BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:STEAM Academy Seminar: The surprising consequences of resource-bas
 ed thinking in HPC [Cancelled]
DTSTART:20260818T140000Z
DTEND:20260818T153000Z
DTSTAMP:20260816T233600Z
UID:indico-event-1696054@indico.cern.ch
CONTACT:steam.academy@cern.ch\;ep-seminars.colloquia@cern.ch
DESCRIPTION:Speakers: Georg Hager (NHR@FAU)\n\nAbstract: In large-scale pa
 rallel computing\, be it AI related or not\, resources are everything\, b
 ut they are also limited: There is only limited memory\, cache\, disk\, a
 nd 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 c
 ost\, 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 exten
 d this motif to power dissipation and energy consumption\, showing that o
 ne can get surprisingly far with simple pen-and-paper calculations.\nBio:
  Georg Hager holds a PhD and a Habilitation degree in Computational Physic
 s from the University of Greifswald. He leads the Research Division at Erl
 angen National High Performance Computing Center (NHR@FAU) and is an assoc
 iate lecturer at the Institute of Physics at the University of Greifswald.
  Recent research includes architecture-specific optimization strategies fo
 r 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 m
 ore than 100 peer-reviewed publications and was instrumental in developing
  and refining the Execution-Cache-Memory (ECM) performance model and energ
 y consumption models for multicore processors. In 2018\, he won the “ISC
  Gauss Award” (together with Johannes Hofmann and Dietmar Fey) for a pap
 er on accurate performance and power modeling. He received the “2011 Inf
 ormatics Europe Curriculum Best Practices Award” (together with Jan Trei
 big and Gerhard Wellein) for outstanding contributions to teaching in comp
 uter science. His textbook “Introduction to High Performance Computing f
 or 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 int
 ernational tutorials on node-level performance engineering and hybrid prog
 ramming.\nThis seminar is part of the CERN STEAM Academy Seminar Series. 
 \nNetworking cocktail will follow the seminar. \n\nWith the support of C
 ERN's Next Generation Triggers Project.\n\n \n\n\nhttps://indico.cern.ch/
 event/1696054/
LOCATION:500/1-001 - Main Auditorium (CERN)
URL:https://indico.cern.ch/event/1696054/
END:VEVENT
END:VCALENDAR