ZIH-Colloquium: "Holistic HPC Performance Engineering and Reproducible Benchmarking"

HPC applications are evolving not only to include traditional modeling and simulation workloads but also so-called scale-out workloads including: artificial intelligence, big data analytics, deep learning, and complex workflows. Given the ever-growing complexity of supercomputers and the advent of exascale computing, these trends can create a gap between expected and observed peak performance. Therefore, holistic performance engineering is critical to bridge this gap through reproducible benchmarking, prediction, optimization, and analysis of large-scale HPC workloads. In this talk, I will first highlight the challenges and opportunities in leveraging modular HPC performance engineering to support exascale scientific discovery. This will include introducing the key pillars of performance engineering, but also the opportunities and challenges of using artificial intelligence. Then, I will focus on how to orchestrate and automate the use of benchmarks following three key principles: reproducibility, comparability, and portability.

Sarah Neuwirth recently became a full professor at Johannes Gutenberg University Mainz (JGU). There, she leads the research group "High Performance Computing and its Applications" (Link: https://www.hpca-group.de/) and is responsible for the further development of the HPC infrastructure and activities at JGU. Her research is focused on parallel file systems, modular supercomputing, performance engineering, networking, reproducible benchmarking, parallel I/O, and parallel programming models. For her contributions, Sarah has been awarded the "2023 PRACE Ada Lovelace Award for HPC" and the "ZONTA Science Award 2019". She received her PhD in Computer Science from Heidelberg University in 2018.

The colloquium is free of charge. Language: German/English
The event will be offered in PRESENCE. You can join the ZIH-Colloquium as following:

• LIVE: Willers-Bau, Room A317