Title :
Implementation of a Lattice Boltzmann Method for Large Eddy Simulation on Multiple GPUs
Author :
Li, Qinjian ; Zhong, Chengwen ; Li, Kai ; Zhang, Guangyong ; Lu, Xiaowei ; Zhang, Qing ; Zhao, Kaiyong ; Chu, Xiaowen
Author_Institution :
Center for High Performance Comput., Northwestern Polytech. Univ., Xi´´an, China
Abstract :
Recently, the Graphic Processor Unit (GPU) has evolved into a highly parallel, multithreaded, many-core processor with tremendous computational horsepower and very high memory bandwidth. To improve the simulation efficiency of complex flow phenomena in the field of computational fluid dynamics, a CUDA-based simulation algorithm of large eddy simulation using multiple GPUs is proposed. Our implementation adopted the "collision after propagation" scheme and performed the propagation process by global memory reading transactions. The working set is split up into equal sub-domains and assigned to each GPU for simplicity. Using recently released hardware, up to four GPUs can be controlled by a single CPU thread and run in parallel. The results show that our multi-GPU implementation could perform simulations on a rather large scale (meshes: 10240×10240) even using double-precision floating point calculation and achieved 190X speedup over the sequential implementation on CPU.
Keywords :
floating point arithmetic; flow simulation; graphics processing units; lattice Boltzmann methods; multi-threading; multiprocessing systems; parallel architectures; storage management; 190X speedup; CUDA-based simulation algorithm; collision after propagation scheme; complex flow phenomena; computational fluid dynamics; double-precision floating point calculation; global memory reading transactions; graphic processor unit; large eddy simulation; lattice Boltzmann method; many-core processor; multiple GPU; multithreaded processor; parallel processor; single CPU thread; very high memory bandwidth; Cavity resonators; Computational modeling; Graphics processing unit; Kernel; Lattices; Mathematical model; Performance evaluation; Large eddy simulation; Lattice Boltzmann method; Multi-GPU Computing; Parellel computing;
Conference_Titel :
High Performance Computing and Communication & 2012 IEEE 9th International Conference on Embedded Software and Systems (HPCC-ICESS), 2012 IEEE 14th International Conference on
Conference_Location :
Liverpool
Print_ISBN :
978-1-4673-2164-8
DOI :
10.1109/HPCC.2012.115