IOPin: Runtime Profiling of Parallel I/O in HPC Systems

被引：16
作者：
Kim, Seong Jo [1 ]
Son, Seung Woo [2 ]
Liao, Wei-keng [2 ]
Kandemir, Mahmut [1 ]
Thakur, Rajeev [3 ]
Choudhary, Alok [2 ]
机构：
[1] Penn State Univ, University Pk, PA 16802 USA
[2] Northwestern Univ, Dept Elect Engn & Comp Sci, Evanston, IL 60208 USA
[3] Argonne Natl Lab, Math & Comp Sci, Argonne, IL 60439 USA
来源：
2012 SC COMPANION: HIGH PERFORMANCE COMPUTING, NETWORKING, STORAGE AND ANALYSIS (SCC) | 2012年
关键词：
D O I：
10.1109/SC.Companion.2012.14
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
Many I/O- and data-intensive scientific applications use parallel I/O software to access files in high performance. On modern parallel machines, the I/O software consists of several layers, including high-level libraries such as Parallel netCDF and HDF, middleware such as MPI-IO, and low-level POSIX interface supported by the file systems. For the I/O software developers, ensuring data flow is important among these software layers with performance close to the hardware limits. This task requires understanding the design of individual libraries and the characteristics of data flow among them. In this paper, we propose a dynamic instrumentation framework that can be used to understand the complex interactions across different I/O layers from applications to the underlying parallel file systems. Our preliminary experience indicates that the costs of using the proposed dynamic instrumentation is about 7% of the application execution time.
引用
收藏
页码：18 / 23
页数：6
相关论文
共 32 条
  • [1] [Anonymous], 2004, THESIS
  • [2] [Anonymous], TECH REP
  • [3] [Anonymous], 1996, VAMPIR VISUALIZATION
  • [4] [Anonymous], 2003, 5 INT WORKSH AUT PER
  • [5] [Anonymous], NHSE REV
  • [6] [Anonymous], NONCONTIGUOUS I O AC
  • [7] Arnold D.C., 2007, PARALLEL DISTRIBUTED, P64
  • [8] Dynamo: A transparent dynamic optimization system
    Bala, V
    Duesterwald, E
    Banerjia, S
    [J]. ACM SIGPLAN NOTICES, 2000, 35 (05) : 1 - 12
  • [9] Carns P., 2009, CLUSTER COMPUTING WO, P1
  • [10] Carns P.H., 2000, P 4 ANN LINUX SHOWCA, V4, P28
1234