From 1b968b6b9b3aac702ac2f133e0dd16cfdbb415ee Mon Sep 17 00:00:00 2001 From: "H.J. Lu" Date: Fri, 5 Mar 2021 07:15:03 -0800 Subject: x86-64: Add memset family functions with 256-bit EVEX Update ifunc-memset.h/ifunc-wmemset.h to select the function optimized with 256-bit EVEX instructions using YMM16-YMM31 registers to avoid RTM abort with usable AVX512VL and AVX512BW since VZEROUPPER isn't needed at function exit. --- sysdeps/x86_64/multiarch/ifunc-impl-list.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'sysdeps/x86_64/multiarch/ifunc-impl-list.c') diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c index e1c39d58d6..aac8e601df 100644 --- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c +++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c @@ -160,6 +160,14 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array, IFUNC_IMPL_ADD (array, i, __memset_chk, CPU_FEATURE_USABLE (AVX2), __memset_chk_avx2_unaligned_erms) + IFUNC_IMPL_ADD (array, i, __memset_chk, + (CPU_FEATURE_USABLE (AVX512VL) + && CPU_FEATURE_USABLE (AVX512BW)), + __memset_chk_evex_unaligned) + IFUNC_IMPL_ADD (array, i, __memset_chk, + (CPU_FEATURE_USABLE (AVX512VL) + && CPU_FEATURE_USABLE (AVX512BW)), + __memset_chk_evex_unaligned_erms) IFUNC_IMPL_ADD (array, i, __memset_chk, CPU_FEATURE_USABLE (AVX512F), __memset_chk_avx512_unaligned_erms) @@ -185,6 +193,14 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array, IFUNC_IMPL_ADD (array, i, memset, CPU_FEATURE_USABLE (AVX2), __memset_avx2_unaligned_erms) + IFUNC_IMPL_ADD (array, i, memset, + (CPU_FEATURE_USABLE (AVX512VL) + && CPU_FEATURE_USABLE (AVX512BW)), + __memset_evex_unaligned) + IFUNC_IMPL_ADD (array, i, memset, + (CPU_FEATURE_USABLE (AVX512VL) + && CPU_FEATURE_USABLE (AVX512BW)), + __memset_evex_unaligned_erms) IFUNC_IMPL_ADD (array, i, memset, CPU_FEATURE_USABLE (AVX512F), __memset_avx512_unaligned_erms) @@ -555,6 +571,9 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array, IFUNC_IMPL_ADD (array, i, wmemset, CPU_FEATURE_USABLE (AVX2), __wmemset_avx2_unaligned) + IFUNC_IMPL_ADD (array, i, wmemset, + CPU_FEATURE_USABLE (AVX512VL), + __wmemset_evex_unaligned) IFUNC_IMPL_ADD (array, i, wmemset, CPU_FEATURE_USABLE (AVX512F), __wmemset_avx512_unaligned)) @@ -723,6 +742,9 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array, IFUNC_IMPL_ADD (array, i, __wmemset_chk, CPU_FEATURE_USABLE (AVX2), __wmemset_chk_avx2_unaligned) + IFUNC_IMPL_ADD (array, i, __wmemset_chk, + CPU_FEATURE_USABLE (AVX512VL), + __wmemset_chk_evex_unaligned) IFUNC_IMPL_ADD (array, i, __wmemset_chk, CPU_FEATURE_USABLE (AVX512F), __wmemset_chk_avx512_unaligned)) -- cgit 1.4.1