|
This article is cited in 9 scientific papers (total in 9 papers)
NUMERICAL METHODS AND THE BASIS FOR THEIR APPLICATION
Parallel implementation of a finite-element algorithms on a graphics accelerator in the software package FEStudio
S. P. Kopysov, I. M. Kuz'min, N. S. Nedozhogin, A. K. Novikov, V. N. Rychkov, Yu. A. Sagdeeva, L. E. Tonkov Institute of Mechanics UB RAS, 34 T. Baramzinoy st., Izhevsk, 426067, Russia
Abstract:
In this paper, we present new parallel algorithms for finite element analysis implemented in the FEStudio software framework. We describe the programming model of finite element method, which supports parallelism on different stages of numerical simulations. Using this model, we develop parallel algorithms of numerical integration for dynamic problems and local stiffness matrices. For constructing and solving the systems of equations, we use the CUDA programming platform.
Keywords:
finite element method, parallel computing, hybrid HPC platforms, object-oriented programming.
Received: 26.11.2013
Citation:
S. P. Kopysov, I. M. Kuz'min, N. S. Nedozhogin, A. K. Novikov, V. N. Rychkov, Yu. A. Sagdeeva, L. E. Tonkov, “Parallel implementation of a finite-element algorithms on a graphics accelerator in the software package FEStudio”, Computer Research and Modeling, 6:1 (2014), 79–97
Linking options:
https://www.mathnet.ru/eng/crm305 https://www.mathnet.ru/eng/crm/v6/i1/p79
|
Statistics & downloads: |
Abstract page: | 216 | Full-text PDF : | 76 | References: | 30 |
|