Numerical Parallel Processing Based on GPU with CUDA Architecture
Coll. of Comput. Sci. & Technol., Wuhan Univ. of Technol., Wuhan, China
International Conference on Wireless Networks and Information Systems, 2009. WNIS ’09
@inproceedings{zou2009numerical,
title={Numerical Parallel Processing Based on GPU with CUDA Architecture},
author={Zou, C. and Xia, C. and Zhao, G.},
booktitle={Wireless Networks and Information Systems, 2009. WNIS’09. International Conference on},
pages={93–96},
year={2009},
organization={IEEE}
}
The characteristics of modern graphics processing unit (GPU) is programmable, high price / performance ratio and high speed. It has a strong ability to adapt the parallel calculation, Based on this, the article study the general method of GPU calculating and use compute unified device architecture (CUDA) to design new parallel algorithm to accelerate the matrix inversion and binarization algorithm. The results show that with the increase of matrix dimension, GPU performs much better than CPU in increase multiple.
July 9, 2011 by hgpu
