From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from lists.gentoo.org ([140.105.134.102] helo=robin.gentoo.org) by nuthatch.gentoo.org with esmtp (Exim 4.62) (envelope-from ) id 1HrdIc-0005gH-An for garchives@archives.gentoo.org; Fri, 25 May 2007 17:09:58 +0000 Received: from robin.gentoo.org (localhost [127.0.0.1]) by robin.gentoo.org (8.14.0/8.14.0) with SMTP id l4PH8anD021006; Fri, 25 May 2007 17:08:36 GMT Received: from an-out-0708.google.com (an-out-0708.google.com [209.85.132.240]) by robin.gentoo.org (8.14.0/8.14.0) with ESMTP id l4PH3dTt015273 for ; Fri, 25 May 2007 17:03:41 GMT Received: by an-out-0708.google.com with SMTP id c8so254289ana for ; Fri, 25 May 2007 10:03:38 -0700 (PDT) DKIM-Signature: a=rsa-sha1; c=relaxed/relaxed; d=gmail.com; s=beta; h=domainkey-signature:received:received:message-id:date:from:to:subject:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=acTdCNAC0ggDlTwQT2egnQSoIMpLJMM7gBCBZc6wKg5VLyIGi4yb71vUnc/CcxZsoLY4IjH89UsCeYqhFeo4Nhr1Gwm1krZrmDpGf4MVoqqAClKCb5mDSNCXjo/PEVjjDSQu5CnFaJKQjs1hDcTMLGaYx3joQUcus25qDyLvF7k= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=beta; h=received:message-id:date:from:to:subject:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=kgaer6OruIYboEgKIOY5plnGMrnceesQDzPVYfawpgrCQSQc1pTjw9D1DqflAPBSwHUF1qzZjGYNe/M1SGG/EazheJKngJYfDVGrh75wjNt+ivvO8w74v/r3jAB/EGAHnyXl7IEmONCokVlCcA6EQ6CQ6XPs3LeulUNzO+bopzA= Received: by 10.100.9.19 with SMTP id 19mr2887914ani.1180112617956; Fri, 25 May 2007 10:03:37 -0700 (PDT) Received: by 10.100.153.9 with HTTP; Fri, 25 May 2007 10:03:37 -0700 (PDT) Message-ID: <72bdee2f0705251003g5075c767pff4252bc9ed28638@mail.gmail.com> Date: Fri, 25 May 2007 19:03:37 +0200 From: "Andreas Claesson" To: gentoo-user@lists.gentoo.org Subject: Re: [gentoo-user] which -march flag to pick for Intel Core 2 Duo in make.conf? In-Reply-To: Precedence: bulk List-Post: List-Help: List-Unsubscribe: List-Subscribe: List-Id: Gentoo Linux mail X-BeenThere: gentoo-user@gentoo.org Reply-to: gentoo-user@lists.gentoo.org MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline References: X-Archives-Salt: 19f63aed-b9fa-47f4-b9f7-3ae2db6e6fc0 X-Archives-Hash: c9e35e6d4e45da6d0fb7b689806dbef8 On 5/25/07, burlingk@cv63.navy.mil wrote: > > > -----Original Message----- > > From: Randy Barlow [mailto:randy@electronsweatshop.com] > > > > > If you are using a lot of memory in your computations, then > > the 64-bit environment will be much friendlier to you :) > > Also, if I understand correctly, you will get higher > > precision on floating point calculations (someone correct me > > if I am wrong here!) I also believe that the 64 bit > > processors are able to perform more instructions per second > > on average when executing 64 bit code vs. 32 bit code if I am > > not mistaken... > > I am not sure, but that makes sense. If nothing else, things executed > directly usually run more smoothly than those who are run through > emulation. 64bit code on 64bit processor good... There is no emulation involved when running 32bit code in either core2 nor amd64 processors. The difference when running in 32bit mode is that some instructions are unavailable, you have a smaller number of registers, and the registers are only 32bit. More registers speed up most kind of code, 64bit registers speed up 64bit calculations, and the extra instructions are good for array calculations and similar (more sse instructions for example). The only bad thing with 64bit code is that the programs get bigger, which may effect memory performance negatively. But if you have a lot of memory then you will benefit from not needing any special addressing modes. Since you (Denis) are doing a lot of mathematical calculations you will probably benefit from running in 64bit mode. -- gentoo-user@gentoo.org mailing list