BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260705T061802Z
UID:cc29ad9c-745c-4ffe-b711-9751daf7dc72
DTSTART:20220627T090000Z
DTEND:20220627T160000Z
DESCRIPTION:This short course will provide an introduction to GPU computing
  with CUDA aimed at scientific application programmers. The course will gi
 ve a background on the difference between CPU and GPU architectures as a p
 relude to introductory exercises in CUDA programming. The course will disc
 uss the execution of kernels\, memory management\, and shared memory opera
 tions. Common performance issues are discussed and their solution addresse
 d. The course will also cover some of the alternatives to CUDA commonly av
 ailable (OpenCL\, OpenACC\, and Kokkos) at the current time.\n\nNote: this
  course will not address machine learning or any machine learning framewor
 ks.\n\nLearning Outcomes\n\nAt the end of the course\, attendees should be
  in a position to make an informed decision on how to approach GPU paralle
 lisation 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 using CUDA Fortra
 n). Some knowledge of parallel/threaded programming models would be useful
 . Access to a GPU machine will be supplied.\n\nRequirements:\n\nParticipan
 ts must bring a laptop with a Mac\, Linux\, or Windows operating system (n
 ot a tablet\, Chromebook\, etc.) that they have administrative privileges 
 on.\n\nThey are also required to abide by the ARCHER2 Code of Conduct.\n\n
 Timetable:\n\nProvisional\n\n\n	10:00 Introduction\n	10:20 GPU Concepts/Ar
 chitectures\n	11:00 Break\n	11:20 CUDA Programming\n	12:00 A first CUDA ex
 ercise\n	13:00 Lunch\n	14:00 CUDA Optimisations\n	14:20 Optimisation Exerc
 ise\n	15:00 Break\n	15:20 Constant and Shared Memory\n	16:00 Exercise\n	17
 :00 Close\n\n\nLocation:\n\nThis course will take place face-to-face at Th
 e Open University\, Milton Keynes\n\nThis course will not be streamed onli
 ne and a recording will not be made.\nhttps://events.prace-ri.eu/event/140
 1/
SUMMARY:GPU Programming with CUDA @ EPCC at The OpenUniversity\, Milton Key
 nes
URL;VALUE=URI:https://events.prace-ri.eu/event/1401/
END:VEVENT
END:VCALENDAR