BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260706T013225Z
UID:6f254e19-fc16-42b1-bf10-1f063f29f4cc
DTSTART:20180531T073000Z
DTEND:20180601T150000Z
DESCRIPTION:When developing a numerical simulation code with high performan
 ce and efficiency in mind\, one is often compelled to accept a trade-off 
 between using a native-hardware programming model (like CUDA or OpenCL)\, 
 which has become tremendously challenging\, and loosing some cross-platfor
 m portability.\n\nPorting a large existing legacy code to a modern HPC pla
 tform\, and developing a new simulation code\, are two different tasks tha
 t may be benefit from a high-level programming model\, which abstracts th
 e low-level hardware details.\n\nThis training presents existing high-lev
 el programming solutions that can preserve at best as possible performance
 \, maintainability and portability across the vast diversity of modern har
 dware architectures (multicore CPU\, manycore\, GPU\, ARM\, ..) and softwa
 re development productivity.\n\nWe will  provide an introduction to the h
 igh-level C++ programming model Kokkos https://github.com/kokkos\, and sh
 ow basic code examples  to illustrate the following concepts through hand
 s-on sessions:\n\nhardware portability: design an algorithm once and let t
 he Kokkos back-end (OpenMP\, CUDA\, ...) actually derive an efficient low
 -level implementation\;\n	efficient architecture-aware memory containers: 
 what is a Kokkos::view\;\n	revisit fundamental parallel patterns with Kokk
 os: parallel for\, reduce\, scan\, ... \;\n	explore some mini-applications
 .\nSeveral detailed examples in C/C++/Fortran will be used in hands-on ses
 sion on the high-end hardware platform Ouessant (http://www.idris.fr/oues
 sant/)\, equipped with Nvidia Pascal GPUs.\n\nPrerequisites:\nSome basic k
 nowledge of the CUDA programming model and of C++.\n\nhttps://events.prace
 -ri.eu/event/712/
SUMMARY:Performance portability for GPU application using high-level progra
 mming approaches @ MdlS /Idris
URL;VALUE=URI:https://events.prace-ri.eu/event/712/
END:VEVENT
END:VCALENDAR