基于神威加速计算架构的LBM多级并行计算

LBM Multi-level Parallel Computing Based on SACA

格子玻尔兹曼方法(lattice Boltzmann method,LBM)是一种基于分子运动理论计算流体力学(computational fluid dynamics,CFD)的方法,提高LBM的并行计算能力是高性能计算领域的一项重要的研究内容.本文基于SW26010Pro处理器,通过区域分解、数据重构、双缓冲、向量化等优化方法,实现了LBM的多级并行.基于以上优化方案,测试了5600万网格规模,实现结果显示,相比于MPI进行级并行,碰撞过程的平均加速倍数达到61.737、迁移过程的平均加速倍数达到17.3,同时对方腔流案例做了强扩展测试,网格规模为1200×1200×1200,以6.2万计算核心为基准,百万核心的并行效率超过60.5%.

The lattice Boltzmann method(LBM)is a computational fluid dynamics(CFD)method based on molecular motion theory.Improving the parallel computing capability of LBM is an important research topic in the highperformance computing field.This article is based on the SW26010Pro processor and achieves multi-level parallelism of LBM through optimization methods such as region decomposition,data reconstruction,double buffering,and vectorization.Based on the above optimization methods,a grid size of 56 million is tested,and the implementation results show that compared to message passing interface(MPI)level parallelism,the average acceleration factor of the collision process reaches 61.737,and that of the migration process reaches 17.3.At the same time,strong expansion testing is conducted on the lid-driven cavity flow case,with a grid size of 1200×1200×1200.Based on 62000 computing cores,the parallel efficiency of one million cores exceeds 60.5%.