20% SPS Gain - Bit Identical - #660
Draft
Kinvert wants to merge 16 commits into
Draft
Conversation
Marginal optimization: about 0.5% SPS while keeping golden checkpoints bit-identical.
Adds about 0.8% Affine578 SPS while keeping golden checkpoints bit-identical. H1024 remains on the legacy path.
Marginal optimization: about 0.17% combined SPS while keeping all golden checkpoints bit-identical. Float precision still compiles through the unchanged path.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
You can try this branch and see how it works on your end. If it's faster and you actually want it, I can clean it up.
I just threw tokens at it while working on other stuff, not expecting much but it seems to work for me.
Golden case Speedup
━━━━━━━━━━━━━━━━━━ ━━━━━━━━━
Affine578 .h +16.65%
────────────────── ─────────
Affine578 .cu +20.48%
────────────────── ─────────
Affine1024x4 .h +7.37%
────────────────── ─────────
Affine1024x4 .cu +9.12%
────────────────── ─────────
Breakout .h +2.14%
────────────────── ─────────
Breakout .cu +19.89%
────────────────── ─────────
G2048 .h -0.39% note this slowdown
────────────────── ─────────
Maze .h +6.62%
────────────────── ─────────
Boxoban .h +3.08%