Improve SVE2 optimizations of SimdSegmentationChangeIndex - #895
Merged
ermig1979 merged 1 commit intoAug 20, 2026
Conversation
Replace the per-iteration WHILELT loop with a ptrue 4-vector body, a residual full-vector pass, and a single tail predicate so the ARM SVE2 path is no longer slower than NEON. Co-authored-by: igor.ermolaev <igor.ermolaev@altezza.org>
ermig1979
marked this pull request as ready for review
August 20, 2026 09:02
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Rewrite the ARM SVE2 implementation of
SimdSegmentationChangeIndexso it is no longer slower than the NEON path.The previous SVE2 version rebuilt a
svwhileltpredicate on every inner-loop iteration. The new path:svptrue_b8()predicate for the main bodyChangeIndex4)docs/2026.htmlrelease 7.2.165 Improving section is updated.Test::SegmentationChangeIndexAutoTestadds extra SVE2 sizes for tails andwidth < svcntb().Testing
Test -fi=SegmentationChangeIndex(Base / SSE4.1 / AVX2 / AVX-512BW): passedneoverse-n2andmax,sve128), VL=64 (max), including extra sizesA+1,A+3, and3x4