From: "H.J. Lu" <hjl.tools@gmail.com>
To: Noah Goldstein <goldstein.w.n@gmail.com>
Cc: GNU C Library <libc-alpha@sourceware.org>,
"Carlos O'Donell" <carlos@systemhalted.org>
Subject: Re: [PATCH v2 1/2] x86: Move mem{p}{mov|cpy}_{chk_}erms to its own file
Date: Wed, 29 Jun 2022 15:19:30 -0700 [thread overview]
Message-ID: <CAMe9rOr1rhTrFt6gfNa_YA6=PY+aJezT_0EedT4GV560ypT1VA@mail.gmail.com> (raw)
In-Reply-To: <20220629221349.1242862-1-goldstein.w.n@gmail.com>
On Wed, Jun 29, 2022 at 3:13 PM Noah Goldstein <goldstein.w.n@gmail.com> wrote:
>
> The primary memmove_{impl}_unaligned_erms implementations don't
> interact with this function. Putting them in same file both
> wastes space and unnecessarily bloats a hot code section.
> ---
> sysdeps/x86_64/multiarch/Makefile | 1 +
> sysdeps/x86_64/multiarch/memmove-erms.S | 53 +++++++++++++++++++
> .../multiarch/memmove-vec-unaligned-erms.S | 50 -----------------
> 3 files changed, 54 insertions(+), 50 deletions(-)
> create mode 100644 sysdeps/x86_64/multiarch/memmove-erms.S
>
> diff --git a/sysdeps/x86_64/multiarch/Makefile b/sysdeps/x86_64/multiarch/Makefile
> index 666ee4d5d6..62a4d96fb8 100644
> --- a/sysdeps/x86_64/multiarch/Makefile
> +++ b/sysdeps/x86_64/multiarch/Makefile
> @@ -18,6 +18,7 @@ sysdep_routines += \
> memmove-avx-unaligned-erms-rtm \
> memmove-avx512-no-vzeroupper \
> memmove-avx512-unaligned-erms \
> + memmove-erms \
> memmove-evex-unaligned-erms \
> memmove-sse2-unaligned-erms \
> memmove-ssse3 \
> diff --git a/sysdeps/x86_64/multiarch/memmove-erms.S b/sysdeps/x86_64/multiarch/memmove-erms.S
> new file mode 100644
> index 0000000000..d98d21644b
> --- /dev/null
> +++ b/sysdeps/x86_64/multiarch/memmove-erms.S
> @@ -0,0 +1,53 @@
Need copyright notice.
> +#include <sysdep.h>
> +
> +#if defined USE_MULTIARCH && IS_IN (libc)
> + .text
> +ENTRY (__mempcpy_chk_erms)
> + cmp %RDX_LP, %RCX_LP
> + jb HIDDEN_JUMPTARGET (__chk_fail)
> +END (__mempcpy_chk_erms)
> +
> +/* Only used to measure performance of REP MOVSB. */
> +ENTRY (__mempcpy_erms)
> + mov %RDI_LP, %RAX_LP
> + /* Skip zero length. */
> + test %RDX_LP, %RDX_LP
> + jz 2f
> + add %RDX_LP, %RAX_LP
> + jmp L(start_movsb)
> +END (__mempcpy_erms)
> +
> +ENTRY (__memmove_chk_erms)
> + cmp %RDX_LP, %RCX_LP
> + jb HIDDEN_JUMPTARGET (__chk_fail)
> +END (__memmove_chk_erms)
> +
> +ENTRY (__memmove_erms)
> + movq %rdi, %rax
> + /* Skip zero length. */
> + test %RDX_LP, %RDX_LP
> + jz 2f
> +L(start_movsb):
> + mov %RDX_LP, %RCX_LP
> + cmp %RSI_LP, %RDI_LP
> + jb 1f
> + /* Source == destination is less common. */
> + je 2f
> + lea (%rsi,%rcx), %RDX_LP
> + cmp %RDX_LP, %RDI_LP
> + jb L(movsb_backward)
> +1:
> + rep movsb
> +2:
> + ret
> +L(movsb_backward):
> + leaq -1(%rdi,%rcx), %rdi
> + leaq -1(%rsi,%rcx), %rsi
> + std
> + rep movsb
> + cld
> + ret
> +END (__memmove_erms)
> +strong_alias (__memmove_erms, __memcpy_erms)
> +strong_alias (__memmove_chk_erms, __memcpy_chk_erms)
> +#endif
> diff --git a/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S b/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S
> index d1518b8bab..04747133b7 100644
> --- a/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S
> +++ b/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S
