UC San Diego

Hundreds of thousands of people die from heart attack in the U.S. every year. Cardiac dysrhythmia is known to be one of the most important causes for heart attack. Optical mapping is a tool for researching cardiac dysrhythmia and preventing heart attack. However, the optical mapping algorithm is computationally intensive and consumes a considerable amount of time. For example, 1 second of data requires 3.7 hours of computation. Therefore, a GPU implementation of the optical mapping algorithm is used in cardiac electrophysiology. The efficiency of different input sizes and memory access are studied to improve the GPU performance. The result shows that GPU implementation of the optical mapping algorithm has a 33X speedup over the equivalent CPU implementation