Abstract
We present a massively parallel algorithm for static and dynamic partitioning of unstructured FEM-meshes. The method consists of two parts. First a fast but inaccurate sequential clustering is determined which is used, together with a simple mapping heuristic, to map the mesh initially onto the processors of a massively parallel system. The second part of the method uses a massively parallel algorithm to remap and optimize the mesh decomposition taking several cost functions into account. It first calculates the amount of nodes that have to be migrated between pairs of clusters in order to obtain an optimal load balancing. In a second step, nodes to be migrated are chosen according to cost functions optimizing the amount and necessary communication and other measures which are important for the numerical solution method (like for example the aspect ratio of the resulting domains).
The parallel parts of the method are implemented in C under Parix to run on the Parsytec GCel systems. Results on up to 64 processors are presented and compared to those of other existing methods.
This work was partly supported by the DFG Sonderforschungsbereich 1511 “Massive Parallelität: Algorithmen, Entwurfsmethoden, Anwendungen”, by the Esprit Basic Research Action Nr. 7141 (ALCOM II) and the EC HC&M Project MAP.
Preview
Unable to display preview. Download preview PDF.
References
P. Bastian: Parallel Adaptive Multigrid Methods. Tech. Rep., IWR Heidelberg 1993
G.E. Blelloch, A. Feldmann, O. Ghattas, J.R. Gilbert, G.L. Miller, D.R. O'Hallaron, E.J. Schwabe, J.R. Shewchuk, S.-H. Teng: Automated Parallel Solution of Unstructured PDE problems. CACM, to appear
S.H. Bokhari: On the Mapping Problem. IEEE TOC 30(3), 1981, pp. 207–214
N. Chrisochoides, C.E. Houstis, E.N. Houstis, S.K. Kortesis, J.R. Rice: Automatic Load Balanced Partitioning Strategies for PDE Computations. Proc. of ACM Int. Conf. on Supercomputing, 1989, pp. 99–107
R. Diekmann, R. Lüling, B. Monien, C. Spräner: A parallel local-search Algorithm for the k-Partitioning Problem. Proc. of the 28th Hawaii Int. Conference on System Sciences (HICSS '95), vol. 2, pp. 41–50 http://www.uni-paderborn.de/fachbereich/AG/monien/PERSONAL/diek.html
R. Diekmann, R. Lüling, A. Reinefeld: Distributed Combinatorial Optimization. Proc. of Sofsem'93, Czech Republik 1993, pp. 33–60
R. Diekmann, B. Monien, R. Preis: Using Helpful Sets to Improve Graph Bisections. Tech. Rep. tr-rf-94-008, CS-Dept., Univ. of Paderborn, 1994 To Appear in: DIMACS Series in Discrete Mathematics and Theoretical Computer Science, American Mathematical Society 1995
C. Farhat: A Simple and Efficient Automatic FEM Domain Decomposer. Computers & Structures, Vol. 28(5), 1988, pp. 579–602
C. Farhat, H.D. Simon: TOP/DOMDEC — a Software Tool for Mesh Partitioning and Parallel Processing. Tech. Rep. RNR-93-011, NASA Ames 1993
T. Feder, D.H. Greene: Optimal Algorithms for Approximate Clustering. ACM Symp. on Theory of Computing (STOC), 1988
N. Floros, J. R. Reeve, J. Clinckemaillie, S. Vlachoutsis, G. Lonsdale: Comparative Efficiencies of Domain Decompositions. Tech. Rep. Univ. of Southampton, 1994
S.W. Hammond: Mapping Unstructured Grid Computations to Massively Parallel Computers. Tech. Rep. No. 92.14, RIACS, NASA Ames, June 1992
B. Hendrickson, R. Leland: The Chaco User's Guide. Technical Report SAND93-2339, Sandia National Laboratories, Nov. 1993
B. Hendrickson, R. Leland: An Improved Spectral Graph Partitioning Algorithm for Mapping Parallel Computations. SIAM J. on Scientific Computing, Vol. 16, No. 2, pp. 452–469, 1995.
M.T. Jones, P.E. Plassmann: Parallel Algorithms for the Adaptive Refinement and Partitioning of Unstructured Meshes. Preprint, Argonne National Laboratory 1994
G. Karypis, V. Kumar: A Fast and High Quality Multilevel Scheme for Partitioning Irregular Graphs. Techn. Rep. 95-035, Dept. of Comp. Science, University of Minnesota, 1995.
H. van Lengen, J. Krome: Automatische Netzeinteilungsalgorithmen zum effektiven Einsatz der parallelen Substrukturtechnik. R. Flieger, R. Grebe (ed.): Parallele Datenverarbeitung aktuell: TAT '94 IOS Press, 1994, S. 327–336 (in German)
O.C. Martin, S.W. Otto: Partitioning of Unstructured Meshes for Load Balancing. Techn. Rep. CSE-94-017, Oregon Grad. Inst. of Science & Technology 1994.
B. Monien, R. Diekmann, R. Feldmann, R. Klasing, R. Lüling, K. Menzel, T. Römke, U.-P. Schroeder: Efficient Use of Parallel & Distributed Systems: From Theory to Practice. To appear in: J. van Leeuwen (ed.) Trends in Computer Science, Springer LNCS 1000, 1995.
C.-W. Ou, S. Ranka: Parallel Remapping Algorithms for Adaptive Problems. Tech. Rep. CRCP-TR94506, Rice University, 1994
A. Pothen, H.D. Simon, K.P. Liu: Partitioning Sparse Matrices with Eigenvectors of Graphs. SIAM J. on Matrix Analysis and Applications 11/3, 1990, pp. 430–452
H.D. Simon: Partitioning of unstructured problems for parallel processing. Comput. Syst. Eng. 2, 1991, pp. 135–148
S. Trewin: PUL-DM Prototype User Guide. Tech. Rep., Edinburgh Parallel Computing Center, 1993
C. Walshaw, M. Berzins: Dynamic Load-balancing for PDE solvers on apative unstructured meshes. Concurrency: Practice and Experience 7(1), 1995, pp. 17–28
C. Walshaw, M. Cross, M.G. Everett: A Parallelisable Algorithm for Optimising Unstructured Mesh Partitions. Math. Res. Rep., Univ. of Greenwich, London, 1995
R.D. Williams: Performance of Dynamic Load Balancing Algorithms for Unstructered Mesh Calculations. Concurrency 3, 1991, pp. 457–481
C. Xu, F. Lau: The Generalized Dimension Exchange Method for Load Balancing in k-ary n-cubes and Variants. J. Par. Distr. Comp. 24(1), 1995, pp. 72–85
C. Xu, B. Monien, R. Lüling, F. Lau: An Analytical Comparison of Nearest Neighbor Algorithms for Load Balancing in Parallel Computers. Proc. of 9th International Parallel Processing Symposium (IPPS '95), 1995.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Diekmann, R., Meyer, D., Monien, B. (1995). Parallel decomposition of unstructured FEM-meshes. In: Ferreira, A., Rolim, J. (eds) Parallel Algorithms for Irregularly Structured Problems. IRREGULAR 1995. Lecture Notes in Computer Science, vol 980. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60321-2_17
Download citation
DOI: https://doi.org/10.1007/3-540-60321-2_17
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60321-4
Online ISBN: 978-3-540-44915-7
eBook Packages: Springer Book Archive