From owner-freebsd-hackers  Fri Apr 11 13:27:07 1997
Return-Path: <owner-hackers>
Received: (from root@localhost)
          by freefall.freebsd.org (8.8.5/8.8.5) id NAA18512
          for hackers-outgoing; Fri, 11 Apr 1997 13:27:07 -0700 (PDT)
Received: from caliban.dihelix.com (caliban.dihelix.com [198.180.136.138])
          by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id NAA18497
          for <hackers@freebsd.org>; Fri, 11 Apr 1997 13:27:00 -0700 (PDT)
Received: (from langfod@localhost) by caliban.dihelix.com (8.8.5/8.8.3) id KAA00588; Fri, 11 Apr 1997 10:24:52 -1000 (HST)
Message-Id: <199704112024.KAA00588@caliban.dihelix.com>
Subject: Re: 430TX ?
In-Reply-To: <199704111759.KAA04490@rah.star-gate.com> from Amancio Hasty at "Apr 11, 97 10:59:13 am"
To: hasty@rah.star-gate.com (Amancio Hasty)
Date: Fri, 11 Apr 1997 10:24:52 -1000 (HST)
Cc: steve@visint.co.uk, louie@TransSys.COM, michaelh@cet.co.jp,
        avalon@coombs.anu.edu.au, terry@lambert.org, hackers@freebsd.org
From: "David Langford" <langfod@dihelix.com>
X-blank-line: This space intentionaly left blank.
X-Mailer: ELM [version 2.4ME+ PL31 (25)]
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Sender: owner-hackers@freebsd.org
X-Loop: FreeBSD.org
Precedence: bulk

>I talked to an Intel representative at WinHEC 97 and politely told him
>that they are shooting themselves on the foot with the issue of memory
>bandwith --- Interestingly , he agreed and his response was we are
>working hard to solve this issue. I believe he was sincere so lets wait
>and see what happens over the next six months.
>
>As far as I can tell , there are two camps to solve the memory bandwith 
>bottleneck, the DRAM folks and the RAMBUS folks. As to who is going to 
>win I don't know.
>	Amancio

What I really dont understand is why HP and ALR(?) seem to be the only
folks doing memory busses larger than 64 bits wide. One would
think that a 128bit 4-way interleaved motherboard would really help 
the crappy memory performance of Intel CPU based systems.

(That and why mohterboard makers dont put caches on Pentium Pro motherboards
 to interface the slow main memory and the faster on chip cache.)

*sigh

-David Langford (awaiting FreeBSD Alpha with glee)
 langfod@dihelix.com