The PVM system: Supercomputer level concurrent computation on a heterogeneous network of workstations

G. A. Geist, V. S. Sunderam

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

39 Scopus citations

Abstract

The PVM (Parallel Virtual Machine) sytem enables supercomputer level concurrent computations to be performed on interconnected networks of heterogeneous computer systems. Specifically, a network of 13 IBM RS/6000 powerstations has been used to run superconductor modeling codes at more than 250 Mflops. This paper describes the PVM system and two example applications running on it.

Original languageEnglish
Title of host publication6th Distributed Memory Computing Conference, DMCC 1991 - Proceedings
EditorsQuentin Stout, Michael Wolfe
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages258-261
Number of pages4
ISBN (Electronic)0818622903, 9780818622908
DOIs
StatePublished - 1991
Event6th Distributed Memory Computing Conference, DMCC 1991 - Portland, United States
Duration: Apr 28 1991May 1 1991

Publication series

Name6th Distributed Memory Computing Conference, DMCC 1991 - Proceedings

Conference

Conference6th Distributed Memory Computing Conference, DMCC 1991
Country/TerritoryUnited States
CityPortland
Period04/28/9105/1/91

Fingerprint

Dive into the research topics of 'The PVM system: Supercomputer level concurrent computation on a heterogeneous network of workstations'. Together they form a unique fingerprint.

Cite this