Abstract
Current analytic solutions to the execution time prediction Y of binary parallel compositions of tasks with arbitrary execution time distributions X 1 and X 2 are either computationally complex or very inaccurate. In this paper we introduce an analytical approach based on the use of lambda distributions to approximate execution time distributions. This allows us to predict the first 4 statistical moments of Y in terms of the first 4 moments of X i at negligible solution complexity. The prediction method applies to a wide range of workload distributions as found in practice, while its accuracy is better or equal compared to comparable low-cost approaches.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Allen, F., Burke, M., Cytron, R., Ferrante, J., Hsieh, W., and Sarkar, V.: “A Framework for Determining Useful Parallelism.” In Proc. 1988 Int. Conf. Parallel Proc., IEEE, Aug. 1988, pp. 207–215.
Bailey, D. et al.: The NAS Parallel Benchmarks, Tech. Rep. RNR-94-007, NASA Ames Research Center, Moffett Field, CA, March 1994.
Fahringer, T. and Zima, H. P.: “A static parameter-based performance prediction tool for parallel programs.” In Proc. 7th ACM Int’l Conf. on Supercomputing, Tokyo, July 1993, pp. 207–219.
Gautama, H.: On the Use of Lambda Distributions in the Prediction of Parallel Program Execution Time, Tech. Rep. 1-68340-44(2000)02, Delft University of Technology, Delft, The Netherlands, Feb. 2000.
Gautama, H. and van Gemund, A. J. C.: “Static Performance Prediction of Data-Dependent Programs.” In ACM Proc. on The Second International Workshop on Software and Performance (WOSP 2000), Ottawa, Canada, Sept. 2000.
Gelenbe, E., Montagne, E., Suros, R.: “A Performance Model of Block Structured Parallel Programs.” In Cosnard, M. et al. (eds.): Parallel Algorithms and Architectures, Elsevier Science Publishers B. V. North-Holland, 1986, pp. 127–138.
Gumbel, E. J.: “Statistical theory of extreme values (main results).” In Contributions to Order Statistics (Sarhan, A. E. and Greenberg, B. G. eds.), John Wiley & Sons, 1962, pp. 56–93.
Kruskal, C. P. and Weiss, A.: “Allocating Independent Subtasks on Parallel Processors.” In IEEE Transactions on Software Engineering Vol. 11, Oct. 1985, pp. 1001–1016.
Lester, B. P.: “A system for Computing The Speedup of Parallel Programs.” In Proc. 1986 Int. Conf. Parallel Proc., IEEE, Aug. 1986, pp. 145–152.
Madala, S. and Sinclair, J.: “Performance of Synchronous Parallel Algorithms with Regular Structures.” In IEEE Trans. on Parallel and Distributed Systems, Vol. 2, No. 1, Jan, 1991, pp. 105–116.
Mendes, C. L. and Reed, D. A.: “Integrated compilation and scalability analysis for parallel systems.” In Proc. Int’l Conf. on Parallel Architectures and Compilation Techniques (PACT’ 98), Paris, Oct. 1998, pp. 385–392.
Ramberg, J. S. et al.: “A Probability Distribution and Its Uses in Fitting Data.” In Technometrics, Vol. 21, No. 2, May, 1979, pp. 201–214.
Sahner, R. A. and Trivedi, K. S.: ”Performance and Reliability Analysis Using Directed Acyclic Graphs.” In IEEE Transactions on Software Engineering, Vol. SE-13, No. 10, Oct. 1987, pp. 1105–1114.
Sarkar, V.: “Determining Average Program Execution Times and their Variance.” In Proc. 1989 ACM SIGPLAN Conf. Prog. Language Design and Implementation, pp. 298–312.
Schopf, J. M. and Berman, F.: “Performance Prediction in Production Environments.” In Proc. of 1998 IPPS/SPDP, 12th Int. Parallel Processing Symp. on Parallel and Distributed Processing, Orlando, Florida, 1998, pp. 647–653.
Shi, H. and Schaeffer, J.: “Parallel Sorting by Regular Sampling.” In Journal of Parallel and Distributed Computing, Vol. 14, No. 4, 1992, pp. 361–372.
Trivedi, K. S.: Probability and Statistics with Reliability, Queueing, and Computer Science Applications, Prentice-Hall, INC., Englewood Cliffs, NJ. 1982.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gautama, H., van Gemund, A.J.C. (2001). Performance Prediction of Data-Dependent Task Parallel Programs. In: Sakellariou, R., Gurd, J., Freeman, L., Keane, J. (eds) Euro-Par 2001 Parallel Processing. Euro-Par 2001. Lecture Notes in Computer Science, vol 2150. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44681-8_17
Download citation
DOI: https://doi.org/10.1007/3-540-44681-8_17
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42495-6
Online ISBN: 978-3-540-44681-1
eBook Packages: Springer Book Archive