Parallel Solvers on the GPU for Large-Scale Finite Element Equations

• Published in: Applied Mechanics and Materials Vol. 701-702; no. Industrial Engineering, Computation and Information Technologies; pp. 207 - 213
• Main Authors: Wang, Dong, Chen, Jun Quan, Zhang, Qing Hu, Jiang, Ya Peng
• Format: Journal Article
• Language: English
• Published: Zurich Trans Tech Publications Ltd 01.12.2014
• Subjects: Central processing units; Computation; Finite element method; Hardware; Magnetic fields; Mathematical analysis; Mathematical models; Solvers; CUDA; Finite Element Equations; Jacobi Conjugate Gradient Method; Parallel; GPU
• ISBN: 9783038353485; 3038353485
• ISSN: 1660-9336; 1662-7482; 1662-7482
• DOI: 10.4028/www.scientific.net/AMM.701-702.207

We present a parallel solution based on CUDA for accelerating the computation for solving large-scale Finite Element equations in electrical and magnetic field. JCG is used for solving equations and corresponding kernel function is designed for spMV. A computation speed test for solving FE equations is taken on NVIDIA Tesla K20c GPU hardware platform, the result proves that the method of kernel can reach 17.1 times faster than the solution using CPU, however it cannot ensure the advantage with CPU if we only use the lib functions on GPU to solve equations.