From owner-freebsd-hardware  Thu Aug 28 13:06:12 1997
Return-Path: <owner-freebsd-hardware>
Received: (from root@localhost)
          by hub.freebsd.org (8.8.7/8.8.7) id NAA18174
          for hardware-outgoing; Thu, 28 Aug 1997 13:06:12 -0700 (PDT)
Received: from biggusdiskus.flyingfox.com (biggusdiskus.flyingfox.com [206.14.52.27])
          by hub.freebsd.org (8.8.7/8.8.7) with ESMTP id NAA18168
          for <freebsd-hardware@freebsd.org>; Thu, 28 Aug 1997 13:06:10 -0700 (PDT)
Received: (from jas@localhost)
	by biggusdiskus.flyingfox.com (8.8.5/8.8.5) id NAA26529;
	Thu, 28 Aug 1997 13:02:47 -0700 (PDT)
Date: Thu, 28 Aug 1997 13:02:47 -0700 (PDT)
From: Jim Shankland <jas@flyingfox.com>
Message-Id: <199708282002.NAA26529@biggusdiskus.flyingfox.com>
To: dg@root.com
Subject: Re: Fwd: K6 Linux Re-Compile Issue
Cc: freebsd-hardware@freebsd.org
Sender: owner-freebsd-hardware@freebsd.org
X-Loop: FreeBSD.org
Precedence: bulk

(Re: K6 chip bug, I mean non-conformance)

> If this was the problem then the failures would be deterministic and not
> random.

Note that AMD says that "Certain other relative internal pipeline
timing conditions must occur"; that sure sounds as though it could
be non-deterministic to me.

Jim Shankland
Flying Fox Computer Systems, Inc.