From: Andi Kleen <ak@suse.de>
To: Jamie Lokier <jamie@shareable.org>
Cc: linux-kernel@vger.kernel.org
Subject: Re: x86, ARM, PARISC, PPC, MIPS and Sparc folks please run this
Date: 29 Aug 2003 13:08:51 +0200 [thread overview]
Message-ID: <p733cfkpvp8.fsf@oldwotan.suse.de> (raw)
In-Reply-To: <20030829053510.GA12663@mail.jlokier.co.uk.suse.lists.linux.kernel>
Jamie Lokier <jamie@shareable.org> writes:
> I already got a surprise (to me): my Athlon MP is much slower
> accessing multiple mappings which are within 32k of each other, than
> mappings which are further apart, although it is coherent. The L1
Most x86 and probably most other modern CPUs have virtually addressed L1 caches.
It's just too slow to wait for the MMU for an L1 access which is really critical.
So such artifacts are expected
> data cache is 64k. (The explanation is easy: virtually indexed,
> physically tagged cache moves data among cache lines, possibly via L2).
On x86 L2 is usually physically tagged.
Mostly only ARM,MIPS et.al. have virtually tagged L2.
-Andi
next parent reply other threads:[~2003-08-29 11:08 UTC|newest]
Thread overview: 106+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20030829053510.GA12663@mail.jlokier.co.uk.suse.lists.linux.kernel>
2003-08-29 11:08 ` Andi Kleen [this message]
2003-08-29 11:17 ` x86, ARM, PARISC, PPC, MIPS and Sparc folks please run this Russell King
2003-09-01 5:03 ` Jamie Lokier
2003-08-29 5:35 Jamie Lokier
2003-08-29 10:03 ` J.A. Magallon
2003-08-29 10:36 ` Alan Cox
2003-09-01 4:49 ` Jamie Lokier
2003-08-29 10:04 ` Sergey S. Kostyliov
2003-08-29 10:15 ` J.A. Magallon
2003-08-29 10:21 ` J.A. Magallon
2003-08-29 10:34 ` CaT
2003-08-29 10:37 ` CaT
2003-08-29 10:49 ` Mikael Pettersson
2003-08-29 11:41 ` Gianni Tedesco
2003-08-29 11:51 ` James Morris
2003-08-29 15:41 ` Larry McVoy
2003-08-29 23:05 ` Mike Fedyk
2003-08-31 5:10 ` David S. Miller
2003-08-31 22:49 ` Jamie Lokier
2003-09-01 5:31 ` David S. Miller
2003-09-01 6:42 ` Jamie Lokier
2003-09-01 7:06 ` David S. Miller
2003-09-01 8:29 ` Jamie Lokier
2003-09-01 9:02 ` David S. Miller
2003-09-01 10:04 ` Jamie Lokier
2003-09-01 10:02 ` David S. Miller
2003-09-03 17:36 ` bill davidsen
2003-09-04 22:50 ` Jamie Lokier
2003-09-01 5:44 ` Jamie Lokier
2003-09-01 14:43 ` Larry McVoy
2003-09-01 16:33 ` Jamie Lokier
2003-09-01 16:58 ` Larry McVoy
2003-09-02 20:29 ` Jamie Lokier
2003-08-29 15:47 ` Herbert Poetzl
2003-08-30 1:48 ` Stuart Longland
2003-08-29 16:27 ` Geert Uytterhoeven
2003-09-01 5:58 ` Jamie Lokier
2003-09-01 8:34 ` Geert Uytterhoeven
2003-09-01 9:09 ` Kars de Jong
2003-09-01 10:08 ` Jamie Lokier
2003-09-01 11:13 ` Roman Zippel
2003-09-02 20:42 ` Kars de Jong
2003-09-02 21:39 ` Jamie Lokier
2003-09-03 7:59 ` Geert Uytterhoeven
2003-09-03 9:13 ` Jamie Lokier
2003-09-03 9:26 ` Geert Uytterhoeven
2003-09-03 12:17 ` Roman Zippel
2003-09-03 12:36 ` Geert Uytterhoeven
2003-09-03 13:29 ` Jamie Lokier
2003-09-03 16:07 ` Nagendra Singh Tomar
2003-09-04 5:03 ` Davide Libenzi
2003-09-03 18:03 ` Nagendra Singh Tomar
2003-09-04 6:38 ` Davide Libenzi
2003-09-04 11:19 ` Alan Cox
2003-09-05 21:24 ` Pavel Machek
2003-09-06 23:09 ` Jamie Lokier
2003-09-07 13:10 ` Pavel Machek
2003-09-07 13:35 ` Jamie Lokier
2003-09-07 13:40 ` Pavel Machek
2003-09-07 13:53 ` Jamie Lokier
2003-09-07 17:56 ` Alan Cox
2003-09-03 12:13 ` Jan-Benedict Glaw
2003-09-01 10:35 ` Sam Creasey
2003-09-01 10:48 ` Jamie Lokier
2003-09-01 12:23 ` Sam Creasey
2003-09-03 8:00 ` Kars de Jong
2003-09-03 8:05 ` Geert Uytterhoeven
2003-09-03 9:24 ` Kars de Jong
2003-08-29 16:31 ` Brian Jackson
2003-08-29 17:39 ` Matt Porter
2003-09-01 6:00 ` Jamie Lokier
2003-09-01 11:17 ` Alan Cox
2003-09-01 17:22 ` Roland Dreier
2003-09-02 2:16 ` Matt Porter
2003-09-02 5:40 ` Jamie Lokier
2003-08-29 19:37 ` Thorsten Kranzkowski
2003-08-29 20:03 ` Sean Neakums
2003-08-29 20:14 ` Iulian Musat
2003-08-29 20:26 ` Paul J.Y. Lahaie
2003-09-01 8:15 ` Russell King
2003-09-01 10:12 ` Jamie Lokier
2003-09-01 11:30 ` Geert Uytterhoeven
2003-09-01 14:17 ` Russell King
2003-09-01 14:51 ` Russell King
2003-09-01 19:09 ` Guennadi Liakhovetski
2003-09-01 16:52 ` Jamie Lokier
2003-09-01 17:11 ` Russell King
2003-09-02 5:34 ` Jamie Lokier
2003-09-02 8:15 ` Russell King
2003-09-02 11:57 ` Jamie Lokier
2003-09-02 18:52 ` Russell King
2003-09-02 23:59 ` Larry McVoy
2003-09-03 7:31 ` Russell King
2003-09-03 7:41 ` Jamie Lokier
2003-09-03 18:05 ` Russell King
2003-09-04 22:20 ` Jamie Lokier
2003-09-04 17:37 ` Maciej W. Rozycki
2003-08-29 22:35 ` Kenneth Johansson
2003-08-29 23:47 ` Kurt Wall
2003-09-01 0:24 ` Paul Mundt
2003-09-01 0:37 ` Jamie Lokier
2003-09-01 1:00 ` Paul Mundt
2003-09-01 1:58 ` Jamie Lokier
2003-09-01 1:13 ` dean gaudet
2003-09-01 4:29 ` Jamie Lokier
2003-09-02 10:08 ` Jan Rychter
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=p733cfkpvp8.fsf@oldwotan.suse.de \
--to=ak@suse.de \
--cc=jamie@shareable.org \
--cc=linux-kernel@vger.kernel.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