BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260622T174321Z
UID:91df6168-a4e0-4cbc-b7af-007e4bbe9a01
DTSTART:20130618T073000Z
DTEND:20130621T150000Z
DESCRIPTION:The purpose of this training course is to present hybrid progra
 mming\, MPI+OpenMP\, as well as to give a feedback of effective implementa
 tions of such a parallel programming model on several application codes.\n
 We will explain why the hybrid programming approach seems to be the best s
 uited model for the next massively parallel architectures. Indeed\, the be
 nefits of hybrid programming are numerous: memory savings\, better perform
 ances\, better load balancing\, greater granularity\, improved scalability
 \, better adequacy of the code to the hardware specificities of the target
  architecture. \n Content:\n\n		Introduction to hybrid MPI-OpenMP parall
 elization\,\n	\n		Advanced MPI\,\n	\n		Advanced OpenMP\,\n	\n		Hybrid MPI-
 OpenMP parallelization concepts\,\n	\n		Feedback on several real applicati
 ons\,\n\n Hands-on sessions will use the PRACE / CURIE supercomputerLea
 rning outcome:\nAfter this course\, participants will be able to:\n		Optim
 ize the original parallel OpenMP and MPI versions of their code\n	\n		Choo
 se the best strategy\, especially the level of thread support\, depending 
 on their code and on the target architecture characteristics\n	\n		Impleme
 nt the strategy to obtain an efficient parallel hybrid MPI+OpenMP version.
 \n\nThey will also know how to use performance/debugging tools to find bug
 s\, deadlocks or determine the part of their code that leads to poor perfo
 rmance.Pre-requisites:\nAdvanced users who have a good knowledge of:\n		C 
 or Fortran programming language\,\n	\n		MPI\n	\n		OpenMP.\n\n\nhttps://eve
 nts.prace-ri.eu/event/118/
SUMMARY:Hybrid MPI/OpenMP programming @ IDRIS
URL;VALUE=URI:https://events.prace-ri.eu/event/118/
END:VEVENT
END:VCALENDAR