Dataflow Programs Analysis and Optimization Using Model Predictive Control Techniques

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.

[1]  Tadao Murata,et al.  Petri nets: Properties, analysis and applications , 1989, Proc. IEEE.

[2]  Mickaël Raulet,et al.  Reconfigurable media coding: An overview , 2013, Signal Process. Image Commun..

[3]  Johan Eker,et al.  CAL language report: Specification of the CAL actor language , 2003 .

[4]  Mickaël Raulet,et al.  MPEG Reconfigurable Video Coding , 2010, Handbook of Signal Processing Systems.

[5]  Johan Ersfolk.  Scheduling dynamic dataflow graphs with model checking , 2014 .

[6]  Jack B. Dennis,et al.  First version of a data flow procedure language , 1974, Symposium on Programming.

[7]  Claudio Alberti,et al.  Design space exploration of high level stream programs on parallel architectures: A focus on the buffer size minimization and optimization problem , 2013, 2013 8th International Symposium on Image and Signal Processing and Analysis (ISPA).

[8]  Claudio Alberti,et al.  Turnus: A unified dataflow design space exploration framework for heterogeneous parallel systems , 2013, 2013 Conference on Design and Architectures for Signal and Image Processing.

[9]  Ghislain Roquier,et al.  Methods to explore design space for MPEG RMC codec specifications , 2013, Signal Process. Image Commun..

[10]  Edward A. Lee,et al.  Synthesis of Embedded Software from Synchronous Dataflow Specifications , 1999, J. VLSI Signal Process..

[11]  Edward A. Lee,et al.  Dataflow process networks , 2001 .

[12]  Ghislain Roquier,et al.  Scheduling of dynamic dataflow programs based on state space analysis , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[13]  Gilles Kahn,et al.  The Semantics of a Simple Language for Parallel Programming , 1974, IFIP Congress.

[14]  Sander Stuijk,et al.  Minimising buffer requirements of synchronous dataflow graphs with model checking , 2005, Proceedings. 42nd Design Automation Conference, 2005..

[15]  Thomas Martyn Parks,et al.  Bounded scheduling of process networks , 1996 .

[16]  Manfred Morari,et al.  Model predictive control: Theory and practice - A survey , 1989, Autom..

[17]  Yu Wang,et al.  An efficient technique for analysis of minimal buffer requirements of synchronous dataflow graphs with model checking , 2009, CODES+ISSS '09.

[18]  S. Joe Qin,et al.  A survey of industrial model predictive control technology , 2003 .

[19]  Claudio Alberti,et al.  Design Space Exploration of High-Level Stream Programs on Parallel Architectures , 2013 .

[20]  Marco Mattavelli.  MPEG Reconfigurable Video Representation , 2012 .

[21]  Edward A. Lee,et al.  Static Scheduling of Synchronous Data Flow Programs for Digital Signal Processing , 1989, IEEE Transactions on Computers.