Load balancing-oriented fault-tolerant NoC design

被引:0
|
作者
Tan, Ta
Chen, Xiaowen [1 ]
Li, Chen
Lu, Jianzhuang
机构
[1] Natl Univ Def Technol, Sch Comp, Changsha, Peoples R China
来源
8TH INTERNATIONAL TEST CONFERENCE IN ASIA, ITC-ASIA 2024 | 2024年
关键词
NoC; fault-tolerant; reliability; load balance-oriented;
D O I
10.1109/ITC-Asia62534.2024.10661350
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Network-on-Chip (NoC) has been widely applied in modern chip multiprocessors due to its high bandwidth and scalability. However, as technology advances to the nanometer scale, NoC is increasingly vulnerable to errors caused by crosstalk, radiation, electromagnetic interference, etc. Conventional Switch-to-Switch (S2S) fault-tolerant designs based on ECC have overlooked the characteristic of the distribution of traffic load. This oversight not only increases area overhead significantly but also leads to low average utilization of ECC decoder modules. In this paper, we analyze the distribution of traffic load in mesh network and propose a load balancing-oriented fault-tolerant NoC design. The core idea is to allocate different numbers of ECC decoder modules to each router based on the distribution of traffic load, aiming to improve the average utilization of ECC decoder modules and reduce the area overhead without compromising fault-tolerant capability of NoC. The experiment under 6 common synthetic traffic patterns shows that compared to the baseline, our design exhibits an average delay performance loss of less than 0.88%. Additionally, the maximum reduction in the number of ECC decoder modules is 160, the maximum reduction in the area overhead of NoC is 15.06%, and the maximum improvement in the average utilization of ECC decoder modules is 1.21x. Furthermore, the experiment under PARSEC benchmarks shows that compared to the baseline, our design exhibits an average delay performance loss of less than 0.08%. Additionally, the maximum reduction in the number of ECC decoder modules is 156, the maximum reduction in total NoC area overhead is 14.69%, and the maximum improvement in the average utilization of ECC decoder modules is 1.13x.
引用
收藏
页数:6
相关论文
共 50 条
  • [21] Fault-Tolerant Design for Data Efficient Retransmission in WiNoC
    Ouyang, Yiming
    Wang, Qi
    Li, Zhe
    Liang, Huaguo
    Li, Jianhua
    TSINGHUA SCIENCE AND TECHNOLOGY, 2021, 26 (01) : 85 - 94
  • [23] Scenario preprocessing approach for the reconfiguration of fault-tolerant NoC-based MPSoCs
    Silveira, Jarbas
    Marcon, Cesar
    Cortez, Paulo
    Barroso, Giovanni
    Ferreira, Joao M.
    Mota, Rafael
    MICROPROCESSORS AND MICROSYSTEMS, 2016, 40 : 137 - 153
  • [24] Fault-Tolerant Routing Algorithm for Mesh based NoC using Reinforcement Learning
    Samala, Jagadheesh
    Takawale, Harshvardhan
    Chokhani, Yash
    Bhanu, P. Veda
    Soumya, J.
    2020 24TH INTERNATIONAL SYMPOSIUM ON VLSI DESIGN AND TEST (VDAT), 2020,
  • [25] A fault-tolerant routing algorithm for NoC based on 2D Mesh
    Jiang, S. Y.
    Jiang, S. S.
    Luo, G.
    Lu, Z.
    Zhou, J.
    INFORMATION SCIENCE AND ELECTRONIC ENGINEERING, 2017, : 35 - 40
  • [26] Hierarchical Agents Based Fault-Tolerant and Congestion-Aware Routing for NoC
    Nayak, Chinmaya Kumar
    Das, Satyabrata
    Behera, Himnsu Sekhar
    COMPUTATIONAL INTELLIGENCE IN DATA MINING, VOL 3, 2015, 33
  • [27] Fault-Tolerant and High Reliability Space Robot Design and Research
    Gao Junyao
    Gao Xueshan
    Zhu Wei
    Zhu Jianguo
    Wei Boyu
    2008 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-8, 2008, : 2413 - 2417
  • [28] Fault-tolerant middleware for robots
    Baek, BumHyeon
    Park, HongSeong
    WMSCI 2007: 11TH WORLD MULTI-CONFERENCE ON SYSTEMICS, CYBERNETICS AND INFORMATICS, VOL II, PROCEEDINGS, 2007, : 90 - 95
  • [29] A Multiphase Fault-Tolerant MLI With Preserved Rated Output for Emergency Load Applications
    Kumar, Balram
    Peddapati, Sankar
    IEEE JOURNAL OF EMERGING AND SELECTED TOPICS IN POWER ELECTRONICS, 2023, 11 (05) : 4989 - 5000
  • [30] Fault Tolerant Multiple Synchronized Parallel Load Balancing in Cloud
    Sreelekshmi, S.
    Babu, K. R. Remesh
    HYBRID INTELLIGENT SYSTEMS, HIS 2017, 2018, 734 : 11 - 19