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:20260731T133318Z
LOCATION:Bldg. 6 - 002
DTSTART;TZID=Europe/Stockholm:20260701T090000
DTEND;TZID=Europe/Stockholm:20260701T110000
UID:submissions.pasc-conference.org_PASC26_sess149@linklings.com
SUMMARY:MS4A - Performance-Portable High-Order CFD for Digital Twins on He
 terogeneous Exascale Architectures
DESCRIPTION:Access the recording\n\nOrganizer(s): Dominik Obrist (Universi
 ty of Bern)\n\nThe emergence of Digital Twins and large-scale computationa
 l design is reshaping high-performance scientific computing, demanding sca
 lable, trustworthy, and hardware-extensible solutions. This minisymposium 
 brings together advances in high-order computational fluid dynamics (CFD) 
 and compiler technologies that enable performance portability across heter
 ogeneous CPU–GPU architectures. The three presentations highlight compleme
 ntary strategies—software architecture, scalable optimization frameworks, 
 and compiler-driven kernel generation—for building next-generation, perfor
 mance-portable CFD and design tools for heterogeneous exascale systems. Th
 e minisymposium will conclude with a podium discussion on future direction
 s in this field.\n\nNext-Generation Digital Twins: C++-Based Solvers Acros
 s CPUs and GPUs\n\nDigital Twins are rapidly becoming a key driver of indu
 strial innovation in sectors such as automotive and aeronautics, placing s
 tringent demands on computational physics solvers for performance, portabi
 lity, and long-term maintainability. Meeting these demands requires more t
 han efficient algorithm...\n\n\nChristophe Coreixas (Beijing Normal - Hong
  Kong Baptist University, University of Geneva) and Jonas Latt (University
  of Geneva)\n---------------------\nNeko-TOP: Exascale Topology Optimizati
 on Framework for Transient Flow Problems\n\nComputational design increasin
 gly integrates machine-driven optimization with human engineering expertis
 e. Ensuring trust in automated design recommendations is critical, particu
 larly for complex systems like transient flow. Topology Optimization offer
 s a mathematical framework for optimal design, b...\n\n\nTim Olsen (Techni
 cal University of Denmark), Abbas Mousavi (Kungliga Tekniska Högskolan), H
 arrison Nobis (Umeå University), and Casper Andreasen and Niels Aage (Tech
 nical University of Denmark)\n---------------------\nNektarIR: A Domain-Sp
 ecific Compiler for High-Order Finite Element Operations on Heterogeneous 
 Hardware\n\nThe transition towards heterogeneous or GPU-dominated hardware
  in high-performance computing (HPC) infrastructure has highlighted the ne
 ed for hardware-extensible implementations of HPC applications in scientif
 ic computing and AI. Ensuring that these implementations are optimized for
  the specific ha...\n\n\nEdward Erasmie-Jones (King's College London), Gia
 como Castiglioni (ETH Zurich / CSCS), and David Moxey (King's College Lond
 on)\n---------------------\nPanel Discussion: Are New HPC Architectures Ch
 anging the Questions Domain Scientists Ask?\n\nThe ongoing evolution of hi
 gh-performance computing enables more complex and efficient CFD models. Th
 is panel will discuss how these advances shape the research questions addr
 essed by domain scientists.\n\n\nDominik Obrist (University of Bern)\n\nDo
 main: Engineering, Computational Methods and Applied Mathematics\n\nSessio
 n Chair: Dominik Obrist (University of Bern)
END:VEVENT
END:VCALENDAR