Path: utzoo!utgpu!attcan!uunet!seismo!sundc!pitstop!sun!chiba!khb
From: khb%chiba@Sun.COM (Keith Bierman - Sun Tactical Engineering)
Newsgroups: comp.arch
Subject: Re: A simple question on RISC
Message-ID: <76083@sun.uucp>
Date: 3 Nov 88 21:42:22 GMT
References: <6544@xanth.cs.odu.edu> <75577@sun.uucp> <10802@cup.portal.com>
Sender: news@sun.uucp
Reply-To: khb@sun.UUCP (Keith Bierman - Sun Tactical Engineering)
Organization: Sun Microsystems, Mountain View
Lines: 40

In article <10802@cup.portal.com> bcase@cup.portal.com (Brian bcase Case) writes:

>As I understand it, the MIPS guys concluded that the early Stanford MIPS
>architecture was too *complicated*, not too simple (the packing of one
>or two instructions per word really complicated the pipeline control, at
>least that's what I remember reading, and some instructions were two-
>address while others were three).  The 801 had a very complex register
>file (3 reads, two writes).  Subsequent machines seem to be simpler
>(although we might all be surprised by John Cocke's Americas machine.).

Simpler in some ways, more complex in others is the trend.

>
>Notice also that Seymour's first machine came out in '76 (I believe).

Wrong. UNIVAC, the all of the CDC machines until he left to found Cray
Research. The CDC 6600 is often listed as the first supercomputer. 

>The 801 research began in 1975, though it was perhaps not as focused
>as it later became.  I'd say this is a pretty close call to who was first.

6600 was a 1960's machine. So if it's RISC, it won by a decade.
                              ^^

>The 801 guys set down the ground rules and then let the compiler guys
>define the instructions.  I don't think this is the way Seymour did it.
>Seymour is a smart guy and understands what can go fast and what cannot,
>but little things like the lack of three-address integer instructions
>shows that he was not designing from the point of view of a compiler
>guy.  And the Multiflow VLIW and Wulf's WM machine are closer to RISC
>vector machines than are the Crays.

True on both counts. Seymour designs simple things which go fast. He
assumes that compiler writers can cope. This is, perhaps, not the best
approach...but his track record is pretty good (CDC owned the high
performance computer market during his long reign). The Multiflow and
Cydra machines are, arguably, RISC's .

Keith H. Bierman
It's Not My Fault ---- I Voted for Bill & Opus