public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
From: "ubizjak at gmail dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug other/47167] Performance regression in numerical code
Date: Wed, 05 Jan 2011 19:50:00 -0000 [thread overview]
Message-ID: <bug-47167-4-3eYMURet6z@http.gcc.gnu.org/bugzilla/> (raw)
In-Reply-To: <bug-47167-4@http.gcc.gnu.org/bugzilla/>
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=47167
--- Comment #3 from Uros Bizjak <ubizjak at gmail dot com> 2011-01-05 19:30:49 UTC ---
> this could be the reason for slowdown.
Hm, not really.
But, by changing the generated assembly around loop entry:
$ diff -u testcase2.s testcase2_.s
--- testcase2.s 2011-01-05 20:21:01.492919294 +0100
+++ testcase2_.s 2011-01-05 20:22:23.616577277 +0100
@@ -1678,6 +1678,7 @@
addq %r15, %rdx
addq $1, %rdi
salq $5, %rdi
+ movapd %xmm10, %xmm0
jmp .L143
.p2align 4,,10
.p2align 3
@@ -1687,7 +1688,7 @@
mulpd %xmm2, %xmm6
movapd %xmm3, %xmm2
movapd %xmm10, (%rsi,%rcx)
- mulpd %xmm10, %xmm2
+ mulpd %xmm0, %xmm2
movsd (%rdx), %xmm0
movsd 8(%rdx), %xmm1
subpd %xmm6, %xmm2
The slowdown is magically fixed:
$ gcc -lm testcase2_.s
$ time ./a.out
real 0m4.041s
user 0m4.034s
sys 0m0.003s
versus:
$ gcc -lm testcase2.s
$ time ./a.out
real 0m4.239s
user 0m4.234s
sys 0m0.001s
The important change is the change of %xmm10 -> %xmm0 in the mulpd instruction.
The functionality of the test didn't change due to existing "movapd %xmm0,
%xmm10" at the top of the loop and added extra "movapd %xmm10, %xmm0" before
the loop.
This all happens on SnB, the code is generated with -O2 only.
H.J., any ideas?
next prev parent reply other threads:[~2011-01-05 19:31 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-01-04 14:45 [Bug other/47167] New: " martin@mpa-garching.mpg.de
2011-01-05 14:46 ` [Bug other/47167] " martin@mpa-garching.mpg.de
2011-01-05 17:38 ` ubizjak at gmail dot com
2011-01-05 19:50 ` ubizjak at gmail dot com [this message]
2011-01-05 20:09 ` ubizjak at gmail dot com
2011-01-05 22:14 ` hjl.tools at gmail dot com
2011-01-06 9:33 ` ubizjak at gmail dot com
2011-01-19 15:37 ` martin@mpa-garching.mpg.de
2011-01-19 16:32 ` rguenth at gcc dot gnu.org
2011-01-19 18:10 ` martin@mpa-garching.mpg.de
2011-01-20 10:41 ` rguenth at gcc dot gnu.org
2011-01-20 10:42 ` rguenth at gcc dot gnu.org
2011-01-20 10:43 ` 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-47167-4-3eYMURet6z@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).