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:20250822T115804Z
LOCATION:Room 5.0B56
DTSTART;TZID=Europe/Stockholm:20250618T103000
DTEND;TZID=Europe/Stockholm:20250618T110000
UID:submissions.pasc-conference.org_PASC25_sess110_msa161@linklings.com
SUMMARY:From Fortran to GPU: The Data-Centric Journey of ECRAD
DESCRIPTION:Alexandru Calotoiu (ETH Zurich) and Torsten Hoefler (ETH Zuric
 h / CSCS)\n\nFortran remains, despite various efforts, the dominant langua
 ge for answering pressing climate-related questions such as when to sell b
 eachfront property, or where to plant olive groves. These, and more seriou
 s questions, require the use of ever larger supercomputers as the resoluti
 on of our models grows ever better. The AI revolution forces Fortran appli
 cations to run on supercomputers composed of GPUs designed to train machin
 e learning models, but making legacy codes learn new tricks is not easy. W
 e offer a path that requires no code changes: we lift the Fortran code and
  all its embedded information into a data-centric representation. We propa
 gate specific runtime configuration details to simplify the code and, more
  importantly, optimize for specific array dimensions. We have created a re
 presentation of the entire radiation solver ECRAD that we can specialize f
 or both CPU and GPU execution. Using this approach, we can run the same si
 mulation expressed in the sequential Fortran code on parallel CPUs, and on
  both AMD and NVIDIA GPUs without requiring the domain scientists to rewri
 te or add a single line of code – and while achieving competitive performa
 nce compared to manual implementations.\n\nDomain: Climate, Weather, and E
 arth Sciences, Computational Methods and Applied Mathematics\n\nSession Ch
 airs: Michael Lange (ECMWF) and Balthasar Reuter (ECMWF)\n\n
END:VEVENT
END:VCALENDAR