期刊文献+

大规模并行计算机系统性能测评体系 被引量:2

Performance evaluation methodology for massively parallel computer systems
下载PDF
导出
摘要 复杂的大规模并行计算机系统需要能客观反映系统性能的测评方法,单个指标难以全面评价系统的性能特点。从用户需求出发,给出了大规模并行计算机系统用户适用性概念,利用适用性概念,建立了大规模系统性能测评体系,包括总体适用性、分项适用性、适用性概念、准则和Benchmark程序。整个测评体系尽量消除主观因素,做到客观定量,利用测评体系,借助性能分析数据获取工具,在得到量化的分项适用性的基础上,通过权重公式可以求出总体适用性,根据总体适用性的大小来判断不同大规模计算机系统是否满足用户的需求。 The complexity of modern massively parallel computer systems requires sophisticated method to facilitate the evaluation of system performance, and it is difficult to measure all the character- istics of systems using a single metric. The concept of applicability is given from the demand of users for supercomputers. Based on the applicability concept, we present a performance evaluation methodology for massively parallel computer systems. The methodology, including total applicability, subentry appli- cability, the concepts of subentry, metrics and benchmarks, can avoid the personal factors and obtains the impersonality results for systems perfm'manee. After collecting data using performance analysis tools, the data can be used to get the subentry applicability. Then the total applicability can be calculat- ed by the weight equation. Based on the total applicability, one can evaluate whether the massively par- allel computer systems satisfy the demand of user or not.
出处 《计算机工程与科学》 CSCD 北大核心 2013年第3期25-30,共6页 Computer Engineering & Science
基金 国家863计划资助项目(2012AA01A301) 国家自然科学基金资助项目(60970033)
关键词 性能测评 大规模并行计算机系统 用户适用性 per{ormance evaluation massively parallel computer system applicability of user
  • 相关文献

参考文献9

  • 1Dongarra J J, Luszczek P, Petitet A. The LINPACK bench mark,Past, present, and future[J]. Concurrency and Com putation: Practice and Experience, 2003, 15(9):803-820.
  • 2High productivity computer systems [ EB/OL]. [ 2011-03-12]. http ://www. highproductivity, org/.
  • 3Chung H H, Wu C F, Jremy S. A. Towards efficient super- computing:A quest for the right metric[C]//Proc of the 19th IEEE International Parallel and Distributed Processing Sym-posium, 2005 : 1.
  • 4SPEC benchmarks[EB/OL]. [2011-03-12]. http: //www. spec. org/benchmarks, html .
  • 5Luszczek P, Dongarra J, Koester D, et al. Introduction to the HPC challenge benchmark suite[EB/OL].[2011-03-12]. http://icl, cs. utk. edu/hpcc/pubs March.
  • 6Gustafson J. Purpose-based benehmarks[EB/OL]. [2011-05- 26]. http://www, highproductivity, org/IJHPCA/8f-Gustaf- son- Productivity. pdf.
  • 7Andrew F, Victor B, Lorin H, et al. Analysis of parallel software development using the relative development time productivity metric[J]. CTWatch, 2006, 2(4A):46-51.
  • 8Sterling T. Productivity metrics and models for high per- formance computing[EB/OL]. [2004-08-29]. http://www. highproductivity, org/IJ HPCA/4f-Sterling-ProductivityPap- err3. pdf.
  • 9Tzu Y C, Meghan G, Beth S, et al. Metrics for ranking the performance of supercomputers[J]. CTWatch, 2006,2(4B) : 46-67.

同被引文献6

引证文献2

二级引证文献3

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