卷积神经网络(CNN)算法的FPGA并行结构设计

王巍; 周凯利; 王伊昌; 王广; 杨正琳; 袁军

Chinese

您当前的位置：

首页 >

文章列表页 >

卷积神经网络(CNN)算法的FPGA并行结构设计

更新时间：2026-09-04

- 卷积神经网络(CNN)算法的FPGA并行结构设计
- FPGA Parallel Structure Design of Convolutional Neural Network (CNN) Algorithm
- 微电子学与计算机 2019年36卷第4期页码：57-62
- 作者机构：
  
  重庆邮电大学机构光电工程学院/国际半导体学院,重庆,400065
- 作者简介：
- 基金信息：
  
  国家自然科学基金 61404019重庆市基础与前沿研究计划项目 cstc2016jcyjA0272
- DOI：
  中图分类号：
- 纸质出版：2019
- 稿件说明：
移动端阅览
王巍, 周凯利, 王伊昌, 王广, 杨正琳, 袁军. 卷积神经网络(CNN)算法的FPGA并行结构设计[J]. 微电子学与计算机, 2019, 36(4): 57-62, 66.

WANG Wei, ZHOU Kai-li, WANG Yi-chang, et al. FPGA Parallel Structure Design of Convolutional Neural Network (CNN) Algorithm[J]. 2019, 36(4): 57-62.
王巍, 周凯利, 王伊昌, 王广, 杨正琳, 袁军. 卷积神经网络(CNN)算法的FPGA并行结构设计[J]. 微电子学与计算机, 2019, 36(4): 57-62, 66. DOI：

WANG Wei, ZHOU Kai-li, WANG Yi-chang, et al. FPGA Parallel Structure Design of Convolutional Neural Network (CNN) Algorithm[J]. 2019, 36(4): 57-62. DOI：

摘要

本文进行了CNN算法的FPGA并行结构设计.该设计首先利用CNN的并行计算特征以及循环变换方法

实现了可高效进行并行流水线的卷积计算电路

然后利用能够减少存储器访存时间的双缓存技术

在输入输出部分实现了缓存阵列

用于提高电路的计算性能(GOPS

每秒十亿次运算数).同时本文还对激活函数进行了优化设计

利用查找表和多项式结合的分段拟合方法设计了激活函数(sigmoid)的硬件电路

以保证近似的激活函数的硬件电路不会使精度下降.实验结果表明:输入时钟为150 MHz时

整体电路在计算性能上由15.87 GOPS提高到了20.62 GOPS

并在MNIST数据集上的识别率达到了98.81%.

Abstract

In this paper

the FPGA parallel structure design of CNN algorithm is carried out. The design first uses the parallel computing features of CNN and the cyclic transformation method to realize a convolution calculation circuit that can efficiently perform parallel pipelines. Then

using the double-buffer technology that can reduce the memory access time

a cache array is implemented in the input and output sections to improve the computational performance of the circuit (GOPS

one billion operations per second). At the same time

the activation function is optimized. The hardware circuit of the activation function (sigmoid) is designed by using the segmentation fitting method of lookup table and polynomial to ensure that the hardware circuit of the approximate activation function will not reduce the accuracy. The experimental results show that when the input clock is 150MHz

the overall performance of the circuit is improved from 15.87 GOPS to 20.62 GOPS

and the recognition rate on the MNIST data set reaches 98.81%.

关键词

Keywords

references

GHAFFARI S, SHARIFIAN S. FPGA-based convolutional neural network accelerator design using high level synthesize[C]// International Conference of Signal Processing and Intelligent Systems. IEEE, 2017: 1-6.

KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C]// International Conference on Neural Information Processing Systems. Curran Associates Inc. 2012: 1097-1105.

CHEN ZHANG, PENG LI, GUANGYU SUN, et al. Optimizing fpga-based accelerator design for deep convolutional neural networks[C]// in Proceedings of the 2015 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays. ACM, 2015: 161-170.

CHEN Y H, KRISHNA T, EMER J, et al. 14.5 Eyeriss: An energy-efficient reconfigurable accelerator for deep convolutional neural networks[C]// IEEE International Solid-State Circuits Conference. IEEE, 2016: 262-263.

FENG G, HU Z, CHEN S, et al. Energy-efficient and high-throughput FPGA-based accelerator for Convolutional Neural Networks[C]// IEEE International Conference on Solid-State and Integrated Circuit Technology. IEEE, 2017: 624-626.

ZHOU Y, JIANG J. An FPGA-based accelerator implementation for deep convolutional neural networks[C]// International Conference on Computer Science and Network Technology. IEEE, 2016: 829-832.

JIANG J, HU R, LUJAN M. A Flexible Memory Controller Supporting Deep Belief Networks with Fixed-Point Arithmetic[C]// Parallel and Distributed Processing Symposium Workshops % Phd Forum. IEEE, 2013: 144-152.

GOKHALE V, JIN J, DUNDAR A, et al. A 240 G-ops/s Mobile Coprocessor for Deep Neural Networks[C]// Computer Vision and Pattern Recognition Workshops. IEEE, 2014: 696-701.

FARABET C, POULET C, HAN J Y, et al. CNP: An FPGA-based processor for Convolutional Networks[C]// International Conference on Field Programmable Logic and Applications. IEEE, 2009: 32-37.

浏览量

121

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

注意力机制与改进密集卷积引导的信息隐藏模型

AlN/GaN混合缓冲层双异质结p-GaN HEMT直流特性仿真

一种用于极低压boost系统的高效率电荷泵

大模型发展综述：从BERT到Deepseek的技术演进

基于反向体偏置的高增益稳定性高温运放设计