BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260703T233216Z
UID:c2042a14-d0ae-431c-8d95-e3e1ee047efb
DTSTART:20220323T083000Z
DTEND:20220324T153000Z
DESCRIPTION:The course will take place in Hybrid format and will be held in
 -person within the UPC premises: Department of Computer Architecture (DAC)
 . Room C6-102\, Barcelona\, Spain\; and also\, online via Zoom with requir
 ed registration.\n\nYou will need to bring your own laptop.\n\nAll the PAT
 C courses at the Barcelona Supercomputing Center are free of charge.  The 
 attendees would need to cover the expenses for travel\, accommodation and 
 meals.\n\nCourse Convener: Xavier Martorell\, BSC Computer Sciences/ Paral
 lel Programming Models Group Manager\n\nLecturers:\n\nBSC - Computer Scien
 ces department\n\n\nXavier Teruel - Best Practices for Performance and Pro
 grammability - Recognised Researcher \n\nXavier Martorell - Programming Mo
 dels - Parallel programming model - Group Manager\n\n\n \n\nObjectives: \
 n\nThe tutorial will motivate the audience on the need for portable\, effi
 cient programming models that put less pressure on program developers whil
 e still getting good performance for clusters and clusters with GPUs.\n\nM
 ore specifically\, the tutorial will:\n\n\n	Introduce the hybrid MPI/OmpSs
  parallel programming model for future exascale systems\n	Demonstrate how 
 to use MPI/OmpSs to incrementally parallelize/optimize:\n	\n		MPI applicat
 ions on clusters of SMPs\, and\n		Leverage CUDA kernels with OmpSs on clus
 ters of GPUs\n	\n	\n\n\nLearning Outcomes:   The students who finish this
  course will be able to develop benchmarks and simple applications with th
 e MPI/OmpSs programming model to be executed in clusters and clusters of G
 PUs\, and with the OmpSs@FPGA\, to be executed on FPGA boards\, like the Z
 edboard\, or Xilinx ZCU102 and Alveo.\n\nPrerequisites:\nGood knowledge of
  C/C++\nBasic knowledge of CUDA/OpenCL\nBasic knowledge of Paraver/Extrae\
 n\n \nhttps://events.prace-ri.eu/event/1324/
SUMMARY:[HYBRID] PATC: Heterogeneous Programming on GPUs with MPI & OmpSs @
  BSC
URL;VALUE=URI:https://events.prace-ri.eu/event/1324/
END:VEVENT
END:VCALENDAR