public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
From: "jv244 at cam dot ac dot uk" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/38306] [4.4/4.5 Regression] 15% slowdown w.r.t. 4.3 of computational kernel on some architectures
Date: Tue, 01 Sep 2009 09:13:00 -0000 [thread overview]
Message-ID: <20090901091339.25866.qmail@sourceware.org> (raw)
In-Reply-To: <bug-38306-6642@http.gcc.gnu.org/bugzilla/>
------- Comment #16 from jv244 at cam dot ac dot uk 2009-09-01 09:13 -------
(In reply to comment #15)
> Please try -O2 and -O2 -funroll-loops too, since -O3 is not always good for
> speed. (It would be even better if -O2 is not slower and you can find out what
> the culprit is at -O3; this is not necessarily possible though).
you're right that, without -fschedule-insns -O2 is faster than -O3 on this
case, but nothing comes close to 4.3 performance. adding '-fschedule-insns' to
the fastest -O2 choice makes it 20% slower.
All numbers with trunk:
-O2 -march=native -funroll-loops -ffast-math: 4.032
-O2 -march=native -funroll-loops -ffast-math -fschedule-insns: 4.712
-O3 -march=native -funroll-loops -ffast-math: 4.408
-O2 -march=native -ffast-math: 11.373
-O2 -march=native -ffast-math -fschedule-insns: 11.409
-O3 -march=native -ffast-math: 4.296
-O3 -march=native -ffast-math -fschedule-insns: 4.656
I can test other flags if you've a hint
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=38306
next prev parent reply other threads:[~2009-09-01 9:13 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-11-28 16:02 [Bug target/38306] New: [4.4 Regression] 15% slowdown of computational kernel jv244 at cam dot ac dot uk
2008-11-28 16:03 ` [Bug target/38306] " jv244 at cam dot ac dot uk
2008-11-28 16:25 ` pinskia at gcc dot gnu dot org
2008-11-30 11:40 ` rguenth at gcc dot gnu dot org
2008-11-30 11:49 ` rguenth at gcc dot gnu dot org
2008-11-30 16:18 ` jv244 at cam dot ac dot uk
2008-11-30 16:27 ` jv244 at cam dot ac dot uk
2008-11-30 16:40 ` rguenth at gcc dot gnu dot org
2008-12-03 19:04 ` [Bug target/38306] [4.4 Regression] 15% slowdown w.r.t. 4.3 of computational kernel on some architectures steven at gcc dot gnu dot org
2008-12-03 21:29 ` hjl dot tools at gmail dot com
2008-12-04 16:12 ` jv244 at cam dot ac dot uk
2008-12-05 12:18 ` rguenth at gcc dot gnu dot org
2008-12-06 15:38 ` steven at gcc dot gnu dot org
2008-12-06 18:56 ` jv244 at cam dot ac dot uk
2009-02-11 19:00 ` bonzini at gnu dot org
2009-02-11 19:25 ` jv244 at cam dot ac dot uk
2009-04-21 15:59 ` [Bug target/38306] [4.4/4.5 " jakub at gcc dot gnu dot org
2009-07-22 10:35 ` jakub at gcc dot gnu dot org
2009-09-01 6:56 ` jv244 at cam dot ac dot uk
2009-09-01 8:54 ` bonzini at gnu dot org
2009-09-01 9:13 ` jv244 at cam dot ac dot uk [this message]
2009-09-01 9:18 ` jv244 at cam dot ac dot uk
2009-10-15 12:50 ` jakub at gcc dot gnu dot org
2010-01-21 13:19 ` jakub at gcc dot gnu dot org
2010-04-30 9:00 ` [Bug target/38306] [4.4/4.5/4.6 " jakub at gcc dot gnu dot 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=20090901091339.25866.qmail@sourceware.org \
--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).