Path: utzoo!attcan!uunet!ogicse!emory!hubcap!feldy
From: feldy@CS.UCLA.EDU (Bob Felderman)
Newsgroups: comp.parallel
Subject: Re: simple coarse-grained parallel programs
Message-ID: <12190@hubcap.clemson.edu>
Date: 11 Dec 90 12:39:14 GMT
Sender: fpst@hubcap.clemson.edu
Organization: UCLA Computer Science Department
Lines: 31
Approved: parallel@hubcap.clemson.edu

In article <12179@hubcap.clemson.edu> anand@top.cis.syr.edu (Rangachari Anand) writes:
>Using a group of workstations connected on a LAN  as a prallel
>computer is an idea that is continually being rediscovered. 

>Anyway, I wonder if there is a survey about packages developed 
>for this task. More to the point, it would be interesting to know the 
>speeds obtained for specific problems.


I participated in a project at UCLA a few years ago which did this type
of thing on a network of PC-ATs. One of the real challenges was dealing with
DOS!
The code was never released, but was used here at UCLA for several projects
and a class. No one seems to be aware of out work, or maybe they aren't
interested!
>From looking around, I think we were one of the first to actually implement
a system that allowed parallel processing. Many other systems just migrated
single process tasks throughout the network.

Here's the reference, it includes some performance analysis of two algorithms,
a merge sort and parallel search (IDA*):

R.E. Felderman, E.M. Schooler, L. Kleinrock
The Benevolent Bandit Laboratory: A Testbed for Distributed Algorithms
IEEE Journal on Selected Areas in Communications
Vol 7, No. 2
February 1989

-- 
Bob Felderman                   	         feldy@cs.ucla.edu
UCLA Computer Science   	...!{rutgers,ucbvax}!cs.ucla.edu!feldy