DOI QR코드

DOI QR Code

외연 Lagrangian 유한요소법 기반의 대규모 유한요소 모델 병렬처리

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

  • 발행 : 2006.08.31

초록

비선형 외연 유한요소법에서 유한요소 병렬 처리 방안을 기술하고 코드에 구현하였다. 성능테스트 장비로 자체 구축한 520 개의 CPU를 갖는 리눅스 클러스터 슈퍼컴퓨터를 사용하였다. 대규모 모델 테스트 결과 256 개의 CPU 까지도 거의 이상적인 속도 증가를 보였다. 유한요소 계산시간 대비 통신시간 계산이 전체 성능에 미치는 영향도 검토하였다. 사용 프로세서가 증가할수록 상용코드의 병렬 성능 대비 더 좋은 성능을 보이는 것으로 나타났다.

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.

키워드

참고문헌

  1. 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 https://doi.org/10.1007/s004660050348
  2. 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 https://doi.org/10.1016/S0045-7825(99)00235-2
  3. 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
  4. 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
  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. 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 https://doi.org/10.1002/nme.1620370404