From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <gcc-return-71428-listarch-gcc=gcc.gnu.org@gcc.gnu.org>
Received: (qmail 19449 invoked by alias); 4 Apr 2003 03:50:26 -0000
Mailing-List: contact gcc-help@gcc.gnu.org; run by ezmlm
Precedence: bulk
List-Archive: <http://gcc.gnu.org/ml/gcc/>
List-Post: <mailto:gcc@gcc.gnu.org>
List-Help: <http://gcc.gnu.org/ml/>
Sender: gcc-owner@gcc.gnu.org
Received: (qmail 19438 invoked from network); 4 Apr 2003 03:50:26 -0000
Received: from unknown (HELO egil.codesourcery.com) (66.92.14.122)
  by sources.redhat.com with SMTP; 4 Apr 2003 03:50:26 -0000
Received: from zack by egil.codesourcery.com with local (Exim 3.36 #1 (Debian))
	id 191IDh-0004GG-00; Thu, 03 Apr 2003 19:50:25 -0800
To: Kevin Atkinson <kevin@atkinson.dhs.org>
Cc: gcc@gcc.gnu.org
Subject: Re: Slow memcmp for aligned strings on Pentium 3
From: Zack Weinberg <zack@codesourcery.com>
Date: Fri, 04 Apr 2003 08:52:00 -0000
In-Reply-To: <Pine.LNX.4.44.0304031945240.912-200000@kevin-pc.atkinson.dhs.org> (Kevin
 Atkinson's message of "Thu, 03 Apr 2003 21:11:04 -0500 (EST)")
Message-ID: <87llyq9b0e.fsf@egil.codesourcery.com>
User-Agent: Gnus/5.090017 (Oort Gnus v0.17) Emacs/21.2 (gnu/linux)
References: <Pine.LNX.4.44.0304031945240.912-200000@kevin-pc.atkinson.dhs.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
X-SW-Source: 2003-04/txt/msg00171.txt.bz2

Kevin Atkinson <kevin@atkinson.dhs.org> writes:

> I was doing some tests with with memcmp and it seams that gcc 3.2.2 always
> uses cmps, even for aligned strings.
>
> I did some tests and discovered that using cmps was rather slow, compared 
> to a simple loop and then a bswap and subtract at the end.

Patches are welcome.

zw