Computing Boundary Element Method’s Matrices on GPU
Matrices resulting from standard boundary element methods are dense and computationally expensive. To speed up the computational time, the matrix computation is done on a GPU. The parallel processing capability of the Graphics Processing Unit (GPU) allows us to divide complex computing tasks into several thousands of smaller tasks that can be run concurrently. We achieved an acceleration of 31 − 36 in comparison to a computation performed on the CPU, serially.
KeywordsGraphic Processing Unit Boundary Element Method Shared Memory Collocation Point Global Memory
Unable to display preview. Download preview PDF.
- 1.Schanz, M.: Wave Propagation in Viscoelastic and Poroelastic Continua: A Boundary Element Approach. Lecture Notes in Applied Mechanics, vol. 2 (2001)Google Scholar
- 5.NVIDIA Corporation, NVIDIA CUDA C Programming Guide Version 4.0 (June 2011), http://developer.download.nvidia.com/compute/DevZone/docs/html/C/doc/CUDA_C_Programming_Guide.pdf