NVIDIA and SINTEF HPC GPU Computing Mini-Workshop

Heterogeneous Computing

We want to thank all of you that attended the NVIDIA and SINTEF mini-workshop 2009, and want to offer a special thanks to all participants of the mingeling session where new and innovative ideas and cooperation projects were discussed. Together with Chris Butler and Timothy Lanfear from NVIDIA's Tesla department, SINTEF Applied Mathematics presented the state of the art in GPU computing. More than 40 participants from Norwegian industri and academic institutions registered to learn more about how to improce their products by GPU Computing.

The mini-workshop focused on:

Why have heterogeneous architectures become increasingly attractive?
How does GPUs differ from traditional symmetric CPUs?
What software tools and what level of developer support exist?
What kind of problems map well to GPU computing?
Challenges of GPU computing, trivial patterns easily become non-trivial.
Experiences and case studies from SINTEF and NVIDIA.

Program

Chair: Christopher Dyken

12:30 Introduction and welcoming
Trond Runar Hagen, SINTEF ICT

12:45 The State of the Art in GPU Computing
Jon Hjelmervik, SINTEF ICT

13:45 The NVIDIA Tesla GPU Compute Platform:
Hardware, Software Developer Tools, and Support
Timothy Lanfear, NVIDIA

14:30 Coffee, discussions, and mingling

Published November 17, 2009