From: linas@austin.ibm.com (Linas Vepstas)
To: Matt Sealey <matt@genesi-usa.com>
Cc: 'linuxppc-dev list' <linuxppc-dev@ozlabs.org>,
'Paul Mackerras' <paulus@samba.org>
Subject: Re: AltiVec in the kernel
Date: Thu, 20 Jul 2006 12:42:55 -0500 [thread overview]
Message-ID: <20060720174255.GP5905@austin.ibm.com> (raw)
In-Reply-To: <001301c6abf8$73d780e0$99dfdfdf@bakuhatsu.net>
On Thu, Jul 20, 2006 at 07:31:32AM -0500, Matt Sealey wrote:
>
> What's the case in the kernel for the memcpy functions etc., are
> they optimized for doing things like longword copies rather than
> byte-per-byte etc.?
arch/powerpc/lib/copy_32.S
arch/powerpc/lib/memcpy_64.S
Looks pretty darned optimized to me.
> We found glibc sucked for that.
Only because someone was asleep at the wheel, or there was a bug.
When glibc gets ported to a new architecture, one of the earliest
tasks is to create optimized versions of memcpy and the like.
Presumably, on powerpc, this would have been done more than a
decade ago; its hard for me to imagine that there'd be a problem
there. Now, I haven't looked at the code, but I just can't imagine
how this would not have been found and fixed by now. Is there
really a problem wiht glibc performance on powerpc? I mean,
this is a pretty serious accusation, and something that should
be fixed asap.
--linas
next prev parent reply other threads:[~2006-07-20 17:43 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-07-18 12:48 AltiVec in the kernel Matt Sealey
2006-07-18 13:53 ` Kumar Gala
2006-07-18 15:10 ` Matt Sealey
2006-07-18 17:56 ` Paul Mackerras
2006-07-19 18:10 ` Linas Vepstas
2006-07-19 18:19 ` Paul Mackerras
2006-07-19 18:38 ` Johannes Berg
2006-07-19 18:57 ` Linas Vepstas
2006-07-20 12:31 ` Matt Sealey
2006-07-20 13:23 ` Kumar Gala
2006-07-20 13:33 ` Matt Sealey
2006-07-20 17:42 ` Linas Vepstas [this message]
2006-07-20 18:47 ` Brian D. Carlstrom
2006-07-20 19:05 ` Olof Johansson
2006-07-20 21:56 ` Brian D. Carlstrom
2006-07-20 22:39 ` Daniel Ostrow
2006-07-21 6:35 ` Olof Johansson
2006-07-21 14:42 ` Matt Sealey
2006-07-21 16:51 ` Linas Vepstas
2006-07-21 18:08 ` Matt Sealey
2006-07-22 3:09 ` Segher Boessenkool
2006-07-23 13:28 ` Matt Sealey
2006-07-23 21:37 ` Benjamin Herrenschmidt
2006-07-21 18:46 ` Brian D. Carlstrom
2006-07-21 21:30 ` Hollis Blanchard
2006-07-21 22:21 ` Peter Bergner
2006-07-18 18:39 ` Benjamin Herrenschmidt
2006-07-18 17:43 ` Paul Mackerras
-- strict thread matches above, loose matches on Subject: below --
2009-12-11 11:45 Simon Richter
2009-12-11 15:49 ` Arnd Bergmann
2009-12-16 22:11 ` Sebastian Andrzej Siewior
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=20060720174255.GP5905@austin.ibm.com \
--to=linas@austin.ibm.com \
--cc=linuxppc-dev@ozlabs.org \
--cc=matt@genesi-usa.com \
--cc=paulus@samba.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.