Parallel Algorithms / Architecture Synthesis, AIZU International Symposium on (1997)
Aizu-Wakamatsu, Fukushima, JAPAN
Mar. 17, 1997 to Mar. 21, 1997
Kun-Ming Yu , Dept. of Comput. Sci., Chung-Hua Polytech. Inst., Hsin-Chu, Taiwan
S.J.-W. Wu , Dept. of Comput. Sci., Chung-Hua Polytech. Inst., Hsin-Chu, Taiwan
Tzung-Pei Hong , Dept. of Comput. Sci., Chung-Hua Polytech. Inst., Hsin-Chu, Taiwan
The static task allocation problem and the dynamic load balancing problem are relevant issues when using a multiprocessor computer system to execute parallelized tasks. The paper presents an artificial intelligence (AI) strategy to resolve the above problems under the PVM (Parallel Virtual Machine). The AI technique is employed to accurately predict better allocation for PVM tasks in their initial assignment as well as execution time. The performance characteristics of the proposed load balancing algorithm are also examined for a homogeneously distributed system. Three different problems are implemented for evaluating our algorithm's performance. Experimental results demonstrate that our algorithm performs more effectively than conventional approaches.
parallel machines; load balancing algorithm; prediction; static task allocation problem; dynamic load balancing problem; multiprocessor computer system; parallelized tasks; artificial intelligence strategy; PVM; Parallel Virtual Machine; AI technique; PVM task allocation; performance characteristics; homogeneously distributed system; algorithm performanc
T. Hong, K. Yu and S. Wu, "A load balancing algorithm using prediction," Parallel Algorithms / Architecture Synthesis, AIZU International Symposium on(PAS), Aizu-Wakamatsu, Fukushima, JAPAN, 1997, pp. 159.