Exploiting GPUs for compute-intensive medical applications

Medical applications are compute and data intensive applications. The complex mathematical models and differential equations in the medical domain require huge computations. Cardiac simulation is one example of such compute-intensive application. In this work, we present an evaluation study for porting the cardiac simulator to the high performance GPUs accelerators. We also conducted a comparative evaluation for using conventional computing platforms: a single CPU and a CPU Cluster system. Our study shows that tremendous speed-up gain can be achieved using GPU-based system over cluster-based system or single CPU systems.