Browse > Article
http://dx.doi.org/10.7471/ikeee.2016.20.3.303

An Implementation of a Convolutional Accelerator based on a GPGPU for a Deep Learning  

Jeon, Hee-Kyeong (Dept. of Computer Engineering, Seokyeong University)
Lee, Kwang-yeob (Dept. of Computer Engineering, Seokyeong University)
Kim, Chi-yong (Dept. of Computer Science, Seokyeong University)
Publication Information
Journal of IKEEE / v.20, no.3, 2016 , pp. 303-306 More about this Journal
Abstract
In this paper, we propose a method to accelerate convolutional neural network by utilizing a GPGPU. Convolutional neural network is a sort of the neural network learning features of images. Convolutional neural network is suitable for the image processing required to learn a lot of data such as images. The convolutional layer of the conventional CNN required a large number of multiplications and it is difficult to operate in the real-time on the embedded environment. In this paper, we reduce the number of multiplications through Winograd convolution operation and perform parallel processing of the convolution by utilizing SIMT-based GPGPU. The experiment was conducted using ModelSim and TestDrive, and the experimental results showed that the processing time was improved by about 17%, compared to the conventional convolution.
Keywords
neural network; gpu; parallelism; convolutional neural network; image processing;
Citations & Related Records
연도 인용수 순위
  • Reference
1 David Silver, Aja Huang, Chris J. Maddison, Arthur Guez, et al., "Mastering the game of Go with deep neural networks and tree search," . Nature, 529, pp. 484-489, 28 January 2016.   DOI
2 http://smart.science.go.kr/scienceSubject/iot/view.action?menuCd=DOM_000000101001012000&subj ect_sid=1322
3 Shmuel Winograd, " Arithmetic complexity of computations," volume 33. Siam, 1980.
4 Lavin, Andrew. "Fast algorithms for convolutional neural networks." arXiv preprint arXiv:1509.09308 2015.
5 Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. "Imagenet classification with deep convolutional neural networks." Advances in neural information processing systems. 2012.
6 Agarwal, R., and J. Cooley. "New algorithms for digital convolution." IEEE Transactions on Acoustics, Speech, and Signal Processing 25.5 (1977): 392-410.   DOI
7 Yunseop Hwang, Kwang yeob Lee, Junmo Jeong, "Design of SIMT Architecture-based Reconfigurable Image Signal Processor," International conference on future information & communication engineering, 25 June 2015.
8 https://sourceforge.net/projects/test-drive/