Design Considerations on Large-scale Parallel Finite Element Code in Shared Memory Architecture with Multi-Core CPU

Jeong-Rae Cho; Keunhee Cho

doi:10.7734/COSEIK.2017.30.2.127

All Issue

2017 Vol.30, Issue 2 Preview Page Next Page

Design Considerations on Large-scale Parallel Finite Element Code in Shared Memory Architecture with Multi-Core CPU 멀티코어 CPU를 갖는 공유 메모리 구조의 대규모 병렬 유한요소 코드에 대한 설계 고려 사항

2017. pp. 127-135

PDF XML

Abstract

The computing environment has changed rapidly to enable large-scale finite element models to be analyzed at the PC or workstation level, such as multi-core CPU, optimal math kernel library implementing BLAS and LAPACK, and popularization of direct sparse solvers. In this paper, the design considerations on a parallel finite element code for shared memory based multi-core CPU system are proposed; (1) the use of optimized numerical libraries, (2) the use of latest direct sparse solvers, (3) parallelism using OpenMP for computing element stiffness matrices, and (4) assembly techniques using triplets, which is a type of sparse matrix storage. In addition, the parallelization effect is examined on the time-consuming works through a large scale finite element model.

Keywords

finite element code

multi-core CPU

OpenMP

sparse solver

멀티코어 CPU와 BLAS, LAPACK을 구현한 최적 수치라이브러리, 직접 희소 솔버의 대중화 등 PC나 워크스테이션 수준 에서도 대규모 유한요소 모델을 해석할 수 있도록 컴퓨팅 환경이 급속도로 변화되었다. 이 논문에서는 멀티코어 CPU를 갖 는 공유 메모리 구조에 대한 병렬 유한요소 프로그램 설계시 고려사항으로 (1) 최적화된 수치라이브러리의 사용, (2) 최신 직접 희소 솔버의 사용, (3) OpenMP를 이용한 병렬 요소 강성 행렬의 계산, (4) 희소행렬 저장방식의 일종인 triplet을 이용 한 어셈블 기법 등을 제시하였다. 또한 대규모 수치모델을 통해 많은 시간이 소요되는 작업을 기준으로 병렬화 효과를 검토 하였다.

키워드

유한요소코드

멀키코어 CPU

OpenMP

희소 솔버

References

References

ABQUS Inc, ABAQUS Analysis User's Manual (Version 6.7) (2007)

ACML-AMD Core Math Library, http://developer.amd.com/tools-and-sdks/archive/compute/amd-core-math-library-acml

ADINA R&D Inc, Theory and Modeling Guide, ADINA System 8.3 (2005)

ANSYS Inc, Release 11.0 Documentation for ANSYS-Mutitibody Analysis Guide (2007)

ATLAS-Automatically Tuned Linear Algebra Software, http://math-atlas.sourceforge.net

KJ Bathe, Finite Element Procedures, Prentice Hall. (1995)

M Benzi, R Kouhia and M Tuma, Comm. Numer. Methods Eng, An Assessment of Some Preconditioning Techniques in Shell Problems, 14; 897-906 (1998)

http://dx.doi.org/10.1002/(SICI)1099-0887(1998100)14:10<897::AID-CNM196>3.0.CO;2-L

M Benzi, JK Cullum and M Tuma, J. Sci. Comput, Robust Approximate Inverse Preconditioning for the Conjugate Gradient Method, 22(4); 1318-1332 (2000)

10.1137/s1064827599356900

M Benzi, J. Comput. Phys, Preconditioning Techniques for Large Linear Systems: A Survey, 182(2); 418-477 (2002)

10.1006/jcph.2002.7176

BLAS (Basic Linear Algebra Subprograms), www.netlib.org/blas/

J-R Cho, Object-oriented Finite Element Framework Using Hybrid Programming, PhD. Dissertation, Seoul National University. (2009)

M Cho and RR Parmerter, Compos. Struct, An Efficient Higher Order Plate Theory for Laminated Composites, 20; 113-123 (1992)

10.1016/0263-8223(92)90067-M

CHOLMOD in SUITESPARSE, http://faculty.cse.tamu.edu/davis/suitesparse.html

TA Davis, Direct Methods for Sparse Linear Systems, Siam. (2006)

10.1137/1.9780898718881

GOTOBLAS2, https://www.tacc.utexas.edu/researchdevelopment/tacc-software/gotoblas2

Intel Math Kernel Library, http://software.intel.com/en-us/intel-mkl

LAPACK-Linear Algebra PACKage, http://www.netlib.org/lapack/

J-S Lim, I-M Son, J-M Kim and C-G Seo, J. Comput. Struct. Eng. Inst. Korea, A Speed-Up in Computing Time for SSI Analysis by p-version Infinite Elements, 29(5); 471-482 (2016)

10.7734/COSEIK.2016.29.5.471

MUMPS, http://mumps.enseeiht.fr/

OpenBLAS, http://www.openblas.net/

PARDISO, http://www.pardiso-project.org

Y Saad, Iterative Methods for Sparse Linear Systems, Siam. (2003)

10.1137/1.9780898718003

UMPFACK in SUITESPARSE, http://faculty.cse.tamu.edu/davis/suitesparse.html

Information

Publisher :Computational Structural Engineering Institute of Korea
Publisher(Ko) :한국전산구조공학회
Journal Title :Journal of the Computational Structural Engineering Institute of Korea
Journal Title(Ko) :한국전산구조공학회 논문집
Volume : 30
No :2
Pages :127-135
Received Date : 2016-12-29
Revised Date : 2017-01-03
Accepted Date : 2017-01-10
DOI :https://doi.org/10.7734/COSEIK.2017.30.2.127

Journal of the Computational Structural Engineering Institute of Korea ISSN:1229-3059(Print) 2287-2302(Online) 한국전산구조공학회 논문집

All Issue

References