Abstract
Hardware performance monitoring is the basis of modern performance analysis tools for application optimization. We are interested in providing such performance analysis tools for the new BlueGene/L supercomputer as early as possible, so that applications can be tuned for that machine. We are faced with two challenges in achieving that goal. First, the machine is still going through its final design and assembly stages and, therefore, it is not yet available to system and application programmers. Second, and most important, key hardware performance metrics, such as instruction counters and Level 1 cache behavior counters, are missing from the BlueGene/L architecture. Our solution to those problems has been to implement a set of nonarchitected performance counters in an instruction-set simulator of BlueGene/L, and to provide a mechanism for executing code to retrieve the value of those counters. Using that mechanism, we have ported a version of the libHPM performance analysis library. We validate our implementation by comparing our results for BlueGene/L to analytical models and to results from a real machine.
Chapter PDF
Similar content being viewed by others
References
Adiga, N., et al.: An Overview of the BlueGene/L Supercomputer. In: Proceedings of SC 2002, Baltimore, Maryland (November 2002)
Ahn, D.H., Vetter, J.S.: Scalable Analysis Techniques for Microprocessor Performance Counter Metrics. In: Proceedings of SC 2002, Baltimore, Maryland (November 2002)
Almasi, G., Archer, C., Castaños, J.G., Gupta, M., Martorell, X., Moreira, J.E., Gropp, W., Rus, S., Toonen, B.: MPI on BlueGene/L: Designing an efficient general purpose messaging solution for a large cellular system. Technical report, IBM Research (2003)
Bailey, D., Harris, T., Saphir, W., van der Wijngaart, R., Woo, A., Yarrow, M.: The NAS Parallel Benchmarks 2.0. Technical Report NAS-95-929, NASA Ames Research Center (December 1995)
Browne, S., Dongarra, J., Garner, N., London, K., Mucci, P.: A Scalable Cross-Platform Infrastructure for Application PerformanceTuning Using Hardware Counters. In: Proceedings of Supercomputing 2000 (November 2000)
Buck, B., Hollingsworth, J.K.: Using Hardware Performance Monitors to Isolate Memory Bottlenecks. In: Proceedings of Supercomputing 2002 (November 2000)
Caubet, J., Labarta, J.G.J., DeRose, L., Vetter, J.: A Dynamic Tracing Mechanism for Performance Analysis of OpenMP Applications. In: Eigenmann, R., Voss, M.J. (eds.) WOMPAT 2001. LNCS, vol. 2104, pp. 53–67. Springer, Heidelberg (2001)
Ceze, L., Strauss, K., Almasi, G., Bohrer, P.J., Brunheroto, J.R., Caşcaval, C., Nos, J.G.C., Lieber, D., Martorell, X., Moreira, J.E., Sanomiya, A., Schenfeld, E.: Full circle: Simulating linux clusters on linux clusters. In: Proceedings of the Fourth LCI International Conference on Linux Clusters: The HPC Revolution 2003, San Jose, CA (June 2003)
DeRose, L.: The Reveal Only Specific Events (ROSE) Micro-benchmark Set for Verification of Hardware Activity. Technical report, IBM Research (2003)
DeRose, L.: The Hardware Performance Monitor Toolkit. In: Proceedings of Euro-Par, August 2001, pp. 122–131 (2001)
DeRose, L., Ekanadham, K., Hollingsworth, J.K.: SIGMA: A Simulator Infrastructure to Guide Memory Analysis. In: Proceedings of SC 2002, Baltimore, Maryland (November 2002)
Janssen, C.: The visual Profiler. Sandia National Laboratories (2002), http://aros.ca.sandia.gov/~cljanss/perf/vprof/
May, J.M.: MPX: Software for Multiplexing Hardware Performance Counters in Multithreaded Programs. In: Proceedings of 2001 International Parallel and Distributed Processing Symposium (April 2001)
Pettersson, M.: Linux X86 Performance-Monitoring Counters Driver, Uppsala University – Sweden (2002), http://user.it.uu.se/~mikpe/linux/perfctr/
Research Centre Juelich GmbH. PCL - The Performance Counter Library: A Common Interface to Access Hardware Performance Counters on Microprocessors, http://www.fz-juelich.de/zam/PCL/
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mindlin, P., Brunheroto, J.R., DeRose, L., Moreira, J.E. (2003). Obtaining Hardware Performance Metrics for the BlueGene/L Supercomputer. In: Kosch, H., Böszörményi, L., Hellwagner, H. (eds) Euro-Par 2003 Parallel Processing. Euro-Par 2003. Lecture Notes in Computer Science, vol 2790. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45209-6_18
Download citation
DOI: https://doi.org/10.1007/978-3-540-45209-6_18
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40788-1
Online ISBN: 978-3-540-45209-6
eBook Packages: Springer Book Archive