Authors

T. Williams;R. Parsons

Comments

Authors: contact us about adding a copy of your work at STARS@ucf.edu

Abbreviated Journal Title

J. Res. Pract. Inf. Technol.

Keywords

heterogeneous distributed computing; BSP; cluster computing; collective; communication; performance evaluation; Computer Science, Information Systems; Computer Science, Software; Engineering

Abstract

Heterogeneous cluster environments are becoming an increasing popular platform for executing parallel applications. Efficient heterogeneous programs must account for the differences inherent in such an environment. We propose the HBSP(1) model of computation as a framework for developing applications for heterogeneous clusters of workstations. The utility of the model is demonstrated through the design and analysis of the scatter and one-to-all broadcast algorithms. Extensive experimentation illustrates the benefits of using the model for heterogeneous program development. By hiding the non-uniformity of the underlying system, the HBSP(1) model provides a framework that embraces the heterogeneity of the underlying system.

Journal Title

Journal of Research and Practice in Information Technology

Volume

33

Issue/Number

2

Publication Date

1-1-2001

Document Type

Article

Language

English

First Page

146

Last Page

157

WOS Identifier

WOS:000172823300005

ISSN

1443-458X

Share

COinS