Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!mnetor!seismo!ut-sally!husc6!cmcl2!beta!hc!fu
From: fu@hc.DSPO.GOV (Castor L. Fu)
Newsgroups: comp.arch
Subject: Re: chewing up mips with graphics
Message-ID: <5486@hc.DSPO.GOV>
Date: Fri, 26-Jun-87 12:29:00 EDT
Article-I.D.: hc.5486
Posted: Fri Jun 26 12:29:00 1987
Date-Received: Sat, 27-Jun-87 09:35:59 EDT
References: <8270@amdahl.amdahl.com> <359@rocky2.UUCP> <2194@mmintl.UUCP> <6771@beta.UUCP> <1613@uvacs.CS.VIRGINIA.EDU>
Reply-To: fu@hc.dspo.gov.UUCP (Castor L. fu)
Organization: Group E-10, Los Alamos National Laboratory, NM
Lines: 14
Keywords: simulation processors parrallelism MIPS

In article <1613@uvacs.CS.VIRGINIA.EDU> mac@uvacs.CS.VIRGINIA.EDU (Alex Colvin) writes:
>> 
>> When Los Alamos went from 6 to 7 Crays a few years back, the Cray folks
>> said that we did something that they had never seen...
>> Gone from 6 saturated Crays at 6 PM to 7 saturated Crays at 6:30 the next
>> morning.
>
>Some load isn't spread out by adding processors.  I hear that the Los Almos
>Crays spend much of their time processing characters in the tty drivers
>and screen editors.

Gosh, as far as I knew, there aren't any screen editors on the crays.
In fact, it is quite common for people to do most of their code preparation
on other computers which have friendly editors o-f46