From owner-freebsd-hardware Mon Jun 9 21:38:57 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id VAA08653 for hardware-outgoing; Mon, 9 Jun 1997 21:38:57 -0700 (PDT) Received: from silvia.HIP.Berkeley.EDU (wck-ca7-16.ix.netcom.com [204.31.231.48]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id VAA08648 for ; Mon, 9 Jun 1997 21:38:54 -0700 (PDT) Received: (from asami@localhost) by silvia.HIP.Berkeley.EDU (8.8.5/8.6.9) id VAA00712; Mon, 9 Jun 1997 21:38:30 -0700 (PDT) Date: Mon, 9 Jun 1997 21:38:30 -0700 (PDT) Message-Id: <199706100438.VAA00712@silvia.HIP.Berkeley.EDU> To: tom@sdf.com CC: smp@csn.net, freebsd-hardware@FreeBSD.ORG In-reply-to: (message from Tom Samplonius on Mon, 9 Jun 1997 18:57:38 -0700 (PDT)) Subject: Re: fastest possible FreeBSD system? From: asami@cs.berkeley.edu (Satoshi Asami) Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk * > 233mHz PPros, now that the PII is available, and intel is struggling to make * > the PII look attractive from a performance point of view. * * I thought the PII was intented to a consumer level product, while the * PPro was the server/workstation product? That is true, but PII is the low-end of the next generation. What PII (Klamath) is to Pentium, the Deschutes is to P6. You can't really compare PII to P6, except that when run at the same clock speed, P6 (256K) usually outperforms the PII. * The smaller cache, and new cost ^^^^^^^ * saving chip packaging seems to point towards targetting the consumer * market. Or more like the "non-existent" on-chip L2 cache. ;) * What about the difference between a PPro with 256k onchip cache, as * opposed to 512k onchip cache? I have this sneaking suspicion that a 512K version is faster, but it's so grossly overprices I don't really think there is no comparison. You can spend all that money (what, $700 dollars for 256K of cache?) for something much more productive. Satoshi