Abstract
Performance analysis tools are an important component of the parallel program development and tuning cycle. To obtain the raw performance data, an instrumented application is run with probes that take measures of specific events or performance indicators. Tracing parallel programs can easily lead to huge trace files of hundreds of Megabytes. Several problems arise in this context: The storage requirement of the high number of traces from executions under slightly changed conditions; visualization packages have difficulties in showing large traces efficiently leading to slow response time; large trace files often contain huge amounts of redundant information. In this paper we propose and evaluate a dynamic scalable tracing mechanism for OpenMP based parallel applications. Our results show: With scaled tracing the size of the trace files becomes significantly reduced. The scaled traces contain only the non-iterative data. The scaled trace reveals important performance information faster to the performance analyst and identifies the application structure.
This work has been supported by the Spanish Ministry of Science and Technology and by the European Union (FEDER) under TIC2001-0995-C02-01.
Chapter PDF
Similar content being viewed by others
References
J. Caubet et al. Comparison of scaled and full traces of OpenMP applications. Tech. Report UPC-DAC-2001-31, Dep. d’Arquitectura de Computadors, UPC, 2001.
J. Caubet, J. Gimenez, J. Labarta, L. DeRose, J. Vetter. A Dynamic Tracing Mechanism for Performance Analysis of OpenMP Applications. In International Workshop on OpenMP Applications and Tools, pages 53–67, July 2001.
F. Freitag, J. Corbalan, J. Labarta. A dynamic periodicity detector: Application to Speedup Computation. In Proceedings of International Parallel and Distributed Processing Symposium (IPDPS 2001), April 2001.
J. Hoeflinger et al. An Integrated Performance Visualizer for MPI/OpemnMP Programs. In In. Workshop on OpenMP Applications and Tools, pages 40–52, July 2001.
J. Labarta, S. Girona, V. Pillet, T. Cortes and L. Gregoris. DiP: A Parallel Program Development Environment. In Proceedings of 2nd International EuroPar Conference (EuroPar 96), August 1996.
B. P. Miller et. al. The Paradyn Parallel Performance Measurement Tools. IEEE Computer 28(11):37–46, November 1995.
Pallas: Vampirtrace. Installation and User’s Guide. http://www.pallas.de
C. E. Wu et al. From Trace Generation to Visualization: A Performance Framework for Distributed Parallel Systems. In Proceedings of SuperComputing (SC2000), November 2000.
O. Zaki, E. Lusk, W. Gropp, and D. Swider. Toward scalable performance visualization with Jumpshot. In International Journal of High Performance Computing Applications, 13(2): pages 277–288, 1999.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Freitag, F., Caubet, J., Labarta, J. (2002). On the Scalability of Tracing Mechanisms. In: Monien, B., Feldmann, R. (eds) Euro-Par 2002 Parallel Processing. Euro-Par 2002. Lecture Notes in Computer Science, vol 2400. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45706-2_10
Download citation
DOI: https://doi.org/10.1007/3-540-45706-2_10
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-44049-9
Online ISBN: 978-3-540-45706-0
eBook Packages: Springer Book Archive