public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Arjan van de Ven <arjan@infradead.org>
To: Linus Torvalds <torvalds@osdl.org>
Cc: Andrew Morton <akpm@osdl.org>,
	Chuck Ebbert <76306.1226@compuserve.com>,
	linux-kernel@vger.kernel.org
Subject: Re: [patch 2.6.13-rc3a] i386: inline restore_fpu
Date: Fri, 22 Jul 2005 07:23:32 -0400	[thread overview]
Message-ID: <1122031412.3577.27.camel@localhost.localdomain> (raw)
In-Reply-To: <Pine.LNX.4.58.0507212211400.6074@g5.osdl.org>


> > We do have the `used_math' optimisation in there which attempts to avoid
> > doing the FP save/restore if the app isn't actually using math.
> 
> No, it's more than that. There's a per-processor "used_math" flag to
> determine if we need to _initialize_ the FPU, but on context switches we 
> always assume the program we're switching to will _not_ use FP, and we 
> just set the "fault on FP" flag and do not normally restore FP state.

This shows room for optimization; if an app is consistently faulting to
use FP after a context switch, in principle the kernel could start to
assume that it will in the next timeslice as well.


> On the other hand, I also wouldn't be surprised if glibc (or similar

I doubt glibc is normally, at least most distros don't ship an SSE
enabled glibc, only an "i686" one.



  reply	other threads:[~2005-07-22 11:23 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-07-22  3:06 [patch 2.6.13-rc3a] i386: inline restore_fpu Chuck Ebbert
2005-07-22  3:27 ` Andrew Morton
2005-07-22  5:22   ` Linus Torvalds
2005-07-22 11:23     ` Arjan van de Ven [this message]
2005-07-22  8:14 ` Adrian Bunk
2005-07-22 18:13   ` Linus Torvalds
2005-07-25 19:26     ` Bill Davidsen
2005-07-22 23:19 ` Linus Torvalds
  -- strict thread matches above, loose matches on Subject: below --
2005-07-22  9:58 Chuck Ebbert
2005-07-23  7:09 Chuck Ebbert
2005-07-23 17:38 ` Linus Torvalds
2005-07-23 17:46   ` Arjan van de Ven
2005-07-23 18:02     ` Linus Torvalds
2005-07-23  7:09 Chuck Ebbert
2005-07-23 17:33 ` Linus Torvalds
     [not found] <200507212309_MC3-1-A534-95EF@compuserve.com.suse.lists.linux.kernel>
     [not found] ` <20050722132756.578acca7.akpm@osdl.org.suse.lists.linux.kernel>
2005-07-23 15:35   ` Andi Kleen
2005-07-24 12:56 Kenneth Parrish
2005-07-25  2:34 Kenneth Parrish
2005-07-26 21:23 Chuck Ebbert
2005-07-26 21:23 Chuck Ebbert
2005-07-26 21:47 ` Linus Torvalds
2005-07-27  1:40 linux

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=1122031412.3577.27.camel@localhost.localdomain \
    --to=arjan@infradead.org \
    --cc=76306.1226@compuserve.com \
    --cc=akpm@osdl.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=torvalds@osdl.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