Uniform load distributing method for use in executing parallel processing in parallel computer

作者: Fumiyasu Hirose , Hidetoshi Matsuoka

DOI:

关键词: Process (computing)SynchronizingParallel computingComputer scienceWaiting timeParallel processing (DSP implementation)

摘要: A uniform load distributing method for use in executing a parallel processing computer plurality of processings manner. The including processors individual processings, network conducting communication between the processors, and synchronizing mechanism issuing an execution start command next step to all under condition that completion information is received from inter-processor has been completed. All are synchronized with one another each process calculation multitude manner by respective only whose output data current used immediately when necessary ready wherein execute processings; informing execution, after completed, mechanism; executing, during waiting time until given mechanism, input required at earliest timing step.

参考文章(9)
M.H. Willebeek-LeMair, A.P. Reeves, Strategies for dynamic load balancing on highly parallel computers IEEE Transactions on Parallel and Distributed Systems. ,vol. 4, pp. 979- 993 ,(1993) , 10.1109/71.243526
Philippe-Hubert deRivet, Patrick Dufond, Henri Verdier, Jacques Bienvenu, Benjamin S. Franklin, John J. Bradley, Claude Carre, Duc L. Tuong, Apparatus and method for transferring information units between processes in a multiprocessing system ,(1978)
A. Dinning, A survey of synchronization methods for parallel computers IEEE Computer. ,vol. 22, pp. 66- 77 ,(1989) , 10.1109/2.30733