From: anton@mips.complang.tuwien.ac.at (Anton Ertl)
To: linux-kernel@vger.kernel.org
Subject: Re: Page Colouring (was: 2.6.0 Huge pages not working as expected)
Date: Sun, 28 Dec 2003 17:17:34 GMT [thread overview]
Message-ID: <2003Dec28.181734@a0.complang.tuwien.ac.at> (raw)
In-Reply-To: <17tHK-3K6-21@gated-at.bofh.it>
Linus Torvalds <torvalds@osdl.org> writes:
>And you should realize that I do not dispute it because the applications
>themselves would run slower with cache coloring.
Ok, I guess I misunderstood that until now.
> Most applications don't
>much care,
Yes, at least as long as the associativity is high enough.
> they either fit in the cache, or the cache misses have random
>enough access patterns that cache layout doesn't much matter.
Random mapping hurts those applications most that do fit in the cache
in principle, but that have enough hot memory (whether accessed
regularly or randomly) that random mapping usually introduces cache
conflicts (this will happen for many applications with direct-mapped
caches, but hardly ever with high-associativity caches).
>And it has to be better on average on _everything_ that Linux supports,
>not just one particular braindamaged piece of hardware. I'm totally not
>interested in something that makes performance on most machines go down,
>if it then improves one or two braindead setups with direct-mapped caches.
As has been discussed in another thread, direct-mapped caches seem to
pretty standard for off-chip caches, and this is not just a
braindamage issue: Higher associativity requires more wires to the
tags, and also to the data, if you want to access the data in parallel
with the tags for lower latency. Running a lot of wires off-chip is a
problem. So the choices are:
- Small on-chip cache with high associativity.
- Medium cache with off-chip data, on-chip tags, high associativity
and high latency.
- Large cache with off-chip data and off-chip tags, and low
associativity.
However, over time off-chip caches seem to become less commonplace, so
we may get rid of low associativity for L2/L3 caches eventually.
- anton
--
M. Anton Ertl Some things have to be seen to be believed
anton@mips.complang.tuwien.ac.at Most things have to be believed to be seen
http://www.complang.tuwien.ac.at/anton/home.html
next prev parent reply other threads:[~2003-12-28 17:57 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <179fV-1iK-23@gated-at.bofh.it>
[not found] ` <179IS-1VD-13@gated-at.bofh.it>
2003-12-27 20:21 ` Anton Ertl
2003-12-27 20:56 ` Linus Torvalds
2003-12-27 23:31 ` Eric W. Biederman
2003-12-27 23:50 ` William Lee Irwin III
2003-12-28 1:09 ` David S. Miller
2003-12-28 4:53 ` Linus Torvalds
2003-12-28 16:39 ` William Lee Irwin III
2003-12-29 0:36 ` Mike Fedyk
2003-12-29 2:55 ` William Lee Irwin III
2003-12-29 4:09 ` Linus Torvalds
2003-12-29 6:52 ` William Lee Irwin III
2003-12-29 9:14 ` Linus Torvalds
2003-12-29 9:22 ` William Lee Irwin III
2003-12-29 9:33 ` Linus Torvalds
2003-12-29 10:23 ` William Lee Irwin III
2003-12-29 10:59 ` Mike Fedyk
2003-12-29 11:14 ` William Lee Irwin III
2003-12-30 2:00 ` Rusty Russell
2003-12-30 4:59 ` William Lee Irwin III
[not found] ` <20031229084304.GA31630@elte.hu>
2003-12-29 12:09 ` Ingo Molnar
2003-12-29 12:49 ` William Lee Irwin III
2003-12-29 20:02 ` Subpages (was: Page Colouring) Daniel Phillips
2003-12-29 20:15 ` Linus Torvalds
2003-12-29 21:11 ` Page Colouring (was: 2.6.0 Huge pages not working as expected) Eric W. Biederman
2003-12-29 21:35 ` Linus Torvalds
[not found] ` <17tHK-3K6-21@gated-at.bofh.it>
2003-12-28 17:17 ` Anton Ertl [this message]
[not found] <176UD-6vl-3@gated-at.bofh.it>
2003-12-26 21:48 ` Anton Ertl
2003-12-26 23:28 ` Linus Torvalds
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=2003Dec28.181734@a0.complang.tuwien.ac.at \
--to=anton@mips.complang.tuwien.ac.at \
--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
Powered by JetHome