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 v1] String: Split memcpy tests so that parallel build is faster
Date: Thu, 11 Nov 2021 08:49:09 -0800 [thread overview]
Message-ID: <CAMe9rOqe-ZVYRNjU-ypcs5t1jSPN=foMGHxq7ie4kXnfQ5a1oA@mail.gmail.com> (raw)
In-Reply-To: <CAFUsyf+bqNsBve1OPoGs4LodvxixPRNrdeGqZFfhSfzcyiN0Xw@mail.gmail.com>
> >
> > LGTM.
> >
> > Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
>
> Thanks. Pushed.
I got
before:
time string/test-memcpy --direct
builtin_memcpy simple_memcpy
__memcpy_avx_unaligned __memcpy_avx_unaligned_erms
__memcpy_avx_unaligned_rtm __memcpy_avx_unaligned_erms_rtm
__memcpy_evex_unaligned __memcpy_evex_unaligned_erms
__memcpy_ssse3_back __memcpy_ssse3 __memcpy_avx512_no_vzeroupper
__memcpy_avx512_unaligned __memcpy_avx512_unaligned_erms
__memcpy_sse2_unaligned __memcpy_sse2_unaligned_erms __memcpy_erms
string/test-memcpy --direct 289.72s user 14.95s system 99% cpu 5:05.38 total
time string/test-mempcpy --direct
simple_mempcpy __mempcpy_avx512_no_vzeroupper
__mempcpy_avx512_unaligned __mempcpy_avx512_unaligned_erms
__mempcpy_avx_unaligned__mempcpy_avx_unaligned_erms
__mempcpy_avx_unaligned_rtm __mempcpy_avx_unaligned_erms_rtm
__mempcpy_evex_unaligned __mempcpy_evex_unaligned_erms
__mempcpy_ssse3_back __mempcpy_ssse3 __mempcpy_sse2_unaligned
__mempcpy_sse2_unaligned_erms __mempcpy_erms
string/test-mempcpy --direct 174.11s user 9.41s system 99% cpu 3:03.93 total
after:
time string/test-mempcpy --direct
simple_mempcpy __mempcpy_avx512_no_vzeroupper
__mempcpy_avx512_unaligned __mempcpy_avx512_unaligned_erms
__mempcpy_avx_unaligned __mempcpy_avx_unaligned_erms
__mempcpy_avx_unaligned_rtm __mempcpy_avx_unaligned_erms_rtm
__mempcpy_evex_unaligned __mempcpy_evex_unaligned_erms
__mempcpy_ssse3_back __mempcpy_ssse3 __mempcpy_sse2_unaligned
__mempcpy_sse2_unaligned_erms __mempcpy_erms
string/test-mempcpy --direct 155.37s user 9.01s system 99% cpu 2:44.77 total
time string/test-memcpy --direct
builtin_memcpy simple_memcpy
__memcpy_avx_unaligned __memcpy_avx_unaligned_erms
__memcpy_avx_unaligned_rtm __memcpy_avx_unaligned_erms_rtm
__memcpy_evex_unaligned __memcpy_evex_unaligned_erms
__memcpy_ssse3_back __memcpy_ssse3 __memcpy_avx512_no_vzeroupper
__memcpy_avx512_unaligned __memcpy_avx512_unaligned_erms
__memcpy_sse2_unaligned __memcpy_sse2_unaligned_erms __memcpy_erms
string/test-memcpy --direct 163.20s user 9.09s system 99% cpu 2:52.69 total
Why isn't string/test-mempcpy run-time almost unchanged?
--
H.J.
prev parent reply other threads:[~2021-11-11 16:49 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-11-10 23:50 Noah Goldstein
2021-11-11 2:02 ` H.J. Lu
2021-11-11 2:15 ` Noah Goldstein
2021-11-11 16:49 ` H.J. Lu [this message]
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='CAMe9rOqe-ZVYRNjU-ypcs5t1jSPN=foMGHxq7ie4kXnfQ5a1oA@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).