From owner-cvs-src@FreeBSD.ORG  Wed Feb 14 12:49:38 2007
Return-Path: <owner-cvs-src@FreeBSD.ORG>
X-Original-To: cvs-src@freebsd.org
Delivered-To: cvs-src@freebsd.org
Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52])
	by hub.freebsd.org (Postfix) with ESMTP id 4115216A400
	for <cvs-src@freebsd.org>; Wed, 14 Feb 2007 12:49:38 +0000 (UTC)
	(envelope-from joerg@britannica.bec.de)
Received: from shell.asta.uni-rostock.de (gateway.stura.uni-rostock.de
	[139.30.252.67])
	by mx1.freebsd.org (Postfix) with ESMTP id 0331213C441
	for <cvs-src@freebsd.org>; Wed, 14 Feb 2007 12:49:37 +0000 (UTC)
	(envelope-from joerg@britannica.bec.de)
Received: from britannica.bec.de (unknown [192.168.16.3])
	by shell.asta.uni-rostock.de (Postfix) with ESMTP id 16C87187E
	for <cvs-src@freebsd.org>; Wed, 14 Feb 2007 12:25:44 +0000 (GMT)
Received: by britannica.bec.de (Postfix, from userid 1000)
	id E06A5B71E; Wed, 14 Feb 2007 13:25:41 +0100 (CET)
Date: Wed, 14 Feb 2007 13:25:41 +0100
From: Joerg Sonnenberger <joerg@britannica.bec.de>
To: cvs-src@freebsd.org
Message-ID: <20070214122541.GA193@britannica.bec.de>
References: <200702140521.l1E5LNQr044119@repoman.freebsd.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <200702140521.l1E5LNQr044119@repoman.freebsd.org>
User-Agent: Mutt/1.5.13 (2006-08-11)
Subject: Re: cvs commit: src/sys/sys systm.h
X-BeenThere: cvs-src@freebsd.org
X-Mailman-Version: 2.1.5
Precedence: list
List-Id: CVS commit messages for the src tree <cvs-src.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/listinfo/cvs-src>,
	<mailto:cvs-src-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/cvs-src>
List-Post: <mailto:cvs-src@freebsd.org>
List-Help: <mailto:cvs-src-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/cvs-src>,
	<mailto:cvs-src-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Wed, 14 Feb 2007 12:49:38 -0000

On Wed, Feb 14, 2007 at 05:21:23AM +0000, Colin Percival wrote:
>   Log:
>   Optimize bitcount32 by replacing 6 logical operations with 2.  The key
>   observation here is that it doesn't matter what garbage accumulates in
>   bits which we're going to end up masking away anyway, as long as the
>   garbage doesn't overflow into bits which we care about.

Three notes:
- The version I found uses 0x3f in the last mask.
- You might want to use __builtin_popcount for those GCC versions, which
support it.
- I found the table version to be faster on Intel, at least in the hot
case.

Joerg