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:20241120T082409Z
LOCATION:HG F 1
DTSTART;TZID=Europe/Stockholm:20240604T170000
DTEND;TZID=Europe/Stockholm:20240604T173000
UID:submissions.pasc-conference.org_PASC24_sess150_msa176@linklings.com
SUMMARY:Progress Report on the GPU Adapatation of IFS and the Destination 
 Earth DTs
DESCRIPTION:Minisymposium\n\nMichael Lange (ECMWF)\n\nThe use of GPUs and 
 accelerator architectures has become widespread in high-performance comput
 ing to achieve unprecedented throughput and computational model performanc
 e. The efficient usage of GPU architectures has long been envisioned at EC
 MWF, but it requires significant, often invasive code refactoring that can
  harm operational model performance on CPUs. \nIn this talk we will descri
 be the ongoing efforts at ECMWF to prepare the Integrated Forecasting Syst
 em (IFS) for GPU accelerators through a combination of library development
 , data-structure refactoring and source-to-source translation. In close co
 llaboration with ECMWF member states and supported by the Destination Eart
 h initiative, we are aiming to restructure core model components of the IF
 S, and various technical infrastructure packages, to allow hybrid CPU-GPU 
 execution. The focus is on sustainable solutions through modern software e
 ngineering methods that allow adaptation of the code to multiple architect
 ures for continuous performance evaluation. \nWe will report on the progre
 ss of the GPU adaptation of IFS via specific build modes of the IFS and pr
 ovide an update on the adaptation of various sub-components. We will highl
 ight specific code characteristics and subsequent challenges and present i
 nitial performance results to assess the potential performance gains on cu
 rrent and future architectures.\n\nDomain: Climate, Weather, and Earth Sci
 ences, Computational Methods and Applied Mathematics\n\nSession Chairs: Iv
 a Kavcic (Met Office), Christopher Michael Maynard (Met Office), and Wei Z
 hang (Oak Ridge National Laboratory)
END:VEVENT
END:VCALENDAR