From owner-freebsd-hardware Mon May 26 12:30:27 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id MAA06542 for hardware-outgoing; Mon, 26 May 1997 12:30:27 -0700 (PDT) Received: from mexico.brainstorm.eu.org (root@mexico.brainstorm.fr [193.56.58.253]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id MAA06533 for ; Mon, 26 May 1997 12:30:20 -0700 (PDT) Received: from brasil.brainstorm.eu.org (brasil.brainstorm.fr [193.56.58.33]) by mexico.brainstorm.eu.org (8.8.4/8.8.4) with ESMTP id VAA16515 for ; Mon, 26 May 1997 21:30:08 +0200 Received: (from uucp@localhost) by brasil.brainstorm.eu.org (8.8.4/8.6.12) with UUCP id VAA03757 for hardware@FreeBSD.ORG; Mon, 26 May 1997 21:30:01 +0200 Received: (from roberto@localhost) by keltia.freenix.fr (8.8.5/keltia-uucp-2.9) id VAA03281; Mon, 26 May 1997 21:14:41 +0200 (CEST) Message-ID: <19970526211440.51805@keltia.freenix.fr> Date: Mon, 26 May 1997 21:14:40 +0200 From: Ollivier Robert To: hardware@FreeBSD.ORG Subject: Re: Intel Pentium II released References: <19970525131757.62904@keltia.freenix.fr> <199705252226.PAA01640@silvia.HIP.Berkeley.EDU> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.67 In-Reply-To: <199705252226.PAA01640@silvia.HIP.Berkeley.EDU>; from Satoshi Asami on Sun, May 25, 1997 at 03:26:15PM -0700 X-Operating-System: FreeBSD 3.0-CURRENT ctm#3332 Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk According to Satoshi Asami: > Ouch. That's horrible! Even a p P133 with 2.1.5 (i.e., without the > fast copyin/out) can get 80MB/s on both.... The culprit is the bcopy/bzero/copyin FPU code. I suspected it a bit as the FPU in the K6 is slower but the results are interesting. With flags 0x4 or 0x7 (so the real culprit is the copyin/out code) I get this : 202 [21:04] roberto@keltia:~> dd if=/dev/zero of=/dev/null bs=64k count=16000 1048576000 bytes transferred in 9.008729 secs (116395552 bytes/sec) 203 [21:07] roberto@keltia:~> dd if=/dev/zero of=/dev/null bs=1m count=1000 1048576000 bytes transferred in 14.700602 secs (71328779 bytes/sec) *much* better. I still can't overclock it at 2.5x 83 MHz. Only 2.5x 75 MHz works with the K6 whereas it worked at 2x 83 MHz for the P133. Oh well, I can live with that... My kernel compilation time (not GENERIC but my own config) fell from 4:55 down to 3:29 :-) -- Ollivier ROBERT -=- FreeBSD: There are no limits -=- roberto@keltia.freenix.fr FreeBSD keltia.freenix.fr 3.0-CURRENT #10: Fri May 23 22:47:39 CEST 1997