diff options
| -rw-r--r-- | numpy/distutils/ccompiler_opt.py | 2 | ||||
| -rw-r--r-- | numpy/distutils/checks/extra_avx512dq_mask.c | 16 |
2 files changed, 17 insertions, 1 deletions
diff --git a/numpy/distutils/ccompiler_opt.py b/numpy/distutils/ccompiler_opt.py index 5fa17b2ee..e6c720399 100644 --- a/numpy/distutils/ccompiler_opt.py +++ b/numpy/distutils/ccompiler_opt.py @@ -259,7 +259,7 @@ class _Config: AVX512_SKX = dict( interest=42, implies="AVX512CD", group="AVX512VL AVX512BW AVX512DQ", detect="AVX512_SKX", implies_detect=False, - extra_checks="AVX512BW_MASK" + extra_checks="AVX512BW_MASK AVX512DQ_MASK" ), AVX512_CLX = dict( interest=43, implies="AVX512_SKX", group="AVX512VNNI", diff --git a/numpy/distutils/checks/extra_avx512dq_mask.c b/numpy/distutils/checks/extra_avx512dq_mask.c new file mode 100644 index 000000000..f0dc88bdd --- /dev/null +++ b/numpy/distutils/checks/extra_avx512dq_mask.c @@ -0,0 +1,16 @@ +#include <immintrin.h> +/** + * Test DQ mask operations due to: + * - MSVC has supported it since vs2019 see, + * https://developercommunity.visualstudio.com/content/problem/518298/missing-avx512bw-mask-intrinsics.html + * - Clang >= v8.0 + * - GCC >= v7.1 + */ +int main(void) +{ + __mmask8 m8 = _mm512_cmpeq_epi64_mask(_mm512_set1_epi64(1), _mm512_set1_epi64(1)); + m8 = _kor_mask8(m8, m8); + m8 = _kxor_mask8(m8, m8); + m8 = _cvtu32_mask8(_cvtmask8_u32(m8)); + return (int)_cvtmask8_u32(m8); +} |