LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Ingo Molnar <mingo@elte.hu>
To: Alexander van Heukelum <heukelum@fastmail.fm>
Cc: Alexander van Heukelum <heukelum@mailshack.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	"H. Peter Anvin" <hpa@zytor.com>,
	LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH] x86: Change x86 to use generic find_next_bit
Date: Mon, 10 Mar 2008 07:29:45 +0100	[thread overview]
Message-ID: <20080310062944.GA31542@elte.hu> (raw)
In-Reply-To: <1205097195.13205.1241421773@webmail.messagingengine.com>


* Alexander van Heukelum <heukelum@fastmail.fm> wrote:

> > ok, that's rather convincing.
> > 
> > the generic version in lib/find_next_bit.c is open-coded C which gcc 
> > can optimize pretty nicely.
> > 
> > the hand-coded assembly versions in arch/x86/lib/bitops_32.c mostly 
> > use the special x86 'bit search forward' (BSF) instruction - which i 
> > know from the days when the scheduler relied on it has some 
> > non-trivial setup costs. So especially when there's _small_ bitmasks 
> > involved, it's more expensive.
> 
> Hi,
> 
> BSF is fine, it doesn't need any special setup. [...]

under "setup costs" i mean cycles spent by the CPU itself - the 
instruction itself is simple (of course) and needs no setup. If you look 
at BSF performance you'll see that it has nontrivial overhead.

	Ingo

  reply	other threads:[~2008-03-10  6:30 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-03-09 20:01 Alexander van Heukelum
2008-03-09 20:10 ` Ingo Molnar
2008-03-09 21:03   ` Andi Kleen
2008-03-09 21:32     ` Andi Kleen
2008-03-09 21:13   ` Alexander van Heukelum
2008-03-10  6:29     ` Ingo Molnar [this message]
2008-03-09 20:11 ` Ingo Molnar
2008-03-09 20:31   ` Alexander van Heukelum
2008-03-09 20:51     ` Ingo Molnar
2008-03-09 21:29       ` Andi Kleen
2008-03-10 23:17       ` [RFC/PATCH] x86: Optimize find_next_(zero_)bit for small constant-size bitmaps Alexander van Heukelum
2008-03-11  9:56         ` Ingo Molnar
2008-03-11 15:17           ` [PATCH] " Alexander van Heukelum
2008-03-11 15:22             ` [RFC] non-x86: " Alexander van Heukelum
2008-03-11 15:23             ` [PATCH] x86: " Ingo Molnar
2008-03-09 20:28 ` [PATCH] x86: Change x86 to use generic find_next_bit Andi Kleen
2008-03-09 21:31 ` Andi Kleen
2008-03-13 12:44 ` Aneesh Kumar K.V
2008-03-13 14:27   ` Alexander van Heukelum

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=20080310062944.GA31542@elte.hu \
    --to=mingo@elte.hu \
    --cc=heukelum@fastmail.fm \
    --cc=heukelum@mailshack.com \
    --cc=hpa@zytor.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=tglx@linutronix.de \
    --subject='Re: [PATCH] x86: Change x86 to use generic find_next_bit' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).