Traditional simulations on High Performance Computing (HPC) systems typically involve modelling very large domains and/or very complex equations. HPC systems allow running large models, but limits in performance increase that have become more prominent in the last 5-10 years will likely be experienced. Therefore new approaches are needed to increase application performance.
Deep learning appears to be a promising way to achieve this. Recently deep learning has been employed to enhance solving problems that traditionally are solved with largescale numerical simulations using HPC. This type of application, deep learning for high performance computing, is the theme of this whitepaper.
The guidelines have been extracted from a number of experiments that have been undertaken in various scientific domains over the last 2 years, in close collaboration with Wageningen University (Chiel van Heerwaarden), Radboud University (Sascha Caron), Utrecht University (Alexandre Bonvin) and Leiden University (Simon Portegies Zwart). We also share the most important lessons that we have learned.
The experiments were carried out in the context of the SURF Open Innovation Lab.