What makes HPC actually high-performing? Besides the (typically mentioned) large-scale computational problems and the resulting involvement of large-scale computing infrastructure, it is probably the pursuit of efficiency at all levels, in order to obtain the high performance desired.
Here, both performance and efficiency can have completely different meanings: the classical complexity-driven one (O(N log N) being worse than O(N)); the node-level one (80% of the peak performance being considered as fabulous); the parallel/scalability one (going for a good exploitation of massively parallel systems); the energy-aware one (looking for “cool” algorithms to avoid the need for power stations); the communication-avoiding one (taking into account the relatively increasing communication cost – some say “Flops are free”); or an emphasis on time-to-solution (focusing on “when do I have the result?” – typically the crucial issue for those who want to get their problems solved, i.e. computed).
While many of these points of view are rather mono-dimensional (e.g., 80% of the peak performance, definitely, is a nice technical result, but it just tells me that I use my weapon well – not at all whether I use the right weapon), the problem is multi-faceted, and it involves modeling, algorithmics, implementation, and other software issues. The resulting complexity implies that education has to be considered in a very fundamental way, too.
The talk will start with a brief general discussion of performance and efficiency in the HPC context, then have a look at ongoing activities on software for exascale computing (with a focus on DFG’s respective Priority Program SPPEXA including its multi-national dimension) as well as HPC education, and conclude with a few examples from our own research.
About the Speaker:
Dr. Hans-Joachim Bungartz is a Professor of Informatics and Mathematics at Technical University of Munich (TUM) and holds the Scientific Computing chair in TUM’s Informatics Department.
Dr. Bungartz earned degrees in Mathematics and Informatics and a doctorate as well as his habilitation in Informatics, all from TUM. He became Associate Professor of Mathematics at University of Augsburg, Full Professor of Informatics at University of Stuttgart, and returned to TUM in 2005.
Since 2008, he has also been affiliated with the Department of Mechanical Engineering at University of Belgrade, Serbia. Since 2013, Dr. Bungartz has served as both Dean of Informatics and TUM Graduate Dean, heading TUM Graduate School with responsibility of doctoral education TUM-wide. He is a member of TUM’s Extended Board of Management.
Dr. Bungartz has served or serves on several editorial boards, and he was a member of the scientific directorate of the Leibniz Institute for Informatics Schloss Dagstuhl. He is involved in various national and international review and advisory board activities. In 2011, he was elected chairman of the German National Research and Educational Network (DFN). Furthermore, Dr. Bungartz is a board member of Leibniz Supercomputing Center. In 2016, Dr. Bungartz has been appointed a steering committee member of the Council for Doctoral Education of the European University Association.
His research interests are where Computational Science & Engineering, Scientific Computing, and Supercomputing meet. He works on parallel numerical algorithms, hardware-aware numerics, high-dimensional problems, data analytics, and aspects of HPC software, with fields of application such as computational fluid dynamics or plasma physics. Most of his projects have been interdisciplinary ones. As an example, he is one of the coordinators of the Priority Program Software for Exascale Computing (SPPEXA) of the German Research Foundation (DFG).