From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <gcc-return-50704-listarch-gcc=gcc.gnu.org@gcc.gnu.org>
Received: (qmail 27100 invoked by alias); 25 Apr 2002 22:39:01 -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 27033 invoked from network); 25 Apr 2002 22:38:59 -0000
Received: from unknown (HELO hermod.ee.princeton.edu) (128.112.48.183)
  by sources.redhat.com with SMTP; 25 Apr 2002 22:38:59 -0000
Received: from ivy.ee.princeton.edu (daemon@ivy.ee.princeton.edu [128.112.48.185])
	by hermod.ee.princeton.edu (8.11.6/8.11.6) with ESMTP id g3PMcwq27785;
	Thu, 25 Apr 2002 18:38:58 -0400 (EDT)
Received: (from wqin@localhost)
	by ivy.ee.princeton.edu (8.11.6/8.11.6) id g3PMcuR07715;
	Thu, 25 Apr 2002 18:38:56 -0400 (EDT)
Date: Thu, 25 Apr 2002 15:47:00 -0000
From: Wei Qin <wqin@EE.Princeton.EDU>
To: Richard Henderson <rth@redhat.com>
cc: gcc <gcc@gcc.gnu.org>, gcc-help <gcc-help@gcc.gnu.org>
Subject: Re: Number of 1's in 64 bit number...[don't read if not interested
 in          algos/math...]
In-Reply-To: <20020425151327.A2527@redhat.com>
Message-ID: <Pine.SOL.4.43.0204251824110.27320-100000@ivy.ee.princeton.edu>
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
X-SW-Source: 2002-04/txt/msg01356.txt.bz2


We ran the popcount 10 million times to get the time. So cache is
hot. But we care about speed only when we have to run it a lot of times.
So for speed sensitive application, I would choose to use table
lookup. It's just 256 bytes anyway.

Wei

On Thu, 25 Apr 2002, Richard Henderson wrote:

> On Thu, Apr 25, 2002 at 03:12:07PM -0400, Wei Qin wrote:
> > On a x86 linux platform, it takes 80% more time than the table lookup one.
>
> On hot cache, maybe.  On cold cache the arithmetic will
> definitely be faster.
>
>
> r~
>