From owner-freebsd-smp Thu Sep 16 17:42:48 1999 Delivered-To: freebsd-smp@freebsd.org Received: from thomson.iqm.unicamp.br (thomson.iqm.unicamp.br [143.106.13.161]) by hub.freebsd.org (Postfix) with ESMTP id 7236B1535F for ; Thu, 16 Sep 1999 17:42:41 -0700 (PDT) (envelope-from fabio@thomson.iqm.unicamp.br) Received: (from fabio@localhost) by thomson.iqm.unicamp.br (8.9.3/8.9.2) id VAA06428; Thu, 16 Sep 1999 21:42:34 -0300 (EST) (envelope-from fabio) From: Fabio Cesar Gozzo Message-Id: <199909170042.VAA06428@thomson.iqm.unicamp.br> Subject: Re: Examples of FreeBSD SMP success? In-Reply-To: <19990916171751.A19950@annwn.phys.washington.edu> from "William R. Somsky" at "Sep 16, 1999 5:17:51 pm" To: somsky@annwn.phys.washington.edu (William R. Somsky) Date: Thu, 16 Sep 1999 21:42:34 -0300 (EST) Cc: freebsd-smp@FreeBSD.ORG X-Mailer: ELM [version 2.4ME+ PL43 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org William R. Somsky wrote: >We're considering getting several Intel-based machines here in >the UW Physics department for use as desktop work- and computation- >stations, and the question has come up whether we would gain much >by getting dual-CPU (say dual 500 MHZ Pentium-III) as opposed to >single-CPU systems. > >The anticipated use where dual-CPUs could help us would probably >be users either running a computation-intensive job (eg, Mathematica), >while simultaneously doing desktop editing/browsing/mailing/TeXing/etc, >or running two computation- intensive jobs. (We don't expect that >Mathematica or any user job will be multi threaded.) > >What I've been asked to find out what the state of FreeBSD SMP >support is, and if anyone has any real-world examples of using >dual-CPUs under FreeBSD that might be similar to this sort of >situation and what the results have been. > >Being as that I've not tried multi-processing under FreeBSD yet, >does anybody have any input I can give to my users? I have been used FreeBSD with SMP machines since pre-3.0 for computational chemistry programs and this system has shown to be a very good choice because: 1) FreeBSD SMP is rock solid. I had jobs that took weeks burnning CPU and eating memory/disk resources without a single problem. 2) The cost/performance for this kind of programs is excelent. You just pay for another processor (ok, the MB is also more expensive) and you almost double the performance. I have compared the time required by two sequential jobs with two jobs in parallel and got a ratio around 1.8. It was a Dual PII 300 Mhz and this ratio can be better now with the 100Mhz bus of the new PIII's. Oh, my programs aren't multithread too. In conclusion, all I have to say is go for it ! Regards, -- ************************************************** Fabio Gozzo fabio@iqm.unicamp.br State University of Campinas UNICAMP Chemistry Institute http://thomson.iqm.unicamp.br ************************************************** To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message