Performance Evaluation of Lattice Boltzmann Method for Fluid Simulation on A64FX Processor and Supercomputer Fugaku
Performance Evaluation of Lattice Boltzmann Method for Fluid Simulation on A64FX Processor and Supercomputer Fugaku
复制标题
A64FX 处理器和超级计算机 Fugaku 上流体模拟的格子玻尔兹曼方法的性能评估
DOI：
10.1145/3492805.3492811
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Changhong Hu
中科院分区：
文献类型：
--
作者：
Seiya Watanabe;Changhong Hu
格子玻尔兹曼方法最近成为流行的替代Navier-Stokes求解器的大规模流体模拟。我们进行了性能研究的晶格玻尔兹曼方法上的A64 FX臂为基础的处理器的超级计算机Fugaku。我们比较了四种类型的数据布局：SoA，AoS，CSoA和CSoA 2，以及LBM流步骤的三种算法：Pull，Push和Swap方案。对单个CMG（核心存储器组）的性能测量表明，CSoA 2布局和交换方案的组合具有最高的性能，为176 GFLOP，相当于单精度峰值性能的11.5%。我们的模拟已经证明了良好的弱扩展到16，384个节点，并实现了单精度10.9 PFLOPS的高性能。强大的可扩展性也是一个很好的结果，当从512扩展到16，384个节点时，D3 Q15，D3 Q19和D3 Q27速度模型的并行效率分别为63.9%，68.3%和72.7%。
The lattice Boltzmann method has recently become popular as an alternative to Navier-Stokes solvers for large-scale fluid simulations. We conduct a performance study of the lattice Boltzmann method on the A64FX Arm-based processor of the supercomputer Fugaku. We compared four types of data layouts: SoA, AoS, Clusterd SoA (CSoA), and CSoA2, and three algorithms for the LBM streaming step: Pull, Push, and Swap schemes. The performance measurement on a single CMG (Core Memory Group) shows that the combination of the CSoA2 layout and the Swap scheme has the highest performance of 176 GFLOP, which corresponds to 11.5% of the single-precision peak performance. Our simulations have demonstrated good weak scaling up to 16,384 nodes and achieved high performance 10.9 PFLOPS in single precision. The strong scalability is also a good result, with parallel efficiencies of 63.9%, 68.3% and 72.7 % for the D3Q15, D3Q19 and D3Q27 velocity model, respectively when scaling from 512 to 16,384 nodes.