Newsgroups: comp.parallel.pvm
From: "R. Kerr" <R.Kerr@ncl.ac.uk>
Subject: Re: Definition of Granularity
Organization: University of Newcastle upon Tyne
Date: 17 Nov 1994 17:07:55 GMT
Message-ID: <3ag2lb$21l@whitbeck.ncl.ac.uk>

John Wright (john@elroy.jpl.nasa.gov) wrote:

> I don't like using the computation/communication time ratio because
> it's dependent on the system as much as the algorithm but I don't
> claim my way is best or objective or anything else.  I just like it.

But I think the reason for Raj's enquiry was to determine the point 
beyond which parallelisation is not cost-effective and that point can 
be critically dependent on the communication time.

Cheers....Ron

------------------------------------------------------------------------
  Ron Kerr, Computing Service, Newcastle University, NE1 7RU, England.
 Tel. +44 191 222 8187       Fax. +44 191 222 8765  (NOTE new area code)
------------------------------------------------------------------------


