Dr. J. (Jonas) Thies
Dr. J. (Jonas) Thies
Profile
Expertise
Jonas has more than 20 years of experience in HPC and scientific computing with applications in CFD, climate research and quantum physics. Specifically he has worked on:
- domain decomposition methods for sparse linear systems
- implicit ocean models
- sparse eigenvalue problems on heterogeneous supercomputers
- code optimization for multi-core CPU´s and vector processors
- software and performance engineering for scientific applications
Biography
Jonas Thies has a Bachelor degree in Computational Engineering (Erlangen 2003), a Master in Scientific Computing (KTH Stockholm, 2006) and a PhD in applied mathematics (Groningen 2011). He spent two years at the Center for Interdisciplinary Mathematics in Uppsala, after which he moved to Cologne as a Scientific Employee of the German Aerospace Center (DLR) Institute for Software Technology. There he led a research group on parallel numerics from 2017 to 2021. Since June 2021 he is an Assistant Professor at the Delft High Performance Computing Center DHPC.
Projects
- ESSEX (Equipping Sparse Solvers for the EXa-scale, 2013-2019). A DFG-funded collaboration to research and develop sparse eigenvalue solvers for extreme-scale heterogeneous supercomputers, with applications in quantum physics (https://blogs.fau.de/essex)
- HGF PilotLab ExaESM (2018-2021), a collaborative project to investigate new ways to scale climate research to the next generation of supercomputers, funded by the Helmholtz organization (https://exaesm.de)
Research interests
Numerical Linear Algebra, High Performance Computing
Publications
-
2023
SIMD vectorization for simultaneous solution of locally varying linear systems with multiple right-hand sides
Martin J. Kühn / Johannes Holke / Annette Lutz / Jonas Thies / Melven Röhrig-Zöllner / Alexander Bleh / Jan Backhaus / Achim Basermann
-
2022
Tensor product scheme for computing bound states of the quantum mechanical three-body problem
Jonas Thies / Moritz Travis Hof / Matthias Zimmermann / Maxim Efremov
-
2022
performance of the low-rank TT-SVD for large dense tensors on modern multicore CPUs
Melven Röhrig-Zöllner / Jonas Thies / Achim Basermann
-
2021-4
A staggered-grid multilevel incomplete LU for steady incompressible flows
Sven Baars / Mark van Der Klok / Jonas Thies / Fred W. Wubs
-
2021-1
Performance engineering for real and complex tall & skinny matrix multiplication kernels on GPUs
Dominik Ernst / Georg Hager / Jonas Thies / Gerhard Wellein
-
Courses 2024
Courses 2023
Ancillary activities
-
2023-06-01 - 2025-05-31