Efficient Exascale Discretizations: High-Order Finite Element Methods

TL;DR

This paper discusses the development of high-order finite element methods optimized for exascale computing architectures, focusing on algorithms that maximize parallelism and minimize data movement for PDE discretizations.

Contribution

It presents the CEED project's efforts in creating next-generation discretization software and algorithms tailored for exascale hardware, emphasizing matrix-free methods and performance optimization.

Findings

Enhanced performance of finite element discretizations on GPU architectures.

Development of scalable, matrix-free linear solvers for large-scale PDEs.

Successful integration with exascale applications and benchmarks.

Abstract

Efficient exploitation of exascale architectures requires rethinking of the numerical algorithms used in many large-scale applications. These architectures favor algorithms that expose ultra fine-grain parallelism and maximize the ratio of floating point operations to energy intensive data movement. One of the few viable approaches to achieve high efficiency in the area of PDE discretizations on unstructured grids is to use matrix-free/partially-assembled high-order finite element methods, since these methods can increase the accuracy and/or lower the computational time due to reduced data motion. In this paper we provide an overview of the research and development activities in the Center for Efficient Exascale Discretizations (CEED), a co-design center in the Exascale Computing Project that is focused on the development of next-generation discretization software and algorithms to enable a wide range of finite element applications to run efficiently on future hardware. CEED is a research partnership involving more than 30 computational scientists from two US national labs and five universities, including members of the Nek5000, MFEM, MAGMA and PETSc projects. We discuss the CEED co-design activities based on targeted benchmarks, miniapps and discretization libraries and our work on performance optimizations for large-scale GPU architectures. We also provide a broad overview of research and development activities in areas such as unstructured adaptive mesh refinement algorithms, matrix-free linear solvers, high-order data visualization, and list examples of collaborations with several ECP and external applications.