Abstract
In general there are many possibilities to parallelize an algorithm and to distribute the tasks to the processors. In some cases the selection of a processor configuration depends on the given problem, too. To decide which implementation for any configuration may be the best, the programmer can use methods of performance evaluation and prediction. If the structure of the parallel program can be modeled by a seriesparallel graph we know a method to obtain the runtime of the total program. This paper deals with the more difficult problem of predicting the runtimes of non-seriesparallel structured programs. It is shown how to compute approximately the average runtime of a program which consists of tasks with deterministically and/or exponentially distributed runtime variables. The method is based on the well known transient state space analysis.
Preview
Unable to display preview. Download preview PDF.
References
G. Chiola. GreatSPN Users' Manual, 1987.
G. Fleischmann and G. Werner. Beschreibung paralleler Softwarestrukturen durch stochastische Graphen und ihre Bewertung mit Hilfe von Markovketten. Technical report, Universität Erlangen-Nürnberg, IMMD IV, 1989.
V. Gerling. Analyse nichtserienparalleler Graphen mit Hilfe von Markov-Ketten. Internal study, Universität Erlangen-Nürnberg, 1989.
A. Greenbaum. Synchronization costs on multiprocessors. Parallel Computing, 10:3–14, 1989.
R. Hofmann, R. Klar, N. Luttenberger, B. Mohr, and G. Werner. An Approach to Monitoring and Modeling of Multiprocessor and Multicomputer Systems. In T. Hasegawa et al., editors, Int. Seminar on Performance of Distributed and Parallel Systems, pages 91–110, Kyoto, 7–9 Dec. 1988.
Wolfgang Kleinöder. Stochastische Bewertung von Aufgabenstrukturen für hierarchische Mehrrechnersysteme. PhD thesis, Universität Erlangen-Nürnberg, 1982.
J. J. Martin. Distribution of the Time through a Directed, Acyclic Network. Operations Research, 13(1):46–66, 1965.
J. Mohan. Performance of Parallel Programs: Model and Analysis. PhD thesis, Carnegie-Mellon University, July 1984.
Heino Pingel. Stochastische Bewertung serien-paralleler Aufgabenstrukturen. Internal study, Universität Erlangen-Nürnberg, 1988.
Heino Pingel. Modellierung und Bewertung der Implementierung eines Mehrgitterverfahrens auf DIRMU-Ringkonfigurationen und Validierung der Bewertungsergebnisse durch Messung an dem implementierten Verfahren. Master's thesis, Universität Erlangen-Nürnberg, 1989.
R.A. Sahner. Of Solving Performance and Reliability Models. PhD thesis, Dep. Comput. Sci., Duke Univ., 1986.
Alexander Thomasian and Paul F. Bay. Analytic Queueing Network Models for Parallel Processing of Task Systems. IEEE Transactions On Computers, C-35(12):1045–1054, December 1986.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1990 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sötz, F. (1990). A method for performance prediction of parallel programs. In: Burkhart, H. (eds) CONPAR 90 — VAPP IV. VAPP CONPAR 1990 1990. Lecture Notes in Computer Science, vol 457. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-53065-7_91
Download citation
DOI: https://doi.org/10.1007/3-540-53065-7_91
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-53065-7
Online ISBN: 978-3-540-46597-3
eBook Packages: Springer Book Archive