Performance of a massively parallel method of moment solver and its application

被引：0

作者：

机构：

[1] Chen, Yan

[2] Lin, Zhongchao

[3] Garcia-Donoro, Daniel

[4] Zhao, Xunwang

[5] Zhang, Yu

来源：

| 1600年 / Applied Computational Electromagnetics Society (ACES)卷 / 32期

基金：

中国博士后科学基金; 中国国家自然科学基金;

关键词：

Lower-upper decomposition;

D O I：

暂无

中图分类号：

O1 [数学];

学科分类号：

0701 ; 070101 ;

摘要：

A massively parallel Method of Moment (MoM) solver able to run on 200,000 CPU cores and solve matrices larger than 1.3 million unknowns is presented. The solver implements a novel LU decomposition algorithm based on the Communication Avoiding LU (CALU) scheme. By using a new pivoting policy, the communication between processes is improved enhancing the parallel speed up of the algorithm. Solver effectiveness and performance are demonstrated comparing the results with two of the most important math libraries used by direct dense solvers: the commercial MKL and the open source ScaLapack. Results show how simulation time is reduced significantly thanks to this novel LU decomposition algorithm making possible the simulation of incredibility electrically large problems using MoM. © ACES.

引用