Presenter: Ian Buck, Stanford University
As the programmability and performance of modern GPUs continues to increase, many researchers are looking to graphics hardware to solve problems previously performed on general purpose CPUs. In many cases, performing general purpose computation on graphics hardware can provide a significant advantage over implementations on traditional CPUs. However, if GPUs are to become a powerful processing resource, it is important to establish the correct abstraction of the hardware. In my talk, I will present the benefits and limitations of computing on the GPU and outline the stream computing model. In addition, I will demonstrate Brook, a C-like programming platform which implements this programming model using the GPU.