Automatic search for patterns of inefficient behavior in parallel applications

Event tracing is a powerful method of analyzing the performance behavior of parallel applications. Because event traces record the temporal and spatial relationships between individual runtime events, they allow application developers to analyze dependences of performance phenomena across concurrent control flows. However, in view of the large amounts of data generated on contemporary parallel machines, the depth and coverage of a purely manual analysis is often limited. In this article, we present an approach of automatically searching event traces for execution patterns indicating inefficient behavior, allowing developers to study the performance of their applications on a very high level of abstraction, while consuming significantly less expert time than a manual analysis.

[1]  Bernd Mohr,et al.  Event-Based Measurement and Analysis of One-Sided Communication , 2005, Euro-Par.

[2]  Bernd Mohr,et al.  Automatic experimental analysis of communication patterns in virtual topologies , 2005, 2005 International Conference on Parallel Processing (ICPP'05).

[3]  Felix Wolf.  EARL - API Documentation , 2004 .

[4]  Bernd Mohr,et al.  Efficient Pattern Search in Large Traces Through Successive Refinement , 2004, Euro-Par.

[5]  Bernd Mohr,et al.  Design and Prototype of a Performance Tool Interface for OpenMP , 2002, The Journal of Supercomputing.

[6]  Andrea Clematis,et al.  Evolutions in parallel distributed and network-based processing , 2003, Journal of systems architecture.

[7]  Bernd Mohr,et al.  Automatic performance analysis of hybrid MPI/OpenMP applications , 2003, Eleventh Euromicro Conference on Parallel, Distributed and Network-Based Processing, 2003. Proceedings..

[8]  Felix Wolf,et al.  Automatic performance analysis on parallel computers with SMP nodes , 2003 .

[9]  Jeffrey S. Vetter,et al.  Scalable Analysis Techniques for Microprocessor Performance Counter Metrics , 2002, ACM/IEEE SC 2002 Conference (SC'02).

[10]  Barton P. Miller,et al.  A callgraph‐based search strategy for automated performance diagnosis , 2002, Concurr. Comput. Pract. Exp..

[11]  T. Fahringer,et al.  Modeling and Detecting Performance Problems for Distributed and Parallel Programs with JavaPSL , 2001, ACM/IEEE SC 2001 Conference (SC'01).

[12]  Chris McDonald,et al.  A preliminary topological debugger for MPI programs , 2001, Proceedings First IEEE/ACM International Symposium on Cluster Computing and the Grid.

[13]  Jeffrey K. Hollingsworth,et al.  The dynamic probe class library-an infrastructure for developing instrumentation for performance tools , 2001, Proceedings 15th International Parallel and Distributed Processing Symposium. IPDPS 2001.

[14]  Angewandte Mathematik,et al.  Knowledge Specification for Automatic Performance Analysis APART Technical Report Revised Version , 2001 .

[15]  Allen D. Malony,et al.  The role of instrumentation and mapping in performance measurement , 2001 .

[16]  Jack J. Dongarra,et al.  A Portable Programming Interface for Performance Evaluation on Modern Processors , 2000, Int. J. High Perform. Comput. Appl..

[17]  A. Morales.  Automatic performance analysis of parallel programs , 2000 .

[18]  Mary K. Vernon,et al.  Predictive analysis of a wavefront application using LogGP , 1999, PPoPP '99.

[19]  Adolfy Hoisie,et al.  Performance Analysis of Wavefront Algorithms on Very-Large Scale Distributed Systems , 1998, Wide Area Networks and High Performance Computing.

[20]  Oscar Naim,et al.  MDL: a language and compiler for dynamic program instrumentation , 1997, Proceedings 1997 International Conference on Parallel Architectures and Compilation Techniques.

[21]  Barton P. Miller,et al.  The Paradyn Parallel Performance Measurement Tool , 1995, Computer.

[22]  Wolfgang E. Nagel,et al.  Performance Optimization of Parallel Programs - Tracing, Zooming, Understanding - , 1995 .

[23]  Michael Gerndt,et al.  Performance Analysis for SVM-Fortran with OPAL , 1995, PDPTA.

[24]  Peter Charles Bates.  Debugging Programs in a Distributed System Environment , 1986 .