Astrophysics on GPUs: introducing AGILE 1.0
Abstract
We present AGILE, a GPU-enabled adaptive mesh refinement (AMR) framework for the solution of (near-) conservation laws which occur in astro- and solar-physical applications. AGILE is written in modern fortran 2003, inherits a part of its modules and mesh handling from MPI-AMRVAC, and achieves excellent GPU performance via OpenACC offloading. We here discuss the design decisions which enable AGILE to perform cost-efficient and scalable deeply nested AMR simulations with moderate block sizes of e.g. cells. AGILE currently implements several physics modules, ie. hydrodynamics, frozen-field hydrodynamics, magnetohydrodynamics and special-relativistic hydrodynamics and can easily be extended further through its modular design. Besides strong scaling tests to up to 2048 GPUs and standard benchmarks which show consistent performance across a large range of devices and problem sizes, we demonstrate AGILE's capabilities by means of state-of-the art science applications with all currently available physics modules.
Cite
@article{arxiv.2607.19277,
title = {Astrophysics on GPUs: introducing AGILE 1.0},
author = {Oliver Porth and Adrian Kelly and Olaf Willocx and Hao Wu and Jesse Vos and Yuhao Zhou and Héctor R. Olivares Sánchez and Leon Oostrum and Johan Hidding and Victor Azizi and Chun Xia and Rony Keppens and Jannis Teunissen},
journal= {arXiv preprint arXiv:2607.19277},
year = {2026}
}
Comments
submitted to RAS Techniques and Instruments