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:20260615T072747Z
LOCATION:Bldg. 6 - Room 002
DTSTART;TZID=Europe/Stockholm:20260701T100000
DTEND;TZID=Europe/Stockholm:20260701T103000
UID:submissions.pasc-conference.org_PASC26_sess149_msaSC105@linklings.com
SUMMARY:NektarIR: A Domain-Specific Compiler for High-Order Finite Element
  Operations on Heterogeneous Hardware
DESCRIPTION:Edward Erasmie-Jones (King's College London), Giacomo Castigli
 oni (ETH Zurich / CSCS), and David Moxey (King's College London)\n\nThe tr
 ansition towards heterogeneous or GPU-dominated hardware in high-performan
 ce computing (HPC) infrastructure has highlighted the need for hardware-ex
 tensible implementations of HPC applications in scientific computing and A
 I. Ensuring that these implementations are optimized for the specific hard
 ware target poses a significant challenge, as the optimization process req
 uires specific hardware-level knowledge that is not only outside the scien
 tific domain but also varies across different hardware types and vendors. 
 In this talk, we present NektarIR, a domain-specific compiler for high-ord
 er finite element operations on CPU and GPU hardwares. Using the MLIR proj
 ect, we have created an intermediate representation of a high-level abstra
 ction of the operations that is rewritten and lowered through a series of 
 passes to optimized and hardware-specific kernels. These kernels are just-
 in-time (JIT) compiled for the specific hardware and architecture using LL
 VM and can be used in the construction of spectral/hp element solvers for 
 computational fluid dynamics. We also present benchmarks for the overhead 
 introduced by our compiler pipeline and a run-time performance comparison 
 of our kernels against the Nektar++ spectral/hp element framework.\n\nDoma
 in: Engineering, Computational Methods and Applied Mathematics\n\nSession 
 Chair: Dominik Obrist (University of Bern)\n\n
END:VEVENT
END:VCALENDAR