Darwin3:a large-scale neuromorphic chip with a novel ISA and on-chip learning  

作　　者：De Ma Xiaofei Jin Shichun Sun Yitao Li Xundong Wu Youneng Hu Fangchao Yang Huajin Tang Xiaolei Zhu Peng Lin Gang Pan 

机构地区：[1]College of Computer Science and Technology,Zhejiang University,Hangzhou 310027,China [2]Research Center for Intelligent Computing Hardware,Zhejiang Lab,Hangzhou 311121,China [3]The State Key Lab of Brain-Machine Intelligence,Zhejiang University,Hangzhou 310027,China [4]MOE Frontier Science Center for Brain Science and Brain-machine Integration,Zhejiang University,Hangzhou 310027,China [5]College of Micro-Nano College of Micro-Nano Electronics,Zhejiang University,Hangzhou 311200,China

出　　处：《National Science Review》2024年第5期22-38,共17页国家科学评论（英文版）

基　　金：supported by theNational Key R&DPlan ofChina(2022YFB4500100);the National Natural Science Foundation of China(61925603,U20A20220 and 62076084);the Key Research Project of Zhejiang Lab(2021KC0AC01);the Key Research and Development Program of Zhejiang Province in China(2020C03004);the Key R&D Program of Zhejiang(2022C01048).

摘　　要：Spiking neural networks(SNNs)are gaining increasing attention for their biological plausibility and potential for improved computational efficiency.To match the high spatial-temporal dynamics in SNNs,neuromorphic chips are highly desired to execute SNNs in hardware-based neuron and synapse circuits directly.This paper presents a large-scale neuromorphic chip named Darwin3 with a novel instruction set architecture,which comprises 10 primary instructions and a few extended instructions.It supports flexible neuron model programming and local learning rule designs.The Darwin3 chip architecture is designed in a mesh of computing nodes with an innovative routing algorithm.We used a compression mechanism to represent synaptic connections,significantly reducing memory usage.The Darwin3 chip supports up to 2.35 million neurons,making it the largest of its kind on the neuron scale.The experimental results showed that the code density was improved by up to 28.3×in Darwin3,and that the neuron core fan-in and fan-out were improved by up to 4096×and 3072×by connection compression compared to the physical memory depth.Our Darwin3 chip also provided memory saving between 6.8×and 200.8×when mapping convolutional spiking neural networks onto the chip,demonstrating state-of-the-art performance in accuracy and latency compared to other neuromorphic chips.

关 键 词：neuromorphic computing spiking neural network instruction set architecture connectivity compression 

分 类 号：TN32[电子电信—物理电子学]