From owner-freebsd-hackers Thu May 15 12:58:27 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id MAA11016 for hackers-outgoing; Thu, 15 May 1997 12:58:27 -0700 (PDT) Received: from usr09.primenet.com (root@usr09.primenet.com [206.165.5.109]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id MAA10902 for ; Thu, 15 May 1997 12:57:04 -0700 (PDT) Received: from primenet.com (root@mailhost02.primenet.com [206.165.5.53]) by usr09.primenet.com (8.8.5/8.8.5) with ESMTP id MAA21025; Thu, 15 May 1997 12:54:32 -0700 (MST) Received: from conceptual.com (consys.com [207.218.17.187]) by primenet.com (8.8.5/8.8.5) with ESMTP id MAA02129; Thu, 15 May 1997 12:54:29 -0700 (MST) Received: from conceptual.com (localhost [127.0.0.1]) by conceptual.com (8.8.5/8.6.9) with ESMTP id MAA24132; Thu, 15 May 1997 12:54:26 -0700 (MST) Message-Id: <199705151954.MAA24132@conceptual.com> X-Mailer: exmh version 2.0gamma 1/27/96 To: Terry Lambert cc: rcarter@consys.com (Russell L. Carter), pgiffuni@fps.biblos.unal.edu.co, hackers@FreeBSD.ORG Subject: Re: Cluster Computing in BSD In-reply-to: Your message of "Thu, 15 May 1997 10:25:37 MST." <199705151725.KAA15126@phaeton.artisoft.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Thu, 15 May 1997 12:54:25 -0700 From: "Russell L. Carter" Sender: owner-hackers@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk > > > computers, but I can live with it :-). (With six boxes, a common > > > scientific process could take nearly 1/6 of the time on a fast network). > > ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ > > > > The difference between "could" and "does" is the > > reason for the failure of (nearly) every business unit that sold > > highly parallel/cluster systems. > > Except Goodyear. And Thinking Machines Corp. And Cray Computing. > And Cray Research. And Fujitsu. And... Oh my. That's bothersome, I almost (but not quite) had a PHK style reaction to your input. I *must* be misinterpreting your English... you *really* meant to lay wreaths on the graves of Goodyear, TMC, Cray Computer BBN Computers, Convex, Floating Point Systems, Tera, whatever Steve Chen is up to these days, Alliant, Evans & Sutherland, and not last and not least Kendall Square Research. Now Teradata, that's another matter; IBM's SP is a money maker but the total value added on the RS6000 base technology is trivial. But, the magnitude of the subsidy each of the big three Japanese supers invests is unknown but suspected to be large. Intel SSD is quite a money pit. Sequent has a nitch, but tiny compared to Teradata. Cray Research has a nitch that is eroding faster than the number of US enemy countries (hell of an investment, SGI... hey they bought the entrails of FPS, too, didn't they...). I don't know what Meiko is up to but I doubt it is fat profits. Of all of the efforts the only ones that evidently are/were successful as a business are Teradata and IBM's . Hey clusters are a fine approach to distributed problems, but parallelism across physically distributed systems has not succeeded often enough to merit more than the merest blip in the computing industry. (lugubriously, I have personally wished, would but were it not so... 8-) Now where were we? Oh yeah, mr. "nearly" most definitely assumes his rightful place at this table. Cheers, Russell > > I think the list of successes so vastly outnumbers the list of > failures that your parenthetical "nearly" is *way* out of place > here. > > > Terry Lambert > terry@lambert.org > --- > Any opinions in this posting are my own and not those of my present > or previous employers. >