From owner-freebsd-hardware  Wed Aug 20 13:11:04 1997
Return-Path: <owner-freebsd-hardware>
Received: (from root@localhost)
          by hub.freebsd.org (8.8.5/8.8.5) id NAA06720
          for hardware-outgoing; Wed, 20 Aug 1997 13:11:04 -0700 (PDT)
Received: from vader.cs.berkeley.edu (vader.CS.Berkeley.EDU [128.32.38.234])
          by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id NAA06704
          for <hardware@FreeBSD.ORG>; Wed, 20 Aug 1997 13:10:55 -0700 (PDT)
Received: (from asami@localhost) by vader.cs.berkeley.edu (8.8.6/8.7.3) id NAA04128; Wed, 20 Aug 1997 13:10:49 -0700 (PDT)
Date: Wed, 20 Aug 1997 13:10:49 -0700 (PDT)
Message-Id: <199708202010.NAA04128@vader.cs.berkeley.edu>
To: rgrimes@GndRsh.aac.dev.com
CC: tom@sdf.com, hardware@FreeBSD.ORG
In-reply-to: <199708201505.IAA24962@GndRsh.aac.dev.com> (rgrimes@GndRsh.aac.dev.com)
Subject: Re: parity errors
From: asami@cs.berkeley.edu (Satoshi Asami)
Sender: owner-freebsd-hardware@FreeBSD.ORG
X-Loop: FreeBSD.org
Precedence: bulk

 * One set of 36 chip simms will run reliably in a P6NP5, but try putting
 * 2 sets (4 total simms) and you'll be on the bloody edge of what the
 * Natoma chipset memory drivers can provide.  You can make it work by
 * lowering the memory timing to one step below your actual DRAM speed,
 * but this is only a ``sometimes'' fix.  

Well, maybe I am incredibly lucky, but the test I mentioned before was 
run with all four of the modules (256MB total) used simultaneously. ;)

Satoshi