Structural Engineering and Mechanics

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Iterative mesh partitioning strategy for improving the efficiency of parallel substructure finite element computations

  • Hsieh, Shang-Hsien (Computer-Aided Engineering, Department of Civil Engineering, National Taiwan University) ;
  • Yang, Yuan-Sen (National Center for Research on Earthquake Engineering) ;
  • Tsai, Po-Liang (Military Police Headquarter)
  • Received : 2001.03.28
  • Accepted : 2002.04.24
  • Published : 2002.07.25
⟨ Previous Next ⟩

Abstract

This work presents an iterative mesh partitioning approach to improve the efficiency of parallel substructure finite element computations. The proposed approach employs an iterative strategy with a set of empirical rules derived from the results of numerical experiments on a number of different finite element meshes. The proposed approach also utilizes state-of-the-art partitioning techniques in its iterative partitioning kernel, a cost function to estimate the computational cost of each submesh, and a mechanism that adjusts element weights to redistribute elements among submeshes during iterative partitioning to partition a mesh into submeshes (or substructures) with balanced computational workloads. In addition, actual parallel finite element structural analyses on several test examples are presented to demonstrate the effectiveness of the approach proposed herein. The results show that the proposed approach can effectively improve the efficiency of parallel substructure finite element computations.

Keywords

References

  1. Ashcraft, C., Pierce, D., Wah, D.K. and Wu, J. (1999), "The reference manual for SPOOLES, Release2.2: An object oriented software library for solving sparse linear systems of equations", Boeing Shared Services Group, USA. (available from http://www.netlib.org/linalg/spooles/).
  2. Farhat, C. (1988), "A simple and efficient automatic FEM domain decomposer", Comput. Struct., 28(5), 579-602. https://doi.org/10.1016/0045-7949(88)90004-1
  3. Geng, P., Oden, J.T. and van de Geijn, R.A. (1997), "A parallel multifrontal algorithm and its implementation", Comput. Method Appl. Mech. Eng., 149, 289-301. https://doi.org/10.1016/S0045-7825(97)00052-2
  4. George, A. and Liu, J.W.H. (1981), Computer Solution of Large Sparse Positive Definite Systems, Prentice-Hall, Inc., New Jersey, U.S.A.
  5. Han, T.Y. and Abel, J.F. (1984), "Substructure condensation using modified decomposition", Int. J. Numer. Meth. Eng., 20(11), 1959-1964. https://doi.org/10.1002/nme.1620201102
  6. Hendrickson, B. and Leland, R. (1994), "The Chaco user's manual: Version 2.0", Sandia Tech Report SAND94-2692, Sandia National Laboratories, U.S.A.
  7. Hsieh, S.H., Paulino, G.H. and Abel, J.F. (1995), "Recursive spectral algorithms for automatic domain partitioning in parallel finite element analysis", Comput. Method Appl. Mech. Eng., 121, 137-162. https://doi.org/10.1016/0045-7825(94)00704-Q
  8. Hsieh, S.H., Paulino, G.H. and Abel, J.F. (1997), "Evaluation of automatic domain partitioning algorithms for parallel finite element analysis", Int. J. Numer. Meth. Eng., 40(6), 1025-1051. https://doi.org/10.1002/(SICI)1097-0207(19970330)40:6<1025::AID-NME103>3.0.CO;2-P
  9. Hsieh, S.H., Yang, Y.S., Cheng, W.C., Lu, M.D. and Sotelino, E.D. (1998), "MPE++: An object-oriented mesh partitioning environment in C++", Proc. 6th Asia-Pacific Conference on Structural Engineering & Construction, January 14-16, 1998, Taipei, Taiwan.
  10. Hsieh, S.H., Yang, Y.S. and Tsai, P.L. (1999), "Improved mesh partitioning for parallel substructure finite element computations", Proc. 7th East Asia-Pacific Conference on Structural Engineering & Construction, August 27-29, 1999, Kochi, Japan, 123-128.
  11. Karypis, G., Schloegel, K. and Kumar, V. (2002), "ParMETIS parallel graph partitioning and sparse matrix ordering library Version 3.0", Technical report, Department of Computer Science/Army HPC Research Center, MN, U.S.A.
  12. Kernighan, B.W. and Lin, S. (1970), "An efficient heuristic procedure for partitioning graphs", The Bell System Technical J., 49, 291-307. https://doi.org/10.1002/j.1538-7305.1970.tb01770.x
  13. Kirkpatrick, S., Gelatt, C.D. and Vecchi, M.P. (1983), "Optimization by simulated annealing," Science, 220, 671-680. https://doi.org/10.1126/science.220.4598.671
  14. Message Passing Interface Forum. (1994), "MPI: a message-passing interface standard", Int. J. Supercomputer Applications, 8(3/4), 159-416.
  15. Nour-Omid, B., Raefsky, A. and Lyzenga, G. (1987). "Solving finite element equations on concurrent computers", in Noor, A.K. (ed.), Parallel Computations and Their Impact on Mechanics, New York, U.S.A.
  16. Simon, H.D. (1991), "Partitioning of unstructured problems for parallel processing", Computing Systems in Engineering, 2(2/3), 135-148. https://doi.org/10.1016/0956-0521(91)90014-V
  17. Vanderstraeten, D. and Keunings, R. (1995), "Optimized partitioning of unstructured finite element meshes", Int. J. Numer. Meth. Eng., 38, 433-450. https://doi.org/10.1002/nme.1620380306
  18. Vanderstraeten, D., Farhat, C., Chen, P.S., Keuning, R. and Ozone, O. (1996), "A retrofit based methodology for the fast generation and optimization of large-scale mesh partitions: Beyond the minimum interface size criterion", Comput. Method Appl. Mech. Eng., 113, 25-45.
  19. Walshaw, C. (1999), "Serial jostle library interface: Version 1.1.8," Technical report, School of Computing and Mathematical Sciences, University of Greenwich, London, UK.
  20. Walshaw, C., Cross, M. and Everett, M. (1997), "Parallel dynamic graph partitioning for adaptive unstructured meshes", J. Parallel and Distributed Computing, 47(2), 102-108. https://doi.org/10.1006/jpdc.1997.1407
  21. Yang, Y.S. and Hsieh, S.H. (1997), "Some experiences on parallel finite element computations using IBM/SP2", Proc. 7th KAIST-NTU-KU Tri-Laterial Seminar/Workshop on Civil Engineering, Kyoto, Japan, December 1-3, 1997, 63-68.

Cited by

  1. FEM and BEM parallel processing: theory and applications – a bibliography (1996‐2002) vol.20, pp.4, 2003, https://doi.org/10.1108/02644400310476333