Abstract
With the advent of multi-core processors and the growing popularity of local clusters installations, better understanding of parallel applications behaviour becomes a necessity. On the other hand performance evaluation constitutes an intrinsic part of every application development process. The performance analysis can be carried out analytically or through experiments. When using experimental approach, its results are based on wall-time measurements and requires consecutive application executions which is time-consuming. In the paper an alternative approach is proposed. Utilizing the decomposition of execution time, a separate analysis of the computation time and overheads related to parallel execution are used to calculating the granularity of application and then determining the efficiency of the application. The usefulness of the new technique has been evaluated by comparing its results with those of classical ones. The obtained results suggest that the presented method can be used for performance evaluation of parallel applications.
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
Alves, C.E.R., Cceres, E.N., Song, S.W.: Sequential and parallel algorithms for the all-substrings longest common subsequence problem. Universidade de So Paulo, Instituto de Matemtica e Estatstica (2003)
Cremonesi, P., Rosti, E., Serazzi, G., Smirni, E.: Performance evaluation of parallel systems. Parallel Comput. 25, 1677–1698 (1999). (North-Holland)
Foster, I.: Designing and Building Parallel Programs. Addison-Wesley, Reading (1995). (http://www.mcs.anl.gov/dbpp/text/book.html)
Grama, A.Y., Gupta, A., Kumar, V.: Isoefficiency: measuring the scalability of parallel algorithms and architectures. IEEE Parallel Distrib. Technol. 1, 12–21 (1993)
Kwiatkowski, J.: Evaluation of parallel programs by measurement of its granularity. In: Wyrzykowski, R., Dongarra, J., Paprzycki, M., Waśniewski, J. (eds.) PPAM 2001. LNCS, vol. 2328, pp. 145–153. Springer, Heidelberg (2002)
Kwiatkowski, J., Pawlik, M., Konieczny, D.: Parallel program execution anomalies. In: Proceedings of the First International Multiconference on Computer Science and Information, Wisla, Poland (2006)
Kwiatkowski, J., Pawlik, M., Konieczny, D.: Comparison of execution time decomposition methods for performance evaluation. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Wasniewski, J. (eds.) PPAM 2007. LNCS, vol. 4967, pp. 1160–1169. Springer, Heidelberg (2008)
Kumar, V., Grama, A., Gupta, A., Karypis, G.: Introduction to Parallel Computing. The Benjamin/Cummings Publishing Company Inc., Redwood City (1995)
Pawlik, M., Kwiatkowski, J., Koniecznym, D.: Parallel program performance evaluation with execution time decomposition. In: Proceedings of the 16th International Conference on Systems Science, Wroclaw, Poland (2007)
MacQueen, J.B.: Some methods for classification and analysis of multivariate observations. In: Proceedings of the Fifth Symposium on Mathematical, Statistics, and Probability, pp. 281–297. University of California Press, Berkeley (1967)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kwiatkowski, J. (2014). Parallel Applications Performance Evaluation Using the Concept of Granularity. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Waśniewski, J. (eds) Parallel Processing and Applied Mathematics. PPAM 2013. Lecture Notes in Computer Science(), vol 8385. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-55195-6_20
Download citation
DOI: https://doi.org/10.1007/978-3-642-55195-6_20
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-55194-9
Online ISBN: 978-3-642-55195-6
eBook Packages: Computer ScienceComputer Science (R0)