Path: utzoo!utgpu!attcan!uunet!lll-winken!ubvax!weitek!dms!albaugh
From: albaugh@dms.UUCP (Mike Albaugh)
Newsgroups: comp.arch
Subject: Re: A simple question on RISC
Message-ID: <559@dms.UUCP>
Date: 4 Nov 88 17:13:41 GMT
References: <76083@sun.uucp>
Organization: Atari Games Inc., Milpitas, CA
Lines: 51

From article <76083@sun.uucp>, by khb%chiba@Sun.COM
(Keith Bierman - Sun Tactical Engineering):
> In article <10802@cup.portal.com> bcase@cup.portal.com (Brian bcase Case)
writes:
>>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. 

	I wondered who else was going to notice this.
> 
> 6600 was a 1960's machine. So if it's RISC, it won by a decade.
>                               ^^
	If things like the 88000 are, what possible "rule" can exclude
the 6600?
> 
>>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
> 
> True on both counts. Seymour designs simple things which go fast. He

	Uhhh... Am I the only one who remembers "IX7 X2+X3"?
Actually, the thing I liked _most_ about the 6600 (which it shared
with the the DEC PDP10 and PDP11) was that one could learn a very
small "grammer" for instruction composition and know that any
instruction that "fit" would in fact exist _and_do_what_the_name_implied
not all the special instructions on any of these machines fit the simplest
possible grammer, but all the generally useful ones did. The second
condition (do_what_...) is widely violated by most recent CISC's (e.g.
680x0) and the first even more so ("whadya mean I can only use that
addressing mode on instructions whose mnemonic, when translated into
Urdu, has a length which modulo 7 == 3 ?" :-). Reading about the current
crop of "RISC" processors, I am overwhelmed by Deja Vu. Multiple
function units, scoreboarding, forwarding, multiple instructions per
word, orthogonal instruction sets, compare_and_branch vs CC's...

	Oh, yeah, lack of Integer Mul & div was a bit of a pain, The
"Return Jump" a kluge (although a common one at the time), and One's
complement not exactly my cup of tea, so I don't maintain that the
6600 was perfect, but considering the competition at the time...

> Keith H. Bierman
> It's Not My Fault ---- I Voted for Bill & Opus
                          ^^^^^^^^^^^^^^^^^^^^^^
	I hope you will again, I probably will	:-)

| Mike Albaugh (albaugh@dms.UUCP || {...decwrl!turtlevax!}weitek!dms!albaugh)
| Atari Games Corp (Arcade Games, no relation to the makers of the ST)
| 675 Sycamore Dr. Milpitas, CA 95035		voice: (408)434-1709
| The opinions expressed are my own (Boy, are they ever)