Accelerating Physical Simulations from a Multicomponent Lattice Boltzmann Method on a Single-Node Multi-GPU Architecture

摘要

In this paper, we introduce an efficient method to accelerate flow simulations for an isothermal multiphase and multicomponent (MPMC) Lattice Boltzmann method (LBM) on a single-node multi-GPU architecture. Our objective is to propose an efficient way to improve performance of multiphase and multicomponent Lattice Boltzmann simulations by the use of Nvidia GPUDirect technology and Peer-to-Peer (P2P) data transfers. Optimization of Peer-to-Peer communications is also studied in this work by the use of a clustering algorithm. Several simulations are shown and performance is discussed in order to validate the method.