Message ID | 20221003195944.3274548-4-aurelien@aurel32.net |
---|---|
State | New |
Headers | show |
Series | x86: Fix AVX2 string functions requiring BMI1, BMI2 or LZCNT (BZ #29611) | expand |
On Mon, Oct 3, 2022 at 12:59 PM Aurelien Jarno <aurelien@aurel32.net> wrote: > > The AVX2 strcmp implementation uses the 'bzhi' instruction, which > belongs to the BMI2 CPU feature. > > NB: It also uses the 'tzcnt' BMI1 instruction, but it is executed as BSF > as BSF if the CPU doesn't support TZCNT, and produces the same result > for non-zero input. > > Partially fixes: b77b06e0e296 ("x86: Optimize strcmp-avx2.S") > Partially resolves: BZ #29611 > --- > sysdeps/x86_64/multiarch/ifunc-impl-list.c | 4 +++- > sysdeps/x86_64/multiarch/strcmp.c | 4 ++-- > 2 files changed, 5 insertions(+), 3 deletions(-) > > diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c > index d208fae4bf..a42b0a4620 100644 > --- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c > +++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c > @@ -591,10 +591,12 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array, > && CPU_FEATURE_USABLE (BMI2)), > __strcmp_evex) > X86_IFUNC_IMPL_ADD_V3 (array, i, strcmp, > - CPU_FEATURE_USABLE (AVX2), > + (CPU_FEATURE_USABLE (AVX2) > + && CPU_FEATURE_USABLE (BMI2)), > __strcmp_avx2) > X86_IFUNC_IMPL_ADD_V3 (array, i, strcmp, > (CPU_FEATURE_USABLE (AVX2) > + && CPU_FEATURE_USABLE (BMI2) > && CPU_FEATURE_USABLE (RTM)), > __strcmp_avx2_rtm) > X86_IFUNC_IMPL_ADD_V2 (array, i, strcmp, > diff --git a/sysdeps/x86_64/multiarch/strcmp.c b/sysdeps/x86_64/multiarch/strcmp.c > index fdd5afe3af..9d6c9f66ba 100644 > --- a/sysdeps/x86_64/multiarch/strcmp.c > +++ b/sysdeps/x86_64/multiarch/strcmp.c > @@ -45,12 +45,12 @@ IFUNC_SELECTOR (void) > const struct cpu_features *cpu_features = __get_cpu_features (); > > if (X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX2) > + && X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, BMI2) > && X86_ISA_CPU_FEATURES_ARCH_P (cpu_features, > AVX_Fast_Unaligned_Load, )) > { > if (X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX512VL) > - && X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX512BW) > - && X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, BMI2)) > + && X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX512BW)) > return OPTIMIZE (evex); > > if (CPU_FEATURE_USABLE_P (cpu_features, RTM)) > -- > 2.35.1 > LGTM. Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c index d208fae4bf..a42b0a4620 100644 --- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c +++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c @@ -591,10 +591,12 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array, && CPU_FEATURE_USABLE (BMI2)), __strcmp_evex) X86_IFUNC_IMPL_ADD_V3 (array, i, strcmp, - CPU_FEATURE_USABLE (AVX2), + (CPU_FEATURE_USABLE (AVX2) + && CPU_FEATURE_USABLE (BMI2)), __strcmp_avx2) X86_IFUNC_IMPL_ADD_V3 (array, i, strcmp, (CPU_FEATURE_USABLE (AVX2) + && CPU_FEATURE_USABLE (BMI2) && CPU_FEATURE_USABLE (RTM)), __strcmp_avx2_rtm) X86_IFUNC_IMPL_ADD_V2 (array, i, strcmp, diff --git a/sysdeps/x86_64/multiarch/strcmp.c b/sysdeps/x86_64/multiarch/strcmp.c index fdd5afe3af..9d6c9f66ba 100644 --- a/sysdeps/x86_64/multiarch/strcmp.c +++ b/sysdeps/x86_64/multiarch/strcmp.c @@ -45,12 +45,12 @@ IFUNC_SELECTOR (void) const struct cpu_features *cpu_features = __get_cpu_features (); if (X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX2) + && X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, BMI2) && X86_ISA_CPU_FEATURES_ARCH_P (cpu_features, AVX_Fast_Unaligned_Load, )) { if (X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX512VL) - && X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX512BW) - && X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, BMI2)) + && X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX512BW)) return OPTIMIZE (evex); if (CPU_FEATURE_USABLE_P (cpu_features, RTM))