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:20260605T154540Z
LOCATION:Bldg. 6 - Room 103
DTSTART;TZID=Europe/Stockholm:20260701T090000
DTEND;TZID=Europe/Stockholm:20260701T110000
UID:submissions.pasc-conference.org_PASC26_sess153@linklings.com
SUMMARY:MS4E - Emerging Paradigms for Performance Portability in Earth-Sys
 tem Modeling
DESCRIPTION:Organizer(s): Georgiana Mania (German Climate Computing Centre
 ), and Xavier Lapillonne (MeteoSwiss)\n\nThe recent advancements in Earth 
 System Models (ESMs) have enabled simulations at unprecedented resolutions
  (1-kilometre global and sub-kilometre local), pushing the boundaries of f
 orecast quality. However, these simulations demand enormous compute resour
 ces, necessitating the largest supercomputers and cutting-edge hardware ar
 chitectures from various vendors. This has created a significant challenge
  for ESMs to ensure performance portability, particularly given the legacy
  Fortran code bases. To address this issue, this mini-symposium brings tog
 ether invited experts who will present diverse approaches to achieving per
 formance portability, including the utilization of existing portability fr
 ameworks, the development of domain-specific languages and compilers, and 
 share their hands-on experiences. By showcasing these innovative solutions
 , this mini-symposium aims to facilitate a comprehensive understanding of 
 the current state-of-the-art and future directions in achieving performanc
 e portability for next-generation ESMs.\n\nPanel Discussion: Overcoming Te
 chnical Hurdles to Achieve Performance Portability\n\nThe mini-symposium w
 ill feature expert speakers who will delve into the various strategies for
  achieving performance portability in Earth-System Modeling. They will exp
 lore the use of domain-specific compiler frameworks, such as PSyclone and 
 GT4Py, as well as the general-purpose parallel programming...\n\n\nGeorgia
 na Mania (DKRZ) and Xavier Lapillonne (MeteoSwiss)\n---------------------\
 nCo-Designing Performance Portability for ICON: An OpenACC to Kokkos Journ
 ey\n\nModern heterogeneous HPC systems, which include multi-core CPUs and 
 GPU accelerators from various vendors, require portability strategies that
  go beyond single-architecture optimization. This is particularly challeng
 ing for large production models like ICON, as it requires a careful balanc
 ing act be...\n\n\nPradipta Samanta (German Climate Computing Centre)\n---
 ------------------\nPSyclone: A Story of Co-Design for Scientific Function
 ality and Performance Portability in the Momentum® Modelling Framework\n\n
 Weather and climate modelling are among the most computationally intensive
  scientific applications, requiring exascale computing to significantly im
 prove prediction and projection capabilities. These complex codes are coll
 aboratively developed across institutions and run on various computing arc
 hite...\n\n\nIva Kavcic (Met Office)\n---------------------\nICON4Py: An I
 CON Performance Portable Implementation in Python Using gt4py\n\nICON4Py r
 epresents a significant shift in the development of the ICON weather and c
 limate modeling framework, transitioning from a Fortran codebase to a perf
 ormance-portable Python implementation. The project combines the Python fl
 exibility with the performance required for large-scale numerical wea...\n
 \n\nNicoletta Farabullini (Center for Climate Systems Modeling (C2SM))\n\n
 Domain: Climate, Weather, and Earth Sciences, Computational Methods and Ap
 plied Mathematics\n\nSession Chairs: Georgiana Mania (DKRZ) and Xavier Lap
 illonne (MeteoSwiss)
END:VEVENT
END:VCALENDAR
