A Model-Based Schedule Representation for Heterogeneous Mapping of Dataflow Graphs

Abstract

Abstract-Dataflow-based application specifications are widely used in model-based design methodologies for signal processing systems. In this paper, we develop a new model called the dataflow schedule graph (DSG) for representing a broad class of dataflow graph schedules. The DSG provides a graphical representation of schedules based on dataflow semantics. In conventional approaches, applications are represented using dataflow graphs, whereas schedules for the graphs are represented using specialized notations, such as various kinds of sequences or looping constructs. In contrast, the DSG approach employs dataflow graphs for representing both application models and schedules that are derived from them.Our DSG approach provides a precise, formal framework for unambiguously representing, analyzing, manipulating, and interchanging schedules. We develop detailed formulations of the DSG representation, and present examples and experimental results that demonstrate the utility of DSGs in the context of heterogeneous signal processing system design.

Modeling and optimization of dynamic signal processing in resource-aware sensor networks

“…The DSG representation, as introduced in [24], is formulated in terms of CFDF semantics, which is highly expressive and subsumes many other useful dataflow models as special cases [21]. However, the DSG representation can be extended or adapted to work with other modeling techniques; see [24] for further details.…”

“…However, the DSG representation can be extended or adapted to work with other modeling techniques; see [24] for further details. DSG representations are intended to complement corresponding dataflow-based application models by providing formal representations of schedules for those models.…”

“…The actors labeled switch and select in the application graph are fundamental dynamic dataflow actors in BDF; each actor labeled R X in the DSG is a reference actor with the associated referenced actor being the actor X in the BDF graph; and the other two DSG actors are schedule control actors. For further details on this example, we refer the reader to [24].…”

“…This makes the representation suitable as an intermediate representation for design tools, and also as a basis for software architectures that support designer-constructed schedules. For more details on the DSG representation, we refer the reader to [24].…”

“…• The dataflow schedule graph (DSG), which provides a formal framework for representing and analyzing dataflow graph schedules, and accommodates a wide range of schedule classes, including static, quasi-static, and dynamic schedules, as well as both sequential and parallel schedule formats [24].…”