HPC and HPDA Projects in DLR Aeronautics and Space Research

Abstract

Aeronautics and space applications regarding for example aircraft or spacecraft design on high performance computing (HPC) systems result in particular challenges regarding algorithm and software framework development. Algorithms must be robust, scalable and allow for highly accurate computations. Software frameworks must exploit hardware parallelism on several levels, must be tunable for different, heterogeneous computing systems and must be easily to maintain. We present a survey on aeronautics and space projects from German Aerospace Center (DLR), Simulation and Software Technology, which require use of HPC and High Performance Data Analytics (HPDA) technology. These projects include solver development for quantum physics problems, multi-disciplinary optimization for thermal management in spacecraft, development of HPDA technology, for example parallel machine learning software, for e.g. earth observation data or space debris analysis, and experimental solution of aeronautics and space problems on quantum computers.