Abstract
We analyze two implementation variants of a parallel computer algebra algorithm in Distributed Maple. The original solution uses a manager-worker mechanism to control task scheduling, which requires an elaborate administration scheme. The new algorithm is based on a dataflow approach where all tasks are immediately started, automatically scheduled by the runtime system, and implicitly synchronized by task dependencies; non-determinism is effectively applied to provide more potential for parallelism. It turns out that the new version is not only more declarative (closer to the mathematical problem description) but also more efficient than the original solution.
Supported by grant SFB F013/F1304 of the Austrian Science Foundation (FWF).
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
L. Bernadin. Maple on a Massively Parallel, Distributed Memory Machine. In PASCO’97 — Second Int. Symp. on Parallel Symbolic Computation, pages 217–222, Maui, Hawaii, July 20–22, 1997. ACM Press.
A. Diaz and E. Kaltofen. FoxBox: A System for Manipulating Symbolic Objects in Black Box Representation. In O. Gloor, editor, ISSAC’98 Int. Symp. on Symbolic and Algebraic Comp. ACM Press, New York, 1998.
H.W. Loidl, P.W. Trinder, K. Hammond, S.B. Junaidu, R.G. Morgan, and S.L. Peyton Jones. Engineering Parallel Symbolic Programs in GPH. Concurrency — Practice and Experience, 11(12):701–751, 1999.
H.W. Loidl. LinSolv: A Case Study in Strategic Parallelism. Proceedings of the Glasgow Workshop on Functional Programming, Ullapool, Scotland, 1997.
C. Mittermaier. Parallel Algorithms in Constructive Algebraic Geometry. Master’s thesis, Johannes Kepler University, Linz, Austria, 2000.
Christian Mittermaier, Wolfgang Schreiner, and Franz Winkler. A Parallel Symbolic-Numerical Approach to Algebraic Curve Plotting. In V. Gerdt and E. W. Mayr, editors, CASC-2000, 3rd Int. Workshop on Computer Algebra in Scientific Computing, Samarkand, Uzbekistan, October 5–9, 2000. Springer, Berlin.
M. Mnuk and F. Winkler. CASA-A System for Computer Aided Constructive Algebraic Geometry. In J. Calmet and C. Limongelli, editors, DISCO’96 — Int. Symposium on the Design and Implementation of Symbolic Computation Systems, volume 1128 of LNCS, pages 297–307, Karsruhe, Germany, 1996. Springer, Berlin.
Wolfgang Schreiner. Distributed Maple-User and Reference Manual. Technical Report 98-05, RISC-Linz, Johannes Kepler University, Linz, Austria, May 1998. http://www.risc.uni-linz.ac.at/software/distmaple.
Wolfgang Schreiner. Developing a Distributed System for Algebraic Geometry. In Barry H.V. Topping, editor, EURO-CM-PAR’99 Third Euro-conference on Parallel and Distributed Computing for Computational Mechanics, pages 137–146, Weimar, Germany, March 20–25, 1999. Civil-Comp Press, Edinburgh.
Wolfgang Schreiner and Hans-Wolfgang Loidl. GHC-Maple Interface, November 2000. http://www.risc.uni-linz.ac.at/software/ghc-maple.
Wolfgang Schreiner, Christian Mittermaier, and Franz Winkler. Analyzing Algebraic Curves by Cluster Computing. In Peter Kacsuk and Gabriele Kotsis, editors, Distributed and Parallel Systems-From Instruction Parallelism to Cluster Computing, Proceedings of DAPSYS’2000, 3rd Austrian-Hungarian Workshop on Distributed and Parallel Systems, pages 175–184, Balatonfüred, Lake Balaton, Hungary, September 10–13, 2000. Kluwer Academic Publishers, Boston.
Wolfgang Schreiner, Christian Mittermaier, and Franz Winkler. On Solving a Problem in Algebraic Geometry by Cluster Computing. In A. Bode et al (eds.), Euro-Par 2000, volume 1900 of Lecture Notes in Computer Science, pages 1196–1200, Munich, Germany, August 29–September 1, 2000. Springer, Berlin.
Wolfgang Schreiner, Christian Mittermaier, and Franz Winkler. Plotting Algebraic Space Curves by Cluster Computing. In X.-S. Gao and D. Wang, editors, ASCM’2000, 4th Asian Symposium on Computer Mathematics, Chiang Mai, Thailand, December 17–21, 2000. World Scientific Publishers, Singapore/River Edge.
K. Siegl. MAPLE. In Fourth ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pages 179–186, San Diego, California, May 19–22, 1993. ACM Press.
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
Schreiner, W. (2001). Manager-Worker Parallelism versus Dataflow in a Distributed Computer Algebra System. In: Malyshkin, V. (eds) Parallel Computing Technologies. PaCT 2001. Lecture Notes in Computer Science, vol 2127. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44743-1_33
Download citation
DOI: https://doi.org/10.1007/3-540-44743-1_33
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42522-9
Online ISBN: 978-3-540-44743-6
eBook Packages: Springer Book Archive