Received: (from major@localhost)
	by minnie.cs.adfa.edu.au (8.9.1/8.9.1) id MAA06440
	for pups-liszt; Tue, 24 Nov 1998 12:49:02 +1100 (EST)
	(envelope-from owner-pups@minnie.cs.adfa.oz.au)
X-Authentication-Warning: minnie.cs.adfa.edu.au: major set sender to owner-pups@minnie.cs.adfa.oz.au using -f
Received: from dfw-ix10.ix.netcom.com (dfw-ix10.ix.netcom.com [206.214.98.10])
	by minnie.cs.adfa.edu.au (8.9.1/8.9.1) with ESMTP id MAA06435
	for <PUPS@MINNIE.CS.ADFA.EDU.AU>; Tue, 24 Nov 1998 12:48:44 +1100 (EST)
	(envelope-from eekg@ix.netcom.com)
Received: (from smap@localhost)
          by dfw-ix10.ix.netcom.com (8.8.4/8.8.4)
	  id TAA20720 for <PUPS@MINNIE.CS.ADFA.EDU.AU>; Mon, 23 Nov 1998 19:48:00 -0600 (CST)
Received: from roc-ny1-13.ix.netcom.com(199.183.209.45) by dfw-ix10.ix.netcom.com via smap (V1.3)
	id rma020559; Mon Nov 23 19:47:10 1998
Message-ID: <002e01be174b$8a9ec6c0$2dd1b7c7@#eekg.ix.netcom.com>
From: "Eric Edwards" <eekg@ix.netcom.com>
To: <PUPS@MINNIE.CS.ADFA.EDU.AU>
Subject: Re: What *was* the Tahoe?
Date: Mon, 23 Nov 1998 20:40:51 -0500
MIME-Version: 1.0
Content-Type: text/plain;
	charset="iso-8859-1"
Content-Transfer-Encoding: 7bit
X-Priority: 3
X-MSMail-Priority: Normal
X-Mailer: Microsoft Outlook Express 4.72.3110.5
X-MimeOLE: Produced By Microsoft MimeOLE V4.72.3110.3
Sender: owner-pups@minnie.cs.adfa.oz.au
Precedence: bulk

The Power 6/32 Tahoe was a product of Computer Consoles Inc. (CCI).  The
internal codename was "Tahoe", as all the CCI processors were named after
lakes in the US (others I can remember were Erie and Huron).  It was
originally intended  to compete with the VAX-11/780 - depending on the
benchmark it was 5 to 10 times faster than the VAX and much smaller and
cheaper.

The base processor consisted of 5 boards - implemented with AMD 2900 series
bit slice processors, PLAs and 74F series parts.  Surprisingly the bit-slice
processors were used in the MMU - the actual ALU was 74F181s. It was a big
endian machine that was sort of a cross between a VAX and a Motorola 68K.
As mentioned elsewhere, it is rumored that if you swap the nibbles in the
instruction bytes they end up the same as the VAX...

I think it also had some odd features: the cache was on the processor side
of the mmu -- so it was indexed by virtual address and instructions were
cached in microcode form.

As guessed from the lack of boot blocks, there was another board in the
system -- the Console Processor (CP).  It was a 68000 based Versabus single
board computer.  The boot monitor understood BSD filesystems on both tape
and disk.  It basically loaded the microcode into the CPU, loaded the boot
image (/boot?) into memory, and then started the main CPU.

CCI ported 4.2BSD to run on the Tahoe and the changes were rolled into the
4.3-Tahoe version.  They also ran System V (including a dual processor
version) and CCI's own fault-tolerant Unix - Perpos.

I think the last of the Berkeley Tahoe machines ended up at Rochester
Institute of Technology's Computer Science House (http://www.csh.rit.edu).
Some guys up there were attempting to do some work with 4.4BSD and the
Tahoe.

I can probably dig up more information if anyone needs it...

-----Original Message-----
From: SHOPPA@trailing-edge.com <SHOPPA@trailing-edge.com>
To: PUPS@MINNIE.CS.ADFA.EDU.AU <PUPS@MINNIE.CS.ADFA.EDU.AU>
Date: Sunday, November 22, 1998 6:47 PM
Subject: What *was* the Tahoe?


>  What is the "Tahoe"?
>Tim. (shoppa@trailing-edge.com)
>


