A portable OpenCL-based unstructured edge-based finite element Navier-Stokes solver on graphics hardware

被引:8
|
作者
Rossi, R. [1 ,2 ]
Mossaiby, F. [3 ]
Idelsohn, S. R. [1 ,4 ]
机构
[1] CIMNE, Barcelona, Spain
[2] UPC, BarcelonaTech, Barcelona 08034, Spain
[3] Univ Isfahan, Fac Engn, Dept Civil Engn, Esfahan 8174473441, Iran
[4] ICREA, Barcelona, Spain
关键词
Unstructured grids; Navier-Stokes; Edge-based; GPU; OpenCL; OpenMP; INCOMPRESSIBLE-FLOW; GPU; EQUATIONS; CUDA;
D O I
10.1016/j.compfluid.2013.04.017
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
The rise of GPUs in modern high-performance systems increases the interest in porting portion of codes to such hardware. The current paper aims to explore the performance of a portable state-of-the-art FE solver on GPU accelerators. Performance evaluation is done by comparing with an existing highly-optimized OpenMP version of the solver. Code portability is ensured by writing the program using the OpenCL 1.1 specifications, while performance portability is sought through an optimization step performed at the beginning of the calculations to find out the optimal parameter set for the solver. The results show that the new implementation can be several times faster than the OpenMP version. (C) 2013 Elsevier Ltd. All rights reserved.
引用
下载
收藏
页码:134 / 144
页数:11
相关论文
共 50 条