Fix the '-0.0' issue of blendv_ps and blendv_pd. #7
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Outdated suggestions cannot be applied.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.