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.

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.

The first 100 registrants will receive a Keeneland hands-on account. This registration page is indicating that you wish to attend this workshop in person at Clemson. If you wish to attend at another site, please visit the Web URL for additional information and choose another site.

There is no Webcast available for this event.

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 tmaiden@psc.edu

XSEDE OpenACC GPU Programming Workshop Agenda

Tuesday January 15
All times are given are EST
1100 Welcome
1115 Overview of Parallel Computing
1215 Computing Environment
1300 Lunch Break
1400 Intro To OpenACC
1530 Exercises
1630 Using OpenACC with CUDA libraries
1700 Adjourn/Exercises

Wednesday January 17
All times are given are EST
1100 GPU Parallel Execution Model and Architecture
1200 Performance Profiling/Tuning
1300 Lunch Break
1400 Advanced OpenACC Features
1500 OpenACC On Complicated Loops: Case Studies
1700 Adjourn