Path: utzoo!attcan!uunet!husc6!rutgers!apple!bionet!agate!eos!eugene
From: eugene@eos.UUCP (Eugene Miya)
Newsgroups: comp.arch
Subject: Seeing the future
Message-ID: <1984@eos.UUCP>
Date: 23 Nov 88 07:42:44 GMT
Reply-To: eugene@eos.UUCP (Eugene Miya)
Organization: NASA Ames Research Center, Calif.
Lines: 34

Last week, I was given the pleasure of meeting Seymour Cray.  Made a
short video tape of "What's all this about Gallium Arsenide?" [if your
school wants a professionally edited copy write:
	University Video Communications
	Stanford University
	P.O. Box 2666
	Stanford, CA 94309
Cost is $20 before Dec. 15 $35 after (VHS only). Intro by Norm Morse.
My tape went to Time.] Should be available end of January.

Anyway's he showed photos of the Cray-3 (housing only, obviously).
Had some performance graphs of the Cray-4.  But aside from Seymour's
and a few other people's technical papers, I was disappointed in the
Supercomputing 88 conference (operationally SC'89 has learned from 88 and
will be better).  Lots of other things, Steve Stevenson can summarize.

I think I have seen the future and it's not in supercomputing (or 
"mainframes").  Oh yes there will be better machines, but I see too
little flexibility, too little short sightedness in all people.  Difficulties
in parallelism are grossly underestimated in some areas.

So this note gives me a chance to post the above Stanford address,
I think the amount of fluff in comp.arch has reached the point
(partially due to the evils of cross-referencing and failure to
edit by novice net posters) and I'm 'u'ing this group.  Just got too much
work to do.  Remember when net.arch was incredibly quiet?

Another gross generalization from

--eugene miya, NASA Ames Research Center, eugene@aurora.arc.nasa.gov
  resident cynic at the Rock of Ages Home for Retired Hackers:
  "Mailers?! HA!", "If my mail does not reach you, please accept my apology."
  {uunet,hplabs,ncar,decwrl,allegra,tektronix}!ames!aurora!eugene
  "Send mail, avoid follow-ups.  If enough, I'll summarize."