Darwin: a neuromorphic hardware co-processor based on Spiking Neural Networks

Abstract

Broadly speaking, the goal of neuromorphic engineering is to build computer systems that mimic the brain. Spiking Neural Network (SNN) is a type of biologically-inspired neural networks that perform information processing based on discrete-time spikes, different from traditional Artificial Neural Network (ANN). Hardware implementation of SNNs is necessary for achieving high-performance and low-power. We present the Darwin Neural Processing Unit (NPU), a neuromorphic hardware co-processor based on SNN implemented with digitallogic, supporting a maximum of 2048 neurons, 2048² = 4194304 synapses, and 15 possible synaptic delays. The Darwin NPU was fabricated by standard 180 nm CMOS technology with an area size of 5 ×5 mm² and 70 MHz clock frequency at the worst case. It consumes 0.84 mW/MHz with 1.8 V power supply for typical applications. Two prototype applications are used to demonstrate the performance and efficiency of the hardware implementation.

创新点

脉冲神经网络(SNN)是一种基于离散神经脉冲进行信息处理的人工神经网络。本文提出的“达尔文”芯片是一款基于SNN的类脑硬件协处理器。它支持神经网络拓扑结构,神经元与突触各种参数的灵活配置,最多可支持2048个神经元,四百万个神经突触及15个不同的突触延迟。该芯片采用180纳米CMOS工艺制造,面积为5x5平方毫米,最坏工作频率达到70MHz,1.8V供电下典型应用功耗为0.84mW/MHz。基于该芯片实现了两个应用案例,包括手写数字识别和运动想象脑电信号分类。