KonstantinSeurer
/
mesa
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

swr/rast: fix _simd16_movemask_(ps,pd) native AVX512 intrinsics 

Reviewed-by: Bruce Cherniak <bruce.cherniak@intel.com>
This commit is contained in:
Tim Rowley 2017-05-04 18:40:35 -05:00
parent 9fd68be133
commit cbd33e71f7
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
src/gallium/drivers/swr/rasterizer/common/simd16intrin.h
View File

@ -539,8 +539,6 @@ INLINE int SIMDAPI _simd16_testz_ps(simd16scalar a, simd16scalar b)
return lo & hi;
}
#define _simd16_cmplt_epi32(a, b) _simd16_cmpgt_epi32(b, a)
SIMD16_EMU_AVX512_2(simd16scalar, _simd16_unpacklo_ps, _simd_unpacklo_ps)
SIMD16_EMU_AVX512_2(simd16scalar, _simd16_unpackhi_ps, _simd_unpackhi_ps)
SIMD16_EMU_AVX512_2(simd16scalard, _simd16_unpacklo_pd, _simd_unpacklo_pd)
@ -898,12 +896,14 @@ INLINE simd16scalari SIMDAPI _simd16_blendv_epi32(simd16scalari a, simd16scalari
INLINE simd16mask SIMDAPI _simd16_movemask_ps(simd16scalar a)
{
return _simd16_scalari2mask(_mm512_castps_si512(a));
// movemask_ps only checks the top bit of the float single elements
return _simd16_scalari2mask(_mm512_and_si512(_mm512_castps_si512(a), _mm512_set1_epi32(0x80000000)));
}
INLINE simd16mask SIMDAPI _simd16_movemask_pd(simd16scalard a)
{
return _simd16_scalard2mask(a);
// movemask_pd only checks the top bit of the float double elements
return _simd16_scalard2mask(_mm512_castsi512_pd(_mm512_and_si512(_mm512_castpd_si512(a), _mm512_set1_epi64(0x8000000000000000))));
}
#if 0