Fix the '-0.0' issue of blendv_ps and blendv_pd. #7
Conversation
This file contains 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
For '_mm256_blendv_ps' and '_mm256_blendv_pd', the selector is controlled by the highest flag of each unit, while the mask is presented as a float or double SIMD register. For the case of '-0.0', which is intepreted as 0x8000..00 in register, digits in the 'b' input should be selected. Previous implementation used 'vcgeq_f32' and 'vcgeq_f64' to get flags of selector. These intrinsics won't think '-0.0 < 0.0', thus digits in 'a' should be selected and an incorrect result would be returned. This fix convert the comparing from float intrinsics to integer ones and preserve the correction of '-0.0' case.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
For '_mm256_blendv_ps' and '_mm256_blendv_pd', the selector is
controlled by the highest flag of each unit, while the mask is
presented as a float or double SIMD register. For the case of
'-0.0', which is intepreted as 0x8000..00 in register, digits
in the 'b' input should be selected.
Previous implementation used 'vcgeq_f32' and 'vcgeq_f64' to get
flags of selector. These intrinsics won't think '-0.0 < 0.0',
thus digits in 'a' should be selected and an incorrect result
would be returned.
This fix convert the comparing from float intrinsics to integer
ones and preserve the correction of '-0.0' case.