BPDF: A Statically Analyzable DataFlow Model with Integer and Boolean Parameters
Vagelis Bebelis, Pascal Fradet, Alain Girault, Bruno Lavigueur

Citation
Vagelis Bebelis, Pascal Fradet, Alain Girault, Bruno Lavigueur. "BPDF: A Statically Analyzable DataFlow Model with Integer and Boolean Parameters". Talk or presentation, 7, November, 2013; Presented at the 10th Biennial Ptolemy Miniconference, Berkeley. .

Abstract
Dataflow programming models are well-suited to program many-core streaming applications. However, many streaming applications have a dynamic behavior. To capture this behavior, parametric data ow models have been introduced over the years. Still, such models do not allow the topology of the data ow graph to change at runtime, a feature that is also required to program modern streaming applications. To overcome these restrictions, we propose a new model of computation, the Boolean Parametric Data Flow (BPDF) model which combines integer parameters (to ex- press dynamic rates) and boolean parameters (to express the activation and deactivation of communication channels). High dynamism is provided by integer parameters which can change at each basic iteration and boolean parameters which can even change within the iteration. The major challenge with such dynamic models is to guarantee liveness and boundedness. We present static analyses which ensure statically the liveness and the boundedness of BDPF graphs. We also introduce a scheduling methodology to implement our model on highly parallel platforms and demonstrate our approach using a video decoder case study.

Electronic downloads

(No downloads are available for this publication.)

Citation formats

• HTML

  Vagelis Bebelis, Pascal Fradet, Alain Girault, Bruno 
  Lavigueur. <a
  href="http://chess.eecs.berkeley.edu/pubs/1041.html"><i>BPDF:
  A Statically Analyzable DataFlow Model with Integer and
  Boolean Parameters</i></a>, Talk or
  presentation,  7, November, 2013; Presented at the <a
  href="http://ptolemy.org/conferences/13" >10th
  Biennial Ptolemy Miniconference</a>, Berkeley.
  .

• Plain text

  Vagelis Bebelis, Pascal Fradet, Alain Girault, Bruno 
  Lavigueur. "BPDF: A Statically Analyzable DataFlow
  Model with Integer and Boolean Parameters". Talk or
  presentation,  7, November, 2013; Presented at the <a
  href="http://ptolemy.org/conferences/13" >10th
  Biennial Ptolemy Miniconference</a>, Berkeley.
  .

• BibTeX

  @presentation{BebelisFradetGiraultLavigueur13_BPDFStaticallyAnalyzableDataFlowModelWithIntegerBoolean,
      author = {Vagelis Bebelis and Pascal Fradet and Alain
                Girault and Bruno  Lavigueur},
      title = {BPDF: A Statically Analyzable DataFlow Model with
                Integer and Boolean Parameters},
      day = {7},
      month = {November},
      year = {2013},
      note = {Presented at the <a
                href="http://ptolemy.org/conferences/13" >10th
                Biennial Ptolemy Miniconference</a>, Berkeley.
  },
      abstract = {Dataflow programming models are well-suited to
                program many-core streaming applications. However,
                many streaming applications have a dynamic
                behavior. To capture this behavior, parametric
                data ow models have been introduced over the
                years. Still, such models do not allow the
                topology of the data ow graph to change at
                runtime, a feature that is also required to
                program modern streaming applications. To overcome
                these restrictions, we propose a new model of
                computation, the Boolean Parametric Data Flow
                (BPDF) model which combines integer parameters (to
                ex- press dynamic rates) and boolean parameters
                (to express the activation and deactivation of
                communication channels). High dynamism is provided
                by integer parameters which can change at each
                basic iteration and boolean parameters which can
                even change within the iteration. The major
                challenge with such dynamic models is to guarantee
                liveness and boundedness. We present static
                analyses which ensure statically the liveness and
                the boundedness of BDPF graphs. We also introduce
                a scheduling methodology to implement our model on
                highly parallel platforms and demonstrate our
                approach using a video decoder case study.},
      URL = {http://chess.eecs.berkeley.edu/pubs/1041.html}
  }
  

Posted by Barb Hoversten on 21 Nov 2013.
Groups: ptolemy
For additional information, see the Publications FAQ or contact webmaster at chess eecs berkeley edu.