public inbox for libc-alpha@sourceware.org
 help / color / mirror / Atom feed
From: Noah Goldstein <goldstein.w.n@gmail.com>
To: Aurelien Jarno <aurelien@aurel32.net>
Cc: libc-alpha@sourceware.org, "H . J . Lu" <hjl.tools@gmail.com>,
	 Sunil K Pandey <skpgkp2@gmail.com>
Subject: Re: [PATCH v3 4/8] x86-64: Require BMI2 for AVX2 strncmp implementation
Date: Mon, 3 Oct 2022 14:11:37 -0700	[thread overview]
Message-ID: <CAFUsyf+6B6zJA3L7DQdeRDpFx9mMgmwYZ38=AxNgnB=0fgdv-w@mail.gmail.com> (raw)
In-Reply-To: <20221003195944.3274548-5-aurelien@aurel32.net>

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>

  reply	other threads:[~2022-10-03 21:11 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-10-03 19:59 [PATCH v3 0/8] x86: Fix AVX2 string functions requiring BMI1, BMI2 or LZCNT (BZ #29611) Aurelien Jarno
2022-10-03 19:59 ` [PATCH v3 1/8] x86: include BMI1 and BMI2 in x86-64-v3 level Aurelien Jarno
2022-10-03 21:11   ` Noah Goldstein
2022-10-03 19:59 ` [PATCH v3 2/8] x86-64: Require BMI2 for AVX2 str(n)casecmp implementations Aurelien Jarno
2022-10-03 21:11   ` Noah Goldstein
2022-10-03 19:59 ` [PATCH v3 3/8] x86-64: Require BMI2 for AVX2 strcmp implementation Aurelien Jarno
2022-10-03 21:12   ` Noah Goldstein
2022-10-03 19:59 ` [PATCH v3 4/8] x86-64: Require BMI2 for AVX2 strncmp implementation Aurelien Jarno
2022-10-03 21:11   ` Noah Goldstein [this message]
2022-10-03 19:59 ` [PATCH v3 5/8] x86-64: Require BMI2 for AVX2 wcs(n)cmp implementations Aurelien Jarno
2022-10-03 21:11   ` Noah Goldstein
2022-10-03 19:59 ` [PATCH v3 6/8] x86-64: Require BMI2 for AVX2 (raw|w)memchr implementations Aurelien Jarno
2022-10-03 21:12   ` Noah Goldstein
2022-10-03 19:59 ` [PATCH v3 7/8] x86-64: Require BMI2 and LZCNT for AVX2 memrchr implementation Aurelien Jarno
2022-10-03 21:12   ` Noah Goldstein
2022-10-03 19:59 ` [PATCH v3 8/8] x86-64: Require BMI1/BMI2 for AVX2 strrchr and wcsrchr implementations Aurelien Jarno
2022-10-03 21:12   ` Noah Goldstein
2022-10-03 20:47 ` [PATCH v3 0/8] x86: Fix AVX2 string functions requiring BMI1, BMI2 or LZCNT (BZ #29611) Sunil Pandey
2022-10-03 21:11 ` Noah Goldstein

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to='CAFUsyf+6B6zJA3L7DQdeRDpFx9mMgmwYZ38=AxNgnB=0fgdv-w@mail.gmail.com' \
    --to=goldstein.w.n@gmail.com \
    --cc=aurelien@aurel32.net \
    --cc=hjl.tools@gmail.com \
    --cc=libc-alpha@sourceware.org \
    --cc=skpgkp2@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).