Fix some SSE on NEON bugs #1360
Merged
+281
−142
Conversation
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
mr-c
reviewed
Jan 7, 2026
Collaborator
|
Thank you @TheNumbat ! |
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Outdated suggestions cannot be applied.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.
_mm_min_pd/_mm_max_pdhad incorrect NaN behavior. The implementations of the four min/max functions were all slightly different; they now use the same logic. The NaN bug also applied to other architectures._mm_round_pdwasn't doing half-to-even rounding in_MM_FROUND_TO_NEAREST_INTmode. It now uses the correct NEON intrinsic. This also applied to ppc._mm_cvtpd_pi32/_mm_cvtpd_epi32wasn't doing half-to-even rounding. It now uses the corrected implementation ofsimde_x_mm_round_pd(moved over fromsse4.1.h).Technically, the conversions (along with
_mm_cvtps_epi32) should use the current rounding mode rather than specifically half-to-even, but it looked like always using half-to-even is intentional.Adds tests that fail without each of the fixes.