Target audience:

staff members, who want to use GPU systems

Contents:

Today's computers are commonly equipped with multicore processors and graphics processing units. To make efficient use of these massively parallel compute resources advanced knowledge of architecture and programming models is indispensable. This course builds on the introduction to

. It focuses on finding and eliminating bottlenecks using profiling and advanced programming techniques, optimal usage of CPUs and GPUs on a single node, and multi-GPU programming across multiple nodes.

The material will be presented in the form of short lectures followed by in-depth hands-on sessions.

Prerequisites:

Basic knowledge about GPU programming

Language:

This course is given in English.

Duration:

2 days

Date:

5- 6 May 2014, 9:00-16:30

Venue:

Jülich Supercomputing Centre, Ausbildungsraum 1, building 16.3, room 021

Number of participants:

maximum 25

Instructors:

Dr. Jan Meinke, Jochen Kreutz, Peter Philippen, Willi Homberg, Dr. Andrej V. Adinets, Dr. Wolfram Schenck, JSC;

Jiri Kraus, NVIDIA

Contact:

Willi Homberg

Registration:

Please register with Willi Homberg

until 1 May 2014