Optimizing locationing of multiple masters for master-worker grid applications
PARA（2004）
摘要
The problem of allocating a large number of independent tasks to a heterogeneous computing platform is considered. A non oriented graph is used to model a Grid, where resources can have different speeds of computation and communication. We claim that the use of multiple masters is necessary to achieve good performance on large-scale platforms. The problem considered is to find the most profitable master locations in order to optimize the platform throughput.
更多查看译文
关键词
optimizing locationing,profitable master location,multiple master,independent task,heterogeneous computing platform,good performance,large number,large-scale platform,master-worker grid application,different speed,platform throughput,non oriented graph,heterogeneous computing,profitability
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要