From owner-freebsd-amd64@FreeBSD.ORG Tue Mar 14 16:26:26 2006 Return-Path: X-Original-To: freebsd-amd64@freebsd.org 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 7305F16A420 for ; Tue, 14 Mar 2006 16:26:26 +0000 (UTC) (envelope-from wmoran@collaborativefusion.com) Received: from mx00.pub.collaborativefusion.com (mx00.pub.collaborativefusion.com [206.210.89.199]) by mx1.FreeBSD.org (Postfix) with ESMTP id E85F743D45 for ; Tue, 14 Mar 2006 16:26:25 +0000 (GMT) (envelope-from wmoran@collaborativefusion.com) Received: from vanquish.pgh.priv.collaborativefusion.com (vanquish.pgh.priv.collaborativefusion.com [192.168.2.61]) by wingspan with esmtp; Tue, 14 Mar 2006 11:26:25 -0500 id 00056422.4416EEB1.0000B04D Date: Tue, 14 Mar 2006 11:26:25 -0500 From: Bill Moran To: freebsd-amd64@freebsd.org Message-Id: <20060314112625.09a3ac2c.wmoran@collaborativefusion.com> In-Reply-To: <200603141710.12822.kono@kth.se> References: <200603140740.38388.joao@matik.com.br> <3.0.1.32.20060314034932.00ae9678@pop.redshift.com> <200603141710.12822.kono@kth.se> Organization: Collaborative Fusion X-Mailer: Sylpheed version 2.2.0 (GTK+ 2.8.12; i386-portbld-freebsd6.0) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Subject: Re: amd64 slower than i386 on identical AMD 64 system? X-BeenThere: freebsd-amd64@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Porting FreeBSD to the AMD64 platform List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 14 Mar 2006 16:26:26 -0000 On Tue, 14 Mar 2006 17:10:12 +0100 Alexander Konovalenko wrote: > > I am just trying to understand, the conclusion is that all people who got i386 > benchmark better than amd64 one, on the same X2 hardware, were running not > SMP kernel on amd64 and never bothered them self to build and use a proper > kernel for their platform? Naively I thought that problem is much > serious... :-P We've been doing some tests here (on Dell Poweredge 2850) and haven't done extensive tweaking (have tried different -O or any other compile flags) So far, our conclusion is that running amd64 binaries on an amd64 kernel is slower than ia32 binaries on an ia32 kernel. We're comparing identical 2850 hardware, both kernels built with SMP (although there seem to be some issues related to running SMP on amd64) We've been using ubench and pgbench (since these will be PostgreSQL servers) to test. We're seeing that the 64b stuff runs just a bit slower. We're also seeing that the amd64 doesn't seem to scale up to using more than one processor, but that's an issue under investigation (see other thread on this list) These are not conclusive tests at this point, but it's more data for you. -- Bill Moran Collaborative Fusion Inc.