| Registration | nVidia Workshop |
|---|---|
|
Modern GPU Architecture: Beyond Graphics
|
|
|
Ten years ago, the graphics card in your PC was just a VGA controller. Since that time, it has evolved into a programmable Graphics Processing Unit (GPU) that can produce stunningly good visual effects. In addition to all this, the GPU has become a fully programmable data parallel computation engine capable of performing hundreds of billions of operations per second. Indeed, the GPU is already the most successful massively parallel computer in history. NVIDIA's CUDA environment enables programmers to harness this potential with relative ease, programming the GPU in a simple C-like language. In this talk, former UIUC professor Dr. Michael Garland will have a look at how GPU architecture has evolved, what a modern GPU looks like, and how to program one. |
|
|
About 
|
Michael Garland is a Research Scientist with the NVIDIA Corporation. Dr. Garland holds a Ph.D. in Computer Science from Carnegie Mellon University, and prior to joining NVIDIA was an assistant professor in the Department of Computer Science at the University of Illinois at Urbana-Champaign. Dr. Garland regularly serves on international program committees for conferences such as ACM SIGGRAPH and IEEE Visualization, and is the program co-chair for the 2007 Eurographics Symposium on Geometry Processing. He has published numerous articles in leading conferences and journals on a range of topics including mesh processing, geometric modeling, animation, data mining, and visualization. |
| Registration |
