[v3,2/8] x86-64: Require BMI2 for AVX2 str(n)casecmp implementations
Commit Message
The AVX2 str(n)casecmp implementations use 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 | 28 +++++++++++++++------
sysdeps/x86_64/multiarch/ifunc-strcasecmp.h | 1 +
2 files changed, 21 insertions(+), 8 deletions(-)
Comments
On Mon, Oct 3, 2022 at 12:59 PM Aurelien Jarno <aurelien@aurel32.net> wrote:
>
> The AVX2 str(n)casecmp implementations use 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 | 28 +++++++++++++++------
> sysdeps/x86_64/multiarch/ifunc-strcasecmp.h | 1 +
> 2 files changed, 21 insertions(+), 8 deletions(-)
>
> diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
> index a71444eccb..d208fae4bf 100644
> --- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c
> +++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
> @@ -448,13 +448,16 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
> IFUNC_IMPL (i, name, strcasecmp,
> X86_IFUNC_IMPL_ADD_V4 (array, i, strcasecmp,
> (CPU_FEATURE_USABLE (AVX512VL)
> - && CPU_FEATURE_USABLE (AVX512BW)),
> + && CPU_FEATURE_USABLE (AVX512BW)
> + && CPU_FEATURE_USABLE (BMI2)),
> __strcasecmp_evex)
> X86_IFUNC_IMPL_ADD_V3 (array, i, strcasecmp,
> - CPU_FEATURE_USABLE (AVX2),
> + (CPU_FEATURE_USABLE (AVX2)
> + && CPU_FEATURE_USABLE (BMI2)),
> __strcasecmp_avx2)
> X86_IFUNC_IMPL_ADD_V3 (array, i, strcasecmp,
> (CPU_FEATURE_USABLE (AVX2)
> + && CPU_FEATURE_USABLE (BMI2)
> && CPU_FEATURE_USABLE (RTM)),
> __strcasecmp_avx2_rtm)
> X86_IFUNC_IMPL_ADD_V2 (array, i, strcasecmp,
> @@ -470,13 +473,16 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
> IFUNC_IMPL (i, name, strcasecmp_l,
> X86_IFUNC_IMPL_ADD_V4 (array, i, strcasecmp,
> (CPU_FEATURE_USABLE (AVX512VL)
> - && CPU_FEATURE_USABLE (AVX512BW)),
> + && CPU_FEATURE_USABLE (AVX512BW)
> + && CPU_FEATURE_USABLE (BMI2)),
> __strcasecmp_l_evex)
> X86_IFUNC_IMPL_ADD_V3 (array, i, strcasecmp,
> - CPU_FEATURE_USABLE (AVX2),
> + (CPU_FEATURE_USABLE (AVX2)
> + && CPU_FEATURE_USABLE (BMI2)),
> __strcasecmp_l_avx2)
> X86_IFUNC_IMPL_ADD_V3 (array, i, strcasecmp,
> (CPU_FEATURE_USABLE (AVX2)
> + && CPU_FEATURE_USABLE (BMI2)
> && CPU_FEATURE_USABLE (RTM)),
> __strcasecmp_l_avx2_rtm)
> X86_IFUNC_IMPL_ADD_V2 (array, i, strcasecmp_l,
> @@ -638,13 +644,16 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
> IFUNC_IMPL (i, name, strncasecmp,
> X86_IFUNC_IMPL_ADD_V4 (array, i, strncasecmp,
> (CPU_FEATURE_USABLE (AVX512VL)
> - && CPU_FEATURE_USABLE (AVX512BW)),
> + && CPU_FEATURE_USABLE (AVX512BW)
> + && CPU_FEATURE_USABLE (BMI2)),
> __strncasecmp_evex)
> X86_IFUNC_IMPL_ADD_V3 (array, i, strncasecmp,
> - CPU_FEATURE_USABLE (AVX2),
> + (CPU_FEATURE_USABLE (AVX2)
> + && CPU_FEATURE_USABLE (BMI2)),
> __strncasecmp_avx2)
> X86_IFUNC_IMPL_ADD_V3 (array, i, strncasecmp,
> (CPU_FEATURE_USABLE (AVX2)
> + && CPU_FEATURE_USABLE (BMI2)
> && CPU_FEATURE_USABLE (RTM)),
> __strncasecmp_avx2_rtm)
> X86_IFUNC_IMPL_ADD_V2 (array, i, strncasecmp,
> @@ -660,13 +669,16 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
> IFUNC_IMPL (i, name, strncasecmp_l,
> X86_IFUNC_IMPL_ADD_V4 (array, i, strncasecmp,
> (CPU_FEATURE_USABLE (AVX512VL)
> - && CPU_FEATURE_USABLE (AVX512BW)),
> + & CPU_FEATURE_USABLE (AVX512BW)
> + && CPU_FEATURE_USABLE (BMI2)),
> __strncasecmp_l_evex)
> X86_IFUNC_IMPL_ADD_V3 (array, i, strncasecmp,
> - CPU_FEATURE_USABLE (AVX2),
> + (CPU_FEATURE_USABLE (AVX2)
> + && CPU_FEATURE_USABLE (BMI2)),
> __strncasecmp_l_avx2)
> X86_IFUNC_IMPL_ADD_V3 (array, i, strncasecmp,
> (CPU_FEATURE_USABLE (AVX2)
> + && CPU_FEATURE_USABLE (BMI2)
> && CPU_FEATURE_USABLE (RTM)),
> __strncasecmp_l_avx2_rtm)
> X86_IFUNC_IMPL_ADD_V2 (array, i, strncasecmp_l,
> diff --git a/sysdeps/x86_64/multiarch/ifunc-strcasecmp.h b/sysdeps/x86_64/multiarch/ifunc-strcasecmp.h
> index 68646ef199..7622af259c 100644
> --- a/sysdeps/x86_64/multiarch/ifunc-strcasecmp.h
> +++ b/sysdeps/x86_64/multiarch/ifunc-strcasecmp.h
> @@ -34,6 +34,7 @@ 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, ))
> {
> --
> 2.35.1
>
LGTM.
Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
@@ -448,13 +448,16 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
IFUNC_IMPL (i, name, strcasecmp,
X86_IFUNC_IMPL_ADD_V4 (array, i, strcasecmp,
(CPU_FEATURE_USABLE (AVX512VL)
- && CPU_FEATURE_USABLE (AVX512BW)),
+ && CPU_FEATURE_USABLE (AVX512BW)
+ && CPU_FEATURE_USABLE (BMI2)),
__strcasecmp_evex)
X86_IFUNC_IMPL_ADD_V3 (array, i, strcasecmp,
- CPU_FEATURE_USABLE (AVX2),
+ (CPU_FEATURE_USABLE (AVX2)
+ && CPU_FEATURE_USABLE (BMI2)),
__strcasecmp_avx2)
X86_IFUNC_IMPL_ADD_V3 (array, i, strcasecmp,
(CPU_FEATURE_USABLE (AVX2)
+ && CPU_FEATURE_USABLE (BMI2)
&& CPU_FEATURE_USABLE (RTM)),
__strcasecmp_avx2_rtm)
X86_IFUNC_IMPL_ADD_V2 (array, i, strcasecmp,
@@ -470,13 +473,16 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
IFUNC_IMPL (i, name, strcasecmp_l,
X86_IFUNC_IMPL_ADD_V4 (array, i, strcasecmp,
(CPU_FEATURE_USABLE (AVX512VL)
- && CPU_FEATURE_USABLE (AVX512BW)),
+ && CPU_FEATURE_USABLE (AVX512BW)
+ && CPU_FEATURE_USABLE (BMI2)),
__strcasecmp_l_evex)
X86_IFUNC_IMPL_ADD_V3 (array, i, strcasecmp,
- CPU_FEATURE_USABLE (AVX2),
+ (CPU_FEATURE_USABLE (AVX2)
+ && CPU_FEATURE_USABLE (BMI2)),
__strcasecmp_l_avx2)
X86_IFUNC_IMPL_ADD_V3 (array, i, strcasecmp,
(CPU_FEATURE_USABLE (AVX2)
+ && CPU_FEATURE_USABLE (BMI2)
&& CPU_FEATURE_USABLE (RTM)),
__strcasecmp_l_avx2_rtm)
X86_IFUNC_IMPL_ADD_V2 (array, i, strcasecmp_l,
@@ -638,13 +644,16 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
IFUNC_IMPL (i, name, strncasecmp,
X86_IFUNC_IMPL_ADD_V4 (array, i, strncasecmp,
(CPU_FEATURE_USABLE (AVX512VL)
- && CPU_FEATURE_USABLE (AVX512BW)),
+ && CPU_FEATURE_USABLE (AVX512BW)
+ && CPU_FEATURE_USABLE (BMI2)),
__strncasecmp_evex)
X86_IFUNC_IMPL_ADD_V3 (array, i, strncasecmp,
- CPU_FEATURE_USABLE (AVX2),
+ (CPU_FEATURE_USABLE (AVX2)
+ && CPU_FEATURE_USABLE (BMI2)),
__strncasecmp_avx2)
X86_IFUNC_IMPL_ADD_V3 (array, i, strncasecmp,
(CPU_FEATURE_USABLE (AVX2)
+ && CPU_FEATURE_USABLE (BMI2)
&& CPU_FEATURE_USABLE (RTM)),
__strncasecmp_avx2_rtm)
X86_IFUNC_IMPL_ADD_V2 (array, i, strncasecmp,
@@ -660,13 +669,16 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
IFUNC_IMPL (i, name, strncasecmp_l,
X86_IFUNC_IMPL_ADD_V4 (array, i, strncasecmp,
(CPU_FEATURE_USABLE (AVX512VL)
- && CPU_FEATURE_USABLE (AVX512BW)),
+ & CPU_FEATURE_USABLE (AVX512BW)
+ && CPU_FEATURE_USABLE (BMI2)),
__strncasecmp_l_evex)
X86_IFUNC_IMPL_ADD_V3 (array, i, strncasecmp,
- CPU_FEATURE_USABLE (AVX2),
+ (CPU_FEATURE_USABLE (AVX2)
+ && CPU_FEATURE_USABLE (BMI2)),
__strncasecmp_l_avx2)
X86_IFUNC_IMPL_ADD_V3 (array, i, strncasecmp,
(CPU_FEATURE_USABLE (AVX2)
+ && CPU_FEATURE_USABLE (BMI2)
&& CPU_FEATURE_USABLE (RTM)),
__strncasecmp_l_avx2_rtm)
X86_IFUNC_IMPL_ADD_V2 (array, i, strncasecmp_l,
@@ -34,6 +34,7 @@ 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, ))
{