Computational Modelling Group

Workshop  22nd July 2013 9 a.m.  Engineering Science Department, Thom building, University of Oxford, Oxford. UK

CUDA Programming on NVIDIA GPUs

Mike Giles
University of Oxford

Web page
http://people.maths.ox.ac.uk/gilesm/cuda/
Categories
C, C++, CUDA, Emerald, GPU, GPU-libs, Linux
Submitter
Jess Jones

Description

This is a 5-day hands-on course for students, postdocs, academics and others who want to learn how to develop applications to run on NVidia GPUs using the CUDA programming environment. All that will be assumed is some proficiency with C and basic C++ programming. No prior experience with parallel computing will be assumed.

The course consists of approximately 3 hours of lectures and 4 hours of practicals each day. The aim is that by the end of the course you will be able to write relatively simple programs and will be confident and able to continue learning through studying the examples provided by NVidia as part of their SDK (software development kit).

Costs

Registration for this course is open now. Costs for the course will be as follows:

  • £100 for those from Oxford University and other members of the e-Infrastructure South consortium (Bristol, Southampton, STFC and UCL)
  • £200 for those from other UK universities
  • £500 for those from other government labs, not-for-profit organisations, and foreign universities
  • £2000 for those from industry (this will include lunch each day)

This course is being run under several banners:

  • for users of the Emerald supercomputer owned jointly by the e-Infrastructure South consortium and STFC
  • for all CCP members, as part of the ASEArch CCP on Algorithms and Software for Emerging Architectures
  • for UK HPC students, as part of the EPSRC Coordinated HPC Training Centre; EPSRC-supported PhD students may be able to get assistance with their travel and accommodation costs from this

Accommodation

Those attending the course must arrange their own accommodation. Please see the website for suggestions and further information, as well as registration.

Preparation

Please bring a printed copy of the NVIDIA CUDA C Programming Guide and have read chapters 1 and 2.

CUDA is an extension of C/C++, so if you are a little rusty with C/C++ you should refresh your memory of it.