http://arxiv.org/abs/2304.13746
Exascale super-computers now becoming available rely on hybrid energy-efficient architectures that involve an accelerator such as Graphics Processing Units (GPU). Leveraging the computational power of these machines often means a significant rewrite of the numerical tools each time a new architecture becomes available. To address these issues, we present Idefix, a new code for astrophysical flows that relies on the Kokkos meta-programming library to guarantee performance portability on a wide variety of architectures while keeping the code as simple as possible for the user. Idefix is based on a Godunov finite-volume method that solves the non-relativistic HD and MHD equations on various grid geometries. Idefix includes a wide choice of solvers and several additional modules (constrained transport, orbital advection, non-ideal MHD) allowing users to address complex astrophysical problems. Idefix has been successfully tested on Intel and AMD CPUs (up to 131 072 CPU cores on Irene-Rome at TGCC) as well as NVidia and AMD GPUs (up to 1024 GPUs on Adastra at CINES). Idefix achieves more than 1e8 cell/s in MHD on a single NVidia V100 GPU and 3e11 cell/s on 256 Adastra nodes (1024 GPUs) with 95% parallelization efficiency (compared to a single node). For the same problem, Idefix is up to 6 times more energy efficient on GPUs compared to Intel Cascade Lake CPUs. Idefix is now a mature exascale-ready open-source code that can be used on a large variety of astrophysical and fluid dynamics applications.
G. Lesur, S. Baghdadi, G. Wafflard-Fernandez, et. al.
Fri, 28 Apr 23
20/68
Comments: 18 pages, 18 figures, 3 tables, accepted for publication in Astronomy & Astrophysics