Citation
Maarten Wiggers. "Buffer Capacity Computation for Throughput Constrained Streaming Applications with Data-Dependent Inter-Task Communication". Talk or presentation, 31, July, 2008.

Abstract
Streaming applications are often implemented as task graphs, in which data is communicated from task to task over buffers. Currently, techniques exist to compute buffer capacities that guarantee satisfaction of the throughput constraint if the amount of data produced and consumed by the tasks is known at design-time. However, applications such as audio and video decoders have tasks that produce and consume an amount of data that depends on the decoded stream. This paper introduces a dataflow model that allows for data-dependent communication, together with an algorithm that computes buffer capacities that guarantee satisfaction of a throughput constraint. The applicability of this algorithm is demonstrated by computing buffer capacities for an H.263 video decoder.

Electronic downloads

• chess_visit_v2.ppt · application/vnd.ms-powerpoint · 6962 kbytes

• HTML

  Maarten Wiggers. <a
  href="http://chess.eecs.berkeley.edu/pubs/474.html"
  ><i>Buffer Capacity Computation for Throughput
  Constrained Streaming Applications with Data-Dependent
  Inter-Task Communication</i></a>, Talk or
  presentation,  31, July, 2008.

• Plain text

  Maarten Wiggers. "Buffer Capacity Computation for
  Throughput Constrained Streaming Applications with
  Data-Dependent Inter-Task Communication". Talk or
  presentation,  31, July, 2008.

• BibTeX

  @presentation{Wiggers08_BufferCapacityComputationForThroughputConstrainedStreaming,
      author = {Maarten Wiggers},
      title = {Buffer Capacity Computation for Throughput
                Constrained Streaming Applications with
                Data-Dependent Inter-Task Communication},
      day = {31},
      month = {July},
      year = {2008},
      abstract = {Streaming applications are often implemented as
                task graphs, in which data is communicated from
                task to task over buffers. Currently, techniques
                exist to compute buffer capacities that guarantee
                satisfaction of the throughput constraint if the
                amount of data produced and consumed by the tasks
                is known at design-time. However, applications
                such as audio and video decoders have tasks that
                produce and consume an amount of data that depends
                on the decoded stream. This paper introduces a
                dataflow model that allows for data-dependent
                communication, together with an algorithm that
                computes buffer capacities that guarantee
                satisfaction of a throughput constraint. The
                applicability of this algorithm is demonstrated by
                computing buffer capacities for an H.263 video
                decoder.},
      URL = {http://chess.eecs.berkeley.edu/pubs/474.html}
  }
  

Posted by Hiren Patel on 31 Jul 2008.
Groups: chess
For additional information, see the Publications FAQ or contact webmaster at chess eecs berkeley edu.