[v3,5/8] x86-64: Require BMI2 for AVX2 wcs(n)cmp implementations
Commit Message
The AVX2 wcs(n)cmp 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 | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
Comments
On Mon, Oct 3, 2022 at 12:59 PM Aurelien Jarno <aurelien@aurel32.net> wrote:
>
> The AVX2 wcs(n)cmp 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 | 8 ++++++--
> 1 file changed, 6 insertions(+), 2 deletions(-)
>
> diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
> index aebef3daaf..fec8790c11 100644
> --- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c
> +++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
> @@ -810,10 +810,12 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
> && CPU_FEATURE_USABLE (BMI2)),
> __wcscmp_evex)
> X86_IFUNC_IMPL_ADD_V3 (array, i, wcscmp,
> - CPU_FEATURE_USABLE (AVX2),
> + (CPU_FEATURE_USABLE (AVX2)
> + && CPU_FEATURE_USABLE (BMI2)),
> __wcscmp_avx2)
> X86_IFUNC_IMPL_ADD_V3 (array, i, wcscmp,
> (CPU_FEATURE_USABLE (AVX2)
> + && CPU_FEATURE_USABLE (BMI2)
> && CPU_FEATURE_USABLE (RTM)),
> __wcscmp_avx2_rtm)
> /* ISA V2 wrapper for SSE2 implementation because the SSE2
> @@ -830,10 +832,12 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
> && CPU_FEATURE_USABLE (BMI2)),
> __wcsncmp_evex)
> X86_IFUNC_IMPL_ADD_V3 (array, i, wcsncmp,
> - CPU_FEATURE_USABLE (AVX2),
> + (CPU_FEATURE_USABLE (AVX2)
> + && CPU_FEATURE_USABLE (BMI2)),
> __wcsncmp_avx2)
> X86_IFUNC_IMPL_ADD_V3 (array, i, wcsncmp,
> (CPU_FEATURE_USABLE (AVX2)
> + && CPU_FEATURE_USABLE (BMI2)
> && CPU_FEATURE_USABLE (RTM)),
> __wcsncmp_avx2_rtm)
> /* ISA V2 wrapper for GENERIC implementation because the
> --
> 2.35.1
>
LGTM.
Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
@@ -810,10 +810,12 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
&& CPU_FEATURE_USABLE (BMI2)),
__wcscmp_evex)
X86_IFUNC_IMPL_ADD_V3 (array, i, wcscmp,
- CPU_FEATURE_USABLE (AVX2),
+ (CPU_FEATURE_USABLE (AVX2)
+ && CPU_FEATURE_USABLE (BMI2)),
__wcscmp_avx2)
X86_IFUNC_IMPL_ADD_V3 (array, i, wcscmp,
(CPU_FEATURE_USABLE (AVX2)
+ && CPU_FEATURE_USABLE (BMI2)
&& CPU_FEATURE_USABLE (RTM)),
__wcscmp_avx2_rtm)
/* ISA V2 wrapper for SSE2 implementation because the SSE2
@@ -830,10 +832,12 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
&& CPU_FEATURE_USABLE (BMI2)),
__wcsncmp_evex)
X86_IFUNC_IMPL_ADD_V3 (array, i, wcsncmp,
- CPU_FEATURE_USABLE (AVX2),
+ (CPU_FEATURE_USABLE (AVX2)
+ && CPU_FEATURE_USABLE (BMI2)),
__wcsncmp_avx2)
X86_IFUNC_IMPL_ADD_V3 (array, i, wcsncmp,
(CPU_FEATURE_USABLE (AVX2)
+ && CPU_FEATURE_USABLE (BMI2)
&& CPU_FEATURE_USABLE (RTM)),
__wcsncmp_avx2_rtm)
/* ISA V2 wrapper for GENERIC implementation because the