| Message ID | 20221003195944.3274548-5-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 strncmp implementations 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 | 7 +++++-- > sysdeps/x86_64/multiarch/strncmp.c | 4 ++-- > 2 files changed, 7 insertions(+), 4 deletions(-) > > diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c > index a42b0a4620..aebef3daaf 100644 > --- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c > +++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c > @@ -1176,13 +1176,16 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array, > IFUNC_IMPL (i, name, strncmp, > X86_IFUNC_IMPL_ADD_V4 (array, i, strncmp, > (CPU_FEATURE_USABLE (AVX512VL) > - && CPU_FEATURE_USABLE (AVX512BW)), > + && CPU_FEATURE_USABLE (AVX512BW) > + && CPU_FEATURE_USABLE (BMI2)), > __strncmp_evex) > X86_IFUNC_IMPL_ADD_V3 (array, i, strncmp, > - CPU_FEATURE_USABLE (AVX2), > + (CPU_FEATURE_USABLE (AVX2) > + && CPU_FEATURE_USABLE (BMI2)), > __strncmp_avx2) > X86_IFUNC_IMPL_ADD_V3 (array, i, strncmp, > (CPU_FEATURE_USABLE (AVX2) > + && CPU_FEATURE_USABLE (BMI2) > && CPU_FEATURE_USABLE (RTM)), > __strncmp_avx2_rtm) > X86_IFUNC_IMPL_ADD_V2 (array, i, strncmp, > diff --git a/sysdeps/x86_64/multiarch/strncmp.c b/sysdeps/x86_64/multiarch/strncmp.c > index 4ebe4bde30..c4f8b6bbb5 100644 > --- a/sysdeps/x86_64/multiarch/strncmp.c > +++ b/sysdeps/x86_64/multiarch/strncmp.c > @@ -41,12 +41,12 @@ 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 a42b0a4620..aebef3daaf 100644 --- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c +++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c @@ -1176,13 +1176,16 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array, IFUNC_IMPL (i, name, strncmp, X86_IFUNC_IMPL_ADD_V4 (array, i, strncmp, (CPU_FEATURE_USABLE (AVX512VL) - && CPU_FEATURE_USABLE (AVX512BW)), + && CPU_FEATURE_USABLE (AVX512BW) + && CPU_FEATURE_USABLE (BMI2)), __strncmp_evex) X86_IFUNC_IMPL_ADD_V3 (array, i, strncmp, - CPU_FEATURE_USABLE (AVX2), + (CPU_FEATURE_USABLE (AVX2) + && CPU_FEATURE_USABLE (BMI2)), __strncmp_avx2) X86_IFUNC_IMPL_ADD_V3 (array, i, strncmp, (CPU_FEATURE_USABLE (AVX2) + && CPU_FEATURE_USABLE (BMI2) && CPU_FEATURE_USABLE (RTM)), __strncmp_avx2_rtm) X86_IFUNC_IMPL_ADD_V2 (array, i, strncmp, diff --git a/sysdeps/x86_64/multiarch/strncmp.c b/sysdeps/x86_64/multiarch/strncmp.c index 4ebe4bde30..c4f8b6bbb5 100644 --- a/sysdeps/x86_64/multiarch/strncmp.c +++ b/sysdeps/x86_64/multiarch/strncmp.c @@ -41,12 +41,12 @@ 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))
The AVX2 strncmp implementations 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 | 7 +++++-- sysdeps/x86_64/multiarch/strncmp.c | 4 ++-- 2 files changed, 7 insertions(+), 4 deletions(-)