期刊文献+

同构DVS集群中基于自适应阈值的并行任务节能调度算法 被引量:9

Adaptive Threshold-Based Energy-Efficient Scheduling Algorithm for Parallel Tasks on Homogeneous DVS-Enabled Clusters
在线阅读 下载PDF
导出
摘要 目前,高能效的并行任务调度算法设计已经成为集群系统的研究热点.现有基于复制的节能调度算法主要利用阈值平衡系统的性能和能耗,但随机设置的阈值无法根据性能需求和环境参数等特征自动调节,导致调度算法存在一定的局限性.文中提出一种面向同构集群系统的两阶段节能调度算法ATES(Adaptive Threshold-basedEnergy-efficient Scheduling).首先,设计一种基于自适应阈值的任务复制策略,该策略能够自动计算最佳阈值,利用该阈值获取近似最优的任务分组.然后,将各分组任务调度到支持DVS的处理器上,并充分利用任务之间的空闲时间降低处理器电压.该算法将任务复制策略与电压调节技术有机结合,在调度过程中能够自动调整阈值,有效提高调度算法的能效.为了验证ATES算法的合理性,通过典型应用进行仿真实验,并与常见任务调度算法进行比较,结果表明ATES算法能够更好地实现性能和能耗之间的平衡. Increasing attention has been directly towards the energy efficient scheduling algo- rithms for parallel applications in high performance clusters. The existing duplication-based ener- gy scheduling algorithms mainly leverage a threshold to balance system performance and energy consumption. However, the threshold is given randomly which cannot flexibly adapt to the clus- ter system and application performance requirements, thus making the ideal energy efficient scheduling results. In this paper, we propose a novel two-phase Adaptive Threshold-based Energy- efficient Scheduling algorithm fATES). At first, we propose an adaptive threshold-based task duplication strategy, which can obtain an optimal tnresnom. It then leverages the optimal threshold to balance schedule lengths and energy savings by selectively replicating predecessor of a task. Therefore, the proposed task duplication strategy can get the suboptimal task groups. Then, it schedules the groups on the DVS-enabled processors to reduce processor energy whenever tasks have slack time due to task dependencies. The algorithm combines DVS(Dynamic Voltage Scal- ing) technique with adaptive threshold-based task duplication strategy. It justifies the threshold automatically to improve the energy efficiency of the scheduling algorithm. To illustrate the effec- tiveness of ATES, we simulate the real-world applications and compare ATES with the other four common task scheduling algorithms. Extensive experiment results show that our algorithm can much effectively balance schedule lengths and energy savings.
出处 《计算机学报》 EI CSCD 北大核心 2013年第2期393-407,共15页 Chinese Journal of Computers
基金 国家自然科学基金(61202173 61272107 61103068) 高等学校博士学科点专项科研基金(20090072110035 20110072120017) 武汉大学软件工程国家重点实验室开放基金(SKLSE20080720 SKLSE2012-09-29) 同济大学嵌入式系统与服务计算教育部重点实验室开放基金资助
关键词 高性能集群 动态电压调节 任务复制 自适应阈值 调度算法 high-performance clusters dynamic voltage scaling (DVS) task duplication adap tive threshold scheduling algorithm
作者简介 刘伟,男,1978年生,博士,副教授,中国计算机学会(CCF)会员,主要研究方向为并行计算、绿色计算.E—mail:liuweiwhut@gmail.com. 尹行,男,硕士研究生,研究方向为并行计算、绿色计算. 段玉光,男,硕士研究生,研究方向为高性能计算. 杜薇,女,博士,讲师,研究方向为分布式计算、可信计算. 王伟,男,博士,副教授,中国计算机学会(CCF)会员,研究方向为绿色计算、可信计算. 曾国荪,男,博士,教授,博士生导师,中国计算机学会(CCF)高级会员,研究领域为并行计算、绿色计算.
  • 相关文献

参考文献26

  • 1Bajai Rashmi, Agrawal Dharma P. Improving scheduling of tasks in a heterogeneous environment. IEEE Transactions on Parallel and Distributed Systems, 2004, 15(2): 107-118.
  • 2Zong Zi-Liang, Adam Manzanares, Ruan XiaJun, Qin Xiao. EAD and PEBD Two energy aware duplication sched- uling algorithms for parallel tasks on homogeneous clusters. IEEE Transactions on Computers, 2011, 60(3) 360 374.
  • 3孙毓忠,臧斌宇.面向高效能的软件及其设计、分析与实现方法专刊前言[J].软件学报,2012,23(2):177-178. 被引量:2
  • 4Tang Yuan. Research on the communication problem of large seale scientific computing on high performance cluster envi ronmentEPh. D. dissertationS. Chinese Academy of Sciences, Beijing, 2004.
  • 5Dick R P, Rhodes D L, Wolf W. TGFF: Task graphs fo free//Proceedings of the 6th International Workshop Hard ware/Software Codesign (Codes/CASHE). Seattle, USA 1998:97 lO1.
  • 6Ge Rong, Feng Xi Zhou, Feng Wu-Chun, Cameron Kirk W. CPU MISER: A performance directed, run time system for power-aware elusters//Proceedings of the 2007 International Conference on Parallel Processing (ICPP). Xi' an, China, 2007:18-25.
  • 7Lee Young Choon, Zomaya Albert Y. Energy conscious scheduling for distributed computing systems under different operating conditions. IEEE Transactions on Parallel and Distributed Systems, 2011, 22(8): 1374-1381.
  • 8Ma Yan, Gong Bin, Zou Li-Da. Energy-efficient scheduling algorithm of task dependent graph on DVS-unabled cluster system//Proceedings of the ]0th ]EEE/ACM International Conference on Grid Computing (CCGrid). Banff, Canada, 2009, 217-224.
  • 9Darbha S, Agrawal D P. Optimal scheduling algorithm for distributed-memory machines. IEEE Transactions on Parallel and Distributed Systems, 1998, 9(1) 87-95.
  • 10Wang Li-Zhe, von Laszewski Gregor et al. Towards energy aware scheduling for precedence constrained parallel tasks in a cluster with DVFS//Proeeedings of the 10th IEEE/ACM International Conference on Cluster, Cloud and Grid Compu- ting(CCGrid). Melbourne, Australia, 2010= 368 377.

