diff options
| author | Raghuveer Devulapalli <raghuveer.devulapalli@intel.com> | 2023-03-21 12:51:16 -0700 |
|---|---|---|
| committer | Raghuveer Devulapalli <raghuveer.devulapalli@intel.com> | 2023-04-05 09:30:40 -0700 |
| commit | 28872618c7504fb3365be9dc91c1910e09c36496 (patch) | |
| tree | ae2864f91c9ec70640c354f2e62c4116be455088 /numpy | |
| parent | b5d36d1b9485e3488d8d9420bf5efdf937d70dfb (diff) | |
| download | numpy-28872618c7504fb3365be9dc91c1910e09c36496.tar.gz | |
ENH: Use x86-simd-sort to disptch avx512_qsort<_Float16>
Diffstat (limited to 'numpy')
| -rw-r--r-- | numpy/core/src/npysort/simd_qsort_16bit.dispatch.cpp | 16 |
1 files changed, 12 insertions, 4 deletions
diff --git a/numpy/core/src/npysort/simd_qsort_16bit.dispatch.cpp b/numpy/core/src/npysort/simd_qsort_16bit.dispatch.cpp index a6465a883..3f5099758 100644 --- a/numpy/core/src/npysort/simd_qsort_16bit.dispatch.cpp +++ b/numpy/core/src/npysort/simd_qsort_16bit.dispatch.cpp @@ -1,5 +1,5 @@ /*@targets - * $maxopt $keep_baseline avx512_icl + * $maxopt $keep_baseline avx512_icl avx512_spr */ // policy $keep_baseline is used to avoid skip building avx512_skx // when its part of baseline features (--cpu-baseline), since @@ -7,16 +7,23 @@ #include "simd_qsort.hpp" -#if defined(NPY_HAVE_AVX512_ICL) && !defined(_MSC_VER) +#if defined(NPY_HAVE_AVX512_SPR) && !defined(_MSC_VER) + #include "x86-simd-sort/src/avx512fp16-16bit-qsort.hpp" +#elif defined(NPY_HAVE_AVX512_ICL) && !defined(_MSC_VER) #include "x86-simd-sort/src/avx512-16bit-qsort.hpp" #endif namespace np { namespace qsort_simd { -#if defined(NPY_HAVE_AVX512_ICL) && !defined(_MSC_VER) +#if !defined(_MSC_VER) +#if defined(NPY_HAVE_AVX512_ICL) || defined(NPY_HAVE_AVX512_SPR) template<> void NPY_CPU_DISPATCH_CURFX(QSort)(Half *arr, intptr_t size) { +#if defined(NPY_HAVE_AVX512_SPR) + avx512_qsort(reinterpret_cast<_Float16*>(arr), size); +#else avx512_qsort_fp16(reinterpret_cast<uint16_t*>(arr), size); +#endif } template<> void NPY_CPU_DISPATCH_CURFX(QSort)(uint16_t *arr, intptr_t size) { @@ -26,6 +33,7 @@ template<> void NPY_CPU_DISPATCH_CURFX(QSort)(int16_t *arr, intptr_t size) { avx512_qsort(arr, size); } -#endif // NPY_HAVE_AVX512_ICL +#endif // NPY_HAVE_AVX512_ICL || SPR +#endif // _MSC_VER }} // namespace np::qsort_simd |