BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260706T192716Z
UID:03d948dd-a2b4-4c45-8536-b8a4d6ec3979
DTSTART:20200504T070000Z
DTEND:20200506T143000Z
DESCRIPTION:This course was postponed to autumn 2020. The exact date will b
 e fixed later.\n\nGPU-accelerated computing drives current scientific rese
 arch. Writing fast numeric algorithms for GPUs offers high application per
 formance by offloading compute-intensive portions of the code to an NVIDIA
  GPU. The course will cover basic aspects of GPU architectures and program
 ming. Focus is on the usage of the parallel programming language CUDA-C wh
 ich allows maximum control of NVIDIA GPU hardware. Examples of increasing 
 complexity will be used to demonstrate optimization and tuning of scientif
 ic applications.\n\nTopics covered will include:\n\n\n	Introduction to GPU
 /Parallel computing\n	Programming model CUDA\n	GPU libraries like CuBLAS a
 nd CuFFT\n	Tools for debugging and profiling\n	Performance optimizations\n
 \n\nPrerequisites: Some knowledge about Linux\, e.g. make\, command line e
 ditor\, Linux shell\, experience in C/C++\n\nApplication \nRegistrations a
 re only considered until 31 March 2020 due to available space\, the maxima
 l number of participants is limited. Applicants will be notified\, whether
  they are accepted for participitation.\n\nInstructors: Dr. Jan Meinke\, J
 ochen Kreutz\, Dr. Andreas Herten\, JSC\; Jiri Kraus\, NVIDIA\n\nContact \
 nFor any questions concerning the course please send an e-mail to j.meinke
 @fz-juelich.de\nhttps://events.prace-ri.eu/event/981/
SUMMARY:[POSTPONED] GPU Programming with CUDA @ JSC
URL;VALUE=URI:https://events.prace-ri.eu/event/981/
END:VEVENT
END:VCALENDAR