Numerical cosmology on the GPU with Enzo and Ramses

TL;DR

This paper compares GPU implementations of two astrophysical simulation codes, Enzo and Ramses, highlighting different strategies and presenting performance benchmarks and scientific results.

Contribution

It introduces and compares GPU porting strategies for Enzo and Ramses, demonstrating their performance and scientific application in astrophysics.

Findings

Ramses GPU version shows competitive performance.

Enzo GPU implementation used in a scientific project.

Performance benchmarks highlight efficiency gains.

Abstract

A number of scientific numerical codes can currently exploit GPUs with remarkable performance. In astrophysics, Enzo and Ramses are prime examples of such applications. The two codes have been ported to GPUs adopting different strategies and programming models, Enzo adopting CUDA and Ramses using OpenACC. We describe here the different solutions used for the GPU implementation of both cases. Performance benchmarks will be presented for Ramses. The results of the usage of the more mature GPU version of Enzo, adopted for a scientific project within the CHRONOS programme, will be summarised.