Abstract
In this paper we discuss the approach of applying task graph rescheduling method to the efficient parallelization of irregular/dynamic problems. Two new rescheduling algorithms are proposed: One for task graph weight variation, the other for dynamic spawning of subgraphs. These algorithms are localized and incremental, with very low complexity. But for coarse grain task graphs they yield schedules that are competitive to global rescheduling from scratch. Experiments with the N-body problem and Vortex Sheet simulation show good speedups for these problems on the NCUBE-2s.
The work presented here was in part supported by ARPA contract DABT-63-93-C-0064 under “Hypercomputing and Design” project.
Chapter PDF
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
Jaswinder Pal Singh, Parallel Hierarchical N-Body Methods And their Implications for Multiprocessors, Ph.D. Thesis, Stanford U., Feb 1993.
Robert D. Blumofe, and Charles E. Leiserson. Scheduling Multithreaded Computations by Work Stealing. In Proceedings of the 35th Annual Symposium on Foundations of Computer Science (FOCS), pages 356–368, Santa Fe, New Mexico, November 20–22, 1994. (90 KBytes, compressed postscript.) California, July 19–21, 1995. postscript.
T. Yang and A. Gerasoulis. DSC: Scheduling parallel tasks on an unbounded number of processors, IEEE Trans. on Parallel and Distributed Systems. Vol. 5, No. 9, 951–967, 1994.
A. Gerasoulis and T. Yang. On the granularity and clustering of directed acyclic task graphs. IEEE Trans. on Parallel and Distributed Systems., Vol. 4, no. 6, June 1993, pp 686–701.
A. Gerasoulis, J. Jiao and T. Yang, Experience with Scheduling Irregular Scientific Computation, Proc. of 1st IPPS Workshop on Solving Irregular Problems on Distributed Memory Machines, 1–8, Santa Barbara, CA, April 1995.
Jia Jiao, Software support for parallel processing of irregular and dynamic computations, Ph.D. Thesis, Rutgers University, Oct. 1996.
Leslie Greengard, The rapid evaluation of potential fields in particle systems, Ph.D. Thesis, Yale University, 1987
R. Krasny, Computation of vortex sheet roll-up in the treffitz plane, Journal of Fluid Mechanics, Vol 184, pp. 123–155. 1987.
F. Chong, S. Sharma, E. Brewer, J. Saltz, Multiprocessor Runtime Support for Fine-Grained, Irregular DAGs. Parallel Processing Letters, December, 1995.
A. Y.Grama, V. Kumar and V. N. Rao, Experimental Evaluation of Load Balancing Techniques for the Hypercube. Proceedings of Parallel Computing 1991, Spe. 1991, London
H. D. Simon, Partitioning of Unstructured Problems for Parallel Processing, Computing Systems in Engineering, Vol. 2, Number 213, pp. 135–148, 1991
Bruce Hendrickson and Robert Leland, Multidimensional Spectral Load Balancing, Proc. 6th SIAM Conf. Parallel Proc., 953–961, 1993
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gerasoulisl, A., Jiao, J. (1997). Rescheduling support for mapping dynamic scientific computation onto distributed memory multiprocessors. In: Lengauer, C., Griebl, M., Gorlatch, S. (eds) Euro-Par'97 Parallel Processing. Euro-Par 1997. Lecture Notes in Computer Science, vol 1300. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0002833
Download citation
DOI: https://doi.org/10.1007/BFb0002833
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63440-9
Online ISBN: 978-3-540-69549-3
eBook Packages: Springer Book Archive