Pittsburgh Supercomputing Center 

Advancing the state-of-the-art in high-performance computing,
communications and data analytics.

OpenACC GPU Programming Workshop

January 15 & 16, 2013

The Pittsburgh Supercomputing Center, the National Institute for Computational Sciences and Georgia Tech will present an OpenACC GPU programming workshop on January 15 and 16, 2013.

Based on demand, we will present this workshop at several satellite sites.  This workshop is NOT available via a webcast.

OpenACC is the accepted standard using compiler directives to allow quick development of GPU capable codes using standard languages and compilers. It has been used with great success to accelerate real applications within very short development periods. This workshop assumes knowledge of either C or Fortran programming. It will have a hands-on component using Keeneland, an XSEDE resource deployed at the National Institute for Computational Sciences. Keeneland is the NSF's premier GPU resource.

You may attend at any of the following sites. Register by following the link for your preferred location. Please note that the hands-on accounts will be limited to 100 students, available across all sites and awarded by order of registration.

The tentative agenda given below is subject to change. It is designed as two short days to be time-zone friendly.

Please address any questions to Tom Maiden at This email address is being protected from spambots. You need JavaScript enabled to view it.

Getting Help

NVIDIA recommends these sources for additional help:

  • NVIDIA forums – devtalk.nvidia.com or nvidia.com/cudazone
    • Great place for active discussions on NVIDIA GPUs and CUDA
    • Actively monitored by many NVIDIA engineers
  • stackoverflow.com
    • Look at the ‘cuda’ and ‘openacc’ tags
    • Over 3000+ already answered CUDA and OpenACC questions
    • Actively monitored by many NVIDIA engineers
  • CUDA Documenation – docs.nvidia.com
  • PGI - pgroup.com
  • Openacc spec: openacc.org

Tentative Agenda

Tuesday, January 15
All times given are EST
11:00 Welcome
11:15 Overview of Parallel Computing
12:15 Computing Environment
1:00 Lunch break
2:00 Introduction To OpenACC
3:30 Exercises (download zip file)
4:30 Using OpenACC with CUDA libraries
5:00 Adjourn/Exercises
Wednesday January 16
All times given are EST
11:00 GPU Parallel Execution Model and Architecture
12:00 Performance Profiling/Tuning
1:00 Lunch break
2:00 Advanced OpenACC Features
3:00 OpenACC On Complicated Loops: Case Studies
5:00 Adjourn


XSEDE, the Extreme Science and Engineering Discovery Environment, is the most advanced, powerful, and robust collection of integrated digital resources and services in the world. It is a single virtual system that scientists and researchers can use to interactively share computing resources, data, and expertise. XSEDE integrates the resources and services, makes them easier to use, and helps more people use them.