Nvidia has added new sessions to the agenda of the GPU Technology Conference. If you attend this conference, and I am seriously thinking about doing so, then you will be able to interface with scientists, researchers and visualization experts who use GPGPU in their work and research.
One of the people I would like to meet is Mark Cheung. He is using GPUs to analyze the large amount of data coming off the Solar Dynamics Observatory, which we have covered here at VizWorld. The following is the abstract from his talk that he will be giving at the GPU Technology Conference.
Learn how GPU computing is enabling astrophysicists in the study of our closest star. NASA’s recently launched Solar Dynamics Observatory is continuously streaming full-disk images of the Sun at visible, UV and EUV wavelengths. The data rate from the telescopes onboard the Atmospheric Imaging Assembly (AIA) and the Helioseismic and Magnetic Imager (HMI) instruments, each delivering a 16-megapixel image every few seconds, amounts to 1.5 TB per day. This presentation will discuss ways that GPU computing is helping scientists cope with the analysis of such immense data volumes as well as in numerical modeling of the Sun.
Another talk that I am very interested in will be given by Dale Southard. He will be talking about the second fastest High Performance Computer on the planet. The Chinese supercomputer, called Nebulae, is built with Intel X5650 processors and NVidia Tesla C2050 GPUs. When you look at the peak performance of Nebulae, it is the fastest system in the world. Its theoretical peak performance is 2.98 PFlop/s. However, when you use Linpack, the performance comes in at 1.271 PFlop/s which gives it the number 2 position.
Learn what to expect when deploying PetaFLOP or larger systems. The June 2010 list of the Top 500 computer systems featured the first GPU based cluster to exceed 1 PetaFLOP of foating point power — a system that was built in a fraction of the time and cost a CPU-only system of that performance would have required. An overview of how system builders and administrators should prepare for large-scale HPC deployments.
