From owner-freebsd-current@FreeBSD.ORG Wed Jan 17 15:41:17 2007 Return-Path: X-Original-To: freebsd-current@FreeBSD.org Delivered-To: freebsd-current@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 0B97516A417 for ; Wed, 17 Jan 2007 15:41:17 +0000 (UTC) (envelope-from rnsanchez@wait4.org) Received: from spunkymail-a19.dreamhost.com (sd-green-bigip-74.dreamhost.com [208.97.132.74]) by mx1.freebsd.org (Postfix) with ESMTP id EDBA413C4F0 for ; Wed, 17 Jan 2007 15:41:09 +0000 (UTC) (envelope-from rnsanchez@wait4.org) Received: from sauron.lan.box (unknown [200.203.29.31]) by spunkymail-a19.dreamhost.com (Postfix) with ESMTP id EA9C710CDA; Wed, 17 Jan 2007 07:41:05 -0800 (PST) Date: Wed, 17 Jan 2007 13:41:00 -0200 From: Ricardo Nabinger Sanchez To: Bruce Evans Message-Id: <20070117134100.94bb6137.rnsanchez@wait4.org> In-Reply-To: <20070117134022.V18339@besplex.bde.org> References: <3bbf2fe10607250813w8ff9e34pc505bf290e71758@mail.gmail.com> <3bbf2fe10607251004wf94e238xb5ea7a31c973817f@mail.gmail.com> <3bbf2fe10607261127p3f01a6c3w80027754f7d4e594@mail.gmail.com> <3bbf2fe10607281004o6727e976h19ee7e054876f914@mail.gmail.com> <3bbf2fe10701160851r79b04464m2cbdbb7f644b22b6@mail.gmail.com> <20070116154258.568e1aaf@pleiades.nextvenue.com> <20070117134022.V18339@besplex.bde.org> Organization: SYS_WAIT4 X-Mailer: Sylpheed 2.3.0+svn (GTK+ 2.10.6; i386-unknown-freebsd6.1) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: freebsd-current@FreeBSD.org, Ivan Voras , freebsd-arch@FreeBSD.org Subject: Re: [PATCH] Mantaining turnstile aligned to 128 bytes in i386 CPUs X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 17 Jan 2007 15:41:17 -0000 On Wed, 17 Jan 2007 15:50:41 +1100 (EST) Bruce Evans wrote: > AXP: (my 5 year old system with a newer CPU): movq through MMX is 60% > faster than movsl for cached moves, but movdqa through XMM is only 4% > faster. movnt with block prefetch is 155% faster than movsl with no > prefetch, and 73% faster with no prefetch for both. > A64 in 32-bit mode: in between P4 and AXP (closer to AXP). movsl doesn't > lose by so much, and prefetchnta actually works so block prefetch is > not needed and there is a better chance of prefetching helping more > than benchmarks. This PDF is somewhat dated, but perhaps some of it still applies today: http://cdrom.amd.com/devconn/events/AMD_block_prefetch_paper.pdf -- Ricardo Nabinger Sanchez Powered by FreeBSD "Left to themselves, things tend to go from bad to worse."