Efficient O-type mapping and routing of large-scale neural networks to torus-based ONoCs

被引:0
|
作者
Yao, Qiuyan [1 ]
Meng, Daqing [1 ]
Yang, Hui [1 ]
Feng, Nan [2 ]
Zhang, Jie [1 ]
机构
[1] Beijing Univ Posts & Telecommun, State Key Lab Informat Photon & Opt Commun, Beijing 100876, Peoples R China
[2] 54th Res Inst CETC, Hebei Key Lab Photon Informat Technol & Applicat, Shijiazhuang 050081, Peoples R China
基金
中国国家自然科学基金;
关键词
Biological neural networks; Neurons; Routing; Optical computing; Network topology; Topology; Optical fiber networks; ACCELERATOR; ALGORITHM;
D O I
10.1364/JOCN.525666
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
The rapid development of artificial intelligence has accelerated the arrival of the era of large models. Artificial-neural-network-based large models typically have millions to billions of parameters, and their training and reasoning processes put strict requirements on hardware, especially at the chip level, in terms of interconnection bandwidth, processing speed, latency, etc. The optical network-on-chip (ONoC) is a new interconnection technology that connects IP cores through a network of optical waveguides. Due to its incomparable advantages such as low loss, high throughput, and low delay, this communication mode has gradually become the key technology to improve the efficiency of large models. At present, the ONoC has been used to reduce the interconnection complexity of neural network accelerators, where neural network models are reshaped to map into the process elements of the ONoC and communicate at high speed on chip. In this paper, we first propose a torus-based O-type mapping strategy to realize efficient mapping of neuron groups to the chip. Additionally, an array congestion information-based low-congestion arbitrator is designed and then a multi-path low-congestion routing algorithm named TMLA is presented to alleviate array congestion and disperse the routing pressure of each path. Results demonstrate that the proposed mapping and routing scheme can reduce the average network delay without additional loss when the injection rate is relatively large, which provides a valuable reference for the research of neural network acceleration.
引用
收藏
页码:918 / 928
页数:11
相关论文
共 20 条
  • [1] A Comprehensive and Efficient Topology Representation in Routing Computation for Large-Scale Transmission Networks
    Wu, Yonghan
    Li, Jin
    Zhang, Min
    Ye, Bing
    Tang, Xiongyan
    IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT, 2025, 22 (01): : 220 - 241
  • [2] Evidence-Efficient Multihop Clustering Routing Scheme for Large-Scale Wireless Sensor Networks
    Li, Zhihua
    Xin, Ping
    WIRELESS COMMUNICATIONS & MOBILE COMPUTING, 2017,
  • [3] Efficient Simulation-Based Toll Optimization for Large-Scale Networks
    Osorio, Carolina
    Atasoy, Bilge
    TRANSPORTATION SCIENCE, 2021, 55 (05) : 1010 - 1024
  • [4] POWER: probabilistic weight-based energy-efficient cluster routing for large-scale wireless sensor networks
    Farooq, Muhammad Umar
    Wang, Xingfu
    Hawbani, Ammar
    Khan, Asad
    Ahmed, Adeel
    Alsamhi, Saeed
    Qureshi, Bushra
    JOURNAL OF SUPERCOMPUTING, 2022, 78 (10) : 12765 - 12791
  • [5] A Novel Genetic Algorithm-Based Methodology for Large-Scale Fixed Charge Plus Routing Network Design Problem With Efficient Operators
    Doostie, Samira
    Nakashima-Paniagua, Tetsuhei
    Doucette, John
    IEEE ACCESS, 2021, 9 : 114836 - 114853
  • [6] A Survey on DHT-Based Routing for Large-Scale Mobile Ad Hoc Networks
    Abid, Shahbaz Akhtar
    Othman, Mazliza
    Shah, Nadir
    ACM COMPUTING SURVEYS, 2015, 47 (02)
  • [7] Joint Clustering and Routing Design for Reliable and Efficient Data Collection in Large-Scale Wireless Sensor Networks
    Xu, Zhezhuang
    Chen, Liquan
    Chen, Cailian
    Guan, Xinping
    IEEE INTERNET OF THINGS JOURNAL, 2016, 3 (04): : 520 - 532
  • [8] Double firefly based efficient clustering for large-scale wireless sensor networks
    Sahraoui, Mohamed
    Harous, Saad
    JOURNAL OF SUPERCOMPUTING, 2024, 80 (13) : 19669 - 19695
  • [9] Efficient community-based influence maximization in large-scale social networks
    Venunath, M.
    Sujatha, Pothula
    Koti, Prasad
    Dharavath, Srinu
    MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 83 (15) : 44397 - 44424
  • [10] An efficient method based on the uniformity principle for synthesis of large-scale heat exchanger networks
    Zhang, Chunwei
    Cui, Guomin
    Chen, Shang
    APPLIED THERMAL ENGINEERING, 2016, 107 : 565 - 574