|
| Solving large finite element system by GPU computation |
| Received:August 20, 2010 Revised:March 18, 2011 |
| View Full Text View/Add Comment Download reader |
| DOI：10.7511/jslx20121026 |
| KeyWord:GPU computation finite element method conjugate gradient method parallel computation CUDA |
| Author | Institution |
| 刘小虎 |
华中科技大学 力学系, 武汉 |
| 胡耀国 |
华中科技大学 力学系, 武汉 |
| 符伟 |
华中科技大学 力学系, 武汉 |
|
| Hits: 3430 |
| Download times: 2601 |
| Abstract: |
| Some techniques for applying GPU(Graphics Processing Units) computation in FEM(Finite Element Method) were investigated in this paper,which include element stiffness matrix parallel calculation and global stiffness matrix assembly method,unstructured sparse matrix-vector multiplication and large-scale linear system solving method.A FEM code was implemented by using CUDA(Compute Unified Device Architecture) platform and tested on nVidia GeForce GPU device.The system stiffness matrix was stored in the graphics memory in CSR(Compressed Sparse Row) format,and assembled via element coloring.Conjugate gradient method was used to solve FEM linear system iteratively.For the truss and 2D examples,the GPU-based FEM code gained speedups up to 9.5x and 6.5x,respectively.It is found that the GPU speedup values are roughly linear with system DOFs(Degree Of Freedoms),and the peak values of GFLOP/s increase approximately 10 times when comparing with those of CPU’s. |
|
|
|