Abstract
Event tracing is a well-accepted technique for post-mortem performance analysis of parallel applications. The expert tool supports the analysis of large traces by automatically searching them for execution patterns that indicate inefficient behavior. However, the current search algorithm works with independent pattern specifications and ignores the specialization hierarchy existing between them, resulting in a long analysis time caused by repeated matching attempts as well as in replicated code. This article describes an optimized design taking advantage of specialization relationships and leading to a significant runtime improvement as well as to more compact pattern specifications.
This work was supported in part by the U.S. Department of Energy under Grants DoE DE-FG02-01ER25510 and DoE DE-FC02-01ER25490 and is embedded in the European IST working group APART under Contract No. IST-2000-28077.
Chapter PDF
Similar content being viewed by others
References
Arnold, A., Detert, U., Nagel, W.E.: Performance Optimization of Parallel Programs: Tracing, Zooming, Understanding. In: Winget, R., Winget, K. (eds.) Proc. of Cray User Group Meeting, Denver, CO, March 1995, pp. 252–258 (1995)
Cain, H.W., Miller, B.P., Wylie, B.J.N.: A Callgraph-Based Search Strategy for Automated Performance Diagnosis. In: Bode, A., Ludwig, T., Karl, W.C., Wismüller, R. (eds.) Euro-Par 2000. LNCS, vol. 1900, p. 108. Springer, Heidelberg (2000)
Espinosa, A.: Automatic Performance Analysis of Parallel Programs. PhD thesis, Universitat Autonoma de Barcelona (September 2000)
Fahringer, T., Gerndt, M., Mohr, B., Riley, G., Träff, J.L., Wolf, F.: Knowledge Specification for Automatic Performance Analysis. Technical Report FZJ-ZAM-IB- 2001-08, ESPRIT IV Working Group APART, Forschungszentrum Jülich (August 2001) (revised version)
Fahringer, T., Seragiotto Jr., C.: Modelling and Detecting Performance Problems for Distributed and Parallel Programs with JavaPSL. In: Proc. of the Conference on Supercomputers (SC 2001), Denver, Colorado (November 2001)
Fürlinger, K., Gerndt, M.: Distributed Application Monitoring for Clustered SMP Architectures. In: Kosch, H., Böszörményi, L., Hellwagner, H. (eds.) Euro-Par 2003. LNCS, vol. 2790, pp. 127–134. Springer, Heidelberg (2003)
Song, F., Wolf, F.: CUBE User Manual. Technical Report ICL-UT-04-01, University of Tennessee, Innovative Computing Laboratory, Knoxville, TN (2004)
Wolf, F.: Automatic Performance Analysis on Parallel Computers with SMP Nodes. PhD thesis, RWTH Aachen, Forschungszentrum Jülich (February 2003) ISBN 3-00- 010003-2
Wolf, F., Mohr, B.: Automatic performance analysis of hybrid MPI/OpenMP applications. Journal of Systems Architecture 49(10-11), 421–439 (2003); Special Issue Evolutions in parallel distributed and network-based processing
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wolf, F., Mohr, B., Dongarra, J., Moore, S. (2004). Efficient Pattern Search in Large Traces Through Successive Refinement. In: Danelutto, M., Vanneschi, M., Laforenza, D. (eds) Euro-Par 2004 Parallel Processing. Euro-Par 2004. Lecture Notes in Computer Science, vol 3149. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-27866-5_7
Download citation
DOI: https://doi.org/10.1007/978-3-540-27866-5_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22924-7
Online ISBN: 978-3-540-27866-5
eBook Packages: Springer Book Archive