BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230831T095754Z
LOCATION:Flüela
DTSTART;TZID=Europe/Stockholm:20230627T160000
DTEND;TZID=Europe/Stockholm:20230627T180000
UID:submissions.pasc-conference.org_PASC23_sess129@linklings.com
SUMMARY:MS4B - Porting of Applications to AMD GPUs: Lessons Learned
DESCRIPTION:Minisymposium\n\nAccelerators, namely GPUs, have become the wo
 rkhorse for floating-point/high-bandwidth intensive applications. Software
  development efforts in this domain have originally been focused around th
 e CUDA programming model tailored for NVIDIA GPUs. In 2016 AMD introduced 
 the HIP Programming language, a C++ runtime API and kernel language that a
 llows developers to create portable applications. Several projects for por
 ting scientific libraries and applications to run on AMD GPUs have started
  with many large supercomputers equipped with AMD GPUs in several supercom
 puter centers (e.g. Frontier in the USA and LUMI in Finland) entering prod
 uction. Moreover, AMD has led a substantial effort to develop a comprehens
 ive ecosystem for AMD GPUs, including compilers, profiling, and debugging 
 tools. For supercomputers provided by HPE, the HPE Cray Programming Enviro
 nment also offers tools for compilation and profiling as well as optimized
  libraries for fast MPI GPU-aware communications and most notably an OpenA
 CC implementation for AMD GPUs. The goal of the minisymposium is to gather
  researchers and developers to discuss their experiences with application 
 development and porting to AMD GPU devices.\n\nPorting ICON to AMD GPUs: L
 essons Learned\n\nThe AMD Instinct MI250X GPU has rapidly become a key ele
 ment of some of the most performant supercomputers in Europe and the USA. 
 This steep ascent confronts HPC vendors and customers with significant cha
 llenges. While the system providers are committed to deliver a software st
 ack that can leverage ...\n\n\nPeter Wauligmann and Aniello Esposito (HPE)
 \n---------------------\nScaling Out Machine Learning Convergence Training
  on LUMI\n\nML workloads are becoming a main FLOP consumer in many HPC cen
 ters in Europe and around the world. These workloads leverage well establi
 shed frameworks like Pytorch or Tensorflow that also work as a portability
  layer enabling ML to be one of the first production-ready workloads for n
 ew systems using...\n\n\nDiana Moise (HPE) and Samuel Antao (AMD)\n-------
 --------------\nPreparing CP2K for LUMI: User Experiences and Lessons Lear
 ned\n\nCP2K is an open source, quantum chemistry and molecular dynamics so
 ftware package comprising of a broad range of computational algorithms and
  simulation methods that can be flexibly combined to solve a given problem
 . Additional functionality is provided by GPU accelerated libraries such a
 s COSMA for...\n\n\nMathieu Taillefumier (ETH Zurich / CSCS), Gina Sitaram
 an (AMD), Alfio Lazzaro (HPE), Leopold Grinberg (AMD), and Marko Kabic (ET
 H Zurich)\n---------------------\nImpressions from the LUMI Porting Progra
 m\n\nThe LUMI porting program was created to help scientists and applicati
 on developers port applications to LUMI and AMD GPUs. Six applications wer
 e selected in different scientific domains: two from high energy physics (
 tmLQCD and PLEGMA), two from quantum chemistry/materials science (GPAW and
  Quantum ...\n\n\nPeter Larsson (KTH Royal Institute of Technology, PDC Ce
 nter for High Performance Computing)\n\nDomain: Computer Science, Machine 
 Learning, and Applied Mathematics 
\n\nSession Chair: Aniello Esposito (HP
 E)
END:VEVENT
END:VCALENDAR