Abstract
An approach to dynamic parallelizing of coarse grained pro- gram where the parallelization sources are both dataflow analysis and the features pointed out in the program by annotating is proposed. Program annotating enables to hold two additional types of parallel computations which cannot be found out only from the analysis of dataflow depen- dences. Firstly, there are speculative computations based on anticipating alternative branches of the program’s computational process. Secondly, there are pipeline computations that sometimes may be initialised for operators at the moment when their input data are not complete. Auto- mated program analysis of this type of concurrence is either very hard or it generates a lot of surplus computation, thus absorbing the effect of program parallelization.
The implementation of the system of dynamic program parallelization for clusters of PCs and results of some experiments performed on it are described.
This work was supported by the Slovak Scientific Grant Agency within Research Project No.2/4102/98
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Attardi G., Traverso C.: A Strategy-accurate Parallel Buchberger Algorithm // J. Symbolic Computation (1996), 21, P. 411–426
Guy E. Blelloch, Margaret Reid-Miller, Pipelining with Futures, in Ninth Annual ACM Symposium on Parallel Algorithms and Architectures (SPAA’97), 22–25 June, Newport, Rhode Island
Buchberger B.: An Algorithm for Finding a Basis for the Residue Class Ring of Zero-Dimensional Polynomial Ideal. Ph. D. Thesis, Math. Inst., Univ. of Insbruck, Austria, 1965.
Godlevsky A. B.: The Parallel Dynamical Semantics of Sequential Program that Allows Speculative and Incremental Computation. Kibernetika i sistemny analiz, 1996, No. 2, pp. 131–153 (in Russian).
M. Hermenegildo.: Automatic Parallelization of Irregular and Pointer-Based Computation: Perspectives from Logic and Constraint Programming, in Euro-Par’97 Parallel Processing, number 1300 in LNCS, pages 31–45, Passau, Germany, August 26-29, 1997. Springer-Verlag
Geist A., Beguelin A. Dongarra J., Jiang W., Manchek R. and Sunderam V.:PVM: Parallel Virtual Machine, A User’s Guide and Tutorial for Networked Parallel Computing. The MIT Press, 1994.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Godlevsky, A., Gažák, M., Hluchý, L. (1999). Parallelizing of Sequential Programs on the Basis of Pipeline and Speculative Features of the Operators* . In: Malyshkin, V. (eds) Parallel Computing Technologies. PaCT 1999. Lecture Notes in Computer Science, vol 1662. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48387-X_5
Download citation
DOI: https://doi.org/10.1007/3-540-48387-X_5
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66363-8
Online ISBN: 978-3-540-48387-8
eBook Packages: Springer Book Archive