[PATCH v3 8/8] x86-64: Require BMI1/BMI2 for AVX2 strrchr and wcsrchr implementations

Noah Goldstein goldstein.w.n@gmail.com
Mon Oct 3 21:12:36 GMT 2022


On Mon, Oct 3, 2022 at 12:59 PM Aurelien Jarno <aurelien@aurel32.net> wrote:
>
> The AVX2 strrchr and wcsrchr implementation uses the 'blsmsk'
> instruction which belongs to the BMI1 CPU feature and the 'shrx'
> instruction, which belongs to the BMI2 CPU feature.
>
> Fixes: df7e295d18ff ("x86: Optimize {str|wcs}rchr-avx2")
> Partially resolves: BZ #29611
> ---
>  sysdeps/x86/isa-level.h                    |  1 +
>  sysdeps/x86_64/multiarch/ifunc-avx2.h      |  1 +
>  sysdeps/x86_64/multiarch/ifunc-impl-list.c | 17 ++++++++++++++---
>  3 files changed, 16 insertions(+), 3 deletions(-)
>
> diff --git a/sysdeps/x86/isa-level.h b/sysdeps/x86/isa-level.h
> index bbb90f5c5e..06f6c9663e 100644
> --- a/sysdeps/x86/isa-level.h
> +++ b/sysdeps/x86/isa-level.h
> @@ -79,6 +79,7 @@
>  /* ISA level >= 3 guaranteed includes.  */
>  #define AVX_X86_ISA_LEVEL 3
>  #define AVX2_X86_ISA_LEVEL 3
> +#define BMI1_X86_ISA_LEVEL 3
>  #define BMI2_X86_ISA_LEVEL 3
>  #define LZCNT_X86_ISA_LEVEL 3
>  #define MOVBE_X86_ISA_LEVEL 3
> diff --git a/sysdeps/x86_64/multiarch/ifunc-avx2.h b/sysdeps/x86_64/multiarch/ifunc-avx2.h
> index f1741083fd..f2f5e8a211 100644
> --- a/sysdeps/x86_64/multiarch/ifunc-avx2.h
> +++ b/sysdeps/x86_64/multiarch/ifunc-avx2.h
> @@ -36,6 +36,7 @@ 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, BMI1)
>        && 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,
> diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
> index ec1c5b55fb..00a91123d3 100644
> --- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c
> +++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
> @@ -578,13 +578,19 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
>    IFUNC_IMPL (i, name, strrchr,
>               X86_IFUNC_IMPL_ADD_V4 (array, i, strrchr,
>                                      (CPU_FEATURE_USABLE (AVX512VL)
> -                                     && CPU_FEATURE_USABLE (AVX512BW)),
> +                                     && CPU_FEATURE_USABLE (AVX512BW)
> +                                     && CPU_FEATURE_USABLE (BMI1)
> +                                     && CPU_FEATURE_USABLE (BMI2)),
>                                      __strrchr_evex)
>               X86_IFUNC_IMPL_ADD_V3 (array, i, strrchr,
> -                                    CPU_FEATURE_USABLE (AVX2),
> +                                    (CPU_FEATURE_USABLE (AVX2)
> +                                     && CPU_FEATURE_USABLE (BMI1)
> +                                     && CPU_FEATURE_USABLE (BMI2)),
>                                      __strrchr_avx2)
>               X86_IFUNC_IMPL_ADD_V3 (array, i, strrchr,
>                                      (CPU_FEATURE_USABLE (AVX2)
> +                                     && CPU_FEATURE_USABLE (BMI1)
> +                                     && CPU_FEATURE_USABLE (BMI2)
>                                       && CPU_FEATURE_USABLE (RTM)),
>                                      __strrchr_avx2_rtm)
>               /* ISA V2 wrapper for SSE2 implementation because the SSE2
> @@ -797,13 +803,18 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
>               X86_IFUNC_IMPL_ADD_V4 (array, i, wcsrchr,
>                                      (CPU_FEATURE_USABLE (AVX512VL)
>                                       && CPU_FEATURE_USABLE (AVX512BW)
> +                                     && CPU_FEATURE_USABLE (BMI1)
>                                       && CPU_FEATURE_USABLE (BMI2)),
>                                      __wcsrchr_evex)
>               X86_IFUNC_IMPL_ADD_V3 (array, i, wcsrchr,
> -                                    CPU_FEATURE_USABLE (AVX2),
> +                                    (CPU_FEATURE_USABLE (AVX2)
> +                                     && CPU_FEATURE_USABLE (BMI1)
> +                                     && CPU_FEATURE_USABLE (BMI2)),
>                                      __wcsrchr_avx2)
>               X86_IFUNC_IMPL_ADD_V3 (array, i, wcsrchr,
>                                      (CPU_FEATURE_USABLE (AVX2)
> +                                     && CPU_FEATURE_USABLE (BMI1)
> +                                     && CPU_FEATURE_USABLE (BMI2)
>                                       && CPU_FEATURE_USABLE (RTM)),
>                                      __wcsrchr_avx2_rtm)
>               /* ISA V2 wrapper for SSE2 implementation because the SSE2
> --
> 2.35.1
>

LGTM.
Reviewed-by: Noah Goldstein  <goldstein.w.n@gmail.com>


More information about the Libc-alpha mailing list