Abstract
In this paper, the D3Q19 multi-relaxation-time lattice Boltzmann model is adopted to simulate three-dimensional cavity flows using graphic processing units (GPUs). For single GPU computations, utilizing on-chip memory generates three to five times speedup over adopting global memory alone. Also, streaming using offset reading attains another two times speedup over employing offset writing. For Message Passing Interface (MPI) based multi-GPU computations, overlapping communication and computation can achieve 38% improvement and provide an efficient scheme to improve the scalability and its performance. Numerical experiments show that 12Tesla TM M2070 GPUs produce around 5500 million lattices updates per second (MLUPS) using 576 3 grid. On the other hand, three GTX Titans deliver 5000 MLUPS for 192 3 grids, while 12Tesla attain half performance.