A New Dynamic Scheduling Algorithm for Real-Time Homogenous Multiprocessor Systems

摘要：

Many time-critical applications require predictable performance and tasks in these applications have deadlines to be met. In this paper, we develop a new algorithm for non-preemptive scheduling of dynamically arriving real-time tasks (aperiodic task) in multiprocessor systems.The new algorithm includes two policies: task selection policy and processor selection policy, named grouping policy and properly choosing policy (PCP), respectively.Grouping policy and PCP aim to maximize the effective utilization of resources and processors, respectively.Simulation results show this algorithm outperforms the myopic algorithm and the thrift algorithm.

关键词： Multiprocessor Systems Dynamic Scheduling Non-preemptive Scheduling And Aperiodic Task

作者: Yuhai Yang Xuelian Bin Shengsheng Yu Jingli Zhou

作者单位: National Storage System Laboratory, School of Computer Science & Technology, Huazhong University of Airforce Army Radar Academy, Wuhan, Hubei 430019, China National Storage System Laboratory, School of Computer Science & Technology, Huazhong University of

会议类型: 国际会议

会议名称: 2006 International Symposium on Distributed Computing and Applications to Business,Engineering and Science(2006年国际电子、工程及科学领域的分布式计算应用学术研讨会)

会议地点: 杭州

会议语种:英文

页码: 1064-1068

在线出版日期: 2006-10-12（万方平台首次上网日期，不代表论文的发表时间）