From owner-freebsd-smp Thu Nov 20 01:45:25 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.7/8.8.7) id BAA24572 for smp-outgoing; Thu, 20 Nov 1997 01:45:25 -0800 (PST) (envelope-from owner-freebsd-smp) Received: from bsd.synx.com (rt.synx.com [194.167.81.239]) by hub.freebsd.org (8.8.7/8.8.7) with SMTP id BAA24504 for ; Thu, 20 Nov 1997 01:44:43 -0800 (PST) (envelope-from remy@synx.com) Received: from s3.synx.com (s3 [192.1.1.247]) by bsd.synx.com (8.6.12/8.6.12) with SMTP id KAA15768; Thu, 20 Nov 1997 10:48:18 +0100 Received: from rs1 by s3.synx.com id aa11302; 20 Nov 97 10:35 GMT Date: Thu, 20 Nov 1997 11:29:46 -0100 (GMT) From: Remy NONNENMACHER To: Kevin Day cc: freebsd-smp@freebsd.org Subject: Re: rc564 on SMP In-Reply-To: <199711191736.LAA08166@home.dragondata.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Wed, 19 Nov 1997, Kevin Day wrote: > > 1) A 3.0 optimized rc564 client will be out soon. > Is there and works better (and faster) than FreeBSD generic one. Under a K6/233 running 3.0, i went from 330 kkeys/s to 375 kkeys/s. The K6 works better using the -c 1 (386/486) Cpu type than the 'K6 optimized code'. (It's due to the fact that the K6 translates [34]86 instructions to its RISC instruction set then rearranges execution paths to paralelize them a max. Wonderfull internals Datasheets from AMD !!). Someone said team-freebsd was #11. The ranking went 120/48/46/34 when i checked. Do i missed something ? Moral Question : seeking for idle cpus, I added an Idleing Windoze NT to team. Can this be considered as immoral ? In one hand, I can say i use the CPU only and that NT stuff is just a spawn helper. In another hand, It's an M$ shit. If someone feals hurt, i will stop it.