• DocumentCode
    2232078
  • Title

    Generic Monitoring and Management Infrastructure for 3D NoC-Bus Hybrid Architectures

  • Author

    Rahmani, Amir-Mohammad ; Vaddina, Kameswar Rao ; Latif, Khalid ; Liljeberg, Pasi ; Plosila, Juha ; Tenhunen, Hannu

  • Author_Institution
    Dept. of Inf. Technol., Univ. of Turku, Turku, Finland
  • fYear
    2012
  • fDate
    9-11 May 2012
  • Firstpage
    177
  • Lastpage
    184
  • Abstract
    Three-dimensional integrated circuits (3D ICs) achieve enhanced system integration and improved performance at lower cost and reduced area footprint. In order to exploit the intrinsic capability of reducing the wire length in 3D ICs, 3D NoC-Bus Hybrid mesh architecture was proposed which provides performance, power consumption, and area benefits. Besides its various advantages, this architecture has a unique and hitherto previously unexplored way to implement an efficient system-wide monitoring network. In this paper, an integrated low-cost monitoring platform for 3D stacked mesh architectures is proposed which can be efficiently used for various system management purposes such as traffic monitoring, thermal management and fault tolerance. The proposed generic monitoring and management infrastructure called ARB-NET utilizes bus arbiters to exchange the monitoring information directly with each other without using the data network. As a test case, based on the proposed monitoring and management platform, a fully congestion-aware and inter-layer fault tolerant routing algorithm named AdaptiveXYZ is presented taking advantage of viable information generated using bus arbiter network. In addition, we propose a thermal monitoring and management strategy on top of our ARB-NET infrastructure. Compared to recently proposed stacked mesh 3D NoCs, our extensive simulations with synthetic and real benchmarks reveal that our architecture using the AdaptiveXYZ routing can help in achieving significant power and performance improvements while preserving the system reliability with negligible hardware overhead.
  • Keywords
    fault tolerance; hybrid integrated circuits; integrated circuit measurement; integrated circuit reliability; network routing; network-on-chip; three-dimensional integrated circuits; 3D NOC-bus hybrid architectures; 3D stacked mesh architectures; AdaptiveXYZ; bus arbiter network; congestion-aware; enhanced system integration; generic monitoring; integrated low-cost monitoring platform; inter-layer fault tolerant routing algorithm; intrinsic capability; management infrastructure; management strategy; system reliability; thermal monitoring; three-dimensional integrated circuits; Fault tolerance; Fault tolerant systems; Monitoring; Routing; Stress; Thermal management; Three dimensional displays; 3D ICs; 3D NoC-Bus Hybrid Architecture; Adaptive Routing Algorithm; Fault Tolerance; Monitoring Infrastructure; Thermal Management;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Networks on Chip (NoCS), 2012 Sixth IEEE/ACM International Symposium on
  • Conference_Location
    Copenhagen
  • Print_ISBN
    978-1-4673-0973-8
  • Type

    conf

  • DOI
    10.1109/NOCS.2012.28
  • Filename
    6209277