High-Performance Scientific Computing Lab starts June 2024
The High-Performance Scientific Computing Lab focuses on the development of high-performance computing software and algorithms for scientific applications at the intersection of mathematics, computer science, and domain sciences such as physics or engineering.
As an interdisciplinary research group, our focus is on the development of scalable algorithms for large-scale simulations, with a special emphasis on adaptive multi-physics simulations, research software engineering, and scientific machine learning. Among other activities, our lab is currently involved in the following research projects:
- DFG Research Unit FOR5409 SNuBIC:
Structure-Preserving Numerical Methods for Bulk- and Interface Coupling of Heterogeneous Models - DFG Project ACTRIX:
Accessible extreme-scale computing with Trixi.jl and the Julia programming language - BMBF Project ADAPTEX:
Adaptive Earth system modelling with strongly reduced computation time for exascale-supercomputers
The HPSC Lab promotes good research software engineering practices and open-source software, and members of the lab are key contributors to the Trixi Framework, especially in the following software projects:
- Trixi.jl: Adaptive high-order numerical simulations of conservation laws in Julia
- libtrixi: Interface library for using Trixi.jl from C/C++/Fortran
- TrixiParticles.jl: Particle-based multiphysics simulations in Julia