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:20230831T095746Z
LOCATION:Wisshorn
DTSTART;TZID=Europe/Stockholm:20230627T110000
DTEND;TZID=Europe/Stockholm:20230627T113000
UID:submissions.pasc-conference.org_PASC23_sess149_msa155@linklings.com
SUMMARY:GPU Porting of Plasma Physics Codes
DESCRIPTION:Minisymposium\n\nEmily Bourne, Gilles Fourestey, and Mathieu P
 eybernes (EPFL)\n\nWe will present the global strategy used for the GPU po
 rting of multiple fusion research codes. The chosen strategy aims to keep 
 a single version of each code using OpenMP/OpenACC directives. Performance
  portability on different architectures (NVIDIA and AMD GPUs) and with var
 ious compilers will be investigated. We will present how algorithms have b
 een improved to get better performance and our selected strategies to impr
 ove performance portability. We will focus only on 3 representative codes 
 to illustrate this global strategy: (1) CAS3D, a magnetohydrodynamic code 
 used to study the properties of fusion plasmas in non-axisymmetric configu
 rations such as stellarators. We will show how the introduction of generic
  pragmas allows the use of either OpenMP or OpenACC to get the best perfor
 mance according to the available compilers. (2) ASCOT5, an orbit-following
  Monte Carlo code, dedicated to stellarator configuration. We will present
  how we have exploited the independent time evolution of each particle and
  used the multi-level parallelism features of OpenMP/OpenACC to improve lo
 ad balancing. (3) GYSELA-X, simulating electrostatic plasma turbulence and
  transport in Tokamak devices. 5D features of GYSELA-X lead to the exploit
 ation OpenMP multi-level parallelism, results on the recent HPE-Cray ADAST
 RA machine equipped with AMD MI250X GPUs will be presented.\n\nDomain: Phy
 sics\n\nSession Chair: Gilles Fourestey (EPFL)
END:VEVENT
END:VCALENDAR