Citation
A. Ghosal, R. Limaye, K. Ravindran, S. Tripakis, A. Prasad, G. G. Wang, T. N. Tran, H. Andrade. "Static dataflow with access patterns: semantics and analysis". DAC 2012, 7, June, 2012.

Abstract
Signal processing and multimedia applications are commonly modeled using Static/Cyclo-Static Dataflow (SDF/CSDF) models. SDF/CSDF explicitly specifies how much data is produced and consumed per firing during computation. This results in strong compile-time analyzability of many useful execution properties such as deadlock absence, channel boundedness, and throughput. However, SDF/CSDF is limited in its ability to capture how data is accessed in time. Hence, using these models often leads to implementations that are sub-optimal (i.e., use more resources than necessary) or even incorrect (i.e., use insufficient resources). In this work, we advance a new model called Static Dataflow with Access Patterns (SDF-AP) that captures the timing of data accesses (for both production and consumption). This paper formalizes the semantics of SDF-AP, defines key properties governing model execution, and discusses algorithms to check these properties under correctness and resource constraints. Results are presented to evaluate these analysis algorithms on practical applications modeled by SDF-AP.

Electronic downloads

• dac2012.pdf · application/pdf · 891 kbytes
• http://dx.doi.org/10.1145/2228360.2228479

• HTML

  A. Ghosal, R. Limaye, K. Ravindran, S. Tripakis, A. Prasad,
  G. G. Wang, T. N. Tran, H. Andrade. <a
  href="http://chess.eecs.berkeley.edu/pubs/910.html"
  >Static dataflow with access patterns: semantics and
  analysis</a>, DAC 2012, 7, June, 2012.

• Plain text

  A. Ghosal, R. Limaye, K. Ravindran, S. Tripakis, A. Prasad,
  G. G. Wang, T. N. Tran, H. Andrade. "Static dataflow
  with access patterns: semantics and analysis". DAC
  2012, 7, June, 2012.

• BibTeX

  @inproceedings{GhosalLimayeRavindranTripakisPrasadWangTranAndrade12_StaticDataflowWithAccessPatternsSemanticsAnalysis,
      author = {A. Ghosal and R. Limaye and K. Ravindran and S.
                Tripakis and A. Prasad and G. G. Wang and T. N.
                Tran and H. Andrade},
      title = {Static dataflow with access patterns: semantics
                and analysis},
      booktitle = {DAC 2012},
      day = {7},
      month = {June},
      year = {2012},
      abstract = {Signal processing and multimedia applications are
                commonly modeled using Static/Cyclo-Static
                Dataflow (SDF/CSDF) models. SDF/CSDF explicitly
                specifies how much data is produced and consumed
                per firing during computation. This results in
                strong compile-time analyzability of many useful
                execution properties such as deadlock absence,
                channel boundedness, and throughput. However,
                SDF/CSDF is limited in its ability to capture how
                data is accessed in time. Hence, using these
                models often leads to implementations that are
                sub-optimal (i.e., use more resources than
                necessary) or even incorrect (i.e., use
                insufficient resources). In this work, we advance
                a new model called Static Dataflow with Access
                Patterns (SDF-AP) that captures the timing of data
                accesses (for both production and consumption).
                This paper formalizes the semantics of SDF-AP,
                defines key properties governing model execution,
                and discusses algorithms to check these properties
                under correctness and resource constraints.
                Results are presented to evaluate these analysis
                algorithms on practical applications modeled by
                SDF-AP.},
      URL = {http://chess.eecs.berkeley.edu/pubs/910.html}
  }
  

Posted by Stavros Tripakis on 8 Jun 2012.
For additional information, see the Publications FAQ or contact webmaster at chess eecs berkeley edu.