Message-Passing Performance of Various Computers <A NAME=tex2html1 HREF="footnode.html#2"><IMG ALIGN=BOTTOM ALT="gif" SRC="http://www.netlib.org/utk/icons/foot_motif.gif"></A> <A NAME=tex2html2 HREF="footnode.html#3"><IMG ALIGN=BOTTOM ALT="gif" SRC="http://www.netlib.org/utk/icons/foot_motif.gif"></A>

Next: Introduction and Motivation

Message-Passing Performance of Various Computers

Jack J. Dongarra Tom Dunigan

Abstract:

This report compares the performance of different computer systems for basic message passing. Latency and bandwidth are measured on Convex, Cray, IBM, Intel, KSR, Meiko, nCUBE, NEC, SGI, and TMC multiprocessors. Communication performance is contrasted with the computational power of each system. The comparison includes both shared and distributed memory computers as well as networked workstation clusters.

Introduction and Motivation
- The Rise of the Microprocessor
- Communications and Parallel Processing Systems
Message Passing
Computation and Communication
Summary
- Rules for Running the Tests
- Obtaining the Software
References
Appendix: Machine Configurations for Echo Tests
About this document ...

Jack Dongarra
Wed Aug 30 08:28:29 EDT 1995