Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!uflorida!gatech!hubcap!scott
From: scott@cs.rochester.edu (Michael Scott)
Newsgroups: comp.parallel
Subject: Re: Linda performance
Message-ID: <1989May11.151336.14127@cs.rochester.edu>
Date: 11 May 89 19:13:36 GMT
References: <5442@hubcap.clemson.edu>
Sender: fpst@hubcap.clemson.edu
Reply-To: scott@cs.rochester.edu (Michael Scott)
Organization: U of Rochester, CS Dept, Rochester, NY
Lines: 26
Approved: parallel@hubcap.clemson.edu

In article <5442@hubcap.clemson.edu> carriero@YALE.EDU (Nicholas Carriero) writes:
| Speculative arguments about Linda's efficiency are irrelevant; eight
| years ago they made sense, but today there are a large number of
| efficient implementations.  (We've made this point recently, so we
| won't elaborate here).

I've been trying to sit this discussion out, but I can't contain myself
any longer.  "Speculative arguments about Linda's efficiency" ARE
relevant precisely because Linda proponents have had eight years to
make the case and they haven't succeeded.

Linda is a simple, elegant, and appealing approach to writing parallel
programs.  For small-scale parallelism with medium to coarse-grain
process interactions it is clearly very nice.  For large-scale parallel
programming, however, Linda has problems with efficiency, modularity,
and scalability that have not been resolved and that I do not believe
can be resolved.

The burden of proof lies on the Linda camp.  They have yet to produce a
single application that addresses the performance question convincingly.
How long is the world supposed to wait?
-- 
Michael L. Scott
University of Rochester    (716) 275-7745
scott@cs.rochester.edu     scott%rochester@CSNET-RELAY
{decvax, allegra, cmcl2}!rochester!scott