首页> 外文会议>Proceedings of 9th Workshop on Latest Advances in Scalable Algorithms for LargeScale Systems >Communication Avoiding Multigrid Preconditioned Conjugate Gradient Method for Extreme Scale Multiphase CFD Simulations
【24h】

Communication Avoiding Multigrid Preconditioned Conjugate Gradient Method for Extreme Scale Multiphase CFD Simulations

机译:用于超大规模多相CFD仿真的避免通信的多网格预处理共轭梯度方法

获取原文
获取原文并翻译 | 示例

摘要

A communication avoiding (CA) multigrid preconditioned conjugate gradient method (CAMGCG) is applied to the pressure Poisson equation in a multiphase CFD code JUPITER, and its computational performance and convergence property are compared against CA Krylov methods. A new geometric multigrid preconditioner is developed using a preconditioned Chebyshev iteration smoother, in which no global reduction communication is needed, halo data communication is reduced by a mixed precision approach, and eigenvalues are computed using the CA Lanczos method. In the JUPITER code, the CAMGCG solver has robust convergence properties regardless of the problem size, and shows both communication reduction and convergence improvement, leading to higher performance gain than CA Krylov solvers, which achieve only the former. The CAMGCG solver is applied to extreme scale multiphase CFD simulations with ~ 90 billion DOFs, and it is shown that compared with a preconditioned CG solver, the number of iterations, and thus, All_Reduce is reduced to ~ 1/800, and ~ 11.6× speedup is achieved with keeping excellent strong scaling up to 8,000 KNLs on the OakforestPACS.
机译:在多相CFD代码JUPITER中将避免通信(CA)多重网格预处理共轭梯度方法(CAMGCG)应用于压力Poisson方程,并将其计算性能和收敛性与CA Krylov方法进行了比较。使用预处理的Chebyshev迭代平滑器开发了一种新的几何多网格预处理器,其中不需要全局归约通信,通过混合精度方法简化晕轮数据通信,并使用CA Lanczos方法计算特征值。在JUPITER代码中,CAMGCG求解器无论问题大小如何都具有鲁棒的收敛特性,并且显示出通信减少和收敛性的提高,与仅实现前者的CA Krylov求解器相比,可以获得更高的性能增益。 CAMGCG求解器应用于具有约900亿个自由度的极限多相CFD仿真,结果表明,与预处理的CG求解器相比,迭代次数减少,因此All_Reduce减少为〜1/800,且约为11.6倍通过在OakforestPACS上保持高达8,000个KNL的出色强大扩展,可以实现加速。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号