High Performance Computing and Scientific Computing @ Durham's Computer Science
We study the Science of Computing behind Computational Sciences.
Scientific computing has become the foundation of many areas of science. It is computer simulations that allow various application areas to progress. In this context, high performance computing is a catalysator for insights-through-computing. With new hardware generations arriving, it emancipates from a nice-to-have feature into a mandatory craft in many disciplines.
Our research goes beyond application-specific number crunching, code analysis and tuning, i.e. it goes beyond the scientific computing and HPC research found in many application areas. Instead, it searches for innovative algorithms, algorithmic paradigms, patterns, and methodolgies to meet next generation’s supercomputing challenges, and it investigates into the foundations of scientific computing as a whole.
At the moment, our major contributions are made in the area of
- domain-specific languages for numerical simulations,
- algorithms behind efficient multiscale methods, and
- adaptive mesh refinement.
- Researchers from Durham’s CS HPC team are a driving force behind the development of Firedrake.
- Durham’s HPC team is the virtual home of the Peano framework.
- The European Union’s H2020 project ExaHyPE is actively driven by our HPC researchers.
The group actively collaborates with various compute-heavy departments in Durham. Highlights are joint projects, activities and research with the Department of Mathematics, the Physics department with its Institute for Particle Physics Phenomenology and its Institute for Computational Cosmology. Further links with Earth Sciences and the Department of Engineering yield interesting research. HPC’s most active interdisciplinary activities are typically organised under the umbrella of the Institute for Data Science.
Our researchers rely on Durham’s own supercomputer Hamilton, they have access to a 3x15m 3d visualisation wall, and we host several experimental workstations. By the end of 2019, we plan to purchase our own Mellanox BlueField cluster in collaboration with the DiRAC consortium.
- 26/02/20, 13:00-14:00: Presentation by Eike Mueller on his recent research around DG methods. Part of the rolling ICG seminar with coffee break/discussion afterwards.
- 29/01/20, 14:00-15:00: SIAM prep meeting (internal). Group members present their poster drafts.
- 16/01/19, 14:00-15:00: Journal Club. Lawrence presents his latest preprint. Please read through the paper prior to the meeting.
- 5/12/19, 16:00-17:00: Journal Club. We discuss the latest Gordon Bell Prize paper. Please read through the paper prior to the meeting.