Performance prediction and its use in parallel and distributed computing systems

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Authors

  • Daniel P. Spooner
  • Helene N.Lim Choi Keung
  • Graham R. Nudd
  • Junwei Cao
  • Subhash Saini

Colleges, School and Institutes

External organisations

  • High Performance Systems Group
  • University of Warwick
  • NEC Laboratories Europe
  • NASA Ames Research Center

Abstract

A performance prediction framework is described in which predictive data generated by the PACE toolkit is stored and published through a Globus MDS-based performance information service. Distributing this data allows additional performance-based middleware tools to be built; the paper describes two such tools, a local-level scheduler and a system for wide-area task management. Experimental evidence shows that by integrating these performance tools for local- and wide-area management, considerable improvements can be made to task scheduling, resource utilisation and load balancing on heterogeneous distributed computing systems.

Bibliographic note

Publisher Copyright: © 2003 IEEE.

Details

Original languageEnglish
Title of host publicationProceedings - International Parallel and Distributed Processing Symposium, IPDPS 2003
Publication statusPublished - 2003
EventInternational Parallel and Distributed Processing Symposium, IPDPS 2003 - Nice, France
Duration: 22 Apr 200326 Apr 2003

Publication series

NameProceedings - International Parallel and Distributed Processing Symposium, IPDPS 2003

Conference

ConferenceInternational Parallel and Distributed Processing Symposium, IPDPS 2003
Country/TerritoryFrance
CityNice
Period22/04/0326/04/03