Bit-width Adaptive Accelerator Design for Convolution Neural Network
Authors:
- 1 January 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
Convolutional neural networks (CNNs) have achieved great success in many applications. Recently, various FPGA-based accelerators have been proposed to improve the performance of CNNs. However, current most FPGA-based methods only use the same bit-width selection for all CNN layers which lead to very low resource utilization and difficulty in further performance improvement. In this paper, we propose a bit-width adaptive accelerator design approach which can adapt to the CNN layers with various bit-width requirements in a same network. We construct multiple different bit-width convolutional processors to compute the CNN layers in parallel way. We partition the FPGA DSP resources and use our optimization approach to find the optimal resource allocation. On a Xilinx Virtex-7 FPGA, our design approach achieves higher throughput than the state-of-the-art FPGA-based CNN accelerators from 5.48× to 7.25× and by 6.20× on average, when we evaluate the convolutional layers of AlexNet and deeper VGG CNNs.Keywords
This publication has 9 references indexed in Scilit:
- Stripes: Bit-serial deep neural network computing2016
- Overcoming resource underutilization in spatial CNN accelerators2016
- Deep Residual Learning for Image Recognition2016
- Going Deeper with Embedded FPGA Platform for Convolutional Neural Network2016
- Going deeper with convolutions2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Optimizing FPGA-based Accelerator Design for Deep Convolutional Neural Networks2015
- Large-Scale Video Classification with Convolutional Neural Networks2014
- A Multichannel Convolutional Neural Network for Hand Posture Recognition2014