Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!utgpu!utcsri!arvind
From: arvind@utcsri.UUCP
Newsgroups: ut.theory
Subject: THEORY NET: shared memory vs nonshared memory vs protocols
Message-ID: <5478@utcsri.UUCP>
Date: Wed, 30-Sep-87 15:36:31 EDT
Article-I.D.: utcsri.5478
Posted: Wed Sep 30 15:36:31 1987
Date-Received: Thu, 1-Oct-87 06:42:36 EDT
Distribution: ut
Organization: CSRI, University of Toronto
Lines: 19

Date:         29 Sep 1987 16:54:52-EDT (Tuesday)
From: Steve Stevenson <STEVE@hubcap.clemson.edu>
Subject:      shared memory vs nonshared memory vs protocols

I am interested in establishing a definitive list of considerations for
evaluating "communications" in parallel systems.  It seems to me that
"protocol" is the genus and implementations are the species.
     
I would like to know if there have been definitive papers/books which
completely treat the issue of what it takes (i.e., primitive objects,
functions) to establish a protocol, the logical principles involved (i.e.,
no deadlock), and performance implications/comparisons.
     
Thanks.
     
--
Steve (really "D. E.") Stevenson           steve@hubcap.clemson.edu
Department of Computer Science,            (803)656-5880.mabell
Clemson University, Clemson, SC 29634-1906