Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!mnetor!seismo!husc6!cmcl2!beta!hwe
From: hwe@beta.UUCP (Skip Egdorf)
Newsgroups: comp.arch
Subject: Re: chewing up mips with graphics
Message-ID: <6771@beta.UUCP>
Date: Wed, 24-Jun-87 20:05:58 EDT
Article-I.D.: beta.6771
Posted: Wed Jun 24 20:05:58 1987
Date-Received: Fri, 26-Jun-87 06:39:50 EDT
References: <8270@amdahl.amdahl.com> <359@rocky2.UUCP> <2194@mmintl.UUCP> <1873@ames.UUCP>
Organization: Los Alamos Natl Lab, Los Alamos, N.M.
Lines: 24
Keywords: simulation processors parrallelism MIPS
Summary: Saturating Crays

In article <1873@ames.UUCP>, eugene@pioneer.arpa (Eugene Miya N.) writes:
> Actually, I have given some thought to this temporary overcapacity as a
> useful measure.  It took 3 weeks before one of our X-MPs (A 4-CPU
> upgrade) became saturated.  I think this might give a useful measurement
> on the derviative of user usage.  Other sites using other smaller CPUs
> reported at SIGMETRICS that their machine became saturated at the 3
> month mark.  This makes a lot of assumptions, but I feel that it makes
> a somewhat useful subjective measure.
> 
> From the Rock of Ages Home for Retired Hackers:
> 
> --eugene miya
>   NASA Ames Research Center
>   eugene@ames-aurora.ARPA

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.

Give me a hundred mips on my desk tomorrow, and I will use it up on BOTH
graphics and simulation.
				Skip Egdorf
				hwe@lanl.gov