Optimal Alignment of Three Sequences On A GPU
Department of Computer and Information Science and Engineering, University of Florida, Gainesville, FL 32611, USA
International Conference on Bioinformatics and Computational Biology (BICoB), 2014
@article{li2014optimal,
title={Optimal Alignment of Three Sequences On A GPU},
author={Li, Junjie and Ranka, Sanjay and Sahni, Sartaj},
year={2014}
}
We develop two algorithms-layered and sloped-to align three sequences on a GPU. Our algorithms can be used to determine the alignment score as well as the actual alignment. Experiments conducted using an NVIDIA C2050 GPU show that our sloped algorithm is 3 times as fast as the layered one. Further, the sloped algorithm delivers a speedup of up to 90 relative to the single core algorithm running on our host CPU when determining the score of the best alignment and a speedup between 21 and 56 when computing the best alignment as well as its score.
January 14, 2014 by hgpu
