BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260706T013126Z
UID:479f5f41-a1e2-41e2-8fbf-b16fb8aaa8e0
DTSTART:20201123T100000Z
DTEND:20201126T170000Z
DESCRIPTION:Outline\n\nThis course will provide an introduction to GPU comp
 uting with CUDA aimed at scientific application programmers. The course wi
 ll give a background on the difference between CPU and GPU architectures a
 s a prelude to introductory exercises in CUDA programming. The course will
  discuss the execution of kernels\, memory management\, and shared memory 
 operations. Common performance issues are discussed and their solution add
 ressed. The course will also cover some of the alternatives to CUDA common
 ly available (OpenCL\, OpenACC\, and Kokkos) at the current time.\n\nA sep
 arate "Hackathon Day" will be available for attendees to try out their own
  problems (or a 'canned' extended example) with the help of staff from bot
 h EPCC and NVIDIA.\n\nLearning Outcomes\n\nAt the end of the course\, atte
 ndees should be in a position to make an informed decision on how to appro
 ach GPU parallelisation in their applications in an efficient and portable
  manner.\n\nPre-requisites\n\nAttendees must be familiar with programming 
 in C or C++ (a number of the baseline CUDA exercises are also available us
 ing CUDA Fortran). Some knowledge of parallel/threaded programming models 
 would be useful. Access to a GPU machine will be supplied.\n\nNote: this c
 ourse will not address machine learning or any machine learning frameworks
 .\nhttps://events.prace-ri.eu/event/1085/
SUMMARY:GPU Programming with CUDA @ EPCC Online
URL;VALUE=URI:https://events.prace-ri.eu/event/1085/
END:VEVENT
END:VCALENDAR