A Brain-Inspired Network-on-Chip Architecture with Hybrid-Mode Routing

Wang Zhichao; Chen Liang; Li Qianpeng; Chen Aoxin; Liu Xin; Song Wenna

doi:10.7544/issn1000-1239.202440683

Journal of Computer Research and Development > 2025 > Uncorrected proof > DOI: 10.7544/issn1000-1239.202440683 CSTR: 32373.14.issn1000-1239.202440683

Wang Zhichao, Chen Liang, Li Qianpeng, Chen Aoxin, Liu Xin, Song Wenna. A Brain-Inspired Network-on-Chip Architecture with Hybrid-Mode Routing[J]. Journal of Computer Research and Development. DOI: 10.7544/issn1000-1239.202440683

Citation:

PDF (1807 KB)

A Brain-Inspired Network-on-Chip Architecture with Hybrid-Mode Routing

Wang Zhichao^{1, 2,},
Chen Liang^1, ,,
Li Qianpeng^{1, 2,},
Chen Aoxin^{1, 2,},
Liu Xin^1,,
Song Wenna^1,

1.
Institute of Automation, Chinese Academy of Sciences, Beijing 100190
2.
School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049

Funds: This work was supported in part by the National Key Research and Development Program of China under STI 2030——Major Projects (2021ZD0200300).

More Information

Author Bio:
Wang Zhichao: born in 2000. Master candidate. His main research interests include neuromorphic computing and network-on-chip design

Chen Liang: born in 1977. Master, associate professor, master’s supervisor. Member of CCF. His main research interests include computer architecture, integrated circuit design and brain-inspired computing

Li Qianpeng: born in 1999. Master. His main research interests include brain-inspired computing and brain-inspired processor. (liqianpeng2021@ia.ac.cn)

Chen Aoxin: born in 2000. Master candidate. His main research interests include artificial intelligence and algorithm deployment optimization. (chenaoxin2022@ia.ac.cn )

Liu Xin: born in 1995. Master, engineer. Her main research interests include integrated circuit design and computer architecture. (liuxin@ia.ac.cn)

Song Wenna: born in 1989. Master, engineer. Her main research interests include System architecture and digital circuit design. (wenna.song@ia.ac.cn)
Received Date: August 12, 2024
Revised Date: March 18, 2025
Accepted Date: April 02, 2025
Available Online: April 02, 2025

Graphical Abstract

Abstract

Abstract

The rise and development of large-scale neuromorphic platforms require network-on-chip to support efficient data transmission mechanisms. Although many efforts have been made to develop high performance topology architectures and routing schemes, they still suffer from single transmission mode or poor scalability, making them stay on a low efficiency in neuromorphic computing. Inspired by the small-world properties of human brain networks, this brief proposes an efficient region-broadcast (ReB) routing scheme to support unicast, multicast, and broadcast transmission modes. Besides, a synaptic connections indexing method is deployed to accommodate the region-broadcast routing scheme and support this hybrid-mode packet transmission. This method replaces the traditional multicast routing table, effectively improving network scalability and reducing power consumption. Experimental results show that compared to existing work, the ReB routing scheme reduces the peak spike traffic and link load standard deviation by 11.5% and 20.4%, respectively. The ReB scheme brings improvements in latency, throughput, and energy under the validation of synthetic traffic, spiking neural network applications and brain cortical networks. Various synthetic traffic patterns are used in the experiments. The datasets used in spiking neural network applications include MNIST, QTDB, Ev-object, and DVS-Gesture. Finally, the proposed ReB router has an excellent bandwidth of 0.24 spike/cycle and only consumes an area of 0.014 mm².
- network-on-chip (NoC),
- brain-inspired,
- routing scheme,
- hybrid-mode router,
- synaptic connections indexing

FullText(HTML)

References (32)

