Exascale HPC architectures are increasingly prevalent in the Top500 list, with CPU based nodes enhanced by accelerators or co-processors optimized for floating-point calculations. We have previously presented case studies of partially porting to parallel GPU-accelerated systems for Nek5000. In this project, we will follow on our previously developed work and continue to optimize the full version of Nek5000 on the GPU-accelerated systems using different strategies. We will study the performance characteristics of Nek5000 on heterogeneous architectures (e.g. NVIDIA and AMD GPUs).
The project will also focus on the technology watch of heterogeneous modelling and its impact on the (pre-)exascale architectures.
For more information on NEK5000 visit https://nek5000.mcs.anl.gov.