• DocumentCode
    190599
  • Title

    Dataflow programs analysis and optimization using model predictive control techniques: An example of bounded buffer scheduling

  • Author

    Canale, M. ; Casale-Brunet, Simone ; Bezati, E. ; Mattavelli, Marco ; Janneck, J.W.

  • Author_Institution
    Dipt. di Autom. e Inf., Politec. di Torino, Turin, Italy
  • fYear
    2014
  • fDate
    20-22 Oct. 2014
  • Firstpage
    1
  • Lastpage
    6
  • Abstract
    This paper presents a new approach to buffer dimensioning for dynamic dataflow implementations. A novel transformation applied to the execution trace graph of a dataflow program is introduced in order to generate an event driven system. It is shown how model predictive control theory techniques can be applied to such a system to analyse the execution space of a dataflow program and to define and to minimize a bounded buffer size configuration that corresponds to a deadlock free execution. Some experimental results obtained using two design examples, i.e. a JPEG and an MPEG HEVC decoder, are reported and compared to the state of the art results in order to show the effectiveness of the introduced approach.
  • Keywords
    buffer storage; data flow analysis; data flow graphs; decoding; optimisation; predictive control; scheduling; video coding; JPEG decoder; MPEG HEVC decoder; bounded buffer scheduling; bounded buffer size configuration minimization; buffer dimensioning; dataflow program analysis; dataflow program optimization; deadlock free execution; dynamic dataflow implementation; event driven system generation; execution space analysis; execution trace graph; model predictive control theory technique; Computational modeling; Decoding; Equations; Optimization; Predictive control; System recovery; Transform coding;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Signal Processing Systems (SiPS), 2014 IEEE Workshop on
  • Conference_Location
    Belfast
  • Type

    conf

  • DOI
    10.1109/SiPS.2014.6986054
  • Filename
    6986054