Analysis of GPU Parallel Computing based on Matlab
School of Computer and Control Engineering, University of Chinese Academy of Sciences, Huairou, Beijing 101408, China
arXiv:1505.06561 [cs.DC], (25 May 2015)
@article{wang2015analysis,
title={Analysis of GPU Parallel Computing based on Matlab},
author={Wang, Mingzhe and Wang, Bo and He, Qiu and Liu, Xiuxiu and Zhu, Kunshuai},
year={2015},
month={may},
archivePrefix={"arXiv"},
primaryClass={cs.DC}
}
Matlab is very widely used in scientific computing, but Matlab computational efficiency is lower than C language program. In order to improve the computing speed, some toolbox can use GPU to accelerate the computation. This paper describes GPU working principle, our experiments and results analysis of parallel computing by using GPU based on Matlab. Experimental results show that for parallel operations, GPU computing speed is faster than CPU, for the logical instructions, GPU computing speed is slower than CPU.
May 28, 2015 by hgpu
