From owner-freebsd-smp Thu Nov 4 18:30:35 1999 Delivered-To: freebsd-smp@freebsd.org Received: from mercury.gfit.net (ns.gfit.net [209.41.124.90]) by hub.freebsd.org (Postfix) with ESMTP id 361691580E for ; Thu, 4 Nov 1999 18:30:28 -0800 (PST) (envelope-from tom@embt.com) Received: from PARANOR (timembt.iinc.com [206.67.169.229]) by mercury.gfit.net (8.8.8/8.8.8) with SMTP id UAA27333; Thu, 4 Nov 1999 20:34:56 -0600 (CST) (envelope-from tom@embt.com) Message-Id: <3.0.3.32.19991104212943.0110c588@mail.embt.com> X-Sender: tembt@mail.embt.com X-Mailer: QUALCOMM Windows Eudora Pro Version 3.0.3 (32) Date: Thu, 04 Nov 1999 21:29:43 -0500 To: Scott Myron From: Tom Embt Subject: Re: Dual Celeron + FreeBSD? Cc: freebsd-smp@freebsd.org In-Reply-To: <382203FA.4F4740B4@hsonline.net> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org At 17:08 11/04/1999 -0500, you wrote: >Hello. I want to get a Dual celeron going with freebsd as the OS. My >question is, do the chips have to have the same stepping? I read >somewhere that if the chips do NOT have the same stepping, it screws up, > >and causes blue screens in NT, and i was wondering if anything similar >happens in FreeBSD. I figure it'll be difficult to get 2 celerons with >the same stepping. I am just planning on getting 2 retial ppga celeron >433's. I read somewhere else that "it was just a myth and the processors > >do NOT have to have the same stepping." so i'm just searching for the >truth. Thanks. > > >Scott I will take a chance here and say, against the many people who have said otherwise, that getting the same stepping is important. Different steppings can (AFAIK) use different microcode, and a mix'n'match approach could cause some very hard to track down errors when the CPUs don't communicate properly. I'm no expert on the subject, that's just my opinion. It might "mostly" work, but what good is that? The good news is that you will almost certainly get two Celerons of the same stepping. I *think* all currently manufactured Celerons are of Id 0x665 (stepping 5). Also, all current Celerons are MP-capable, unlike the Pentium days when you had to look for an "SSS" CPU. Any two new Celeries of the same speed are pretty much guaranteed to do SMP together. In short: I don't think it's a myth, it's just not something to worry about in your particular situation. Disclaimer: Of course, I may be talking out of my ***. Tom Embt ICQ UIN: 11245398 tom@embt.com d:-)> ------------------------------------------------------------------ "You're one of those condescending Unix computer users!" "Here's a nickel, kid. Get yourself a better computer" - Dilbert. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message