TeraFLOP computing on a desktop PC with GPUs for 3D CFD
TeraFLOP computing on a desktop PC with GPUs for 3D CFD
复制标题
DOI：
10.1080/10618560802238275
复制
发表时间：
2008-08
影响因子：
1.3
通讯作者：
J. Tölke;M. Krafczyk
中科院分区：
文献类型：
--
作者：
J. Tölke;M. Krafczyk
提出了使用 nVIDIA 开发的计算统一设备架构接口在图形处理单元上以 3D 形式非常高效地实现格子玻尔兹曼 (LB) 内核的方法。通过利用图形硬件提供的显式并行性，我们可以将 PC 的计算性能提高两个数量级。一个重要的示例显示了 LB 实现的性能，该实现基于详细描述的 D3Q13 模型。
A very efficient implementation of a lattice Boltzmann (LB) kernel in 3D on a graphical processing unit using the compute unified device architecture interface developed by nVIDIA is presented. By exploiting the explicit parallelism offered by the graphics hardware, we obtain an efficiency gain of up to two orders of magnitude with respect to the computational performance of a PC. A non-trivial example shows the performance of the LB implementation, which is based on a D3Q13 model that is described in detail.