Xref: utzoo comp.sys.super:376 comp.arch:23113
Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!think.com!snorkelwacker.mit.edu!ai-lab!raisin-scone!lethin
From: lethin@raisin-scone.ai.mit.edu (Richard A. Lethin)
Newsgroups: comp.sys.super,comp.arch
Subject: Re: Massively Parallel LINPACK on the Intel Touchstone Delta machine
Message-ID: <16333@life.ai.mit.edu>
Date: 6 Jun 91 15:40:15 GMT
References: <1991Jun3.130104.15667@hubcap.clemson.edu> <1991Jun3.233741.8570@elroy.jpl.nasa.gov> <13301@pt.cs.cmu.edu>
Sender: news@ai.mit.edu
Organization: MIT Artificial Intelligence Laboratory
Lines: 11

Some questions?

At what size N for massive linpack does the accumulated numerical fuzz
swamp the precision available in a double precision number?

Aren't really large problems of interest sparse matrices anyway?  Who
holds the record for massive sparse matrix solves?

Perhaps some of the numerical experts out there could tell us
something about the characteristics of these massive numerical
problems.