Add criterion benchmarks for the wide wrappers - #90
Closed
marknefedov wants to merge 2 commits into
Closed
Conversation
Covers extract/replace lane access, map_lanes-based math ops, horizontal reductions, boolean mask ops, and raw wide ceilings.
marknefedov
force-pushed
the
criterion-wide-benches
branch
from
August 14, 2026 21:05
045dbfe to
a226a07
Compare
marknefedov
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Stacked on #87; the first commit is that branch, only the last commit is new.
Adds criterion micro-benchmarks for the
Wide*wrappers: per-lane extract/replace, themap_lanesmath ops, horizontal reductions, boolean mask ops, and the rawwideoperations as a reference ceiling.harness = false, runs on stable.An earlier version of this PR also switched
extract/replacetowide1.6'sas_arrayaccessors. The benchmarks measured that change as neutral at opt-level 3 (LLVM already folds the old round trip in hot inlined code), so the commit was dropped. The benches remain as regression coverage for exactly that kind of change.