作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2007, Vol. 33 ›› Issue (23): 81-83. doi: 10.3969/j.issn.1000-3428.2007.23.028

• 软件技术与数据库 • 上一篇    下一篇

动态可扩展机群系统任务分配算法

吴潜蛟1,兰 蓉2   

  1. (1. 长安大学信息工程学院,西安 710064;2. 西安交通大学经济与金融学院,西安 710061)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-12-05 发布日期:2007-12-05

Tasks Distribution Algorithm of Dynamic Scalable Cluster System

WU Qian-jiao1, LAN Rong2   

  1. (1. School of Information Engineering, Chang’an University, Xi’an 710064; 2. School of Economic & Finance, Xi’an Jiaotong University, Xi’an 710061)
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-12-05 Published:2007-12-05

摘要: 结点机性能差异及动态运行环境是导致系统运行状态忙闲不均的主要原因。该文提出了结点机差异测量的指标和方法,结合机群系统主/从计算模型和SPMD应用类型提出了3种任务分配算法。实践证明了该算法的有效性。

关键词: SPMD编程模型, 机群主/从计算模型, Monte Carlo仿真

Abstract: Difference of node machine performance and dynamic operation environment are main reasons to cause the unequal division. This paper proposes index and method of difference scaling, combines master/worker computing model with SPMD application types, and gives three kinds of load balancing algorithm. The application shows the algorithms is effective.

Key words: SPMD programming model, master/worker(M/W) computing model, Monte Carlo simulation

中图分类号: