From owner-freebsd-hardware  Thu Sep 11 21:32:15 1997
Return-Path: <owner-freebsd-hardware>
Received: (from root@localhost)
          by hub.freebsd.org (8.8.7/8.8.7) id VAA00348
          for hardware-outgoing; Thu, 11 Sep 1997 21:32:15 -0700 (PDT)
Received: from silvia.HIP.Berkeley.EDU (ala-ca11-23.ix.netcom.com [199.35.209.183])
          by hub.freebsd.org (8.8.7/8.8.7) with ESMTP id VAA00343
          for <freebsd-hardware@FreeBSD.ORG>; Thu, 11 Sep 1997 21:32:11 -0700 (PDT)
Received: (from asami@localhost) by silvia.HIP.Berkeley.EDU (8.8.7/8.6.9) id VAA28321; Thu, 11 Sep 1997 21:31:50 -0700 (PDT)
Date: Thu, 11 Sep 1997 21:31:50 -0700 (PDT)
Message-Id: <199709120431.VAA28321@silvia.HIP.Berkeley.EDU>
To: roberto@keltia.freenix.fr
CC: freebsd-hardware@FreeBSD.ORG
In-reply-to: <19970911221642.45617@keltia.freenix.fr> (message from Ollivier Robert on Thu, 11 Sep 1997 22:16:42 +0200)
Subject: Re: IBM/Cyrix PR200+
From: asami@cs.berkeley.edu (Satoshi Asami)
Sender: owner-freebsd-hardware@FreeBSD.ORG
X-Loop: FreeBSD.org
Precedence: bulk

 * > My too -- however, i suppose that Pentium-oriented copy/zero block
 * > procedures don't work.
 * 
 * Oh they do but much slower then the regular ones.
 * 
 * Always use "flags 0x7" for npx0 in your config. file for both Cyrix and
 * AMD's processors.

Speaking of which, can anyone with an *MX processor check the gus mmx
extension PR (filed under "gnu", I think) and try and see if copying
through the mmx registers instead of FP would be faster for some of
the CPU's?

Satoshi