diff options
| author | Aurelien Jarno <aurelien@aurel32.net> | 2022-10-03 23:46:11 +0200 |
|---|---|---|
| committer | Aurelien Jarno <aurelien@aurel32.net> | 2022-10-03 23:46:11 +0200 |
| commit | 3c0c78afabfed4b6fc161c159e628fbf14ff370b (patch) | |
| tree | c8dafc90670cbdc7cf4061477cee1671f31f6476 /sysdeps/x86_64/multiarch | |
| parent | e3e7fab7fe5186d18ca2046d99ba321c27db30ad (diff) | |
| download | glibc-3c0c78afabfed4b6fc161c159e628fbf14ff370b.tar glibc-3c0c78afabfed4b6fc161c159e628fbf14ff370b.tar.gz glibc-3c0c78afabfed4b6fc161c159e628fbf14ff370b.tar.bz2 glibc-3c0c78afabfed4b6fc161c159e628fbf14ff370b.zip | |
x86-64: Require BMI2 and LZCNT for AVX2 memrchr implementation
The AVX2 memrchr implementation uses the 'shlxl' instruction, which
belongs to the BMI2 CPU feature and uses the 'lzcnt' instruction, which
belongs to the LZCNT CPU feature.
Fixes: af5306a735eb ("x86: Optimize memrchr-avx2.S")
Partially resolves: BZ #29611
Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
Diffstat (limited to 'sysdeps/x86_64/multiarch')
| -rw-r--r-- | sysdeps/x86_64/multiarch/ifunc-avx2.h | 1 | ||||
| -rw-r--r-- | sysdeps/x86_64/multiarch/ifunc-impl-list.c | 10 |
2 files changed, 9 insertions, 2 deletions
diff --git a/sysdeps/x86_64/multiarch/ifunc-avx2.h b/sysdeps/x86_64/multiarch/ifunc-avx2.h index a57a9952f3..f1741083fd 100644 --- a/sysdeps/x86_64/multiarch/ifunc-avx2.h +++ b/sysdeps/x86_64/multiarch/ifunc-avx2.h @@ -37,6 +37,7 @@ IFUNC_SELECTOR (void) if (X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX2) && X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, BMI2) + && X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, LZCNT) && X86_ISA_CPU_FEATURES_ARCH_P (cpu_features, AVX_Fast_Unaligned_Load, )) { diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c index 7c84963d92..ec1c5b55fb 100644 --- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c +++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c @@ -209,13 +209,19 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array, IFUNC_IMPL (i, name, memrchr, X86_IFUNC_IMPL_ADD_V4 (array, i, memrchr, (CPU_FEATURE_USABLE (AVX512VL) - && CPU_FEATURE_USABLE (AVX512BW)), + && CPU_FEATURE_USABLE (AVX512BW) + && CPU_FEATURE_USABLE (BMI2) + && CPU_FEATURE_USABLE (LZCNT)), __memrchr_evex) X86_IFUNC_IMPL_ADD_V3 (array, i, memrchr, - CPU_FEATURE_USABLE (AVX2), + (CPU_FEATURE_USABLE (AVX2) + && CPU_FEATURE_USABLE (BMI2) + && CPU_FEATURE_USABLE (LZCNT)), __memrchr_avx2) X86_IFUNC_IMPL_ADD_V3 (array, i, memrchr, (CPU_FEATURE_USABLE (AVX2) + && CPU_FEATURE_USABLE (BMI2) + && CPU_FEATURE_USABLE (LZCNT) && CPU_FEATURE_USABLE (RTM)), __memrchr_avx2_rtm) /* ISA V2 wrapper for SSE2 implementation because the SSE2 |