abstract = {Graphics processors can be easily programmed to provide significant acceleration in many common parallel tasks. However, with additional architecture knowledge and understanding of optimization strategies, a savvy programmer can unleash the full potential of the GPU's massive memory bandwidth and ensure the processing resources are utilized to their fullest extent. In this talk, we'll explore several different approaches to a very simple but ubiquitous image processing algorithm, the convolution. A naive approach shows the detrimental impact of poorly written code, a simple approach achieves decent results with little effort or code complexity, and a few highly optimized techniques realize the GPUs full power for the most demanding tasks. The techniques explored in this simple but illustrative example will serve as a base for understanding the optimization strategies to apply towards more complex algorithms.},
year = {2010},
abstract = {Graphics processors can be easily programmed to provide significant acceleration in many common parallel tasks. However, with additional architecture knowledge and understanding of optimization strategies, a savvy programmer can unleash the full potential of the GPU's massive memory bandwidth and ensure the processing resources are utilized to their fullest extent. In this talk, we'll explore several different approaches to a very simple but ubiquitous image processing algorithm, the convolution. A naive approach shows the detrimental impact of poorly written code, a simple approach achieves decent results with little effort or code complexity, and a few highly optimized techniques realize the GPUs full power for the most demanding tasks. The techniques explored in this simple but illustrative example will serve as a base for understanding the optimization strategies to apply towards more complex algorithms.},
year = {2010},
