Abstract
Sparse matrix-vector multiplication is the kernel for many scientific computations. Parallelizing this operation requires the matrix to be divided among processors. This division is commonly phrased in terms of graph partitioning. Although this abstraction has proved to be very useful, it has significant flaws and limitations. The cost model implicit in this abstraction is only a weak approximation to the true cost of the parallel matrix-vector multiplication. And the graph model is unnecessarily restrictive. This paper will detail the shortcomings of the current paradigm and suggest directions for improvement and further research.
This work was funded by the Applied Mathematical Sciences program, U.S. Department of Energy, Office of Energy Research and performed at Sandia National Laboratories operated for the U.S. DOE under contract number DE-AC04-76DP00789.
Preview
Unable to display preview. Download preview PDF.
References
C. Farhat, N. Maman and G. Brown, Mesh partitioning for implicit computation via domain decomposition: impact and optimization of the subdomain aspect ratio, Int. J. Num. Meth. Engrg. 38 (1995), pp. 989–1000.
B. Hendrickson and R. Leland, The Chaco user's guide, version 2.0, Tech. Rep. SAND95-2344, Sandia Natl. Lab., Albuquerque, NM, 87185, 1995.
B. Hendrickson and T. G. Kolda, Parallel algorithms for nonsymmetric iterative solvers. In preparation.
—, Partitioning Sparse Rectangular Matrices for Parallel Computation of Ax and A T v. In Lecture Notes in Computer Science, Springer-Verlag, 1998. Proc. PARA'98. To appear.
G. Karypis and V. Kumar, A fast and high quality multilevel scheme for partitioning irregular graphs, Tech. Rep. 95-035, Dept. Computer Science, Univ. Minnesota, Minneapolis, MN 55455, 1995.
—, Parallel multilevel graph partitioning, Tech. Rep. 95-036, Dept. Computer Science, Univ. Minnesota, Minneapolis, MN 55455, 1995.
—, Multilevel algorithms for multi-constraint graph partitioning, Tech. Rep. 98-019, Dept. Computer Science, Univ. Minnesota, Minneapolis, MN 55455, 1995.
T. G. Kolda, Partitioning sparse rectangular matrices for parallel processing. In Proc. Irregular'98, 1998.
F. Pellegrini, SCOTCH 3.1 user's guide, Tech. Rep. 1137-96, Laboratoire Bordelais de Recherche en Informatique, Universite Bordeaux,, France, 1996.
R. Preis, R. Diekmann, The PARTY Partitioning-Library, User Guide — Version 1.1, Tech. Rep. tr-rsfb-96-024, University of Paderborn, Paderborn, Germany, 1996.
C. Walshaw, M. Cross, and M. Everett, Mesh partitioning and load-balancing for distributed memory parallel systems, in Proc. Parallel & Distributed Computing for Computational Mechanics, Lochinver, Scotland, 1997, B. Topping, ed., 1998.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hendrickson, B. (1998). Graph partitioning and parallel solvers: Has the emperor no clothes?. In: Ferreira, A., Rolim, J., Simon, H., Teng, SH. (eds) Solving Irregularly Structured Problems in Parallel. IRREGULAR 1998. Lecture Notes in Computer Science, vol 1457. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0018541
Download citation
DOI: https://doi.org/10.1007/BFb0018541
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-64809-3
Online ISBN: 978-3-540-68533-3
eBook Packages: Springer Book Archive