• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

Lv, Hai (Lv, Hai.) | Di, Ruihua (Di, Ruihua.) | Gong, Hua (Gong, Hua.) | Li, Xinchun (Li, Xinchun.)

Indexed by:

EI Scopus

Abstract:

Finite element method, as one of calculation methods, has been widely applied in numerical solution of differential equations, engineering structural analysis, and electromagnetic analysis, etc. When solving large-scale, dynamic loading of engineering structures, it is computationally challenging to find the large-scale nonlinear equations. A parallel implementation of nonlinear equation solver, using a combination of MPI and OpenMP, has been developed in OpenSees which is an open source finite element analysis software. It shows good performance to apply this new solver to analyze the scale of tens of thousands of equations order. Furthermore, the HPCToolkit parallel program performance analysis tool is used to analyze the experimental results, Statistics show that the hybrid parallel programming model is more efficient than the one using pure MPI in the multi-core cluster architecture computing environment. © 2011 IEEE.

Keyword:

Nonlinear equations Multicore programming Nonlinear analysis Dynamic loads Numerical methods Open systems Parallel programming Ordinary differential equations Application programming interfaces (API) Finite element method Cluster computing Open source software

Author Community:

  • [ 1 ] [Lv, Hai]Computer College, Beijing University of Technology, Beijing, China
  • [ 2 ] [Di, Ruihua]Computer College, Beijing University of Technology, Beijing, China
  • [ 3 ] [Gong, Hua]Computer College, Beijing University of Technology, Beijing, China
  • [ 4 ] [Li, Xinchun]Computer College, Beijing University of Technology, Beijing, China

Reprint Author's Address:

Show more details

Related Keywords:

Related Article:

Source :

Proceedings - 2011 6th Annual ChinaGrid Conference, ChinaGrid 2011

Year: 2011

Page: 215-219

Cited Count:

WoS CC Cited Count: 0

SCOPUS Cited Count: 1

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 9

Online/Total:361/10596195
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.