The Scalasca performance toolset architecture

被引：256
作者：
Geimer, Markus [2 ]
Wolf, Felix [1 ,2 ,3 ]
Wylie, Brian J. N. [2 ]
Abraham, Erika [3 ]
Becker, Daniel [2 ,3 ]
Mohr, Bernd [2 ]
机构：
[1] German Res Sch Simulat Sci, D-52062 Aachen, Germany
[2] Forschungszentrum Julich, Julich Supercomp Ctr, D-52425 Julich, Germany
[3] Rhein Westfal TH Aachen, Dept Comp Sci, D-52056 Aachen, Germany
来源：
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE | 2010年 / 22卷 / 06期
关键词：
parallel computing; performance analysis; scalability;
D O I：
10.1002/cpe.1556
中图分类号：
TP31 [计算机软件];
学科分类号：
081202 ; 0835 ;
摘要：
Scalasca is a performance toolset that has been specifically designed to analyze parallel application execution behavior on large-scale systems with many thousands of processors. It offers an incremental performance-analysis procedure that integrates runtime summaries with in-depth studies of concurrent behavior via event tracing, adopting a strategy of successively refined measurement configurations. Distinctive features are its ability to identify wait states in applications with very large numbers of processes and to combine these with efficiently summarized local measurements. In this article, we review the current toolset architecture, emphasizing its scalable design and the role of the different components in transforming raw measurement data into knowledge of application execution behavior. The scalability and effectiveness of Scalasca are then surveyed from experience measuring and analyzing real-world applications on a range of computer systems. Copyright (C) 2010 John Wiley & Sons, Ltd.
引用
收藏
页码：702 / 719
页数：18
相关论文
共 28 条
  • [1] [Anonymous], 2005, P INT C PARCO PRAG C
  • [2] [Anonymous], NAS03010 NASA AM RES
  • [3] Becker D, 2007, LECT NOTES COMPUT SC, V4757, P315
  • [4] FRINGS W, 2009, P ACM IEEE SC 09 C P
  • [5] Fürlinger K, 2003, LECT NOTES COMPUT SC, V2790, P127
  • [6] Geimer M, 2007, LECT NOTES COMPUT SC, V4699, P398
  • [7] Geimer M, 2006, LECT NOTES COMPUT SC, V4192, P303
  • [8] Geimer M, 2008, ADV PAR COM, V15, P645
  • [9] A scalable tool architecture for diagnosing wait states in massively parallel applications
    Geimer, Markus
    Wolf, Felix
    Wylie, Brian J. N.
    Mohr, Bernd
    [J]. PARALLEL COMPUTING, 2009, 35 (07) : 375 - 388
  • [10] Geimer M, 2009, LECT NOTES COMPUT SC, V5545, P696, DOI 10.1007/978-3-642-01973-9_78
123