二级参考文献54

  • 1黄金贵,陈建二,陈松乔.网络集群计算系统中的并行任务调度[J].计算机学报,2004,27(6):765-771. 被引量:16
  • 2韩建军,李庆华,缪天鹏,Abbas A.Essa.实时多处理器系统中基于能量节约的动态调度算法[J].小型微型计算机系统,2006,27(4):691-694. 被引量:1
  • 3杜晓丽,蒋昌俊,徐国荣,丁志军.一种基于模糊聚类的网格DAG任务图调度算法[J].软件学报,2006,17(11):2277-2288. 被引量:48
  • 4....http://www.top500.org,,2005/09/01..
  • 5http://www.green500.org/home.php.
  • 6Li KQ. Performance analysis of power-aware task scheduling algorithms on multiprocessor computers with dynamic voltage and speed. IEEE Trans. on Parallel and Distributed System, 2008,19(11): 1484-1497. Idol: 10.1109/TPDS.2008.122].
  • 7Dong Y, Chen J, Yang XJ, Deng L, Zhang XM. Energy-Oriented openmp parallel loop scheduling. In: Prec. of the 2008 IEEE Int'l Symp. on Parallel and Distributed Processing with Applications (ISPA 2008). Washington: IEEE Computer Society, 2008. 162-169. [doi: 10.1109/ISPA.2008.68].
  • 8Kadayif I, Kandemir M, Karakoy M. An energy saving strategy based on adaptive loop parallelization. In: Proc. of the 39th Annual Design Automation Conf. (DAC 2002). New York: ACM, 2002. 195-200. [doi:10.1145/513918.513968].
  • 9Kadayif I, Kandemir M, Kolcu I. Exploiting processor workload heterogeneity for reducing energy consumption in chip multiprocessors. In: Proc. of the Design, Automation and Test in EuropeConf. and Exhibition (DATE 2004), Vol.2. 2004. 1158- 1163. [doi: 10.1109/DATE.2004.1269048].
  • 10Li J, Martinez JF. Dynamic power-performance adaptation of parallel computation on chip multiprocessors. In: Proc. of the 12th Int'l Syrup. on High-Performance Computer Architecture (HPCA-12). 2006. [doi: 10.1109/HPCA.2006.1598114].

共引文献393

同被引文献127

  • 1陈立华,梅亚东,董雅洁,杨娜.改进遗传算法及其在水库群优化调度中的应用[J].水利学报,2008,39(5):550-556. 被引量:78
  • 2史琰,刘增基,盛敏.一种保证负载均衡的网络资源分配算法[J].西安电子科技大学学报,2005,32(6):885-889. 被引量:6
  • 3陈君波,叶庆卫,周宇,曹小华.一种新的混合变异粒子群算法[J].计算机工程与应用,2007,43(7):59-61. 被引量:13
  • 4梁宏斌,彭代渊,刘燕.基于SMDP的动态云计算资源优化管理系统[J].软件学报,2012,23(S1):25-37.
  • 5刘勇鹏,朱鸿,卢凯,迟万庆,刘勇燕.基于NInO模型的大规模计算系统的功耗控制[J].软件学报,2011,22(Suppl.(2)):199-207.
  • 6TOOSI A N. Resource Provisioning Policies to Increase IaaS Provider's Profit in a Federated Cloud Environment[C]// proceedings of the 13rd International Conference on High Performance and Communications, Banff, Canada, 2011: 279-287.
  • 7Goller A,Leberl F.Radar Image Processing with Clusters of Computers[J].IEEE Aerospace and El-ectronics Systems Magazine,2009,24(1):18-22.
  • 8Li Yu,Liu Yi,Qian Depei.An Energy-aware Heuristic Scheduling Algorithm for Heterogeneous Clusters[C]//Proceedings of the 15th International Conference on Parallel and Distributed Systems.[S.l.]:IEEE Press,2009:407-413.
  • 9Jejurikar R,Pereira C,Gupta R.Leakage Aware Dynamic Voltage Scaling for Real-time Embedded Systems[C]//Proceedings of the 41st Annual Design Automation Conference.San Diego,USA:ACM Press,2004:275-280.
  • 10Liu Wei,Yin Hang,Du Wei.Dynamic Threshold-based Energy Efficient Scheduling Algorithm for Parallel Tasks on Homogeneous DVS-enabled Clusters[C]//Proceedings of 2011 International Conference on Cyberenabled Distributed Computing and Knowledge Discovery.Washington D.C.,USA:IEEE Press,2011:321-328.

引证文献9

二级引证文献25

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