From dataflow analysis basics to the programming of ASICs

Abstract

Programming stream processing multiprocessor systems is a challenging task especially if there are real-time requirements. Therefore it is desirable to use formal models and real-time analysis techniques. However the classical periodic task-model does not match well with stream processing applications which results in suboptimal designs. In this talk we show that data-driven execution of stream processing application improves the robustness against faulty workload assumptions. Using the earlier-the-better-refinement theory practically useful deterministic timed-dataflow analysis models can be created of these applications. Strong analytical properties are obtained by reservation of resources in the multiprocessor systems. Compilation tools can hide the modelling effort for the programmers of the multiprocessor systems. Future cyber-physical systems can benefit from the higher level of non-determinism that is supported by the presented timed-dataflow analysis techniques.