High-performance finite elements with MFEM

J Andrej, N Atallah, JP Bäcker… - … Journal of High …, 2024 - journals.sagepub.com
The MFEM (Modular Finite Element Methods) library is a high-performance C++ library for
finite element discretizations. MFEM supports numerous types of finite element methods and …

GPU algorithms for efficient exascale discretizations

A Abdelfattah, V Barra, N Beams, R Bleile, J Brown… - Parallel Computing, 2021 - Elsevier
In this paper we describe the research and development activities in the Center for Efficient
Exascale Discretization within the US Exascale Computing Project, targeting state-of-the-art …

Large-Scale direct numerical simulations of turbulence using GPUs and modern Fortran

M Karp, D Massaro, N Jansson, A Hart… - … Journal of High …, 2023 - journals.sagepub.com
We present our approach to making direct numerical simulations of turbulence with
applications in sustainable ship**. We use modern Fortran and the spectral element …

Matrix-Free High-Performance Saddle-Point Solvers for High-Order Problems in

W Pazner, T Kolev, PS Vassilevski - SIAM Journal on Scientific Computing, 2024 - SIAM
This work describes the development of matrix-free GPU-accelerated solvers for high-order
finite element problems in. The solvers are applicable to grad-div and Darcy problems in …

Entropy stable discontinuous Galerkin methods for balance laws in non-conservative form: Applications to the Euler equations with gravity

M Waruszewski, JE Kozdon, LC Wilcox… - Journal of …, 2022 - Elsevier
In this work a non-conservative balance law formulation is considered that encompasses the
rotating, compressible Euler equations for dry atmospheric flows. We develop a semi …

[HTML][HTML] On the construction of an efficient finite-element solver for phase-field simulations of many-particle solid-state-sintering processes

P Munch, V Ivannikov, C Cyron… - Computational Materials …, 2024 - Elsevier
We present an efficient solver for the simulation of many-particle solid-state-sintering
processes. The microstructure evolution is described by a system of equations consisting of …

[HTML][HTML] Develo** performance portable plasma edge simulations: A survey

SA Wright, CP Ridgers, GR Mudalige, Z Lantra… - Computer Physics …, 2024 - Elsevier
Heterogeneous architectures are increasingly common in modern High-Performance
Computing (HPC) systems. Achieving high-performance on such heterogeneous systems …

Efficient distributed matrix-free multigrid methods on locally refined meshes for FEM computations

P Munch, T Heister, L Prieto Saavedra… - ACM transactions on …, 2023 - dl.acm.org
This work studies three multigrid variants for matrix-free finite-element computations on
locally refined meshes: geometric local smoothing, geometric global coarsening (both h …