计算机应用 ›› 2014, Vol. 34 ›› Issue (3): 663-667.DOI: 10.11772/j.issn.1001-9081.2014.03.0663

• 先进计算 • 上一篇    下一篇

延迟可扩展性与并行执行时间的关系

熊焕亮1,2,3,曾国荪1,3,吴沧海2,匡桂娟1,3,4,何火娇2   

  1. 1. 国家高性能计算机工程技术中心 同济分中心,上海201804;
    2. 江西农业大学 软件学院,南昌330045;
    3. 同济大学 计算机科学与技术系,上海201804;2.江西农业大学 软件学院,南昌330045;
    4. 青岛农业大学 理学与信息科学学院,山东 青岛266109
  • 收稿日期:2013-09-16 修回日期:2013-11-11 出版日期:2014-03-01 发布日期:2014-04-01
  • 通讯作者: 熊焕亮
  • 作者简介:熊焕亮(1977-),男,江西新建人,讲师,博士研究生,CCF会员,主要研究方向:并行分布式计算、云计算;曾国荪(1964-),男,江西吉安人,教授,博士生导师,博士,CCF高级会员,主要研究方向:并行计算、可信软件、信息安全;吴沧海(1979-),女,浙江上虞人,讲师,硕士,主要研究方向:并行分布式计算、云计算;匡桂娟(1972-),女,山东青岛人,讲师,博士研究生,主要研究方向:分布式计算、云计算;何火娇(1949-),女,江西鄱阳人,教授,主要研究方向:并行计算、农业信息化。
  • 基金资助:

    国家863计划项目;国家自然科学基金资助项目;上海市优秀学科带头人计划项目;教育部网络时代的科技论文快速共享专项研究课题

Relationships between latency scalability and execution time

XIONG Huanliang1,2,3,ZENG Guosun1,3,WU Canghai2,KUANG Guijuan1,3,4,HE Huojiao2   

  1. 1. Department of Computer Science and Technology, Tongji University, Shanghai 201804, China;
    2. Software College, Jiangxi Agricultural University, Nanchang Jiangxi 330045, China;
    3. Tongji Branch, National Engineering and Technology Center of High Performance Computer, Shanghai 201804, China;
    4. Science and Information College, Qingdao Agricultural University, Qingdao Shandong 266109, China
  • Received:2013-09-16 Revised:2013-11-11 Online:2014-03-01 Published:2014-04-01
  • Contact: XIONG Huanliang

摘要:

针对以往关于可扩展性研究中未充分考虑并行执行时间因素,可扩展性与并行执行时间的关系仍未研究清楚的问题,深入和全面研究延迟可扩展性和并行执行时间的关系,得出并证明了不同算法〖CD*2〗机器组合体在相同初始状态下进行延迟扩展后,若执行更快的组合体具有更好的延迟扩展性,则该组合体在扩展后仍将保持更快等重要结论。这些结论丰富了可扩展性和并行执行时间关系的研究内容,为并行计算延迟扩展获得理想扩展性能提供了理论依据。最后,通过对不同算法〖CD*2〗机器组合体进行扩展实验,进一步验证了结论的有效性。

关键词: 并行计算, 可扩展性, 延迟度量, 执行时间

Abstract:

Concerning the problem that previous studies on the scalability do not fully consider parallel execution time, and the relationships between latency scalability and parallel execution time have not been yet studied thoroughly, this paper studied the relationships between latency scalability and parallel execution time deeply and fully. Thereby some important conclusions were drawn, and they were about the relationships between latency scalability and parallel execution time after different algorithm-machines were extended from the same initial state. Then the proof of the above conclusions was given in this paper. The derived conclusions enriched the research content about the relationships between latency scalability and parallel execution time and provided a theoretical basis for obtaining ideal latency scalability of parallel computing. Finally the important conclusions and analytical expressions were verified through experimental results obtained for different algorithm-machines.

Key words: parallel computing, scalability, latency metric, execution time

中图分类号: