一种隐式算法的GPU加速技术

GPU Speed-up for the Implicit Algorithm

本文利用CUDA平台，将本文作者之一袁新开发的用于计算流体力学的隐式高精度高分辨率求解器由CPU版本（FORTRAN代码）修改为利用GPU计算的版本（CUDAC代码），实现了高精度隐式算法的GPU加速。本文使用GPU为：NVDIAGeForceGTX560Ti，CPU为：单核i5（2．8-3．0GHz）处理器。通过简单的方管算例验证程序的正确性，并得到初步的加速比为9．53；并且通过典型跨声速的VKI的算例验证GPU计算的优势，实测加速比为9．95。最后，根据这些算例的计算结果分析GPU加速比的相关影响因素。

In this study, an in-house high-order implicit CFD solver for the Navier-Stokes equation is implemented to run on a single Graphic Process Unit （GPU） using the Compute Unified Device Architecture （CUDA）. The case of the fluid in a tube and the case of VKI 59 is used to test the accelerations. Results obtained on a single GPU （NVDIA GeForce GTX 560 Ti） are compared with the results obtained on the single CPU （Intel i5 2.8-3.0 GHz）. The best acceleration is 9.95. The detailed results are given and analyzed.