期刊文献+

并行计算系统可扩展性的研究 被引量:3

Research on scalability of parallel computing system
下载PDF
导出
摘要 可扩展性是设计并行计算系统和并行算法所要考虑的一个重要性能指标。分析了等效率、等速度、平均延迟和等并行计算开销比几种并行系统可扩展性模型的特征,提出了一种新的更有效的可扩展性度量标准。通过实验结果分析,该模型能很好地评测并行计算系统的可扩展性。 Scalability has become an important concept in parallel computer system and parallel algorithms.The characteristics of four existing scalability metrics are analysed for parallel computing system,i.e.,the iso-efficiency metrics,iso-speed metrics,average latency metrics and iso-ratio-of-parallel calculation-overhead metrics.A new scalability metric which reflects the scalability of parallel computer system more directly and precisely is proposed.This paper presents some experiments.The results show that this metric can estimate preferably the scalability of parallel computing systems.
出处 《计算机工程与应用》 CSCD 北大核心 2011年第21期47-49,共3页 Computer Engineering and Applications
基金 山东省高等学校重点实验研究项目(No.2005-400) 曲阜师范大学校科研项目(No.XJ0734)
关键词 体系结构 并行计算 性能 可扩展性 architecture parallel computing performance scalability
  • 相关文献

参考文献8

二级参考文献11

  • 1Sterling T, Becher D J, Savarese D. Beowulf." A Parallel Workstation for Scientific Computation[C]//Proc. of International Conference on Parallel Processing. Washington D. C., USA: [s. n.], 1995.
  • 2Chen Jun, Li Xiaornei. A Practical Scalability Metric[C]//Proc. of the HPC Asia'2000. Singapore: [s. n.], 2000.
  • 3Alan H K, Horace P F. Measuring Parallel Processor Performance[J]. Communications ofACM, 1990, 33(5): 539-543.
  • 4Barbosa J, Tavanes J, Padilha A J. Linear Algebra Algorithm in a Heterogeneous Cluster of Personal Computers[C]//Proc. of the 9th Heterogeneous Computing Workshop. Cancun, Mexico: [s. n.], 2000.
  • 5Clematis A, Corana A. Modeling Performance of Heterogeneous Parallel Computing Systems[J]. Parallel Computing, 1999, 25(9): 1131-1146.
  • 6Xu Z,IEEE Paralel Distributed Technology,1996年,4卷,1期,9页
  • 7Sun X,IEEE Trans Parallel Distributed Systems,1994年,5卷,6期,599页
  • 8Ji Yongchang,Proc HPC Asia 2000,2000年,405页
  • 9Chen Jun,Proceedings of the HPC Asia 2000,2000年,403页
  • 10Sun X,IEEE Trans Parallel Distributed System,1994年,5卷,6期,599页

共引文献25

同被引文献28

  • 1江小平,李成华,向文,张新访,颜海涛.k-means聚类算法的MapReduce并行化实现[J].华中科技大学学报(自然科学版),2011,39(S1):120-124. 被引量:79
  • 2何家华,陈国良,单久龙.如何测量SMP机群可扩放性(英文)[J].软件学报,2004,15(7):977-986. 被引量:1
  • 3迟利华,刘杰,胡庆丰.数值并行计算可扩展性评价与测试[J].计算机研究与发展,2005,42(6):1073-1078. 被引量:10
  • 4SALMON J K, MORAES M A, DROR R O, et al. Parallel random numbers: as easy as 1, 2, 3 [ C]//SC'11 : Proceedings of 2011 In- ternational Conference for High Performance Computing, Networ- king, Storage and Analysis. New York: ACM, 2011: Article No. 16.
  • 5WANG M, GUO F, QU H, et al. Combined random number gener- ators: a review [C]//ICCSN 2011: Proceedings of the 2011 IEEE 3rd International Conference on Communication Software and Net- works. Piscataway: IEEE, 2011:443-447.
  • 6OYA K, KITADA T, TANAKA S. Study on random number genera- tor in Monte Carlo code [J]. Atomic Energy Society, 2011, 10(4) : 301 - 309.
  • 7LEHMER D H. Mathematical methods in large-scale computing u- nits [ C]// Proceedings of the Second Symposium on Large-Scale Digital Calculating Machinery. Cambridge: Harvard University Press, 1951:141-146.
  • 8KNUTH D E. The art of computer pwgramming, volume 2: seminumer- ical algorithms [ M]. 3rd ed. Boston: Addison-Wesley, 1998: 108.
  • 9MARTON K, SUCIU A, PETRICEAN D. A parallel unpredictable random number generator [ C]//Proceedings of the 2011 10th Roe- dunet International Conference: Networking in Education and Re- search. Piscataway: IEEE, 2011:1-5.
  • 10GAO S, PETERSON G D. GASPRNG: GPU accelerated sealable parallel random number generator library [ J]. Computer Physics Communications, 2013, 184(4) : 1241 - 1249.

引证文献3

二级引证文献1

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