From owner-freebsd-amd64@FreeBSD.ORG Fri May 20 07:32:38 2005 Return-Path: Delivered-To: freebsd-amd64@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 62B5516A4CE for ; Fri, 20 May 2005 07:32:38 +0000 (GMT) Received: from ciao.gmane.org (main.gmane.org [80.91.229.2]) by mx1.FreeBSD.org (Postfix) with ESMTP id 750D643DB7 for ; Fri, 20 May 2005 07:32:36 +0000 (GMT) (envelope-from gofda-freebsd-amd64@m.gmane.org) Received: from list by ciao.gmane.org with local (Exim 4.43) id 1DZ1xx-0006Yi-DQ for freebsd-amd64@freebsd.org; Fri, 20 May 2005 09:30:41 +0200 Received: from dhcp193.ifado.de ([195.253.22.193]) by main.gmane.org with esmtp (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Fri, 20 May 2005 09:30:41 +0200 Received: from wb by dhcp193.ifado.de with local (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Fri, 20 May 2005 09:30:41 +0200 X-Injected-Via-Gmane: http://gmane.org/ To: freebsd-amd64@freebsd.org From: "Wilhelm B. Kloke" Date: Fri, 20 May 2005 07:29:24 +0000 (UTC) Organization: InstArbPhysUniDo Lines: 10 Message-ID: References: <42842F46.9040608@samsco.org> <4284FD37.2070009@jonny.eng.br> <20050519054630.GC68698@dragon.NUXI.org> <428CC670.50002@jonny.eng.br> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit X-Complaints-To: usenet@sea.gmane.org X-Gmane-NNTP-Posting-Host: dhcp193.ifado.de User-Agent: slrn/0.9.8.0 (FreeBSD) Cache-Post-Path: vestein!unknown@yorikke X-Cache: nntpcache 3.0.1 (see http://www.nntpcache.org/) Sender: news Subject: Re: Actual benefits of amd64 over i386 X-BeenThere: freebsd-amd64@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Porting FreeBSD to the AMD64 platform List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 20 May 2005 07:32:38 -0000 João Carlos Mendes Luís schrieb: > > Would these benefits outcome the losses caused by bigger binaries? > Isn't it possible to use 64 bit registers in a 32 bit segment? Just > like i386 segments, where one could define the default register size... I have made the experience, that the same piece of software (Algol68G interpreter) has had about 10% performance gain in amd64 mode over i386 on the same machine. I don't have the figure about the increase in size at hand.