Multi-Constraint Mesh Partitioning for Contact/Impact Computations

ABSTRACT

We present a novel approach for decomposing contact/impact computations in which the mesh elements come in contact with each other during the course of the simulation. Effective decomposition of these computations poses a number of challenges as it needs to both balance the computations and minimize the amount of communication that is performed during the finite element and the contact search phase. Our approach achieves the first goal by partitioning the underlying mesh such that it simultaneously balances both the work that is performed during the finite element phase and that performed during contact search phase, while producing subdomains whose boundaries consist of piecewise axes-parallel lines or planes. The second goal is achieved by using a decision tree to decompose the space into rectangular or box-shaped regions that contain contact points from a single partition. Our experimental evaluation on a sequence of 100 meshes, shows that this new approach can reduce the overall communication overhead over existing algorithms.

References

1. {1} Leo Breiman, Jerome H. Friedman, Richard A. Olshen, and Charles J. Stone. Classification and Regression Trees. Chapman & Hall, New York, 1984.
2. {2} K. Brown, S. Attaway, S. Plimpton, and B. Hendrickson. Parallel strategies for crash and impact simulations. Computational Methods in Applied Mechanics & Engineering, 184:375-390, 2000.
3. {3} T. Bui and C. Jones. A heuristic for reducing fill in sparse matrix factorization. In 6th SIAM Conf. Parallel Processing for Scientific Computing, pages 445-452, 1993.
4. {4} G. Camacho and M. Ortiz. Adaptive langrangian modeling of ballistic penetration of metalic targets. Computational Methods in Applied Mechanical Engineering, 147:269- 301, 1997.
5. {5} R. Diekmann, J. Hungershofer, M. Lux, L. Taenzer, and J. Wierum. Efficient contact search for finite element analysis. In European Congress on Computational Methods in Applied Sciences and Engineering, 2000.
6. {6} M. Heinstein, S. Attaway, F. Mello, and J. Swegle. A general-purpose contact detection algorithm for nonlinear structural analysis codes. Technical Report SAND92-2141, Sandia National Laboratories, 1993.
7. {7} B. Hendrickson. Graph partitioning and parallel solvers: Has the emperor no clothes? In Proc. Irregular'98, pages 218-225, 1998.
8. {8} B. Hendrickson and K. Devine. Dynamic load balancing in computational mechanics. Computational Methods in Applied Mechanics & Engineering, 184:485-500, 2000.
9. {9} B. Hendrickson and T. Kolda. Graph partitioning models for parallel computing. Parallel Computing (to appear), 2000.
10. {10} Bruce Hendrickson and Robert Leland. The chaco user's guide, version 1.0. Technical Report SAND93-2339, Sandia National Laboratories, 1993.
11. {11} Bruce Hendrickson and Robert Leland. A multilevel algorithm for partitioning graphs. Technical Report SAND93- 1301, Sandia National Laboratories, 1993.
12. {12} C. Hoover, A. DeGroot, J. Maltby, and R. Procassini. Paradyn: Dyna3d for massively parallel computers, 1995. Presentation at Tri-Laboratory engineering Conference on Computational Modeling.
13. {13} G. Johnson, R. Stryk, and S. Beissel. User Instructions for the 2001 Version of the EPIC code. Alliant Techsystems, Inc., Hopkins, Minnesota, April 2001.
14. {14} M. V. Joshi, G. Karypis, and V. Kumar. ScalParC: A new scalable and efficient parallel classification algorithm for mining large datasets. In Proc. of the International Parallel Processing Symposium, 1998.
15. {15} G. Karypis and V. Kumar. METIS 4.0: Unstructured graph partitioning and sparse matrix ordering system. Technical report, Department of Computer Science, University of Minnesota, 1998. Available on the WWW at URL http://www.cs.umn.edu/~metis.
16. {16} G. Karypis and V. Kumar. Multilevel algorithms for multi-constraint graph partitioning. In Proceedings of Supercomputing , 1998. Also available on WWW at URL http://www.cs.umn.edu/~karypis.
