From owner-freebsd-amd64@FreeBSD.ORG Fri May 13 20:51:15 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 288A116A50F for ; Fri, 13 May 2005 20:51:15 +0000 (GMT) Received: from maltanet.net (mailer4.maltanet.net [194.158.37.38]) by mx1.FreeBSD.org (Postfix) with ESMTP id 3B96043D31 for ; Fri, 13 May 2005 20:51:13 +0000 (GMT) (envelope-from peterk@maltanet.net) Received: (qmail 14526 invoked by uid 516); 13 May 2005 20:54:24 -0000 Received: from 195.158.83.238 by mailer4.maltanet.net (envelope-from , uid 509) with qmail-scanner-1.25st (perlscan: 1.25st. Clear:RC:1(195.158.83.238):. Processed in 0.244243 secs); 13 May 2005 20:54:24 -0000 Received: from unknown (HELO [195.158.83.238]) ([195.158.83.238]) (envelope-sender ) by 0 (qmail-ldap-1.03) with SMTP for ; 13 May 2005 20:54:24 -0000 Message-ID: <4285134B.8000903@maltanet.net> Date: Fri, 13 May 2005 22:51:23 +0200 From: Peter Korsten User-Agent: Mozilla Thunderbird 1.0.2 (Windows/20050317) X-Accept-Language: en-us, en MIME-Version: 1.0 To: =?ISO-8859-1?Q?Jo=E3o_Carlos_Mendes_Lu=EDs?= , freebsd-amd64@freebsd.org References: <42842F46.9040608@samsco.org> <4284FD37.2070009@jonny.eng.br> In-Reply-To: <4284FD37.2070009@jonny.eng.br> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 8bit 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, 13 May 2005 20:51:15 -0000 João Carlos Mendes Luís wrote: > What about a 64 bit kernel, and mixed mode (32bit and 64bit) > userland? Solaris does this, and it sounds efficient, from the comments > I've seen in this list. Yeah well... I'm still to see significant performance benefits of 64 bits applications over 32 bits ones on my Sun Blade 100 at work. > The bad part: Most (probably all) libraries would duplicated, and > the kernel and compiler should be modified to understand this "feature". True, but it's just a compiler flag, really, for the libraries. It works well enough in Solaris. The kernel is a different issue that I won't comment upon, mostly because I don't know much about it. :) - Peter