References

[1]	Lent R, Azevedo F A C, Andrade-Moraes C H, et al. How many neurons do you have? Some dogmas of quantitative neuroscience under revision[J]. European Journal of Neuroscience, 2012, 35(1): 1−9
[2]	Bullmore E, Sporns O. The economy of brain network organization[J]. Nature Reviews Neuroscience, 2012, 13(5): 336−349
[3]	Capra M, Bussolino B, Marchisio A, et al. Hardware and software optimizations for accelerating deep neural networks: Survey of current trends, challenges, and the road ahead[J]. IEEE Access, 2020, 8: 225134−225180
[4]	Rathi N, Chakraborty I, Kosta A, et al. Exploring neuromorphic computing based on spiking neural networks: Algorithms to hardware[J]. ACM Computing Surveys, 2023, 55(12): 1−49
[5]	Wu Jibin, Xu Chenglin, Han Xiao, et al. Progressive tandem learning for pattern recognition with deep spiking neural networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 44(11): 7824−7840
[6]	Kumarasinghe K, Kasabov N, Taylor D. Brain-inspired spiking neural networks for decoding and understanding muscle activity and kinematics from electroencephalography signals during hand movements[J]. Scientific Reports, 2021, 11(1): 2486−2486
[7]	Ananthanarayanan R, Esser S K, Simon H D, et al. The cat is out of the bag: Cortical simulations with 109 neurons, 1013 synapses[C/OL]//Proc of the Conf on High Performance Computing Networking, Storage and Analysis. New York: ACM, 2009[2025-01-21]. https://dl.acm.org/doi/abs/10.1145/1654059.1654124
[8]	Furber S B, Galluppi F, Temple S, et al. The spinnaker project[J]. Proceedings of the IEEE, 2014, 102(5): 652−665
[9]	Vainbrand D, Ginosar R. Scalable network-on-chip architecture for configurable neural networks[J]. Microprocessors and Microsystems, 2011, 35(2): 152−166
[10]	Kauth K, Stadtmann T, Brandhofer R, et al. Communication architecture enabling 100x accelerated simulation of biological neural networks[C/OL]//Proc of the Workshop on System-Level Interconnect: Problems and Pathfinding Workshop. New York: ACM, 2020[2025-01-21]. https://dl.acm.org/doi/abs/10.1145/3414622.3431909
[11]	Akopyan F, Sawada J, Cassidy A, et al. Truenorth: Design and tool flow of a 65 mw 1 million neuron programmable neurosynaptic chip[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2015, 34(10): 1537−1557
[12]	Davies M, Srinivasa N, Lin T H, et al. Loihi: A neuromorphic manycore processor with on-chip learning[J]. IEEE Micro, 2018, 38(1): 82−99
[13]	Pei Jing, Deng Lei, Song Sen, et al. Towards artificial general intelligence with hybrid Tianjic chip architecture[J]. Nature, 2019, 572(7767): 106−111 doi: 10.1038/s41586-019-1424-8
[14]	Yazdanpanah F. A two-level network-on-chip architecture with multicast support[J]. Journal of Parallel and Distributed Computing, 2023, 172: 114−130 doi: 10.1016/j.jpdc.2022.10.011
[15]	Pu J, Goh W L, Nambiar V P, et al. A low power and low area router with congestion-aware routing algorithm for spiking neural network hardware implementations[J]. IEEE Transactions on Circuits and Systems II: Express Briefs, 2020, 68(1): 471−475
[16]	Ding Chen, Huan Yuxiang, Jia Hao, et al. A hybrid-mode on-chip router for the large-scale FPGA-based neuromorphic platform[J]. IEEE Transactions on Circuits and Systems I: Regular Papers, 2022, 69(5): 1990−2001 doi: 10.1109/TCSI.2022.3145016
[17]	Vu T H, Abdallah A B. Low-latency K-means based multicast routing algorithm and architecture for three dimensional spiking neuromorphic chips[C/OL]//Proc of the 2019 IEEE Int Conf on Big Data and Smart Computing (BigComp). Piscataway, NJ: IEEE, 2019[2025-01-21]. https://ieeexplore.ieee.org/abstract/document/8679363/
[18]	Navaridas J, Luján M, Plana L A, et al. SpiNNaker: Enhanced multicast routing[J]. Parallel Computing, 2015, 45: 49−66 doi: 10.1016/j.parco.2015.01.002
[19]	Latora V, Marchiori M. Efficient behavior of small-world networks[J]. Physical Review Letters, 2001, 87(19): 198701 doi: 10.1103/PhysRevLett.87.198701
[20]	Seguin C, Sporns O, Zalesky A. Brain network communication: Concepts, models and applications[J]. Nature Reviews Neuroscience, 2023, 24(9): 557−574 doi: 10.1038/s41583-023-00718-5
[21]	Benjamin B V, Gao P, McQuinn E, et al. Neurogrid: A mixed-analog-digital multichip system for large-scale neural simulations[J]. Proceedings of the IEEE, 2014, 102(5): 699−716 doi: 10.1109/JPROC.2014.2313565
[22]	Furber S B, Lester D R, Plana L A, et al. Overview of the SpiNNaker system architecture[J]. IEEE Transactions on Computers, 2012, 62(12): 2454−2467
[23]	Akbari N, Modarressi M. A high-performance network-on-chip topology for neuromorphic architectures[C]//Proc of the 2017 IEEE Int Conf on Computational Science and Engineering (CSE) and IEEE Int Conf on Embedded and Ubiquitous Computing (EUC). Piscataway, NJ: IEEE, 2017: 9−16
[24]	杨智杰,王蕾,石伟,等. 类脑处理器异步片上网络架构[J]. 计算机研究与发展,2023,60(1):17−29 doi: 10.7544/issn1000-1239.202111032 Yang Zhijie, Wang Lei, Shi Wei, et al. Asynchronous network-on-chip architecture for neuromorphic processor[J]. Journal of Computer Research and Development, 2023, 60(1): 17−29(in Chinese) doi: 10.7544/issn1000-1239.202111032
[25]	Glass C J, Ni L M. The turn model for adaptive routing[J]. ACM SIGARCH Computer Architecture News, 1992, 20(2): 278−287 doi: 10.1145/146628.140384
[26]	Norollah A, Derafshi D, Beitollahi H, et al. PAT-NOXIM: A precise power & thermal cycle-accurate NoC SImulator[C]//Proc of the 31st IEEE Int System-on-Chip Conf (SOCC). Piscataway, NJ: IEEE, 2018: 163−168
[27]	LeCun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278−2324 doi: 10.1109/5.726791
[28]	Laguna P, Mark R G, Goldberg A, et al. A database for evaluation of algorithms for measurement of QT and other waveform intervals in the ECG[C]//Proc of the Computers in cardiology 1997. Piscataway, NJ: IEEE, 1997: 673−676
[29]	Gu Fuqiang, Sng W, Taunyazov T, et al. Tactilesgnet: A spiking graph neural network for event-based tactile object recognition[C]//Proc of the 2020 IEEE/RSJ Int Conf on Intelligent Robots and Systems (IROS). Piscataway, NJ: IEEE, 2020: 9876−9882
[30]	Zhang Yuan, Cao Jian, Chen Jue, et al. Razor SNN: Efficient spiking neural network with temporal embeddings[C]//Proc of the Int Conf on Artificial Neural Networks. Berlin: Springer, 2023: 411−422
[31]	Potjans TC, Diesmann M. The cell-type specific cortical microcircuit: Relating structure and activity in a full-scale spiking network model[J]. Cereb Cortex, 2014, 24(3): 785−806 doi: 10.1093/cercor/bhs358
[32]	Zhou Pujun, Yu Qi, Chen Min, et al. Fullerene-inspired efficient neuromorphic network-on-chip scheme[J]. IEEE Transactions on Circuits and Systems II: Express Briefs, 2023, 71(3): 1376−1380

