BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260705T143351Z
UID:bafbf219-738d-429e-91bd-4bd0c532530b
DTSTART:20180312T080000Z
DTEND:20180313T153000Z
DESCRIPTION:Overview\n\nThis workshop will cover the directive-based progra
 mming model based on OpenMP v4 whose multi-vendor support allows users to 
 portably develop applications for parallel accelerated supercomputers. It 
 also includes comparison to the predecessor interface OpenACC v2. The wo
 rkshop will also demonstrate how to use the Cray Programming Environment t
 ools to identify application bottlenecks\, facilitate the porting\, provid
 e accelerated performance feedback and to tune the ported applications. Th
 e Cray scientific libraries for accelerators will be presented\, and inter
 operability of the directives approach with these and with CUDA will be de
 monstrated. Through application case studies and tutorials\, users will ga
 in direct experience of using both OpenMP and OpenACC directives in realis
 tic applications. Users may also bring their own codes to discuss with Cra
 y specialists or begin porting. This course provides scientific training i
 n Computational Science\, and in addition\, the scientific exchange of the
  participants among themselves.\n\nFor further information and registratio
 n please visit the HLRS course page.\n\nhttps://events.prace-ri.eu/event/6
 84/
SUMMARY:OpenMP GPU Directives for Parallel Accelerated Supercomputers - an 
 alternative to CUDA from Cray perspective  @ HLRS
URL;VALUE=URI:https://events.prace-ri.eu/event/684/
END:VEVENT
END:VCALENDAR