Event Detail

Registration

Sorry, the registration period for this event is over.

Programming for GPUs: Introduction to OpenACC 2.0 & CUDA 5.5 - December 4-6, 2013

 

CSCS is pleased to announce 3-day training course on GPU programming. Experts from Cray and NVIDIA, together with CSCS staff will teach participants the basics of programming in the latest versions of OpenACC and CUDA, together with tools for code debugging and parallel performance analysis.

The course will involve practical training and tutorials therefore participants should bring their laptops. They are encouraged, moreover, to bring their own codes.

Registration deadline: November 27, 2013.

Please contact Themis Athanassiadou (themis.athanassiadou(at)cscs.ch) or Sadaf Alam (sadaf.alam(at)cscs.ch) for further technical informations.

Instructors

Alistair Hart, Cray; Peter Messmer, NVIDIA and CSCS own staff.

VenueCSCS, Via Trevano 131, Lugano     http://www.cscs.ch/about/visitor_Information/index.html
Time
Day 1: 09:00 - 17:30; Day 2:  09:00 - 17:30; Day 3: 09:00 - 16:30
Prerequisites

You will need to bring a laptop computer with the capability of ssh access to CSCS machines and the ability to display output from applications using the X11 window system.

Maximum number of participants 

30
Minimal number of participantsIf the minimal number of participants is not reached we reserve the right to cancel the course. You will be informed two weeks in advance.
Accommodation
Participants are kindly requested to make their own arrangements for accommodation.

*** 

Tentative Agenda:

OpenACC:

  •   OpenACC introduction and roadmap
  •   Programming exercises using the Cray OpenACC Compiler
  •   Code development, debugging and performance analysis tools (OpenACC)

Cuda:

  •   CUDA introduction and roadmap
  •   New and improved features in CUDA 6
  •   CUDA 5.5 programming exercises
  •   Code development, debugging and performance analysis tools (CUDA)
  •   CUDA and OpenACC interoperability 

3rd party Tools:

  •   DDT (debugging)
  •   Vampir (performance analysis)

Participants developing GPU code are encouraged to bring their code, as there will be some time devoted to Q&A / help session with the instructors.


Back to listing