A parallel trace-data interface for scalable performance analysis

被引：0

作者：

Geimer, Markus ^{[1
]}

Wolf, Felix ^{[1
,2
]}

Knuepfer, Andreas ^{[3
]}

Mohr, Bernd ^{[1
]}

Wylie, Brian J. N. ^{[1
]}

机构：

[1] Forschungszentrum Julich, John von Neumann Inst Comp, D-52425 Julich, Germany

[2] Rhein Westfal TH Aachen, Dept Comp Sci, D-52056 Aachen, Germany

[3] Tech Univ Dresden, Ctr Informat Serv & High Performance Comp ZIH, D-01062 Dresden, Germany

来源：

APPLIED PARALLEL COMPUTING: STATE OF THE ART IN SCIENTIFIC COMPUTING | 2007年 / 4699卷

关键词：

D O I：

暂无

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Automatic trace analysis is an effective method of identifying complex performance phenomena in parallel applications. To simplify the development of complex trace-analysis algorithms, the EARL library interface offers high-level access to individual events contained in a global trace file. However, as the size of parallel systems grows further and the number of processors used by individual applications is continuously raised, the traditional approach of analyzing a single global trace file becomes increasingly constrained by the large number of events. To enable scalable trace analysis, we present a new design of the aforementioned EARL interface that accesses multiple local trace files in parallel while offering means to conveniently exchange events between processes. This article describes the modified view of the trace data as well as related programming abstractions provided by the new PEARL library interface and discusses its application in performance analysis.

引用

页码：398 / +

页数：3

共 15 条

[1] Brunsta H, 2004, ADV PARALLEL COMPUT, V13, P737
[2] Freitag F, 2002, LECT NOTES COMPUT SC, V2400, P97
[3] GAMMA E, 1995, DESIGN PATTERNS
[4] Geimer M, 2006, LECT NOTES COMPUT SC, V4192, P303
[5] Construction and compression of complete call graphs for post-mortem program trace analysis
Knüpfer, A
Nagel, WE
[J]. 2005 International Conference on Parallel Processsing, Proceedings, 2005, : 165 - 172
[6] Labarta J., 1996, LNCS, V1124, P665
[7] MILLER JH, 1990, PHARMEUROPA, V2, P206
[8] Nagel WE, 1996, SUPERCOMPUTER, V12, P69
[9] Wolf F, 2004, LECT NOTES COMPUT SC, V3149, P47
[10] Automatic performance analysis of hybrid MPI/OpenMP applications
Wolf, F
Mohr, B
[J]. JOURNAL OF SYSTEMS ARCHITECTURE, 2003, 49 (10-11) : 421 - 439

← 1 2 →