BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260628T071826Z
UID:d94ac8d0-74ce-4f9f-a46e-9e8780008e61
DTSTART:20150420T070000Z
DTEND:20150422T143000Z
DESCRIPTION:GPU-accelerated computing drives current scientific research. W
 riting fast numeric algorithms for GPUs offers high application performanc
 e by offloading compute-intensive portions of the code to an NVIDIA GPU. T
 he course will cover basic aspects of GPU architectures and programming. F
 ocus is on the usage of the parallel programming language CUDA-C which all
 ows maximum control of NVIDIA GPU hardware. Examples of increasing complex
 ity will be used to demonstrate optimization and tuning of scientific appl
 ications.\n\nTopics covered will include:\n\nIntroduction to GPU/Parallel 
 computing\n	Programming model CUDA\n	GPU libraries like CuBLAS and CuFFT\n
 	Tools for debugging and profiling\n	Performance optimizations\nPrerequisi
 tes: Some knowledge about Linux\, e.g. make\, command line editor\, Linux 
 shell\, experience in C\n\nThis course is a Prace Advanced Training Centre
 s (PATC) course.Application \nRegistrations are only considered until 31 M
 arch 2014\;\ndue to available space\, the maximal number of participants i
 s limited.\nApplicants will be notified\, whether they are accepted for pa
 rticipitation.Instructors:\nDr. Jan Meinke\, Jochen Kreutz\, JSC\;\nJiri K
 raus\, NVIDIAContact \nFor any questions concerning the course please send
  an e-mail to j.meinke@fz-juelich.de\n\nhttps://events.prace-ri.eu/event/3
 66/
SUMMARY:GPU Programming with CUDA @ JSC
URL;VALUE=URI:https://events.prace-ri.eu/event/366/
END:VEVENT
END:VCALENDAR