BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260627T183939Z
UID:295ff99c-db59-4c0a-933d-246a36d84062
DTSTART:20141028T070000Z
DTEND:20141030T141500Z
DESCRIPTION:This course will give a short introduction to NVidia GPUs and I
 ntel Xeon Phis\, which are currently the two most popular accelerator arch
 itectures. After a short hardware overview we will present two simple prag
 ma-based programming models for accelerators: offloading for Xeon Phi syst
 ems and OpenACC for GPUs. Some basic performance considerations and limita
 tions due to the memory traffic between the host and accelerator will be d
 iscussed. Last part of the course will give a short one-day introduction t
 o the lower level approach for GPU programming using CUDA.AgendaTuesday 28
 th October\n\n09:00 - 09:15 Course introduction\n	09:15 - 10:15 Introducti
 on to Xeon Phi\n	10:15 - 10:30 Coffee break\n	10:30 - 11:30 Offload\n	11:
 30 - 12:00 Exercises\n	12:00 - 12:45 Lunch break\n	12:45 - 13:45 Data a
 ccess and performance\n	13:45 - 14:30 Exercises\n	14:30 - 14:45 Coffee bre
 ak\n	14:45 - 15:45 Exercises\n	15:45 - 16:15 Advanced topics and wrap-up\n
 Wednesday 29th October\n\n09:00 - 09:30 Introduction to GPUs\n	09:30 - 10:
 30 OpenACC basics\n	10:30 - 10:45 Coffee break\n	10:45 - 12:00 Exercises\n
 	12:00 - 12:45 Lunch break\n	12:45 - 13:45 Data access and performance\n	1
 3:45 - 14:30 Exercises\n	14:30 - 14:45 Coffee break\n	14:45 - 15:45 Exer
 cises\n	15:45 - 16:15 Advanced topics and wrap-up\nThursday 30th October\n
 \n09:00 - 10:15 CUDA programming I\n	10:15 - 10:30 Coffee break\n	10:30 -
  11:15 Exercises\n	11:15 - 12:15 CUDA programming II\n	12:15 - 13:00 Lun
 ch break\n	13:00 - 14:00 Exercises\n	14:00 - 14:30 CUDA programming III\n	
 14:30 - 14:45 Coffee break\n	14:45 - 15:45 Exercises\n	15:45 - 16:15 Cours
 e wrap-up\nLearning outcome\nThe students should know the basics of accele
 rators and utilize them using either offloading or OpenACC.Pre-requisites\
 nGood knowledge on C programming language is needed for the CUDA part. Som
 e basic knowledge about parallel programming is beneficial\, but no prior 
 knowledge on GPUs is needed.Price: Free of chargeLecturers: Sami Ilvonen
  (CSC)\, Mikko Byckling (CSC)\n\nhttps://events.prace-ri.eu/event/295/
SUMMARY:Introduction to Accelerators @ CSC
URL;VALUE=URI:https://events.prace-ri.eu/event/295/
END:VEVENT
END:VCALENDAR