What makes high-performance computing (HPC) actually high-performing? Besides the (probably most frequently mentioned) large-scale computational problems and the resulting need for large-scale computing infrastructure, it is, or should definitely be, the permanent striving for efficiency at all levels, in order to obtain the high performance desired. Here, the terms efficiency and performance are multi-faceted. As often, finding the proper balance is the key: Neither a perfect implementation of a lousy algorithm nor a lousy implementation of a perfect algorithm exploit the potential. Algorithm and performance engineering have emerged as sub-fields (partially) dealing with performance and efficiency issues and addressing these questions – crucial for HPC and crucial for a more HPC-using data science.
After some introductory remarks, the talk will give an overview of sparse grid methods as a prominent example of an algorithmic approach addressing various facets of efficiency, in particular in the context of high-dimensional problems, as they arise in classical simulation (model-driven) or, more recently, in data analytics (data-driven) contexts. The discussion will comprise both sparse grid fundamentals and applications involving sparse grid methodology.
A coffee break will be offered at ground floor, in front of A-004/005, after the colloquium.