high performance computing on graphics processing units: hgpu.org

Graphics processing units (GPUs), originally designed for computing and manipulating pixels, have become general-purpose processors capable of executing in excess of trillion calculations per second. Taking advantage of GPU’s compute power and commodity popularity, the field of computing systems is exhibiting a trend toward heterogeneous platforms consisting of a central processor integrated with graphics hardware. To leverage parallelism within graphics processors, programming approaches employing CUDA and more recent OpenCL framework are evaluated in the context of implementing a ballistic threat field calculation.