BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:GPU Programming Part 1: Foundations
DTSTART:20260324T080000Z
DTEND:20260326T153000Z
DTSTAMP:20260422T140500Z
UID:indico-event-223@events.hpc-portal.eu
CONTACT:j.meinke@fz-juelich.de
DESCRIPTION:GPU-accelerated computing drives current scientific research. 
 Writing fast numeric algorithms for GPUs offers high application performan
 ce by offloading compute-intensive portions of the code to a GPU.\nThis b
 asic course will cover aspects of GPU architectures and programming. Focu
 s is on the usage of the parallel programming language CUDA C++\, which al
 lows maximum control of NVIDIA GPU hardware. Examples of increasing comple
 xity are used to demonstrate the optimisation and tuning of scientific app
 lications.\nThe course covers the foundations of GPU programming including
  an introduction to GPU/parallel computing\, programming with CUDA\, GPU l
 ibraries\, tools for debugging and profiling\, and performance optimisatio
 ns:\nA) Introduction to GPUs and GPU computingB) Programming model CU
 DAC) Tools for debugging and profilingD) GPU libraries (like cuBLAS\,
  cuFFT)E) Introduction to multi-GPU programming\nNote: In addition to thi
 s basic course\, you can also register for the advanced course GPU Progra
 mming Part 2: Special and Advanced Topics. It provides more in-depth cove
 rage of multi-GPU programming\, modern CUDA concepts\, CUDA Fortran\, and 
 portable programming models such as OpenACC and C++ parallel STL algorithm
 s. The advanced course consists of five modules. Attendees are invited to
  pick and choose the modules they want to attend. The advanced modules are
  mostly freestanding.\nIn order to participate in the advanced course\, pa
 rticipants either need to attend the "GPU Programming Part 1: Foundations"
  course first or prove equivalent knowledge of GPU programming. The advan
 ced course will take place online from 29 June to 3 July 2026. Please visi
 t GPU Programming Part 2: Special and Advanced Topics for more informati
 on and to register.\nPrerequisites:\nSome knowledge about Linux\, e.g. mak
 e\, command line editor\, Linux shell\, experience in C/C++\nA personal in
 stitutional email address (university/research institution\, government ag
 ency\, organisation\, or company) is required to register for JSC training
  courses. If you don't have an institutional email address\, please get in
  touch with the contact person for this course.\nTarget Audience:\nScienti
 sts who want to use GPU systems\nLanguage:\nThis course is given in Englis
 h.\nDuration:\n3 days\nDates:\n24-26 March 2026\, 09:00-16:30 each day\nVe
 nue:\nJülich Supercomputing Centre\, building 16.3\, room 213a (Ausbildun
 gsraum 1)\nNumber of Participants:\nMaximum 26\nInstructors:\nJan Meinke\,
  Andreas Herten\, Kaveh Haghighi-Mood (JSC)Laura Morgenstern (NVIDIA)\n\nh
 ttps://events.hpc-portal.eu/event/223/
LOCATION:building 16.3\, room 213a (Jülich Supercomputing Centre)
URL:https://events.hpc-portal.eu/event/223/
END:VEVENT
END:VCALENDAR