Leveraging Parallelism with CUDA and OpenCL
U. S. Army Research Laboratory, APG, MD
The 2011 International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA’11), 2011
@article{park2011leveraging,
title={Leveraging Parallelism with CUDA and OpenCL},
author={Park, S. and Shires, D. and Ross, J. and Richie, D.},
year={2011}
}
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.
December 18, 2011 by hgpu
