DocumentCode :
3241133
Title :
Adaptive matrix multiplication in heterogeneous environments
Author :
Hong, Bo ; Prasanna, Viktor K.
Author_Institution :
Dept. of Electr. Eng. Syst., Univ. of Southern California, Los Angeles, CA, USA
fYear :
2002
fDate :
17-20 Dec. 2002
Firstpage :
129
Lastpage :
136
Abstract :
In this paper an adaptive matrix multiplication algorithm for dynamic heterogeneous environments is developed and evaluated. Unlike the state-of-the-art approaches, where load balancing is achieved through unequal distribution of the matrix data among the heterogeneous nodes, the matrices in our approach are partitioned into blocks of equal size. Task allocation and the block size are adapted during run time. Data pre-fetch is used to perform efficient communication. Our approach enables the use of various task scheduling heuristics. Further we show that the control and coordination overheads of this approach are negligible when compared with the overall execution time. The effectiveness of the approach is verified through a configurable simulator developed for understanding the performance of heterogeneous computing environments.
Keywords :
distributed processing; matrix multiplication; resource allocation; block size; distributed heterogeneous computing systems; distributed resources; heterogeneous computing; heterogeneous environments; load balancing; matrix multiplication; task allocation; Communication system control; Costs; Distributed computing; Heuristic algorithms; High performance computing; Libraries; Linear matrix inequalities; Load management; Military computing; Partitioning algorithms;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Parallel and Distributed Systems, 2002. Proceedings. Ninth International Conference on
ISSN :
1521-9097
Print_ISBN :
0-7695-1760-9
Type :
conf
DOI :
10.1109/ICPADS.2002.1183389
Filename :
1183389
Link To Document :
بازگشت