Implementations about multiple GPU computation of lattice Boltzmann method with adaptive mesh refinement

Hasegawa, Yuta   

To realize the large-scale LES simulation for the aerodynamics of complex shape bodies and the local wind analysis of urban areas, multiple GPU computation of the lattice Boltzmann method (LBM) with adaptive mesh refinement has been implemented. In this presentation, we will explain optimization techniques for the developed code such as single GPU optimization, an optimization of MPI communication, and a spacial parallel implementation for intra-node multiple GPU computation on the latest GPU platforms.