Andreas Klöckner, PhD
About the speaker
Andreas Klöckner obtained his PhD degree working with Jan Hesthaven at the Department of Applied Mathematics at Brown University. He worked on a variety of topics all aiming to broaden the utility of discontinuous Galerkin (DG) methods. This included their use in the simulation of plasma physics and the demonstration of their particular suitability for computation on throughput-oriented graphics processors (GPUs). He also worked on multi-rate time stepping methods and shock capturing schemes for DG.
In support of his research, Dr Klöckner has released numerous scientific software packages under liberal open-source licenses. Among his most widely-used packages are the PyCUDA and PyOpenCL toolkits, which permit high-performance, hybrid GPU computing from the high-level scripting language Python. In addition to providing a very convenient way of programming compute devices, they offer a number of abstractions such as on-GPU linear algebra and a practical way of generating GPU code at run-time for automated tuning and library flexibility.
In the fall of 2010, Klöckner will be joining the Courant Institute of Mathematical Sciences at New York University as a Courant Instructor. There, he will be working on problems in computational electromagnetics with Prof Leslie Greengard.
Klöckner’s research interests include:
- High-order unstructured particle-in-cell methods for plasma simulation
- Discontinuous Galerkin methods for Maxwell equations
- Programming tools for parallel architectures
Sample publications
- PyCUDA: GPU run-time code generation for high-performance computing, A. Klöckner, N. Pinto, Y. Lee, B. Catanzaro, P. Ivanov, and A. Fasih, preprint on arXiv.
- Nodal discontinuous Galerkin methods on graphics processors, A. Klöckner, T. Warburton, J. Bridge, J. S. Hesthaven, J. Comput. Phys. Vol. 228(21): 7863–7882 (2009) [doi:10.1016/j.jcp.2009.06.041]