PARALLELIZATION STRATEGIES FOR DISTRIBUTED GRID COMPUTING
Grid and distributed computing systems have been used successfully in many different applications that range from numerical modelling to web applications. However, in order to maximise the benefits of using such systems different partitioning and parallelisation strategies must be employed, which depends on the applications as well as the underlying architectures. In order to demonstrate the various strategies, examples based on modelling and discrete event stochastic simulation techniques commonly used in science and engineering are considered. The problems that are encountered in each case are discussed, and the advantages and disadvantages of using the different strategies are presented.
Souheil Khaddaj
Faculty of Computing, Information Systems and Mathematics, Kingston University,Kingston upon Thames, KT12EE, UK
国际会议
武汉
英文
256-260
2009-10-16(万方平台首次上网日期,不代表论文的发表时间)