> @@ -239,56 +239,6 @@ L(start):
> #endif
> #if defined USE_MULTIARCH && IS_IN (libc)
> END (MEMMOVE_SYMBOL (__memmove, unaligned))
> -# if VEC_SIZE == 16
> -ENTRY (__mempcpy_chk_erms)
> - cmp %RDX_LP, %RCX_LP
> - jb HIDDEN_JUMPTARGET (__chk_fail)
> -END (__mempcpy_chk_erms)
> -
> -/* Only used to measure performance of REP MOVSB. */
> -ENTRY (__mempcpy_erms)
> - mov %RDI_LP, %RAX_LP
> - /* Skip zero length. */
> - test %RDX_LP, %RDX_LP
> - jz 2f
> - add %RDX_LP, %RAX_LP
> - jmp L(start_movsb)
> -END (__mempcpy_erms)
> -
> -ENTRY (__memmove_chk_erms)
> - cmp %RDX_LP, %RCX_LP
> - jb HIDDEN_JUMPTARGET (__chk_fail)
> -END (__memmove_chk_erms)
> -
> -ENTRY (__memmove_erms)
> - movq %rdi, %rax
> - /* Skip zero length. */
> - test %RDX_LP, %RDX_LP
> - jz 2f
> -L(start_movsb):
> - mov %RDX_LP, %RCX_LP
> - cmp %RSI_LP, %RDI_LP
> - jb 1f
> - /* Source == destination is less common. */
> - je 2f
> - lea (%rsi,%rcx), %RDX_LP
> - cmp %RDX_LP, %RDI_LP
> - jb L(movsb_backward)
> -1:
> - rep movsb
> -2:
> - ret
> -L(movsb_backward):
> - leaq -1(%rdi,%rcx), %rdi
> - leaq -1(%rsi,%rcx), %rsi
> - std
> - rep movsb
> - cld
> - ret
> -END (__memmove_erms)
> -strong_alias (__memmove_erms, __memcpy_erms)
> -strong_alias (__memmove_chk_erms, __memcpy_chk_erms)
> -# endif
>
> # ifdef SHARED
> ENTRY (MEMMOVE_CHK_SYMBOL (__mempcpy_chk, unaligned_erms))
> --
> 2.34.1
>
--
H.J.
next prev parent reply other threads:[~2022-06-29 22:20 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-06-28 15:27 [PATCH v1 " Noah Goldstein
2022-06-28 15:27 ` [PATCH v1 2/2] x86: Add support for building {w}memmove{_chk} with explicit ISA level Noah Goldstein
2022-06-30 3:13 ` [PATCH v4] " Noah Goldstein
2022-07-05 15:33 ` H.J. Lu
2022-07-05 19:23 ` Noah Goldstein
2022-07-05 19:38 ` H.J. Lu
2022-07-05 19:22 ` [PATCH v5] " Noah Goldstein
2022-07-05 19:41 ` [PATCH v6] " Noah Goldstein
2022-07-05 19:51 ` H.J. Lu
2022-06-29 19:31 ` [PATCH v1 1/2] x86: Move mem{p}{mov|cpy}_{chk_}erms to its own file H.J. Lu
2022-06-29 19:34 ` Noah Goldstein
2022-06-29 19:45 ` H.J. Lu
2022-06-29 19:48 ` Noah Goldstein
2022-06-29 19:59 ` H.J. Lu
2022-06-29 20:02 ` Noah Goldstein
2022-06-29 20:16 ` H.J. Lu
2022-06-29 22:13 ` Noah Goldstein
2022-06-29 22:13 ` [PATCH v2 " Noah Goldstein
2022-06-29 22:13 ` [PATCH v2 2/2] x86: Add support for building {w}memmove{_chk} with explicit ISA level Noah Goldstein
2022-06-29 23:27 ` H.J. Lu
2022-06-30 3:12 ` Noah Goldstein
2022-06-30 3:14 ` Noah Goldstein
2022-06-29 22:19 ` H.J. Lu [this message]
2022-06-29 23:09 ` [PATCH v2 1/2] x86: Move mem{p}{mov|cpy}_{chk_}erms to its own file Noah Goldstein
2022-06-29 23:07 ` [PATCH v3 " Noah Goldstein
2022-06-29 23:07 ` [PATCH v3 2/2] x86: Add support for building {w}memmove{_chk} with explicit ISA level Noah Goldstein
2022-06-29 23:30 ` [PATCH v3 1/2] x86: Move mem{p}{mov|cpy}_{chk_}erms to its own file H.J. Lu
2022-07-14 3:05 ` Sunil Pandey
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='CAMe9rOr1rhTrFt6gfNa_YA6=PY+aJezT_0EedT4GV560ypT1VA@mail.gmail.com' \
--to=hjl.tools@gmail.com \
--cc=carlos@systemhalted.org \
--cc=goldstein.w.n@gmail.com \
--cc=libc-alpha@sourceware.org \
/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).