An Interchip Communication Method Suitable for Neuromorphic Chips by Detecting Data Stability

Jiaxu Cong

doi:10.1109/LES.2025.3562862

2026-02-01

PRE

DOI：10.1109/LES.2025.3562862

原文链接

原文求助

摘要

En 中文

神经形态计算中脉冲生成的稀疏性使异步通信在处理稀疏芯片间传输方面比串行器/解串器（SerDes）更具固有优势。然而，传统异步方法通常由于数据编码方案而需要比数据位宽更多的连线。本文介绍了一种新型方法，即数据稳定收发器（D2SRT），用于神经形态芯片的芯片间通信。通过检测数据稳定性，D2SRT实现了低功耗和高性能，单比特能耗为13.9 pJ，吞吐量为217.2 Mb/s，超越了传统方法。实验结果表明，D2SRT满足了大多数脉冲神经网络（SNN）的带宽需求，并实现了极低的动态功耗。

Keyword:

Delays

Circuit stability

Clocks

Asynchronous circuits

Neuromorphics

Wires

Encoding

Receivers

Testing

Registers

completion-detection

data stability detection

interchip communication

low power consumption

neuromorphic chips

期刊

IEEE Embedded Systems Letters

IF:

论文数:

101

被引数:

696

机构

university of chinese academy of sciences, cas

学者数:

4.1W

论文数: 3.8W

被引数: 75

chinese academy of sciences

学者数:

56.7W

论文数: 45.0W

被引数: 704

引用论文

Delay-insensitive, point-to-point interconnect using m-of-n codes 延迟不敏感的点对点互连，采用m-of-n码

Ninth International Symposium on Asynchronous Circuits and Systems, 2003. Proceedings.

IF0

2024-10-29

PREAI

W.J. Bainbridge; W.B. Toms; D.A. Edwards; S.B. Furber

Design and FPGA-implementation of Asynchronous Circuits Using Two-Phase Handshaking 基于双相握手协议的异步电路设计与FPGA实现

2019 25th IEEE International Symposium on Asynchronous Circuits and Systems (ASYNC)

IF0

2019-05-01

PREAI

Adrian Mardari; Zuzana Jelcicova; Jens Sparso

NeuronLink: An Efficient Chip-to-Chip Interconnect for Large-Scale Neural Network Accelerators NeuronLink：一种用于大规模神经网络加速器的芯片间高效互连

IEEE Transactions on Very Large Scale Integration (VLSI) Systems

IF0

2020-09-01

PREAI

Shanlin Xiao; Yuhao Guo; Wenkang Liao; Huipeng Deng; Yi Luo; Huanliang Zheng; Jian Wang; Cheng Li; Gezi Li; Zhiyi Yu

Firing Frequency Maxima of Fast-Spiking Neurons in Human, Monkey, and Mouse Neocortex

FRONTIERS IN CELLULAR NEUROSCIENCE

IF4

2016-10-18

OAAI

Wang, Bo; Ke, Wei; Guang, Jing; Chen, Guang; Yin, Luping; Deng, Suixin; He, Quansheng; Liu, Yaping; He, Ting; Zheng, Rui; Jiang, Yanbo; Zhang, Xiaoxue; Li, Tianfu; Luan, Guoming; Lu, Haidong D.; Zhang, Mingsha; Zhang, Xiaohui; Shu, Yousheng

Investigation of asynchronous pipeline circuits based on bundled-data encoding: Implementation styles, behavioral modeling, and timing analysis

TSINGHUA SCIENCE AND TECHNOLOGY

IF3.5

2022-06-01

OAAI

Zhou, Yu

MOUSETRAP: High-Speed Transition-Signaling Asynchronous Pipelines

IEEE Transactions on Very Large Scale Integration (VLSI) Systems

IF0

2007-06-01

OAAI

M. Singh; S.M. Nowick

TrueNorth: Design and Tool Flow of a 65 mW 1 Million Neuron Programmable Neurosynaptic Chip TrueNorth：一种功耗为65 mW、包含100万个神经元的可编程神经突触芯片的设计与工具流程

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems

IF0

2015-10-01

PREAI

Filipp Akopyan; Jun Sawada; Andrew Cassidy; Rodrigo Alvarez-Icaza; John Arthur; Paul Merolla; Nabil Imam; Yutaka Nakamura; Pallab Datta; Gi-Joon Nam; Brian Taba; Michael Beakes; Bernard Brezzo; Jente B. Kuang; Rajit Manohar; William P. Risk; Bryan Jackson; Dharmendra S. Modha

The computational power of the human brain 人脑的计算能力

FRONTIERS IN CELLULAR NEUROSCIENCE

IF4

2023-08-07

OAAI

Gebicke-Haerter, Peter J.

Point to point GALS interconnect

Proceedings Eighth International Symposium on Asynchronous Circuits and Systems

IF0

2024-10-23

OAAI

S. Moore; G. Taylor; R. Mullins; P. Robinson

Towards artificial general intelligence with hybrid Tianjic chip architecture 基于混合Tianjic芯片架构的人工通用智能

Nature

IF0

2019-07-31

PREAI

Jing Pei; Lei Deng; Sen Song; Mingguo Zhao; Youhui Zhang; Shuang Wu; Guanrui Wang; Zhe Zou; Zhenzhi Wu; Wei He; Feng Chen; Ning Deng; Si Wu; Yu Wang; Yujie Wu; Zheyu Yang; Cheng Ma; Guoqi Li; Wentao Han; Huanglong Li; Huaqiang Wu; Rong Zhao; Yuan Xie; Luping Shi

查看更多内容