Exasim: Generating discontinuous Galerkin codes for numerical solutions of partial differential equations on graphics processors
Exasim: Generating discontinuous Galerkin codes for numerical solutions of partial differential equations on graphics processors
复制标题
Exasim：为图形处理器上的偏微分方程数值解生成不连续 Galerkin 代码
DOI：
10.1016/j.softx.2022.101212
复制
发表时间：
2022
期刊：
影响因子：
3.4
通讯作者：
Peraire, Jaume
中科院分区：
文献类型：
--
作者：
Vila-Pérez, Jordi;Van Heyningen, R. Loek;Nguyen, Ngoc-Cuong;Peraire, Jaume
本文概述了exasim的功能和应用，exasim是一个用于生成高阶不连续伽辽金码以数值求解参数化偏微分方程（PDEs）的开源代码。该软件结合高级和低级语言，通过Julia、Python或Matlab脚本构建参数化PDE模型，并生成高性能c++代码，用于在CPU和Nvidia GPU分布式内存处理器上求解PDE模型。exasimm提供无矩阵的不连续伽辽金离散化方案，以及可扩展的降基预调节器和牛顿- gmres解算器，使其适用于广泛类别的偏微分方程的准确和有效逼近。
This paper presents an overview of the functionalities and applications ofExasim, an open-source code for generating high-order discontinuous Galerkin codes to numerically solve parametrized partial differential equations (PDEs). The software combines high-level and low-level languages to construct parametrized PDE models via Julia, Python or Matlab scripts and produce high-performance C++ codes for solving the PDE models on CPU and Nvidia GPU processors with distributed memory.Exasimprovides matrix-free discontinuous Galerkin discretization schemes together with scalable reduced basis preconditioners and Newton-GMRES solvers, making it suitable for accurate and efficient approximation of wide-ranging classes of PDEs.