17. {17} G. Karypis and V. Kumar. Multilevel k-way partitioning scheme for irregular graphs. Journal of Parallel and Distributed Computing, 48(1):96-129, 1998. Also available on WWW at URL http://www.cs.umn.edu/~karypis.
18. {18} G. Karypis and V. Kumar. A parallel algorithm for multilevel graph partitioning and sparse matrix ordering. Journal of Parallel and Distributed Computing, 48(1):71-95, 1998. Also available on WWW at URL http://www.cs.umn.edu/~karypis. A short version appears in Intl. Parallel Processing Symposium 1996.
19. {19} G. Karypis and V. Kumar. A fast and highly quality multi-level scheme for partitioning irregular graphs. SIAM Journal on Scientific Computing, 20(1), 1999. Also available on WWW at URL http://www.cs.umn.edu/~karypis. A short version appears in Intl. Conf. on Parallel Processing 1995.
20. {20} G. Karypis and V. Kumar. Parallel multilevel k-way partitioning for irregular graphs. SIAM Review, 41(2):278-300, 1999.
21. {21} G. Karypis, Kirk Schloegel, and V. Kumar. PARMETIS 3.0: Parallel graph partitioning and sparse matrix ordering library. Technical report, Department of Computer Science, University of Minnesota, 2002. Available on the WWW at URL http://www.cs.umn.edu/~metis.
22. {22} George Karypis and Vipin Kumar. A coarse-grain parallel multilevel k-way partitioning algorithm. In Proceedings of the eighth SIAM conference on Parallel Processing for Scientific Computing, 1997.
23. {23} G. Lonsdale, J. Clinckemaillie, S. Vlachoutsis, and J. Dubois. Communication requirements in parallel crash-wirthiness simulation. In Proceedings of the HPCN 94, pages 55-61, 1994.
24. {24} J. Malone and N. Johnson. A parallel finite element contact/impact algorithms for non-linear explicit transient analysis: Part II - parallel implementation. Intl. J. Num. Methods Eng., 37:591-603, 1994.
25. {25} B. Monien, R. Preis, and R. Diekmann. Quality matching and local improvement for multilevel graph-partitioning. Technical report, University of Paderborn, 1999.
26. {26} M. Oldenburg and L. Nilsson. The position code algorithm for contact searching. International Journal for Numerical Methods in Engineering, 37:359-386, 1994.
27. {27} S. Plimpton, S. Attaway, B. Hendrickson, J. Swegle, C. Vaughan, and D. Gardner. Transient dynamics simulations: Parallel algorithms for contact detection and smoothed particle hydrodynamics. Journal of Parallel and Distributed Computing, 50:104-122, 1998.
28. {28} A. Pothen. Graph partitioning algorithms with applications to scientific computing. In D. Keyes, A. Sameh, and V. Venkatakrishnan, editors, Parallel Numerical Algorithms . Kluwer Academic Press, 1996.
29. {29} J. Ross Quinlan. Induction of decision trees. Machine Learning, 1:81-106, 1986.
30. {30} J. Ross Quinlan. C4.5: Programs for Machine Learning. Morgan Kaufmann, San Mateo, CA, 1993.
31. {31} K. Schloegel, G. Karypis, and V. Kumar. A new algorithm for multi-objective graph partitioning. In Proceedings of Europar 1999, September 1999.
32. {32} K. Schloegel, G. Karypis, and V. Kumar. Parallel multilevel algorithms for multi-constraint graph partitioning. In Proceedings of Europar 2000, September 2000. Distinguished Paper Award.
33. {33} Kirk Schloegel, George Karypis, and Vipin Kumar. Multilevel diffusion algorithms for repartitioning of adaptive meshes. Journal of Parallel and Distributed Computing, 47(2):109-124, 1997. Also available on WWW at URL http://www.cs.umn.edu/~karypis.
34. {34} Kirk Schloegel, George Karypis, and Vipin Kumar. Graph partitioning for high-performance scientific simulations. In Jack Dongara, Ian Foster, Geoffrey Fox, William Gropp, Ken Kennedy, Linda Torczon, and Andy White, editors, Sourcebook on Parallel Computing, chapter 18, pages 491- 541. Morgan Kaufmann, San Francisco, CA, 2002.
35. {35} C. Walshaw and M. Cross. Parallel optimisation algorithms for multilevel mesh partitioning. Technical Report 99/IM/44, University of Greenwich, London, UK, 1999.
36. {36} Z. Zhong and L. Nilsson. A contact searching algorithm for general contact problems. Comp. & Struct., 33:197-209, 1989.