ZIH-Kolloquien 2023

Vergangene Termine 2023

30. November 2023, 15:00 MESZ, WIL-A317:
Prof. Dr. Sarah Neuwirth (Johannes Gutenberg-Universität Mainz) - „Holistic HPC Performance Engineering and Reproducible Benchmarking: Opportunities and Challenges“ Folien

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.

13. Juli 2023, 15:30 MESZ, WIL-A317/Online:
Jun. Prof. Dr Matthew McGinity (Technische Universität Dresden) - „Multi-user immersive visualisation - challenges and opportunities“

The TU Dresden Immersive Experience Lab (IXLAB) conducts interdisciplinary research into the foundations, technology and applications of immersive media - media in which virtual or remote things are, in some way, experienced as real and present. The creation of shared immersive experiences, in which people see and interact with the same virtual entities, remains a difficult technical challenge. In this talk I discuss different approaches to multi-user immersion, and then describe the development of our own multi-user mixed reality system, in which users collectively inhabit a shared virtual world. After presenting briefly our collaborations and applications in psychotherapy, education, robotics and art, I then turn to the specific challenges and opportunities of immersive multi-user systems for scientific visualisation.

Matthew McGinity is Junior Professor for Immersive Media Design at TU Dresden, where he leads the Immersive Experience Lab. Prior to joining TU Dresden in 2020, he developed immersive media systems in artistic, industrial and academic domains, ranging from immersive museum exhibitions to astronaut training simulations at the European Space Agency. He received his PhD from the University of New South Wales iCinema Centre for Interactive Cinema in 2014.

26. Mai 2023, 10:00 MESZ, APB-1004/Online:
Dr. Ignacio Laguna (Lawrence Livermore National Laboratory, Livermore, California) - „Mitigating Numerical Inconsistencies and Exceptions in Heterogeneous HPC Systems“ (Folien)

Scientific computing applications running on heterogeneous systems may suffer from numerical reproducibility and correctness issues, which can take a significant amount of time to detect and fix. This talk will present several tools and techniques to isolate numerical errors that arise when scientific software is ported to GPUs. The approaches include isolating compiler-induced numerical inconsistencies, detecting numerical exceptions, and finding inputs that trigger exceptions in GPU software.

Dr. Ignacio Laguna is a Computer Scientists and a Group Leader at the Center for Applied Scientific Computing at the Lawrence Livermore National Laboratory (LLNL), California. His research is focused on programing models for HPC, software correctness, debugging tools, and fault tolerance. He received his PhD in Computer Engineering from Purdue University in 2012 and has been at LLNL for more than ten years.

25. Mai 2023, 15:00 MESZ, Hörsaal A317 Willers-Bau/Online:
Dr. Günther Rezniczek (Marien Hospital Herne, Herne) - „REDCap: Erweiterbarkeit auf der Grundlage des EM Frameworks. Anwendungsfälle und die Technologie dahinter“ (Folien)

Externe Module sind eine leistungsstarke Funktion in REDCap, mit der Benutzer:innen die Funktionalität der Plattform über ihre Kernfähigkeiten hinaus erweitern können. Mit externen Modulen können Benutzer:innen neue Funktionen hinzufügen, vorhandene verbessern oder mit externen Tools und Systemen integrieren. Dies hat eine völlig neue Welt von Möglichkeiten für REDCap-Benutzer:innen eröffnet, die es ihnen ermöglicht, die Plattform an ihre spezifischen Anforderungen und Workflows anzupassen. Einige Vorteile von externen Modulen sind erhöhte Effizienz, verbesserte Datenqualität, verbesserte Benutzer:innenerfahrung und bessere Integration mit anderen Systemen. Darüber hinaus hat die REDCap-Community eine umfangreiche Bibliothek von externen Modulen erstellt, die allen Benutzer:innen frei zur Verfügung stehen und es einfach machen, Code über Projekte und Institutionen hinweg zu teilen und wiederzuverwenden. Dieser Vortrag gibt einen Überblick über diese Funktion, präsentiert einige bestehende Module und vermittelt tiefere technische Einblicke in die Funktionsweise von externen Modulen.

Dr. Günther Rezniczek got his PhD in Biochemistry and after doing basic research on the cytoskeletal protein plectin, he transitioned into clinical research, heading the Research Lab of the Department of Obstetrics and Gynecology, Marien Hospital Herne, University Clinic of Ruhr-Universität Bochum, where he established REDCap (Research Electronic Data Capture) as the go-to data capture tool. Inside the REDCap Consortium, he contributed significantly to the development of REDCap, and in 2021, won the REDCap Consortium MVP Award, and in 2022, he was among the REDCap All-Star Medal winners. Dr. Rezniczek has been one of the co-speakers of the REDCap German User Group since its establishment in 2020.

27. April 2023, 15:00 MESZ, Online:
Samuel Antao (AMD, München) - „Hardware, Software, and Application Co-Design on the Frontier and Lumi Systems“ (Folien) 

AMD Instinct GPUs are featured in several of the top most powerful supercomputers in the world, being Frontier and LUMI flagship systems for US and Europe, respectively. A concerted effort between hardware, software toolchain, and application is absolutely mandatory so as to get the most of the GPU accelerators and deliver on unprecedented breakthroughs in computational science enabled by these devices. This talk covers several examples on how a close interaction and co-design of the different layers, from hardware to application, has been instrumental for some of the most popular application run today on Frontier and LUMI.

Samuel Antao has a vast experience in optimisation and performance tuning for HPC applications and systems with focus on accelerators. His work spans hardware design with FPGAs, programming model research, compiler development and application optimisation. Samuel has participated in several cutting edge projects around HPC in Europe and in US, including CORAL, having spearheaded the GPU support for OpenMP in Clang/LLVM and helping numerous scientists and software developers to adopt the latest HPC technology and making the most out it. Samuel Antao is a Senior Member of Technical Staff with AMD and AMD lead to the LUMI Center of Excellence.

Historie: ZIH-Kolloquien der vergangenen Jahre

Historie 2023
Historie 2022
Historie 2021
Historie 2019/2020
Historie 2018
Historie 2017
Historie 2016
Historie 2014/2015
Historie 2013
Historie 2012
Historie 2011
Historie 2010
Historie 2009
Historie 2008
Historie 1998 - 2007