The Power of Heterogeneous Computing
Abstract: In the past, graphics processors were special purpose hardwired application accelerators, suitable only for conventional rasterization-style graphics applications. Modern GPUs are now fully programmable, massively parallel floating point processors. This talk will describe how NVIDIA's massively multithreaded computing architecture and CUDA software for GPU computing have changed both graphics and computing. It's no longer news that GPUs can accelerate many applications and compute kernels 100x or more. The true importance of this change lies in what new science and applications will be enabled.