The Community for Technology Leaders
Computer Architecture and High Performance Computing, Symposium on (2004)
Foz do Igua?u, PR - Brazil
Oct. 27, 2004 to Oct. 29, 2004
ISSN: 1550-6533
ISBN: 0-7695-2240-8
pp: 180-187
Hazem Fkaier , ?cole Sup?rieure des Sciences et Techniques de Tunis, Tunisie
Mohamed Jemni , ?cole Sup?rieure des Sciences et Techniques de Tunis, Tunisie
Michel Koskas , Universit? de Picardie Jules Verne, France
Christophe C?rin , Universit? de Picardie Jules Verne, France
ABSTRACT
The aim of the paper is to introduce techniques in order to optimize the parallel execution time of sorting on heterogeneous platforms (processors speeds are related by a constant factor). We develop a constant time technique for mastering processor load balancing and execution time in an heterogeneous environment. We develop an analytical model for the parallel execution time, sustained by preliminary experimental results in the case of a 2-processors systems. The computation of the solution is independent of the problem size. Consequently, there is no overhead regarding the sorting problem.
INDEX TERMS
in-core parallel sorting algorithms, heterogeneous computing, complexity of parallel algorithms
CITATION
Hazem Fkaier, Mohamed Jemni, Michel Koskas, Christophe C?rin, "Improving Parallel Execution Time of Sorting on Heterogeneous Clusters", Computer Architecture and High Performance Computing, Symposium on, vol. 00, no. , pp. 180-187, 2004, doi:10.1109/CAHPC.2004.21
78 ms
(Ver 3.3 (11022016))