x86 avx: adjust rounding modes & other fixes#1379
Merged
mr-c merged 3 commits intosimd-everywhere:masterfrom Jan 31, 2026
Merged
x86 avx: adjust rounding modes & other fixes#1379mr-c merged 3 commits intosimd-everywhere:masterfrom
mr-c merged 3 commits intosimd-everywhere:masterfrom
Conversation
Collaborator
|
Thank you @TheNumbat ! |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
_mm256_cvtpd_epi32/_mm256_cvtps_epi32didn't respect out-of-range inputs, and used a different rounding mode than their 128-bit counterparts. They now call the 128-bit versions when available, and otherwise use a C implementation copied from the 128-bit version._mm256_testnzc_si256usedrc & rz, meaning it returns0if they have non-overlapping set bits.vptestexamines all bits, so this should be using a logical and. I've also slightly refactored the othertest_si256implementations to call their 128-bit versions when available.Adds tests that fail without the fixes.