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:20241120T082410Z
LOCATION:HG F 30 Audi Max
DTSTART;TZID=Europe/Stockholm:20240604T094600
DTEND;TZID=Europe/Stockholm:20240604T094600
UID:submissions.pasc-conference.org_PASC24_sess158_pos165@linklings.com
SUMMARY:P28 - GT4Py: A Python Framework for the Development of High-Perfor
 mance Weather and Climate Applications
DESCRIPTION:Poster\n\nMauro Bianco and Till Ehrengruber (ETH Zurich / CSCS
 ); Nina Burgdorfer (MeteoSwiss); Nicoletta Farabullini, Abishek Gopal, Sam
 uel Kellerhans, and Peter Kardos (ETH Zurich); and Enrique Paredes, Rico H
 äuselmann, Felix Thaler, Hannes Vogt, Philip Müller, and Christos Kotsalos
  (ETH Zurich / CSCS)\n\nGT4Py is a Python framework for weather and climat
 e applications simplifying the development and maintenance of high-perform
 ance codes in prototyping and production environments. GT4Py separates mod
 el development from hardware architecture dependent optimizations, instead
  of intermixing both together in source code, as regularly done in lower-l
 evel languages like Fortran, C, or C++. Domain scientists focus solely on 
 numerical modeling using a declarative embedded domain specific language s
 upporting common computational patterns of dynamical cores and physical pa
 rametrizations. An optimizing toolchain then transforms this high-level re
 presentation into a finely-tuned implementation for the target hardware ar
 chitecture. This separation of concerns allows performance engineers to im
 plement new optimizations or support new hardware architectures without re
 quiring changes to the application, increasing productivity for domain sci
 entists and performance engineers alike. We will present recent developmen
 ts in the project: support for interactive debugging, new compiler passes 
 that optimize data-movement, an improved frontend with support for high-le
 vel constructs, and new backends connecting GT4Py with existing HPC framew
 orks (DaCe, Jax). We further showcase performance results of two atmospher
 ic models (ICON, FVM) on the new NVIDIA Grace-Hopper nodes of the CSCS Alp
 s supercomputer.\n\nSession Chair: Iva Kavcic (Met Office)
END:VEVENT
END:VCALENDAR