Improved Program Performance Using a Cluster of Workstations
暂无分享,去创建一个
Computers linked via a network can be used together to provide a powerful computing resource. Spreading the work of computationally intensive calculations across a cluster of computers considerably reduces the elapsed execution time compared to that achieved on a single workstation. Overall performance is limited by the slowest machine in the cluster. Here we investigate mechanisms by which the effects of slow machines can be ameliorated.
[1] Vaidy S. Sunderam,et al. PVM: A Framework for Parallel Distributed Computing , 1990, Concurr. Pract. Exp..
[2] Shirley Williams,et al. A Cluster Computing Implemetation of a Monte Carlo Simulation of a Particle Growth Mechanism , 1994, Parallel Algorithms Appl..