From: Andi Kleen <ak@suse.de>
To: Mark Mitchell <mark@codesourcery.com>
Cc: gcc@gcc.gnu.org
Subject: Re: GCSE store motion
Date: Thu, 16 May 2002 11:42:00 -0000 [thread overview]
Message-ID: <p73bsbgymfr.fsf@oldwotan.suse.de> (raw)
In-Reply-To: Mark Mitchell's message of "16 May 2002 16:59:22 +0200"
Mark Mitchell <mark@codesourcery.com> writes:
>
> My point is that I can well imagine the compiler spending 10% of its time
> on software pipelining for scientific code, but that would seem highly
> out of whack on code like that in GCC.
I just did an full profile of an gcc 3.1 bootstrap. The top offender
(~5%) is ggc_alloc in ggc-page where I suspect the bitmap scanning loop
eats most of the CPU time. If software pipelining of that single simple loop
cut off some of the 5% then it would surely be noticeable in gcc bootstrap
times :-)
-Andi
next parent reply other threads:[~2002-05-16 18:31 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20020516114838.949B6F28C9@nile.gnat.com.suse.lists.egcs>
[not found] ` <164620000.1021559673@gandalf.codesourcery.com.suse.lists.egcs>
2002-05-16 11:42 ` Andi Kleen [this message]
2002-05-16 8:29 Robert Dewar
-- strict thread matches above, loose matches on Subject: below --
2002-05-16 5:36 Robert Dewar
2002-05-16 5:30 Robert Dewar
2002-05-16 7:59 ` Mark Mitchell
2002-05-16 8:31 ` Daniel Berlin
2002-05-15 13:56 Robert Dewar
2002-05-15 14:06 ` Gabriel Dos Reis
2002-05-15 15:09 ` Toon Moene
2002-05-15 15:20 ` Dale Johannesen
2002-05-15 12:45 Robert Dewar
2002-05-15 12:56 ` Mark Mitchell
2002-05-15 13:29 ` Daniel Berlin
2002-05-15 9:07 Roger Sayle
2002-05-15 9:21 ` Daniel Berlin
2002-05-15 9:53 ` Daniel Berlin
2002-05-15 10:05 ` Roger Sayle
2002-05-15 10:09 ` Daniel Berlin
2002-05-15 10:21 ` Jakub Jelinek
2002-05-15 10:31 ` Mark Mitchell
2002-05-15 11:56 ` law
2002-05-15 11:05 ` Kevin Handy
2002-05-15 11:50 ` Janis Johnson
2002-05-15 11:54 ` law
2002-05-15 9:58 ` Roger Sayle
2002-05-15 10:06 ` Daniel Berlin
2002-05-15 10:15 ` David Edelsohn
2002-05-15 11:56 ` law
2002-05-15 12:07 ` Mark Mitchell
2002-05-15 10:18 ` Roger Sayle
2002-05-15 10:32 ` David Edelsohn
2002-05-16 1:51 ` Jan Hubicka
2002-05-16 9:59 ` Daniel Berlin
2002-05-15 10:02 ` Mark Mitchell
2002-05-15 10:08 ` Roger Sayle
2002-05-15 10:14 ` Mark Mitchell
2002-05-15 10:41 ` Roger Sayle
2002-05-15 11:56 ` law
2002-05-15 12:07 ` Mark Mitchell
2002-05-15 13:48 ` Toon Moene
2002-05-16 13:50 ` law
2002-05-17 15:03 ` Tim Hollebeek
2002-05-16 13:53 ` law
2002-05-16 14:44 ` Daniel Berlin
2002-05-16 21:12 ` Eric Christopher
2002-05-15 12:32 ` law
2002-05-14 23:27 David S. Miller
2002-05-14 23:33 ` Daniel Berlin
2002-05-15 0:03 ` David S. Miller
2002-05-15 0:41 ` Daniel Berlin
2002-05-15 1:27 ` Jan Hubicka
2002-05-15 1:22 ` Mark Mitchell
2002-05-15 1:29 ` David S. Miller
2002-05-15 1:32 ` Mark Mitchell
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=p73bsbgymfr.fsf@oldwotan.suse.de \
--to=ak@suse.de \
--cc=gcc@gcc.gnu.org \
--cc=mark@codesourcery.com \
/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).