BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20211207T055347Z
LOCATION:Online
DTSTART;TZID=America/Chicago:20211115T160000
DTEND;TZID=America/Chicago:20211115T163000
UID:submissions.supercomputing.org_SC21_sess422_ws_pmbsf124@linklings.com
SUMMARY:Comparing Julia to Performance Portable Parallel Programming Model
 s for HPC
DESCRIPTION:Workshop\n\nComparing Julia to Performance Portable Parallel P
 rogramming Models for HPC\n\nLin, McIntosh-Smith\n\nJulia is a general-pur
 pose, managed, strongly and dynamically-typed programming language with em
 phasis on high-performance scientific computing. Traditionally, HPC softwa
 re development uses languages such as C, C++ and Fortran, which compile to
  unmanaged code. This offers the programmer near bare-metal performance at
  the expense of safety properties that a managed runtime would otherwise p
 rovide. Julia, on the other hand, combines novel programming language desi
 gn approaches to achieve high levels of productivity without sacrificing p
 erformance while using a fully managed runtime.\n\nThis study provides an 
 evaluation of Julia's suitability for HPC applications from a performance 
 point of view across a diverse range of CPU and GPU platforms. We select r
 epresentative memory-bandwidth bound and compute bound mini-apps, port the
 m to Julia, and conduct benchmarks across a wide range of current HPC CPUs
  and GPUs from vendors such as Intel, AMD, NVIDIA, Marvell and Fujitsu. We
  then compare and characterize the results against existing parallel progr
 amming frameworks such as OpenMP, Kokkos, OpenCL and first-party framework
 s such as CUDA, HIP and oneAPI SYCL. Finally, we show that Julia's perform
 ance either matches the competition or is only a short way behind.\n\nTag:
  Online Only, Accelerator-based Architectures, Applications, Computational
  Science, Emerging Technologies, Extreme Scale Computing, File Systems and
  I/O, Heterogeneous Systems, Parallel Programming Languages and Models, Pe
 rformance, Scientific Computing, Software Engineering\n\nRegistration Cate
 gory: Workshop Reg Pass
END:VEVENT
END:VCALENDAR