Browse > Article
http://dx.doi.org/10.5139/JKSAS.2006.34.8.033

Parallel Computing of Large Scale FE Model based on Explicit Lagrangian FEM  

백승훈 (서울대학교)
김승조 (서울대학교)
이민형 (세종대학교)
Publication Information
Journal of the Korean Society for Aeronautical & Space Sciences / v.34, no.8, 2006 , pp. 33-40 More about this Journal
Abstract
A parallel computing strategy for finite element(FE) processing is described and implemented in nonlinear explicit FE code and its parallel performances are evaluated. A self-made linux-cluster supercomputer with 520 CPUs is used as a bench mark test bed. It is observed that speed-up is increased almost idealy even up to 256 CPUs for a large scale model. A communication over head and its effect on the parallel performance is also examined. Parallel performance is compare with the commercial code and developed code shows superior performance as the number of CPUs used are increased.
Keywords
parallel computing; large scale problem; linux-cluster; explicit time integration method;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Malone J.G., Johnson N.L., 'A parallel finite element contact/impact algorithm for non-linear explicit transient analysis : Part II Parallel implementation', Int. J. Num. Meth. Eng., Vol. 37, 1994, pp. 591-603   DOI   ScienceOn
2 Attaway S.W., Hendrickson B.A., Plimpton S.J., Gardner D.R., Vaughan C.T., 'A Parallel contact detection algorithm for transient solid dynamics simulation using PRONTO3D' Computational Mechanics. Vol. 22, 1998, pp. 143-59   DOI
3 Paik, S.H., Kim, S.J., 'High speed impact and penetration analysis using explicit finite element method', Journal of the Korea Institute of Military Science and Technology, Vol. 8, No.4, 2005, pp. 5-13
4 Paik, S.H. Moon, J.J., Kim, S.J. and Lee, M., 'Parallel performance of large-scale impact problem in linux cluster super computer', Computers & Structures, Vol.84, 2006, pp. 732-741
5 Malard J. MPI: A message-passing interface standard. history, overview and current Status. Technology Watch Report, 1996, Edinburgh Parallel Computing Center
6 Karypis G., Kumar V., Metis: Unstructured graph partitioning and sparse matrix ordering system. Technical Report, 1995, Department of Computer Science, University of Minnesota
7 Kevin Brown, Steve Attaway, Steve Plimpton, Bruce Hendrickson, 'Parallel Strategies for crash and impact simulations', Comput. Methods Appl. Engng., Vol. 184, 2000, pp. 375-390   DOI   ScienceOn