All of lore.kernel.org
 help / color / mirror / Atom feed
From: Brian Gerst <bgerst@didntduck.org>
To: Manfred Spraul <manfred@colorfullife.com>
Cc: linux-kernel@vger.kernel.org, arjanv@redhat.com
Subject: Re: [CFT] faster athlon/duron memory copy implementation
Date: Thu, 24 Oct 2002 15:19:56 -0400	[thread overview]
Message-ID: <3DB847DC.4090601@didntduck.org> (raw)
In-Reply-To: 3DB82ABF.8030706@colorfullife.com

Manfred Spraul wrote:
> AMD recommends to perform memory copies with backward read operations 
> instead of prefetch.
> 
> http://208.15.46.63/events/gdc2002.htm
> 
> Attached is a test app that compares several memory copy implementations.
> Could you run it and report the results to me, together with cpu, 
> chipset and memory type?
> 
> Please run 2 or 3 times.
> 

Athlon XP 1600+ (1400 MHz)
512 MB PC-133 memory
Host bridge: VIA Technologies, Inc. VT8363/8365 [KT133/KM133] (rev 03)

processor       : 0
vendor_id       : AuthenticAMD
cpu family      : 6
model           : 6
model name      : AMD Athlon(tm) Processor
stepping        : 2
cpu MHz         : 1410.668
cache size      : 256 KB

copy_page() tests
copy_page function 'warm up run'         took 21428 cycles per page
copy_page function '2.4 non MMX'         took 22404 cycles per page
copy_page function '2.4 MMX fallback'    took 22426 cycles per page
copy_page function '2.4 MMX version'     took 21472 cycles per page
copy_page function 'faster_copy'         took 13618 cycles per page
copy_page function 'even_faster'         took 13284 cycles per page
copy_page function 'no_prefetch'         took 11943 cycles per page

copy_page() tests
copy_page function 'warm up run'         took 21640 cycles per page
copy_page function '2.4 non MMX'         took 22865 cycles per page
copy_page function '2.4 MMX fallback'    took 22843 cycles per page
copy_page function '2.4 MMX version'     took 21597 cycles per page
copy_page function 'faster_copy'         took 13751 cycles per page
copy_page function 'even_faster'         took 13407 cycles per page
copy_page function 'no_prefetch'         took 11952 cycles per page

copy_page() tests
copy_page function 'warm up run'         took 21681 cycles per page
copy_page function '2.4 non MMX'         took 22900 cycles per page
copy_page function '2.4 MMX fallback'    took 22999 cycles per page
copy_page function '2.4 MMX version'     took 21679 cycles per page
copy_page function 'faster_copy'         took 13782 cycles per page
copy_page function 'even_faster'         took 13481 cycles per page
copy_page function 'no_prefetch'         took 11969 cycles per page




  parent reply	other threads:[~2002-10-24 19:13 UTC|newest]

Thread overview: 51+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2002-10-24 17:15 [CFT] faster athlon/duron memory copy implementation Manfred Spraul
2002-10-24 17:37 ` Robert Love
2002-10-24 18:05   ` Zach Brown
2002-10-24 17:41 ` Andreas Steinmetz
2002-10-24 17:48 ` Matthias Welk
2002-10-24 19:01   ` erich
2002-10-24 19:11     ` Arjan van de Ven
2002-10-24 19:38     ` Manfred Spraul
2002-10-25  0:59       ` Panagiotis Papadakos
2002-10-24 17:53 ` Roger Luethi
2002-10-24 18:10 ` Daniel Egger
2002-10-24 19:15   ` Florin Iucha
2002-10-24 19:28   ` Manfred Spraul
2002-10-24 19:38     ` Dave Jones
2002-10-24 19:43     ` Ken Witherow
2002-10-25 13:08     ` Daniel Egger
2002-10-24 18:17 ` Eric Lammerts
2002-10-24 18:26 ` David Rees
2002-10-24 18:35 ` Josh McKinney
2002-10-24 18:36 ` Dave Jones
2002-10-24 18:43 ` Simon Fowler
2002-10-24 18:50   ` Simon Fowler
2002-10-24 18:56   ` Dave Jones
2002-10-24 18:48 ` Ernst Herzberg
2002-10-24 20:09   ` Ed Sweetman
2002-10-24 20:13     ` Robert Love
2002-10-24 20:31       ` Ed Sweetman
2002-10-24 20:49         ` Dave Jones
2002-10-24 20:26     ` Dave Jones
2002-10-25  9:19       ` Måns Rullgård
2002-10-24 19:11 ` Marcus Libäck
2002-10-24 19:19 ` Brian Gerst [this message]
2002-10-24 19:31 ` Matthias Schniedermeyer
2002-10-24 19:33 ` Pascal Schmidt
2002-10-24 19:39 ` Olaf Dietsche
2002-10-24 20:27 ` Mike Civil
2002-10-24 20:44 ` Willy TARREAU
2002-10-24 21:46 ` Josh Fryman
2002-10-24 22:18 ` Tim Schmielau
2002-10-24 23:09 ` Hirokazu Takahashi
2002-10-24 23:37 ` Ryan Cumming
2002-10-25  0:10 ` Matthias Andree
2002-10-25  8:35 ` venom
2002-10-25 13:31 ` Denis Vlasenko
2002-10-26 12:11 ` Jurjen Oskam
  -- strict thread matches above, loose matches on Subject: below --
2002-10-24 18:27 Shawn Starr
2002-10-24 20:51 Dieter Nützel
2002-10-24 21:01 ` Dieter Nützel
2002-10-24 21:16 ` Willy TARREAU
2002-10-24 22:01 Harm Verhagen
2002-10-25 16:29 Jorge Bernal "Koke"

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=3DB847DC.4090601@didntduck.org \
    --to=bgerst@didntduck.org \
    --cc=arjanv@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=manfred@colorfullife.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 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.