Journal of Frontiers of Computer Science and Technology ›› 2021, Vol. 15 ›› Issue (11): 2105-2115.DOI: 10.3778/j.issn.1673-9418.2105050

• Brain-Like Computing • Previous Articles     Next Articles

Hardware Architecture of Stochastic Computing Neural Network

CHEN Yuhao, SONG Yinjie, ZHU Yanan, GAO Yunfei, LI Hongge   

  1. College of Electronic Information Engineering, Beihang University, Beijing 100191, China
  • Online:2021-11-01 Published:2021-11-09

概率计算神经网络硬件架构

陈宇昊宋印杰祝亚楠高云飞李洪革   

  1. 北京航空航天大学 电子信息工程学院,北京 100191

Abstract:

Stochastic computing is a kind of logic calculation that converts binary into probabilistic coded digital pulse stream. At the cost of computing power and time delay, it has the computing advantages of low power consumption and high energy efficiency. In this paper, the basic concept of stochastic computing is explained, and a stochastic computing circuit with single-channel or multi-channel is designed to improve the speed and accuracy. Based on the stochastic computing circuit, the stochastic pulse neuron is designed, and the reconfigurable computing architecture of neural network, BUAA-ChouSuan, is realized. The design is implemented with KINTEX-7 (FPGA), the logic resource (lookup table, LUT) of stochastic MAC (multiply accumulate) is 80% lower than that of traditional MAC. In SCNN (stochastic convolutional neural network) experiment, LeNet and AlexNet are tested. Under the condition of 350 MHz clock frequency, the average energy efficiency can reach 0.536 TSOPS/W, and the utilization rate of processing unit (PE) can reach more than 90%.

Key words: stochastic computing, spiking neural network, low power consumption, brain like chip

摘要:

概率计算(逻辑)是一种将二进制转换为概率编码的数字脉冲码流的逻辑计算,以计算精度与时延为代价,具有低功耗、高能效的计算优势。阐释了概率计算的基本概念,设计了单通道与多通道的概率计算电路,有效提高了概率计算的速度与精度。基于所提出概率计算电路,设计了概率脉冲神经元,从而实现了神经网络的可重构计算架构——北航筹算。该设计采用KINTEX-7(FPGA)实现,相较于传统二进制阵列乘法器构成的乘加器计算单元,概率计算的逻辑资源开销(LUT)降低80%。在SCNN网络计算实验中,测试运行了LeNet与AlexNet,时钟频率350 MHz条件下,均值能效可达0.536 TSOPS/W,PE利用率可达90%以上。

关键词: 概率计算, 脉冲神经网络, 低功耗, 类脑芯片