Margetts, Lee · Research Explorer (The University of Manchester) · 2002
Finite element analysis is versatile and used widely in a range of engineering andscientific disciplines. As time passes, the problems that engineers and designers areexpected to solve are becoming more computationally demanding. Often theproblems involve the interplay of two or more processes which are physically andtherefore mathematically coupled. Although parallel computers have been availablefor about twenty years to satisfy this demand, finite element analysis is still largelyexecuted on serial machines. Parallelisation appears to be difficult, even for thespecialist. Parallel machines, programming languages, libraries and tools are used toparallelise old serial programs with mixed success. In some cases the serialalgorithm is not naturally suitable for parallel computing. Some argue that rewritingthe programs from scratch, using an entirely different solution strategy is a betterapproach. Taking this point of view, using MPI for portability, a mesh free elementby element method for simple data distribution and the appropriate iterative solvers,a general parallel strategy for finite element analysis is developed and assessed.
Cited by 0
Leong, David Kok Hong · Monash University · 2021
This thesis was scanned from the print manuscript for digital preservation and is copyright the author. Researchers can access this thesis by asking their local university, institution or public library to make a request on their behalf. Monash staff and postgraduate students can use the link in the References field.
Cited by 0Open access
Kuo‐Ning Chiang, Robert E. Fulton · Computers & Structures · 1992
Cited by 2
David Leong · Figshare · 2021
This thesis was scanned from the print manuscript for digital preservation and is copyright the author. Researchers can access this thesis by asking their local university, institution or public library to make a request on their behalf. Monash staff and postgraduate students can use the link in the References field.
Cited by 0Open access
Ryuji Shioya, Hiroyuki TAKUBO, Genki YAGAWA · TRANSACTIONS OF THE JAPAN SOCIETY OF MECHANICAL ENGINEERS Series A · 1999
As computers can be connected to each other through the internet, we are able to use a remote computer even if it is located overseas in the same way as using a computer which is located nearby. This paper describes a parallel finite element system using the domain decomposition method, which is implemented on a computer network made from remote computers at the Internet. The above system was successfully applied to the 3 D structural analyses with a high parallel efficiency.
Cited by 0Open access
Víctor E. Cardoso, Salvador Botello · Communications in computer and information science · 2016
Cited by 2
Amane Takei, Makoto Sakamoto · Proceedings of International Conference on Artificial Life and Robotics · 2019
Cited by 0
R. Valkenberg, G. Warzee, P. Saint-Georges et al. · Civil-comp proceedings · 2009
The purpose of this contribution is to show the performances of three parallel preconditioners developped for stress analysis.The problem is the solution of large linear systems of algebraic equations, which arise in the finite element discretizations of linear elastic structures, the computation Ing made by a parallel iterative method.During the last W years, a general theory has been developped for the study of additive and multiplicative Schwarz methods.We apply the additive Schwarz theory, as a preconditioner which is by nature parallel.Other widely used preconditioners are based on incomplete Cholesky factorizations (IC), but for the problems treated here a reduction stage to a Stieltjes form is required in order to obtain an IC factorizable matrix [1].The parallelization of the IC preconditioner is performed by replication of boundary unknowns on two or more subdomains.The last preconditioner is based on the Schur complement n :thod which consists in solving the boundary problem obtained after elimination of the intermal unknowns.These three preconditioners are based on domain decomposition schemes.Numerical analyses on regular and irregular meshes show the performances of the three methods and the influences of different parameters such as the amount of overlap, the mber of subdomains or the decomposition method.
Cited by 1
Pranjal Naik, Sayan Gupta · 2014
Cited by 0
Edward J. Plaskacz · Computer-Aided Civil and Infrastructure Engineering · 1997
Cited by 11
Asad I. Khan, B.H.V. Topping · Computing Systems in Engineering · 1993
Cited by 26
Yasuharu Nakabayashi, Genki YAGAWA, Hiroshi Okuda · Computational Mechanics · 1996
Cited by 12
Yasuharu Nakabayashi, H. Okuda, Genki YAGAWA et al. · Computational Mechanics · 1996
Cited by 2
Shun Doi, Hidehiro Fujio, Kouta Sugihara · 1996
The authors have been developing a finite element based simulation language system FEEL (Finite Element Equation Language). The current version of the system has the functionality to generate a portable message-passing parallel program from a user’s description of 2D partial differential equations. This paper introduces the FEEL system with an emphasis on its parallel program generation functionality. Discussion will be presented on how this tool can contribute to finite element programmers from several viewpoints. Since the development of efficient message-passing parallel programs requires a good knowledge of the target parallel computers, the functionality is expected to help numerical analysts who have need to develop finite element programs which require high-performance computing resources.
Cited by 0
Kuo‐Ning Chiang, Robert E. Fulton · Computers & Structures · 1990
Cited by 23
J. Sziveri · 1997
Cited by 1
Mohamed E. M. El-Sayed, Ching-Kuo Hsiung · Computers & Structures · 1991
Cited by 21
Amane Takei, Isamu Higashi, Masaru Aikawa et al. · Journal of Advanced Simulation in Science and Engineering · 2019
With the expansion of electromagnetic field analysis using computers, large spaces that include complex shapes have also become an analysis target, and the development of a high-accuracy analysis is required for these problems. Therefore, in the present study, Berenger's PML, which is currently the most effective absorbing boundary condition, is applied to the parallel finite element method based on the domain decomposition method, which is an effective analysis method for the microwave band. As a basic study, we developed an analysis code using a parallel finite element method based on the iterative domain decomposition method. In verifying the accuracy of the analysis code, we analyzed TEAM Workshop Problem 29, which is a benchmark problem, and confirmed that a highly accurate solution is obtained. Next, a model with Berenger's PML added to the dipole antenna model is used as an analysis object, and the absorption performance of the PML is evaluated using a reflection coefficient based on the S parameter. Moreover, the accuracy of the antenna analysis is evaluated by comparing the directivity of the dipole antenna with the theoretical solution. As a result, the effectiveness of the proposed method for microwave analysis is confirmed.
Cited by 2Open access
R.I. Mackie · Civil-comp proceedings · 2009
Developments in computers mean that parallel and distributed computing are now mainstream elements, therefore engineering software needs to be parallel as a matter of course. This adds greater complexity. This paper describes how component and object oriented methods can be used to make it relatively easy for software to be designed that can take advantage of parallelism. This is applied to equation solution, mesh generation, node ordering, equation assembly, and non-linear solution methods. The results of sample calculations are given demonstrating the speed-up achived.
Cited by 0
Buntono · DR-NTU (Nanyang Technological University) · 2002
Three explicit domain decomposition algorithms with substructuring method, which requires the physical partitioning of the finite element model, were considered in this research.
Cited by 0