Skip to Main Content
Summary form only given. Dynamic signal processing systems, where significant changes in functionality and computational structure must be achieved while applications are running, are becoming increasingly important as computational platforms become more powerful, and feature-sets of DSP-powered products become more sophisticated. This talk covers two new, complementary dataflow models of computation that are being developed in the Maryland DSPCAD Research Group to help address the challenges of structured design, simulation, and synthesis of dynamic signal processing systems. The first of these models, called enable-invoke dataflow (EIDF), is aimed improving the predictability of actor invocation and the efficiency with which dynamic scheduling techniques can be realized. The second model, called the dataflow schedule graph (DSG), provides a formal framework for representing and analyzing dataflow graph schedules that is rooted in formal dataflow semantics, and accommodates a wide range of schedule classes, including static, quasi-static, and dynamic schedules, as well as both sequential and parallel schedule formats. In this talk, I will present the EIDF and DSG models and discuss their potential to improve the processes by which dynamic signal processing systems are developed.