public inbox for gentoo-amd64@lists.gentoo.org
 help / color / mirror / Atom feed
From: Jeremy Huddleston <eradicator@gentoo.org>
To: gentoo-amd64@lists.gentoo.org
Cc: simon.strandman@telia.com
Subject: Re: [gentoo-amd64] x86_64 optimization patches for glibc.
Date: Mon, 25 Jul 2005 13:08:01 -0700	[thread overview]
Message-ID: <1122322081.12747.5.camel@cloud.outersquare.org> (raw)
In-Reply-To: <42E258A7.5080501@telia.com>

[-- Attachment #1: Type: text/plain, Size: 2210 bytes --]

Hey,  I just finished reading through this thread.  I'm not as good
keeping up on the lists as I should be.

BUT... This sounds promising.  Unfortunately you send the email just
after I unmasked 2.3.5-r1, so it's not going to get in there, but it
could get into the next release with further testing.  Can you post both
patches to the bug, and I'll try to take care of getting the libm patch
to apply if nobody beats me to it.  Also be sure to report back the bug
number, so folks here can follow it too.

Thanks,
Jeremy

On Sat, 2005-07-23 at 16:48 +0200, Simon Strandman wrote:
> Hi!
> 
> Some binary distros like Mandrake and suse patches their glibcs with 
> x86_64 optimized strings and an x86_64 optimized libm to improve 
> performance.
> 
> I tried extracting those patches from an mandrake SRPM and add them to 
> the glibc 2.3.5 ebuild. The x86_64 optimized strings patch built and 
> worked perfectly and gave a large speedup as you can see below. But I 
> couldn't get glibc to build with the libm patch because of unresolved 
> symbols (and I'm no programmer so I have no idea how to fix that).
> 
> I found a small C program on a suse mailing-list to measure glibc memory 
> copy performance:
> http://lists.suse.com/archive/suse-amd64/2005-Mar/0220.html
> 
> With the glibc 2.3.5 currently in gentoo I get:
> isidor ~ # ./memcpy 2200 1000 1048576
> Memory to memory copy rate = 1291.600098 MBytes / sec. Block size = 1048576.
> 
> But with glibc 2.3.5 + amd64 optimized strings I get:
> isidor ~ # ./memcpy 2200 1000 1048576
> Memory to memory copy rate = 2389.321777 MBytes / sec. Block size = 1048576.
> 
> That's an improvement of over 1000mb/s! Suse 9.3 also gives about 
> 2300mb/s out of the box.
> 
> How about adding these patches to gentoo? Perhaps in glibc 2.3.5-r1 
> before it leaves package.mask? I'll create a bugreport about it if you 
> agree!
> 
> This .tar.bz2 contains the glibc directory from my overlay with the 
> mandrake patches included in files/mdk, but the libm patches are 
> commented out in the ebuild.
> http://snigel.no-ip.com/~nxsty/linux/glibc.tar.bz2
> 
> -- 
> Simon Strandman <simon.strandman@telia.com>


[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 189 bytes --]

  parent reply	other threads:[~2005-07-25 20:10 UTC|newest]

Thread overview: 50+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-07-23 14:48 [gentoo-amd64] x86_64 optimization patches for glibc Simon Strandman
2005-07-23 16:36 ` Allan Wang
2005-07-23 17:08   ` Simon Strandman
2005-07-23 17:30     ` Allan Wang
2005-07-23 18:11       ` Jared Lindsay
2005-07-23 18:19         ` Allan Wang
2005-07-27 10:09     ` netpython
2005-07-27 16:11       ` [gentoo-amd64] " Duncan
2005-07-23 18:44   ` [gentoo-amd64] " Brian Litzinger
2005-07-25 22:24     ` Luke-Jr
2005-07-25 22:38       ` Olivier Crete
2005-07-26 15:40         ` Luke-Jr
2005-07-26 16:50           ` [gentoo-amd64] " Duncan
2005-07-26 17:02             ` Raffaele BELARDI
2005-07-26 17:49               ` Michael Edwards
2005-07-26 18:42                 ` [gentoo-amd64] " Duncan
2005-07-27  0:05             ` [gentoo-amd64] " Sami Samhuri
2005-07-27  2:50             ` Matt Randolph
2005-07-26  2:54       ` [gentoo-amd64] " Brian Litzinger
2005-07-23 16:39 ` Sean Johnson
2005-07-23 22:15 ` Matt Randolph
2005-07-23 22:36   ` Matt Randolph
2005-07-24  1:47     ` Sean Johnson
2005-07-24  3:36       ` Matt Randolph
2005-07-24  5:36         ` Ian McCulloch
2005-07-24  7:42           ` Jared Lindsay
2005-07-24 14:35             ` Simon Strandman
2005-07-24 18:13               ` Jared Lindsay
2005-07-25 20:08 ` Jeremy Huddleston [this message]
2005-07-25 21:34   ` Simon Strandman
2005-07-25 22:00     ` Jared Lindsay
2005-07-31 14:24     ` [gentoo-amd64] " Duncan
2005-07-31 14:56       ` Brian Hall
2005-07-31 16:23         ` [gentoo-amd64] " Duncan
2005-07-31 17:42           ` Ben Skeggs
2005-07-31 18:46             ` Jared Lindsay
2005-07-31 18:52               ` Nuitari
2005-08-01 13:51             ` [gentoo-amd64] " Duncan
2005-07-31 19:21       ` [gentoo-amd64] " Simon Strandman
2005-08-01  9:04       ` Jan Jitse Venselaar
2005-08-01 13:45         ` [gentoo-amd64] " Duncan
2005-08-01 17:03           ` Karol Krizka
2005-08-02 10:21             ` [gentoo-amd64] " Duncan
2005-08-02 19:41               ` Matt Randolph
2005-08-02 23:27                 ` [gentoo-amd64] hijacked! :) television (was: x86_64 optimization patches for glibc.) Sami Samhuri
2005-08-04  2:28                   ` Luke-Jr
2005-08-05  0:28                     ` Sami Samhuri
2005-08-05  7:43                       ` Arm Suwarnaratana
2005-08-09 10:29         ` [gentoo-amd64] Re: x86_64 optimization patches for glibc Simon Strandman
2005-07-26 17:40 ` [gentoo-amd64] " ardour

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=1122322081.12747.5.camel@cloud.outersquare.org \
    --to=eradicator@gentoo.org \
    --cc=gentoo-amd64@lists.gentoo.org \
    --cc=simon.strandman@telia.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