期刊文献+

产出率并行加速比模型 被引量:1

Productivity Parallel Speedup Model
下载PDF
导出
摘要 针对并行计算系统的性能度量问题,在产出率度量模型的基础上,建立综合系统可靠性、通信、并行化控制和成本投入要素的产出率并行加速比模型,分析总结模型中各要素影响产出率并行加速比的关键因子,包括容错开销因子、通信开销因子、并行控制开销因子及成本开销因子,对上述关键因子进行模拟实验,以验证该模型的有效性。 Aiming at measurement of parallel computing system performance,based on productivity model,this paper proposes a productivity parallel speedup model,which integrates reliability,communication,parallel control and cost in the view of system scalability.The key factors affect parallel productivity including the factors of fault tolerant overhead,communication overhead,parallel control overhead and cost overhead are analyzed and tested to verify the validity of the model.
作者 王之元
出处 《计算机工程》 CAS CSCD 北大核心 2011年第5期10-12,共3页 Computer Engineering
基金 国家自然科学基金资助项目(60633050 60873014)
关键词 产出率模型 产出率并行加速比模型 高产出率计算系统 productivity model productivity parallel speedup model high productivity computing system
  • 相关文献

参考文献4

  • 1Kothe D B. Science Prospects and Benefits with Exascale Computing[R]. Oak Ridge National Laboratory, Tech. Rep.: ORNL/TM-2007/232, 2007.
  • 2祝永志,王国仁,李丙锋,魏榕晖.异构并行计算系统可扩展模型的实现[J].计算机工程,2009,35(17):97-99. 被引量:3
  • 3Snir M, Bade D. A Framework for Measuring Supercomputer Productivity[J]. International Jourmd of High Performance Computing Applications, 2004, 18(4): 417-432.
  • 4Elnozahy E N, Alvisi L, Wang Yimin, et al. A Survey of Rollback- recovery Protocols in Message-passing Systems[J]. ACM Computing Surveys, 2002, 34(3): 375-408.

二级参考文献5

  • 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.

共引文献2

同被引文献44

  • 1BansaI N,Kimbrel T,Prush K.Speed sca1ing to manage energy and temperature[J].Journal of the ACM,2007,4(1):1-39.
  • 2Wierman A,Andrew L L H,Tang Ao.Power-aware speed sca-ling in processor sharing systems:Optimality and robustness[J].Performance Evaluation,2012(69):601-622.
  • 3Burd T D,Brodersen R W.Energy efficient cmos microprocessor design[C]∥Proc.of The HICSS Conference.Jan.1995.
  • 4Benoit A,Cole M,Gilmore S,et al.Flexible Skeletal Programming with eSkel[J].Submitted to EuroPar 2005.Lisbon,Portagal,2005,3648:761-770.
  • 5MacDonald S,Anvik J,Bromling S,et al.From patterns toframeworks to parallel programs[J].Parallel Computing,2002(28):1663-1683.
  • 6Bromling S,MacDonald S,Anvik J,et al.Pattern-based Parallel Programming[C]∥Proceedings of the International Conference on Parallel Processing (ICPP’02).2002.
  • 7Macdonald S.Deferring Design Pattern Decisions and Automa-ting Structural Pattern Changes using a Design-Pattern-Based Programming System[J].ACM Transactions on Programming Languages and Systems,2007:1-45.
  • 8Yzelman A N,Bisseling R H.An object-oriented bulk synchronous parallel library for multicore programming[M]∥Concurrency and Computation:Practice and Experience Concurrency Computat.:Pract.Exper.2012,24(5):533-553.
  • 9Yu Ce,Xu Zhen.ParaModel:A Visual Modeling and Code Skeleton Generation System for Programming Parallel Applications[J].ACM SIGPLAN Notices,2008,43(4).
  • 10Benoit A,Cole M.Two Fundamental Concepts in Skeletal Parallel Programming[C]∥ICCS 2005,LNCS 3515.2005:764-771.

引证文献1

二级引证文献2

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