public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
From: "hjl.tools at gmail dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/47000] Major performance regression in parallel SSE2 impl of SHA256 hash algorithm
Date: Sat, 18 Dec 2010 15:36:00 -0000 [thread overview]
Message-ID: <bug-47000-4-QzozDN04gv@http.gcc.gnu.org/bugzilla/> (raw)
In-Reply-To: <bug-47000-4@http.gcc.gnu.org/bugzilla/>
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=47000
H.J. Lu <hjl.tools at gmail dot com> changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |hubicka at gcc dot gnu.org
--- Comment #5 from H.J. Lu <hjl.tools at gmail dot com> 2010-12-18 15:36:30 UTC ---
(In reply to comment #3)
> Compiled like so:
> $ gcc-4.4.2 -S -O2 sha256_4way.i -o sha256_4way-44.s
> $ gcc-4.5.0 -S -O2 sha256_4way.i -o sha256_4way-45.s
>
> $ grep -c call *.s
> sha256_4way-44.s:0
> sha256_4way-45.s:484
> $ grep call *.s|head
> sha256_4way-45.s: call ROTR
> sha256_4way-45.s: call ROTR
> sha256_4way-45.s: call ROTR
> sha256_4way-45.s: call ROTR
> sha256_4way-45.s: call ROTR
> sha256_4way-45.s: call ROTR
> sha256_4way-45.s: call ROTR
> sha256_4way-45.s: call ROTR
> sha256_4way-45.s: call ROTR
> sha256_4way-45.s: call ROTR
> $
>
> ROTR should have been inlined:
>
> static inline __m128i ROTR(__m128i x, const int n) {
> return _mm_srli_epi32(x, n) | _mm_slli_epi32(x, 32 - n);
> }
>
> This probably explains the slowdown.
This is caused by revision 151511:
http://gcc.gnu.org/ml/gcc-cvs/2009-09/msg00257.html
next prev parent reply other threads:[~2010-12-18 15:36 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-12-18 7:46 [Bug c/47000] New: " jgarzik at pobox dot com
2010-12-18 7:48 ` [Bug c/47000] " jgarzik at pobox dot com
2010-12-18 12:27 ` [Bug target/47000] " steven at gcc dot gnu.org
2010-12-18 12:39 ` steven at gcc dot gnu.org
2010-12-18 12:49 ` steven at gcc dot gnu.org
2010-12-18 15:36 ` hjl.tools at gmail dot com [this message]
2010-12-18 15:41 ` hjl.tools at gmail dot com
2010-12-18 15:43 ` hjl.tools at gmail dot com
2010-12-18 16:04 ` hjl.tools at gmail dot com
2010-12-18 18:24 ` jgarzik at pobox dot com
2010-12-18 18:49 ` jgarzik at pobox dot com
2010-12-18 19:08 ` jgarzik at pobox dot com
2010-12-18 19:09 ` jgarzik at pobox dot com
2010-12-18 19:21 ` steven at gcc dot gnu.org
2010-12-18 19:35 ` [Bug target/47000] [4.5 Regression] Failure to inline SSE intrinsics hjl.tools at gmail dot com
2010-12-18 19:39 ` hjl.tools at gmail dot com
2010-12-18 20:26 ` jakub at gcc dot gnu.org
2010-12-18 21:15 ` jgarzik at pobox dot com
2010-12-18 21:16 ` jgarzik at pobox dot com
2010-12-18 21:17 ` jgarzik at pobox dot com
2010-12-18 21:26 ` jgarzik at pobox dot com
2010-12-19 11:50 ` hubicka at ucw dot cz
2010-12-19 11:53 ` hubicka at gcc dot gnu.org
2010-12-19 11:58 ` hubicka at gcc dot gnu.org
2010-12-20 8:32 ` jakub at gcc dot gnu.org
2010-12-21 10:31 ` hubicka at gcc dot gnu.org
2010-12-21 10:39 ` hubicka at gcc dot gnu.org
2010-12-28 14:57 ` rguenth at gcc dot gnu.org
2011-03-08 13:20 ` rguenth at gcc dot gnu.org
2011-04-28 15:28 ` rguenth at gcc dot gnu.org
2012-07-02 10:28 ` rguenth at gcc dot gnu.org
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=bug-47000-4-QzozDN04gv@http.gcc.gnu.org/bugzilla/ \
--to=gcc-bugzilla@gcc.gnu.org \
--cc=gcc-bugs@gcc.gnu.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).