Abstract
In this paper we present a new method for achieving a higher cost-efficiency on parallel computers. We insert routines into a program which detect the amount of computational work without using problem-specific parameters and adapt the number of used CPUs at runtime under given speedup/efficiency constraints. Several user-tunable strategies for selecting the number of processors are presented and compared. The modularity of this approach and its application-independence permit a general use on parallel computers with a scalable degree of parallelism.
This research was performed at the EMBL (European Molecular Biology Laboratory) Heidelberg in co-operation with the University of Karlsruhe.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
I. Foster, Designing and Building Parallel Programs, Addison-Wesley, 1995, ISBN: 0-201-57594-9, http://www.hensa.ac.uk/parallel/books/addison-wesley/index.html
R. v. Hanxleden, T. W. Clark, J. A. McCammon, L. R. Scott, Parallelization Strategies for a Molecular Dynamics Program, Intel Technology Focus Conf. Proc., 1992
J. A. McCammon und S. C. Harvey, Dynamics of proteins and nucleic acids, Cambridge University Press 1987, ISBN: 0-521-35654-0.
A Geist, A. Beguelin, J. Dongarra, W. Jiang, R. Manchek and V. S. Sunderam, A Users' Guide and Tutorial for Network Parallel Computing, MIT Press, November 1994 ISBN-0-262-57108-0, http://www.hensa.ac.uk/parallel/books/mit/pvm
N. Reimer, Dynamische Einstellung des Parallelitätsgrades mit reflexiven Programmen, reimer@ira.uka.de, University of Karlsruhe, January 1996
Silicon Graphics Inc., Power Challenge Technical Report, SGI 2011 Northern Shoreline Boulevard, Mountain View, CA 94039-7311, 1994
T. P. Straatsma, ARGOS Reference Manual, tp_straatsma@pnl.gov, 1994
T. P. Straatsma, J. A. McCammon, ARGOS, a vectorized general molecular dynamics program, Journal of Computational Chemistry II(8): 943–951, 1990
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Reimer, N., Hänßgen, S.U., Tichy, W.F. (1996). Dynamically adapting the degree of parallelism with reflexive programs. In: Ferreira, A., Rolim, J., Saad, Y., Yang, T. (eds) Parallel Algorithms for Irregularly Structured Problems. IRREGULAR 1996. Lecture Notes in Computer Science, vol 1117. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0030122
Download citation
DOI: https://doi.org/10.1007/BFb0030122
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61549-1
Online ISBN: 978-3-540-68808-2
eBook Packages: Springer Book Archive