• DocumentCode
    2667552
  • Title

    Power- and performance-aware IP mapping for NoC-based MPSoC platforms

  • Author

    Latif, Khalid ; Rahmani, Amir-Mohammad ; Seceleanu, Tiberiu ; Tenhunen, Hannu

  • Author_Institution
    Dept. of Inf. Technol., Univ. of Turku, Turku, Finland
  • fYear
    2010
  • fDate
    12-15 Dec. 2010
  • Firstpage
    758
  • Lastpage
    761
  • Abstract
    In this paper, we address the performance of MPSoC platforms with homogeneous processing nodes, where the cores generate and consume the large amount of data, thus the system approaches congestion. Mostly, the time dependent media applications are time critical, where traffic must be delivered on time in order to operate properly. Proper task allocation or placement of IP cores at layout time is very important to meet such application requirements. Apart from meeting the application requirements, it also lowers the traffic congestion, power consumption and Average Packet Latency (APL). For task allocation or IP placement, the prioritization criteria has been proposed, which is used in next step to map the application on MPSoC platform. The proposed technique shows significant improvement in system performance and reduction in power consumption. To estimate the efficiency, the video conference encoding application and MPEG4 video encoder were mapped to 5×5 and 4×4 NoC mesh. Up to 11% reduction in power consumption and 20% reduction in APL has been observed as compared to other proposed mapping techniques.
  • Keywords
    low-power electronics; network-on-chip; power aware computing; NoC-based MPSoC platforms; average packet latency; performance-aware IP mapping; power consumption; power-aware IP mapping; time dependent media applications; traffic congestion; Artificial neural networks; Computer architecture; Nickel;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Electronics, Circuits, and Systems (ICECS), 2010 17th IEEE International Conference on
  • Conference_Location
    Athens
  • Print_ISBN
    978-1-4244-8155-2
  • Type

    conf

  • DOI
    10.1109/ICECS.2010.5724623
  • Filename
    5724623