From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-gx0-f21.google.com (mail-gx0-f21.google.com [209.85.217.21]) by ozlabs.org (Postfix) with ESMTP id 2576FDE1B1 for ; Fri, 5 Sep 2008 01:14:12 +1000 (EST) Received: by gxk14 with SMTP id 14so6342711gxk.9 for ; Thu, 04 Sep 2008 08:14:11 -0700 (PDT) Message-ID: Date: Thu, 4 Sep 2008 17:14:11 +0200 From: "Gunnar Von Boehn" To: munroesj@us.ibm.com Subject: Re: Efficient memcpy()/memmove() for G2/G3 cores... In-Reply-To: <1220538673.28869.261.camel@spokane1.rchland.ibm.com> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 References: <200808251131.02071.david.jander@protonic.nl> <200809041405.16489.david.jander@protonic.nl> <20080904121926.GA12867@yoda.jdub.homelinux.org> <200809041459.27606.david.jander@protonic.nl> <1220538673.28869.261.camel@spokane1.rchland.ibm.com> Cc: David Jander , John Rigby , linuxppc-dev@ozlabs.org, Paul Mackerras , prodyut hazarika List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Hi Steve, > I have personally optimized memcpy for power4/5/6 and they are all > different. There are dozens of different PPC implementations from > different manufacturers and design, every one is different! With painful > negotiation I was able to get the --with-cpu= framework added to glibc > but not all distro use it. You can thank me later Steve, you make it sound like very many different PowerPC chips: You said you did the Power 4, Power 5 , Power 6 and now Power 7 routines. And there are the 970 and the Cell. While this sounds like 7 different PPC chips. But aren't this actually only 2 main families? Wouldn't it be possible to create two main routine to cover all? One type that performs good on the family of Power4/5 and 7. And one that performs good on the family of P6 and Cell? How are the Linux hackers handling this? Maybe there is room for consolidating? Cheers Gunnar