Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Posting-Version: version B 2.10.2 9/18/84; site dolphy.UUCP
Path: utzoo!linus!philabs!cmcl2!phri!dolphy!jmg
From: jmg@dolphy.UUCP (Intergalactic Psychic Police Of Uranus)
Newsgroups: net.arch
Subject: Re: Multiple 68020's on VME ?
Message-ID: <10@dolphy.UUCP>
Date: Sat, 5-Oct-85 23:31:35 EDT
Article-I.D.: dolphy.10
Posted: Sat Oct  5 23:31:35 1985
Date-Received: Wed, 9-Oct-85 06:06:39 EDT
References: <442@rna.UUCP> <552@spar.UUCP>
Organization: Lesbian Vampires Of Sodom Corp.
Lines: 24

> > 
> > 	We would like to hear from people who know about or who have
> > used multiple 680XX's on a bus. We are tentatively considering a ~10
> > processor machine using 68020's on VME for a particular real-time
> > data collection, analysis and display application.
> > 					Cheers,
> > 					Dan Ts'o
> 
> The August 1, 1985 issue of Computer Design contains a rather interesting
> article on metastability problems in multiprocessor VME systems.
> logic that is not vulnerable to metastability problems in synchronization.
> ... some folks at CMU's robotics lab discovered that "as few as two"
> 8-MHz Motorola VM02 68000 boards would lock up "within 4 to 10 minutes".
> 						Baba ROM DOS

I codeveloped Auragen's Fault-Tolerant UNIX system (coming someday
from Nixdorf)...it had as many as 4 68010's on a local VME bus...
68020's were added after I left, and I heard of no problems.  We also
used VM02 boards on the same bus in development and simulation of
the operating system...and had now problems.

Multiple 68000's and 68010's may not operate a peak because of bus
contention...but it may be a lesser problem with all the instruction
and data cacheing on the 68020's.