Spotlight on Professors: Prof. Dr. Michael Kuhn
Michael Kuhn is a professor for Parallel Computing and I/O at our faculty. The courses he teaches can be taken as electives by students in the BiBa. He teaches and conducts research in the area of parallel systems with a special focus on storage systems, I/O interfaces and programming concepts. Other interests of his include data reduction techniques and high performance computing in general.
His interest in this topic was already sparked as an undergraduate while attending the University of Heidelberg, where he completed his bachelor’s and master’s in 2007 and 2009, respectively. He then moved to the University of Hamburg, where he followed up with his PhD thesis on “Dynamically Adaptable I/O Semantics for High Performance Computing” in 2015. This resulted in the creation of the JULEA storage framework that is still being developed and used in both research in teaching. He stayed in Hamburg until 2020 when he moved to the OVGU Magdeburg for his current professorship.
Since even mobile phones contain multiple processor cores nowadays, parallel computing is increasingly important. Supercomputers can even consist of several million processor cores. They allow conducting highly complex analyses and simulations, which are required to solve many scientific problems. Moreover, the exponentially growing data volumes resulting from this have to be stored, analyzed and processed.
An example of this is shown in Fig. 1, illustrating the transition from serial computing to parallel computing. Problems need to be broken down into smaller parts that can be processed concurrently while maintaining the correctness of the results. In this example, a calculation using a matrix of numerical values can be performed by four tasks in parallel, reducing the runtime to one fourth of its serial duration. However, the actual speedup will typically be less than this due to overhead caused by distribution and collection of data, as well as coordination.
Abb. 1: Serial vs. parallel computations
For the faculty, Michael Kuhn is currently responsible for public relations, including our web pages. His group regularly offers lectures and courses on parallel programming, parallel storage systems, and other topics related to high-performance computing. He likes tinkering with systems and code when possible. Beyond that, he likes watching movies, playing video games and cooking.
Adapted from the BiBa Newsletter 2024/2,
June 14, 2024