An Energy-Efficient NoC Router with Adaptive Fault-Tolerance Using Channel Slicing and On-Demand TMR

被引:5
|
作者
Li, Cheng [1 ]
Yang, Mo [1 ]
Ampadu, Paul [1 ]
机构
[1] Univ Rochester, Dept Elect & Comp Engn, Rochester, NY 14623 USA
基金
美国国家科学基金会;
关键词
NoC router; TMR; energy efficient; fault-tolerance; channel slicing; power gating; multiple physical networks; SYSTEM;
D O I
10.1109/TETC.2016.2597799
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The competing goals of energy-efficiency, performance, and fault tolerance have not been well bridged in current NoC designs. In this paper, we propose an energy-efficient NoC router that exhibits strong fault-tolerance by leveraging channel slicing. This router has three identical router slices connected with internal sharing paths. Channel slicing reduces the overhead of applying power gating to improve energy-efficiency. When faults occur in any of the slices, resource sharing is enabled to enhance fault-tolerance. These router slices can also be harnessed for on-demand TMR, to further improve fault-tolerance and reduce the need for deploying costly on-chip testers. Our method can diagnose and repair both control and datapath faults without interrupting normal NoC operations. Experimental results show that our proposed router can tolerate 180 percent more gate faults than the state-of-the-art fault-tolerant NoC router architecture HPR. In addition, 64 percent energy improvement at low injection rate, and 28 percent energy improvement at high injection rate are achieved compared to HPR. Furthermore, our method attains 100 percent higher throughput (with 40 faults in one router) compared to HPR. Our proposed method increases router logic area by 7.8 percent compared to baseline.
引用
收藏
页码:538 / 550
页数:13
相关论文
共 7 条
  • [1] High-performance and energy-efficient fault-tolerance core mapping in NoC
    Beechu, Naresh Kumar Reddy
    Harishchandra, Vasantha Moodabettu
    Balachandra, Nithin Kumar Yernad
    SUSTAINABLE COMPUTING-INFORMATICS & SYSTEMS, 2017, 16 : 1 - 10
  • [2] HEFT: A Hybrid System-Level Framework for Enabling Energy-Efficient Fault-Tolerance in NoC based MPSoCs
    Zou, Yong
    Pasricha, Sudeep
    2014 INTERNATIONAL CONFERENCE ON HARDWARE/SOFTWARE CODESIGN AND SYSTEM SYNTHESIS (CODES+ISSS), 2014,
  • [3] ReSpawn: Energy-Efficient Fault-Tolerance for Spiking Neural Networks considering Unreliable Memories
    Putra, Rachmad Vidya Wicaksana
    Hanif, Muhammad Abdullah
    Shafique, Muhammad
    2021 IEEE/ACM INTERNATIONAL CONFERENCE ON COMPUTER AIDED DESIGN (ICCAD), 2021,
  • [4] High-performance and Energy-efficient Fault Tolerance Scheduling Algorithm Based on Improved TMR for Heterogeneous System
    Yu, Shigan
    Tang, Zhimin
    Ye, Xiaochun
    Zhang, Zhimin
    Fan, Dongrui
    Jiang, Zhiying
    2018 IEEE INT CONF ON PARALLEL & DISTRIBUTED PROCESSING WITH APPLICATIONS, UBIQUITOUS COMPUTING & COMMUNICATIONS, BIG DATA & CLOUD COMPUTING, SOCIAL COMPUTING & NETWORKING, SUSTAINABLE COMPUTING & COMMUNICATIONS, 2018, : 207 - 214
  • [5] A Gracefully Degrading and Energy-Efficient Fault Tolerant NoC Using Spare core
    Reddy, B. Naresh Kumar
    Vasantha, M. H.
    Kumar, Nithin Y. B.
    2016 IEEE COMPUTER SOCIETY ANNUAL SYMPOSIUM ON VLSI (ISVLSI), 2016, : 146 - 151
  • [6] Energy-Efficient Task Scheduling Using Fault Tolerance Technique for IoT Applications in Fog Computing Environment
    Khan, Salman
    Shah, Ibrar Ali
    Aurangzeb, Khursheed
    Ahmad, Shabir
    Khan, Javed Ali
    Anwar, Muhammad Shahid
    IEEE INTERNET OF THINGS JOURNAL, 2024, 11 (24): : 39009 - 39019
  • [7] An Energy-Efficient Seizure Detection Processor using Event-Driven Multi-Stage CNN Classification and Segmented Data Processing with Adaptive Channel Selection
    Liu, Jiahao
    Zhong, Zirui
    Zhou, Yong
    Qiu, Hui
    Xiao, Jianbiao
    Fan, Jiajing
    Zhang, Zhaomin
    Li, Sixu
    Xu, Yiming
    Yang, Siqi
    Shan, Weiwei
    Lin, Shuisheng
    Chang, Liang
    Zhou, Jun
    PROCEEDINGS OF THE 59TH ACM/IEEE DESIGN AUTOMATION CONFERENCE, DAC 2022, 2022, : 217 - 222