Abstract
Scientific applications can have so many parameters, possible usage scenarios and target architectures, that a single experiment is often not enough for an effective analysis that gets sound understanding of their performance behavior. Different software and hardware settings may have a strong impact on the results, but trying and measuring in detail even just a few possible combinations to decide which configuration is better, rapidly floods the user with excessive amounts of information to compare.
In this chapter we introduce a novel methodology for performance analysis based on object tracking techniques. The most compute-intensive parts of the program are automatically identified via cluster analysis, and then we track the evolution of these regions across different experiments to see how the behavior of the program changes with respect to the varying settings and over time. This methodology addresses an important problem in HPC performance analysis, where the volume of data that can be collected expands rapidly in a potentially high dimensional space of performance metrics, and we are able to manage this complexity and identify coarse properties that change when parameters are varied to target tuning and more detailed performance studies.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Browne, S., Dongarra, J., Garner, N., Ho, G., Mucci, P.: A portable programming interface for performance evaluation on modern processors. Int. J. High Perform. Comput. Appl. 14, 189–204 (2000)
BSC Facilities. http://www.bsc.es/marenostrum-support-services
BSC Tools. http://www.bsc.es/paraver
Buck, B., Hollingsworth, J.K.: An API for runtime code patching. Int. J. High Perform. Comput. Appl. 14, 317–329 (2000)
Casas, M., Badia, R., Labarta, J.: Automatic analysis of speedup of MPI applications. In: Proceedings of the 22nd Annual International Conference on Supercomputing (ICS’08), Island of Kos, pp. 349–358. ACM, New York (2008)
Casas, M., Bronevetsky, G.: Active measurement of memory resource consumption. In: Proceedings of the 2014 IEEE 28th International Parallel and Distributed Processing Symposium (IPDPS’14), Phoenix, pp. 995–1004. IEEE Computer Society, Washington, DC (2014)
Geimer, M., Saviankou, P., Strube, A., Szebenyi, Z., Wolf, F., Wylie, B.J.N.: Further improving the scalability of the SCALASCA toolset. In: Proceedings of the 10th International Conference on Applied Parallel and Scientific Computing (PARA’10), Reykjavik, vol. 2, pp. 463–473. Springer, Berlin/Heidelberg (2012)
GNU Binutils. http://www.gnu.org/software/binutils
González, J., et al.: Automatic detection of parallel applications computation phases. In: IPDPS: 23rd IEEE International Parallel and Distributed Processing Symposium, Sao Paulo (2009)
González, J., et al.: Automatic evaluation of the computation structure of parallel applications. In: PDCAT: Proceedings of the 2009 International Conference on Parallel and Distributed Computing, Applications and Technologies, Higashi Hiroshima, pp. 138–145 (2009)
González, J., et al.: Performance data extrapolation in parallel codes. In: ICPADS: 16th IEEE International Conference on Parallel and Distributed Systems, Shanghai, pp. 155–163 (2010)
Huck, K.A., Malony, A.D.: PerfExplorer: a performance data mining framework for large-scale parallel computing. In: Proceedings of the Conference on Supercomputing, New York, p. 41 (2005)
Ibarra, O.H., Kim, C.E.: Fast approximation algorithms for the knapsack and sum of subset problems. J. ACM 22(4), 463–468 (1975)
Jones, P.: Parallel Ocean Program (POP) user guide. Technical report, Los Alamos National Laboratory, March 2003
Lavalléea, P.-F., et al.: HYDRO. http://www.prace-ri.eu
Mellor-Crummey, J.: HPCToolkit: multi-platform tools for profile-based performance analysis. In: APART, Nov 2003
Mimica, P., Giannios, D., Aloy, M.A.: Deceleration of arbitrarily magnetized GRB Ejecta: the complete evolution. Technical report arXiv:0810.2961, Oct 2008. Comments: 13 pages, 10 figures, revised version sent to the referee (first version submitted on 6th of August)
NAS Parallel Benchmarks. http://www.nas.nasa.gov/Software/NPB
Open source package for Material eXplorer. http://www.openmx-square.org
Palaniappan, K., et al.: Moving object segmentation using the flux tensor for biological video microscopy. In: PCM, Hong Kong, p. 483 (2007)
Patwary, M.A., Palsetia, D., Agrawal, A., Liao, W.-K., Manne, F., Choudhary, A.: A new scalable parallel DBSCAN algorithm using the disjoint-set data structure. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (SC’12), Salt Lake City, pp. 62:1–62:11. IEEE Computer Society, Los Alamitos (2012)
Roth, P.C.: ETRUSCA: event trace reduction using statistical data clustering analysis. Master’s thesis, University of Iowa (1992)
Servat, H., et al.: Detailed performance analysis using coarse grain sampling. In: PROPER (2009)
Servat, H., et al.: Unveiling internal evolution of parallel application computation phases. In: ICPP, Taipei, pp. 155–164 (2011)
Shende, S.S., Malony, A.D.: The tau parallel performance system. Int. J. High Perform. Comput. Appl. 20, 287–311 (2006)
Song, F., et al.: An algebra for cross-experiment performance analysis. In: ICPP, Montreal, pp. 63–72 (2004)
The CGPOP Miniapp website. http://www.cs.colostate.edu/hpc/cgpop
The libunwind project. http://www.nongnu.org/libunwind
The Weather Research & Forecasting model. http://www.wrf-model.org
Yilmaz, A., et al.: Object tracking: a survey. ACM Comput. Surv. 38(4) (2006)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Llort, G., Servat, H., Gonzalez, J., Gimenez, J., Labarta, J. (2015). Studying Performance Changes with Tracking Analysis. In: Niethammer, C., Gracia, J., Knüpfer, A., Resch, M., Nagel, W. (eds) Tools for High Performance Computing 2014. Springer, Cham. https://doi.org/10.1007/978-3-319-16012-2_9
Download citation
DOI: https://doi.org/10.1007/978-3-319-16012-2_9
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16011-5
Online ISBN: 978-3-319-16012-2
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)