From owner-freebsd-hackers Thu Jun 10 15:59: 4 1999 Delivered-To: freebsd-hackers@freebsd.org Received: from pop3-3.enteract.com (pop3-3.enteract.com [207.229.143.32]) by hub.freebsd.org (Postfix) with SMTP id CA6AC1544E for ; Thu, 10 Jun 1999 15:59:02 -0700 (PDT) (envelope-from dscheidt@enteract.com) Received: (qmail 71511 invoked from network); 10 Jun 1999 22:59:01 -0000 Received: from shell-3.enteract.com (dscheidt@207.229.143.42) by pop3-3.enteract.com with SMTP; 10 Jun 1999 22:59:01 -0000 Received: from localhost (dscheidt@localhost) by shell-3.enteract.com (8.9.3/8.9.2) with SMTP id RAA24145; Thu, 10 Jun 1999 17:59:01 -0500 (CDT) (envelope-from dscheidt@enteract.com) X-Authentication-Warning: shell-3.enteract.com: dscheidt owned process doing -bs Date: Thu, 10 Jun 1999 17:59:01 -0500 (CDT) From: David Scheidt To: Dennis Cc: hackers@freebsd.org Subject: Re: P5 vs Celeron vs PII In-Reply-To: <199906102221.SAA01467@etinc.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG On Thu, 10 Jun 1999, Dennis wrote: > In a nutshell, does anyone have a handle on the relative preformance of > these are? > 333Mhz Celeron vs 333 Mhz PII For a typical job mix, it is pretty close to a wash. The PII seems to have a slight advantage, on the order of 5%. If you are compute bound, and the task fits in cache, the Celery has an advantage, since there is no wait state on cache hits. The PII has a much bigger cache, so even though cache hits are more expensive, they are more likely. I am pretty much unable to tell the difference between a Celeron and a PII at the same clock. The vast majority of my desktop computing isn't compute bound, though. David Scheidt To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message