| 二维扩散方程的GPU加速 |
| |
| 引用本文： | 董廷星,王龙,迟学斌.二维扩散方程的GPU加速[J].计算机工程与科学,2009,31(11). |
| |
| 作者姓名： | 董廷星 王龙 迟学斌 |
| |
| 作者单位： | 中国科学院计算机网络信息中心超级计算中心,北京,100190 |
| |
| 基金项目： | 中国科学院知识创新工程青年人才领域项目 |
| |
| 摘 要： | 近几年来,GPU因拥有比CPU更强大的浮点性能备受瞩目。NVIDIA推出的CUDA架构,使得GPU上的通用计算成为现实。本文将计算流体力学中Benchmark问题的二维扩散方程移植到GPU,并采用了全局存储和纹理存储两种方法。结果显示,当网格达到百万量级的时候,得到了34倍的加速。
|
| 关 键 词： | GPU CUDA 二维扩散方程 计算流体力学 |
The GPU Acceleration of a Two-Dimensional Diffusion Equation |
| |
| DONG Ting-xing,WANG Long,CHI Xue-bin.The GPU Acceleration of a Two-Dimensional Diffusion Equation[J].Computer Engineering & Science,2009,31(11). |
| |
| Authors: | DONG Ting-xing WANG Long CHI Xue-bin |
| |
| Abstract: | In recent years, GPU has been enjoying the reputation of possessing much higher floating-point capacity than CPU. CUDA, which is developed by NVIDIA,realizes GPU-based general purpose computing. In this paper, we implement a CFD benchmark problem call 2D diffusion on GPU with two strategies-global memory and texture memory. A speed-up of 34 is observed when the grid is on the scale of one million. |
| |
| Keywords: | GPU CUDA |
| 本文献已被 万方数据 等数据库收录！ |
|
