The Erlangen National High-Performance Computing Center (NHR@FAU) is part of the Network for National High Performance Computing (NHR), or "NHR Alliance." It operates large-scale HPC systems and provides HPC services, related user support, and HPC training to German universities. Its HPC research activities focus on performance engineering, analytic performance modelling, performance tools development, and research software engineering for modern HPC architectures. NHR@FAU investigates and further develops hardware-efficient building blocks, programming concepts, and numerical algorithms for scalable, efficient, and robust iterative sparse matrix applications and stencil-based solvers on large-scale HPC systems. Popular contributions include the LIKWID performance toolkit, the highly-scalable walberla simulation framework, the Execution Cache Memory (ECM) performance model, and the Node-Level Performance Engineering tutorial series. Many of NHR@FAU’s applications are centered around atomistic structure simulations in chemistry, life science, materials science, and physics.