Accelerated CFD computing of turbomachinery on GPU platform
-
摘要: 通过数据并行的方式对一个成熟的叶轮机多块网格气动计算程序(MAP)进行了并行化处理,利用计算统一设备架构(CUDA)技术实现了在图形处理单元(GPU)上的并行计算.保留了原程序中的2阶空间迎风格式和隐式时间离散格式,并采用了隐式迭代对线性系统进行求解.经过2个叶轮机械算例的测试,与在传统的中央处理器(CPU)上运行的原程序相比,在计算结果完全一致的前提下,单GPU的计算速度最高可达单CPU计算速度的8.89倍,与四核并行的CPU计算相比可以得到2.39倍的加速.Abstract: The well-developed turbomachinery computational fluid dynamics code multi-block aerodynamic prediction (MAP) was solved by data-parallelized computing and implemented on a graphic processing unit(GPU) platform with the help of compute unified device architecture (CUDA) technology.The second-order upwind spatial scheme and the implicit temporal scheme in the original program were retained,while the linear system was solved by implicit iterations.During the test of two turbomachinery examples on a single GPU,a speed-up appeares to be 8.89 times comparing with one central processing unit (CPU) process and 2.39 times comparing with four CPU processes,with no extra deviation induced into the result.
-
Key words:
- GPU /
- CUDA /
- parallel computing /
- implicit scheme /
- turbomachinery
-
[1] Harris M J.Fast fluid dynamics simulation on the GPU[C]//GPU Gems.Boston:Addison Wesley, 2004:637-665. [2] Harris M J, Baxter W V, Scheuermann T, et al.Simulation of cloud dynamics on graphics hardware[C]//Proceedings of the ACM Siggraph/Eurographics Conference on Graphics Hardware.Aire-la-Ville, Switzerland:Eurographics Association, 2003:92-101. [3] Hagen T R, Lie K A, Natvig J R.Solving the Euler equations on graphics processing units[R].Berlin:International Conference on Computational Science, 2006. [4] Brandvik T, Pullan G.Acceleration of a 2D Euler solver using graphics hardware[R].Cambridge University Engineering Department Technical Report, CUED/A-TURBO/TR.132, 2007. [5] Brandvik T, Pullan G.Acceleration of a 3D Euler solver using commodity graphics hardware[R].AIAA-2008-607, 2008. [6] Kestener P, Chateau F, Teyssier R.Accelerating Euler equations numerical solver on graphics processing units[J].Lecture Notes in Computer Science, 2010, 6082:281-288. [7] Elsen E, Legresley P, Darve E.Large calculation of the flow over a hypersonic vehicle using a GPU[J].Journal of Computational Physics, 2008, 227(24):10148-10161. [8] Thibault J C, Senocak I.CUDA implementation of a Navier-Stokes solver on multi-GPU desktop platforms for incompressible flows[R].AIAA-2009-758, 2009. [9] Thibault J C.Implementation of a Cartesian grid incompressible Navier-Stokes solver on multi-GPU desktop platforms using CUDA[D].Boise:Boise State University, 2009. [10] Senocak I, Thibault J, Caylor M.Rapid-response urban CFD simulations using a GPU computing paradigm on desktop supercomputers[R].Phoenix:8th American Meteorological Society Symposium on the Urban Environment, 2009. [11] Jacobsen D A, Thibault J C, Senocak I.An MPI-CUDA implementation for massively parallel incompressible flow computations on multi-GPU clusters[R].AIAA-2010-522, 2010. [12] Jespersen D C.Acceleration of a CFD code with a GPU[R].NASA Advanced Supercomputing Technical Report, NAS-09-003, 2009. [13] Brandvik T, Pullan G.An accelerated 3D Navier-Stokes solver for flows in turbomachines[J].Journal of Turbomachinery, 2011, 133(2):021025.1-021025.9. [14] 王健, 许明, 葛蔚, 等.单相流动数值模拟的SIMPLE算法在GPU上的实现[J].科学通报, 2010, 55(20):1979-1986. WANG Jian, XU Ming, GE Wei, et al.GPU accelerated direct numerical simulation with SIMPLE arithmetic for single-phase flow[J].Chinese Science Bulletin, 2010, 55(20):1979-1986.(in Chinese) [15] 董延星, 李新亮, 李森, 等.GPU上计算流体力学的加速[J].计算机系统应用, 2011, 20(1):104-109. DONG Yanxing, LI Xinliang, LI Sen, et al.Acceleration of computational fluid dynamics codes on GPU[J].Computer Systems and Applications, 2011, 20(1):104-109.(in Chinese) [16] 张兵, 韩景龙.一种GPU上的CFD并行计算方法[C]//第十一届全国空气弹性学术交流会.昆明:中国空气动力学会, 中国力学学会, 2009:371-377. [17] 张兵, 韩景龙.基于GPU和隐式格式的CFD并行计算方法[J].航空学报, 2010, 31(2):249-256. ZHANG Bing, HAN Jinglong.Parallel computing methods for CFD using a GPU and implicit scheme[J].Acta Aeronautica et Astronautica Sinica, 2010, 31(2):249-256.(in Chinese) [18] 苗树明.N-S方程在GPU上的实现[D].上海:上海交通大学, 2011. MIAO Shuming.Implementation of N-S equations in parallel on GPU[D].Shanghai:Shanghai Jiaotong University, 2011.(in Chinese) [19] 宁方飞.考虑真实几何复杂性的跨音压气机内部流动的数值模拟[D].北京:北京航空航天大学, 2002. NING Fangfei.Numerical investigations of flows in transonic compressors with real geometrical complexities[D].Beijing:Beijing University of Aeronautics and Astronautics, 2002.(in Chinese) [20] NVIDIA Corporation.NVIDIA CUDA C programming guide, version 4.2[EB/OL].[2012-11-06].http://docs. nvidia.com/cuda/pdf/CUDA_C_Programming_Guide.pdf. [21] Jameson A, Yoon S.Lower-upper implicit schemes with multiple grids for the Euler equations[J].AIAA Journal, 1987, 25(7):929-935. [22] Blazek J.Computational fluid dynamics:principles and applications[M].New York:Elsevier Science, 2001. [23] NVIDIA Corporation.NVIDIA'S next generation CUDATM compute architecture:KEPLERTM GK110[EB/OL].[2013-06-04].http://www.nvidia.com/content/PDF/kepler/NVIDIA-Kepler-GK110-Architecture-Whitepaper.pdf.
点击查看大图
计量
- 文章访问数: 1409
- HTML浏览量: 1
- PDF量: 828
- 被引次数: 0