BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260730T100006Z
UID:13620071-cf79-4430-8022-60040df6c21b
DTSTART:20260818T140000Z
DTEND:20260818T153000Z
DESCRIPTION:Speakers: Georg Hager (NHR@FAU)\n\nAbstract: In large-scale par
 allel computing\, be it AI related or not\, resources are everything\, bu
 t they are also limited: There is only limited memory\, cache\, disk\, an
 d network bandwidth\, there is considerable (but still limited) compute c
 apability\, 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 co
 st\, power limits\, and overall cost (TCO) is extremely useful for code o
 ptimization\, sustainable operations\, and site planning. This talk will 
 show by example how we can make best use of resource-based thinking in a
 ll these activities. Starting from simple "roofline thinking\," we extend
  this motif to power dissipation and energy consumption\, showing that on
 e can get surprisingly far with simple pen-and-paper calculations.\nBio: 
 Georg Hager holds a PhD and a Habilitation degree in Computational Physics
  from the University of Greifswald. He leads the Research Division at Erla
 ngen National High Performance Computing Center (NHR@FAU) and is an associ
 ate 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 mo
 re 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 pape
 r on accurate performance and power modeling. He received the “2011 Info
 rmatics Europe Curriculum Best Practices Award” (together with Jan Treib
 ig and Gerhard Wellein) for outstanding contributions to teaching in compu
 ter science. His textbook “Introduction to High Performance Computing fo
 r Scientists and Engineers” is recommended or required reading in many H
 PC-related lectures and courses worldwide. Together with colleagues from F
 AU\, HLRS Stuttgart\, and TU Wien he develops and conducts successful inte
 rnational tutorials on node-level performance engineering and hybrid progr
 amming.\nThis seminar is part of the CERN STEAM Academy Seminar Series. \
 nNetworking cocktail will follow the seminar. \n\nWith the support of CE
 RN's Next Generation Triggers Project.\n\n \n\n\nhttps://indico.cern.ch/e
 vent/1696054/\n\nZoom: https://cern.zoom.us/j/64966048364?pwd=NMtu9pGMJVCk
 lqPLXD6cp9oUUg9ZKF.1
LOCATION:500/1-001 - Main Auditorium (CERN)
SUMMARY:STEAM Academy Seminar: The surprising consequences of resource-base
 d thinking in HPC [Cancelled]
URL;VALUE=URI:https://indico.cern.ch/event/1696054/
END:VEVENT
END:VCALENDAR