[Bug target/94046] cast to __m256d in mask argument of avx2 float gather intrinsics

[jakub at gcc dot gnu.org]

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

--- Comment #3 from Jakub Jelinek <jakub at gcc dot gnu.org> ---
This shows a couple of suspect conversions in macros, will need to verify all
of them:
grep '(__v[0-9]*[qhsd][if])(__m\(128\|256\|512\)\(\|d\|i\))' *.h | grep -v
'\((__v2di)(__m128i)\|(__v4si)(__m128i)\|(__v8hi)(__m128i)\|(__v16qi)(__m128i)\|(__v4di)(__m256i)\|(__v8si)(__m256i)\|(__v16hi)(__m256i)\|(__v32qi)(__m256i)\|(__v8di)(__m512i)\|(__v16si)(__m512i)\|(__v32hi)(__m512i)\|(__v64qi)(__m512i)\|(__v2df)(__m128d)\|(__v4sf)(__m128)\|(__v4df)(__m256d)\|(__v8sf)(__m256)\|(__v8df)(__m512d)\|(__v16sf)(__m512)\)'
avx2intrin.h:  (__m128) __builtin_ia32_gathersiv4sf ((__v4sf)(__m128d)SRC,     
 \
avx2intrin.h:                                   (__v4sf)(__m128d)MASK,   \
avx2intrin.h:                                   (__v8sf)(__m256d)MASK,  \
avx2intrin.h:                                   (__v4sf)(__m128d)MASK,   \
xopintrin.h:                                    (__v2di)(__m128d)(C),          
\
xopintrin.h:                                       (__v4di)(__m256d)(C),       
\
xopintrin.h:                                   (__v4si)(__m128)(C),            
\
xopintrin.h:                                      (__v8si)(__m256)(C),         
\