[1]	Zhang Hengshan, Gao Yukun, Chen Yanping, Wang Zhongmin. Clustering Ensemble Algorithm with Cluster Connection Based on Wisdom of Crowds[J]. Journal of Computer Research and Development, 2018, 55(12): 2611-2619. DOI: 10.7544/issn1000-1239.2018.20180575
[2]	Zhou Jun, Li Huawei, Wang Tiancheng, Li Xiaowei. A Lightweight Fine-Grained Fault-Tolerant Scheme for 3D Networks-on-Chip[J]. Journal of Computer Research and Development, 2016, 53(2): 341-353. DOI: 10.7544/issn1000-1239.2016.20148436
[3]	Yuan Xinpan, Long Jun, Zhang Zuping, Luo Yueyi, Zhang Hao, and Gui Weihua. Connected Bit Minwise Hashing[J]. Journal of Computer Research and Development, 2013, 50(4): 883-890.
[4]	Liu Xiaozhu, Peng Zhiyong. On-Line Dynamic Index Hybrid Update Scheme Based on Self-Learning of Allocated Space[J]. Journal of Computer Research and Development, 2012, 49(10): 2118-2130.
[5]	Qi Shubo, Li Jinwen, Yue Daheng, Zhao Tianlei, and Zhang Minxuan. Adaptive Buffer Management for Leakage Power Optimization in NoC Routers[J]. Journal of Computer Research and Development, 2011, 48(12): 2400-2409.
[6]	Li Zhi, Zha Xuanyue, Liu Fengyu, and Zhang Hong. Indexing Based Multi-Level Clustering Routing Algorithm in Public Transportation Delay Tolerant Networks[J]. Journal of Computer Research and Development, 2011, 48(3): 407-414.
[7]	Tang Mingdong, Zhang Guoqing, Yang Jing. Graph Embedding-Based Scalable Routing in Large Networks[J]. Journal of Computer Research and Development, 2010, 47(7): 1225-1233.
[8]	Jiang Xuefeng, Heng Xingchen, Qin Zheng, Shao Liping. Efficient Extension Join Algorithm for Querying XML Data Based on Index Techniques[J]. Journal of Computer Research and Development, 2008, 45(6).
[9]	Yu Yaxin, Wang Guoren, Zhang Haining, and Li Jianxin. An Index for Supporting XML Structural Join Efficiently and Effectively—CATI[J]. Journal of Computer Research and Development, 2007, 44(1): 111-118.
[10]	Liao Wei, Xiong Wei, Jing Ning, Chen Hongsheng, and Zhong Zhinong. Hybrid Indexing of Moving Objects with Frequent Updates[J]. Journal of Computer Research and Development, 2006, 43(5): 888-893.