期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

多核CPU-GPU异构平台下并行Agent仿真负载均衡方法 被引量：3

Load balancing mechanism for parallel agent-based simulation on multi-core CPU and GPU heterogeneous platform
在线阅读 下载PDF
导出
摘要 多核中央处理器(central processing unit,CPU)-图形处理器(graphic processing unit,GPU)异构平台为并行Agent仿真提供了一个新的硬件执行平台,而负载均衡方法是充分利用硬件计算资源、提高并行仿真运行性能的一个有效途径。针对多核CPU-GPU异构平台下并行Agent仿真的负载均衡问题,建立了面向多核CPU-GPU的并行Agent仿真多层负载分配模型,提出了基于带约束的k-means空间聚类算法的并行Agent仿真静态负载划分方法和动态负载均衡策略,并给出了划分子集间的可交互性判定,以过滤掉大量不会发生交互关系的Agent之间的交互判定计算。最后通过实验验证了本文提出方法的有效性。 The platforms equipped with multi-core central processing units （CPU） and graphics processing units （ GPU） provide a new hardware for executing parallel agent-based simulations （PABS） and the load balancing mechanism is an effective approach to make the best of hardware resources and improve the running performance of parallel simulations. In order to solve the load balancing for PABS on multi core CPU and GPU her erogeneous platforms, a multiqayer load distributing model for PABS is built and a static load partitioning algorithm based on the constrained k-means clustering algorithm and a dynamic load balancing algorithm are proposed. The method of finding interactions between partitions is presented so as to avoid a lot of unnecessary computations between agents that actually can not interact with each other. The experiments show that the mechanism is viable and effective.
作者 王维平 余文广 侯洪涛 李群
机构地区 国防科学技术大学信息系统与管理学院
出处 《系统工程与电子技术》 EI CSCD 北大核心 2012年第11期2366-2373,共8页 Systems Engineering and Electronics
基金 国家自然科学基金(60974073 60974074)资助课题
关键词 并行Agent仿真 多核中央处理器 图形处理器 负载均衡 parallel agent-based simulation （PABS） multi-core central processing units（CPU） graphic processing unit（GPU） load balancing
分类号 TP391.9 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献16

  • 1Popov K, Vlassov V, Rafea M, et al. Parallel agent based simu lation ona cluster of workstation[C]// Proc. of the 9th Interna tional European Conference on Parallel and Distributed Corn puting, 2003:470 - 480.
  • 2Gebre M R. MUSE= a parallel agent based simulation environ- ment[D]. Miami, USA: Miami University, 2009.
  • 3Cosenza B, Cordasco G, Chiara R D, et al. Distributed load bal- ancing for parallel agent-based simulations [C]//Proc. of the 19th Euromicro International Conference on Parallel, Distribu- ted and Network-Based Computing, 2011 : 62 - 69.
  • 4Chen T P, Chen Y K. Challenges and opportunities of obtaining performance from multi-core CPUs and many core GPUs[C]// Proc. of the 34th IEEE International Conference on Acoustics, Speech and Signal Processing, 2009 :613 - 616.
  • 5Scheutz M, Schermerhorn P. Adaptive algorithms for the dynamic distribution and parallel execution of agent based models[J]. Journal of Parallel and Distributed Conzputing, 2006,66(8):1037-1051.
  • 6Wang Y W, Lees M, Cai W T, et al. Cluster based partitioning for agent based crowd simulations[C]// Proc. of the Winter Sir~ulation Conference, 2009:1047-1058.
  • 7Oguara T, Chen D, Theodoropoulos G, et al. An adaptive load management mechanism for distributed simulation of multi agent systems[C]// Proc. of the 9th IEEE International Symposium on Distributed Simulation and Real Time Applications, 2005: 179 - 186.
  • 8Long Q Q, l.in J, Sun Z X. Agent scheduling model for adaptive dy namic load balancing in agent based distributed simulations[J]. Sire ulation Modelling Practice and Theory, 2011, 19(4) : 1021 - 1034.
  • 9Jang M W, Agha G. Agent framework services to reduce agent com munication overhead in large-scale agent-based simulations[J].Sim- ulation Modelling Practice and Theory, 2006, 14(6): 679- 694.
  • 10Aaby B G, Perumalla K S, Seal S K. Efficient simulation of agent- based models on multi-GPU and multi-core clusters[C]//Proc, of the 3rd International ICST ()mference on Simulation Tools and Techniques , 2010.

同被引文献30

  • 1杜国红,韦伟,李路遥.作战仿真实体组件化建模研究[J].系统仿真学报,2015,27(2):234-239. 被引量：15
  • 2胡凯.网络分布式并行计算的负载平衡[J].北京航空航天大学学报,2004,30(11):1121-1124. 被引量：5
  • 3王学慧,杨菲,黄柯棣.并行分布仿真中负载平衡的调度算法研究[J].系统仿真学报,2005,17(8):2018-2021. 被引量：4
  • 4Cai W, Yuan Z, Low M Y, et al. Federate migration in HI.A- based simulation[J]. Future Generation Computer Systems, 2005, 21(1): 87-95.
  • 5Azzedine B. Dynamic load balancing using grid services for HLA based simulations on largscale distributed systems[C]//Proc, of the 13th IEEE/ACM International Symposium on Distributed Sire ulation and Real Time Applications, 2009 :175 - 183.
  • 6Karger D R. Simple efficient load balancing algorithms for peer to peer systems[C]//Proc, of the 6th Annual ACM Symposium on Parallelism in Algorithms and Architectures, 2004 : 36 - 43.
  • 7Ajaltouni E E. An efficient dynamic load balancing scheme for distributed simulations on a grid infrastructure[C]//Proc, of the 12th International Symposium on Distributed Simulation and Real-Time Applications, 2008 : 61 - 68.
  • 8Huiskamp W, Jense H. An HLA based flight simulation archi- tecture[C]//Proc, of the AIAA Modeling and Simulation Technologies Conference and Exhibit, 2000 : 1 - 8.
  • 9Tan G, Lira K C. Load distribution services in HLA[C]//Proc. of the 8th IEEE International Symposium on Distributed Simu- lation and Real Time Applications, 2004 : 113 - 221.
  • 10Massie M L, Chun B N, Culler D E. The ganglia distributed moni toting system: design, implementation, and experience[J]. Paral lel Computing, 2004, 30(7) : 817 - 840.

引证文献3

二级引证文献2

系统工程与电子技术
2012年 第11期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部