期刊名称：Journal of Emerging Trends in Computing and Information Sciences
电子版ISSN：2079-8407
出版年度：2012
卷号：3
期号：2
页码：231-240
出版社：ARPN Publishers
摘要：This paper proposes distributed shared memory cluster architecture with load balancing. The architecture is based on dynamic task scheduling approach for distribution and assignment. It enhances the performance of communication across clusters for data access. The proposed dynamic load balancing model uses the concept of work stealing, which intelligently balances the load among different nodes. The work stealing consistently provides higher system utilization when many jobs are running with varying characteristics. This results in efficient use of the system. The performance analysis shows the proposed architecture to outperform the previously proposed distributed shared memory clusters in terms of scalability and efficiency.
关键词：Block Data Layout; Data Locality; Task Distribution; Master-Slave Paradigm; Work Stealing.
