STEAM Academy Seminar: The surprising consequences of resource-based thinking in HPC

by Prof. Georg Hager (NHR@FAU)

Tuesday 18 Aug 2026, 16:00 → 17:30 Europe/Zurich

500/1-001 - Main Auditorium (CERN)

Abstract: In large-scale parallel computing, be it AI related or not, resources are everything, but they are also limited: There is only limited memory, cache, disk, and network bandwidth, there is considerable (but still limited) compute capability, there is only limited power, and overall there is (at least in the academic context) limited money. This is why any model which uses such resources as primary input and which can predict runtime, energy cost, power limits, and overall cost (TCO) is extremely useful for code optimization, sustainable operations, and site planning. This talk will show by example how we can make best use of resource-based thinking in all these activities. Starting from simple "roofline thinking," we extend this motif to power dissipation and energy consumption, showing that one can get surprisingly far with simple pen-and-paper calculations.

Bio: Georg Hager holds a PhD and a Habilitation degree in Computational Physics from the University of Greifswald. He leads the Research Division at Erlangen National High Performance Computing Center (NHR@FAU) and is an associate lecturer at the Institute of Physics at the University of Greifswald. Recent research includes architecture-specific optimization strategies for current microprocessors, performance engineering of scientific codes on chip and system levels, and the analytic modeling of structure formation in large-scale parallel codes. Georg Hager has authored and co-authored more than 100 peer-reviewed publications and was instrumental in developing and refining the Execution-Cache-Memory (ECM) performance model and energy consumption models for multicore processors. In 2018, he won the “ISC Gauss Award” (together with Johannes Hofmann and Dietmar Fey) for a paper on accurate performance and power modeling. He received the “2011 Informatics Europe Curriculum Best Practices Award” (together with Jan Treibig and Gerhard Wellein) for outstanding contributions to teaching in computer science. His textbook “Introduction to High Performance Computing for Scientists and Engineers” is recommended or required reading in many HPC-related lectures and courses worldwide. Together with colleagues from FAU, HLRS Stuttgart, and TU Wien he develops and conducts successful international tutorials on node-level performance engineering and hybrid programming.

This seminar is part of the CERN STEAM Academy Seminar Series. 

Networking cocktail will follow the seminar. 

With the support of CERN's Next Generation Triggers Project.