From owner-freebsd-hardware Tue Jun 10 11:23:20 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id LAA21760 for hardware-outgoing; Tue, 10 Jun 1997 11:23:20 -0700 (PDT) Received: from persprog.com (persprog.com [204.215.255.203]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id LAA21748 for ; Tue, 10 Jun 1997 11:23:14 -0700 (PDT) Received: by persprog.com (8.7.5/4.10) id NAA31062; Tue, 10 Jun 1997 13:00:51 -0500 Received: from dave(192.2.2.6) by cerberus.ppi.com via smap (V1.3) id sma031042; Tue Jun 10 14:00:50 1997 Message-ID: <339D9655.6B9285BE@persprog.com> Date: Tue, 10 Jun 1997 14:00:53 -0400 From: Dave Alderman Reply-To: dave@persprog.com Organization: Personalized Programming, Inc X-Mailer: Mozilla 4.0b5 [en] (Win95; I) MIME-Version: 1.0 To: Steve Passe CC: Chuck Robey , Tom Samplonius , freebsd-hardware@FreeBSD.ORG Subject: Re: fastest possible FreeBSD system? X-Priority: 3 (Normal) References: <199706100358.VAA18537@Ilsa.StevesCafe.com> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Steve Passe wrote: > > Chuck, > > > Steve, since the PPro cache is accessed at the clock rate, and the > > Pentium II cache is accessed at the bus rate, I would think the > > PPro would win hands down, in performance, no? > > the benches I have seen say no, check out: > > http://sysdoc.pair.com/pentiumII.html Unfortunately, these benchmarks do not evaluate multiprocessor performance. In multiprocessor tests (unfortunately with Windows NT), A Dell dual Pentium Pro 200 server was slightly outperforming a dual Pentium II 266 server from Dell. I saw this in PC Week (I think). If anyone can cite the article, please do so. For some reason, Dell had priced the Pentium Pro system MUCH higher that the Pentium II - far more than the simple hardware differences would justify. I would speculate that SMP is more sensitive to changes in the L2 cache performance uniprocessor designs since the Pentium II is otherwise superior unless there is something fundamentally flawed with Slot One (which will be replaced by the end of the year anyhow with Slot Two). Another possibility is that the quite mature FX chip set is less optimal with Pentium II's when attempting SMP. -- It's not my fault! It's some guy named "General Protection"! --Ratbert David W. Alderman dave@persprog.com