BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T143141Z
LOCATION:B301
DTSTART;TZID=America/New_York:20241118T153000
DTEND;TZID=America/New_York:20241118T154800
UID:submissions.supercomputing.org_SC24_sess760_ws_waccpd101@linklings.com
SUMMARY:JACC: Leveraging HPC Meta-Programming and Performance Portability 
 with the Just-in-Time and LLVM-based Julia Language
DESCRIPTION:Pedro Valero-Lara, William Godoy, Het Mankad, and Keita Terani
 shi (Oak Ridge National Laboratory (ORNL)); Jeffrey S. Vetter (Oak Ridge N
 ational Laboratory); Johannes Blashke (Lawrence Berkeley National Laborato
 ry (LBNL)); and Michel Schanen (Argonne National Laboratory (ANL))\n\nWe p
 resent JACC (Julia for ACCelerators), the first high-level, metaprogrammin
 g, and performance-portable model for the just-in-time and LLVM-based Juli
 a language. JACC provides a unified and lightweight front end across diffe
 rent back ends available in Julia, enabling the same Julia code to run eff
 iciently on many CPU and GPU targets. We evaluated the performance of JACC
  for common HPC kernels as well as for the most computationally demanding 
 kernels used in applications, such as MiniFE, a proxy application for unst
 ructured implicit finite element codes, HPCCG, a supercomputing benchmark 
 test for sparse domains, and HARVEY, a blood flow simulator to assist in t
 he diagnosis and treatment of patients suffering from vascular\ndiseases. 
 We carried out the performance analysis on the most advanced US DOE superc
 omputers: Aurora, Frontier, and Perlmutter. Overall, we show that JACC has
  a negligible\noverhead versus vendor-specific solutions, reporting GPU sp
 eedups over the CPU implementations with no extra cost.\n\nTag: Accelerato
 rs, Heterogeneous Computing, Parallel Programming Methods, Models, Languag
 es and Environments\n\nRegistration Category: Workshop Reg Pass\n\nSession
  Chairs: Maciej Cytowski (Pawsey Supercomputing Research Centre; Commonwea
 lth Scientific and Industrial Research Organisation (CSIRO), Australia); J
 oseph Schoonover (Fluid Numerics LLC); and Emma Tolley (Swiss Federal Inst
 itute of Technology Lausanne (EPFL))\n\n
END:VEVENT
END:VCALENDAR