基于异构平台的细胞神经网络算法研究

An Algorithm of CNN on the Heterogeneous Architecture

随着GPU的发展,其计算能力和访存带宽都超过了CPU,在GPU上进行通用计算具有成本低、性能高的特点。细胞神经网络由于其特有的性质,非常适合利用GPU进行并行计算,因此,该文提出了利用CU-DA实现的基于GPU的细胞神经网络异构算法,并应用在图像边缘检测上。实验结果证明,与传统的利用CPU实现的边缘检测方法相比,在速度上,基于GPU实现的图像边缘检测方法提高了数十倍,为细胞神经网络在实时图像、视频处理上的应用提供了新的方法。

As the rapid development of GPU technology,GPU has higher performance in computing ability and memory bandwidth than CPU.Due to the special characteristics of CNN,it is adapted to the parallel computing.Therefore,in this paper,we,introduce a heterogeneous algorithm of CNN based on GPU using CUDA and then realize this image edge detection.The result shows that image edge detection based on GPU has than the traditional method using CPU on the computing speed,which support a new method for CNN applied to the real time image and video processing.