Training in HPC is fundamental for working productively in many areas of science, engineering and industry. HPC techniques are essential not only for computational scientists that want to take full advantage of parallel shared-memory architectures and distributed systems with hundreds of thousands of processors but also for data-scientists who want to analyze large amounts of data (big-data).
Flavio Vella, post-doctoral researcher at the University of Bolzano, organized the Summer School 2021 in HPC and AI, aimed at training and educating researchers and engineers. The curriculum consisted of providing fundamentals concepts and hands-on sessions focusing on the tools needed for working with and developing programs for HPC platforms. More than 60 participants from multiple domains and institutions joined in order to learn more about HPC.
Philipp Gschwandtner of the FZ HPC was invited as a trainer for a full-day course on modern parallel hardware and teaching the concepts and use of OpenMP. This included programming, execution, and memory models as well as API use in both theoretical sessions and practical exercises.