Title :
Multiphase LBM Distributed over Multiple GPUs
Author_Institution :
Texas Adv. Comput. Center, Univ. of Texas at Austin, Austin, TX, USA
Abstract :
A parallel distributed CUDA implementation of a Lattice Boltzmann Method for multiphase flows with large density ratios is described in this paper. Validation runs studying the terminal velocity of a rising bubble under the effect of gravity show good agreement with the expected theoretical values. The code is benchmarked against the performance of a typical CPU implementation of the same algorithm on both AMD and Intel platforms, and a single GPU is observed to perform up to 10X faster than a quad-core CPU socket, a 40X speedup with respect to a single core. The code is shown to scale well when executed on multiple GPUs, which makes the port to CUDA valuable even when compared to parallel CPU implementations.
Keywords :
computer graphic equipment; coprocessors; parallel processing; AMD platforms; CPU implementation; GPU; Intel platforms; LBM distributed multiphase; Lattice Boltzmann method; density ratios; parallel distributed CUDA implementation; quad-core CPU socket; Arrays; Computational modeling; Equations; Graphics processing unit; Instruction sets; Kernel; Mathematical model; CFD; CUDA; Distributed; GPU; LBM; Mutiphase; Parallel;
Conference_Titel :
Cluster Computing (CLUSTER), 2011 IEEE International Conference on
Conference_Location :
Austin, TX
Print_ISBN :
978-1-4577-1355-2
Electronic_ISBN :
978-0-7695-4516-5
DOI :
10.1109/CLUSTER.2011.9
