Asynchronism for iterative algorithms in a global computing environment

The subject of this paper is to show the very high power of asynchronism for iterative algorithms in the context of global computing, that is to say, with machines scattered all around the world. The question is whether or not asynchronism helps to reduce the communication penalty and the overall co...

Full description

Saved in:
Bibliographic Details
Published in16th Annual International Symposium on High Performance Computing Systems and Applications, 16-19 June 2002, Moncton, NB, Canada: Proceedings pp. 90 - 97
Main Authors Bahi, J.M., Contassot-Vivier, S., Couturier, R.
Format Conference Proceeding
LanguageEnglish
Published IEEE 2002
Subjects
Clustering algorithms
Concurrent computing
Context
Differential equations
Distributed algorithms
Iterative algorithms
Parallel algorithms
Scattering
Testing
Workstations
Online AccessGet full text
ISBN9780769516264
0769516262
DOI10.1109/HPCSA.2002.1019139

Cover

More Information
Summary:The subject of this paper is to show the very high power of asynchronism for iterative algorithms in the context of global computing, that is to say, with machines scattered all around the world. The question is whether or not asynchronism helps to reduce the communication penalty and the overall computation time of a given parallel algorithm. The asynchronous programming model is applied to a given problem implemented with a multi-threaded environment and tested over two kinds of clusters of workstations; a homogeneous local cluster and a heterogeneous non-local one. The main features of this programming model are exhibited and the high efficiency and interest of such algorithms is pointed out.
ISBN:9780769516264
0769516262
DOI:10.1109/HPCSA.2002.1019139