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:20230124T171524Z
LOCATION:C155
DTSTART;TZID=America/Chicago:20221113T133000
DTEND;TZID=America/Chicago:20221113T135300
UID:submissions.supercomputing.org_SC22_sess428_ws_p3hpc111@linklings.com
SUMMARY:Performance Portable Vlasov Code with C++ Parallel Algorithm
DESCRIPTION:Workshop\n\nPerformance Portable Vlasov Code with C++ Parallel
  Algorithm\n\nAsahi, Padioleau, Latu, Bigot, Grandgirard...\n\nThis paper 
 presents the performance portable implementation of a kinetic plasma simul
 ation code with C++ parallel algorithm to run across multiple CPUs and GPU
 s. Relying on the language standard parallelism stdpar and proposed langua
 ge standard multi-dimensional array support mdspan, we demonstrate that a 
 performance portable implementation is possible without harming the readab
 ility and productivity. We obtain a good overall performance for a mini-ap
 plication in the range of 20% to the Kokkos version on Intel Icelake, NVID
 IA V100, and A100 GPUs. Our conclusion is that stdpar can be a good candid
 ate to develop a performance portable and productive code targeting the ex
 ascale era platform, assuming this approach will be available on AMD and/o
 r Intel GPUs in the future.\n\nSession Format: Recorded\n\nTag: Performanc
 e Portability\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR