[Bug c++/94046] New: cast to __m256d in mask argument of avx2 float gather intrinsics

[niklas at nolte dot dev]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94046

            Bug ID: 94046
           Summary: cast to __m256d in mask argument of avx2 float gather
                    intrinsics
           Product: gcc
           Version: 10.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: c++
          Assignee: unassigned at gcc dot gnu.org
          Reporter: niklas at nolte dot dev
  Target Milestone: ---

I cannot call the _mm256_mask_i32gather_ps intrinsic with a mask argument that
is not implicitly convertible to __mm256d, only in -O0 mode.

Please correct me if i'm misunderstanding, but it seems like the cast to
__m256d for the mask argument is a mistake.

reproducer:
https://godbolt.org/z/wu4DmN