In real-time systems, the application's behavior has to be predictable at compile-time to guarantee timing constraints. However, modern streaming applications which exhibit adaptive behavior due to... Show moreIn real-time systems, the application's behavior has to be predictable at compile-time to guarantee timing constraints. However, modern streaming applications which exhibit adaptive behavior due to mode switching at run-time, may degrade system predictability due to unknown behavior of the application during mode transitions. Therefore, proper temporal analysis during mode transitions is imperative to preserve system predictability. To this end, in this paper, we initially introduce mode-aware data flow (MADF) which is our new predictable model of computation to efficiently capture the behavior of adaptive streaming applications. Then, as an important part of the operational semantics of MADF, we propose the maximum-overlap offset which is our novel protocol for mode transitions. The main advantage of this transition protocol is that, in contrast to self-timed transition protocols, it avoids timing interference between modes upon mode transitions. As a result, any mode transition can be analyzed independently from the mode transitions that occurred in the past. Based on this transition protocol, we propose a hard real-time analysis as well to guarantee timing constraints by avoiding processor overloading during mode transitions. Therefore, using this protocol, we can derive a lower bound and an upper bound on the earliest starting time of the tasks in the new mode during mode transitions in such a way that hard real-time constraints are respected. Show less
This thesis presents a highly automated design framework, called DaedalusRT, and several novel techniques. As the foundation of the DaedalusRT design framework, two types of dataflow Models-of... Show moreThis thesis presents a highly automated design framework, called DaedalusRT, and several novel techniques. As the foundation of the DaedalusRT design framework, two types of dataflow Models-of-Computation (MoC) are used, one as timing analysis model and another one as the implementation model. The timing analysis model is used to formally reason about timing behavior of an application. In the context of DaedalusRT, the Mode-Aware Data Flow (MADF) MoC has been developed as the timing analysis model for adaptive streaming applications using different static modes. A novel mode transition protocol is devised to allow efficient reasoning of timing behavior during mode transitions. Based on the transition protocol, a hard real-time scheduling approach is proposed. On the other hand, the implementation model is used for efficient code generation of parallel computation, communication, and synchronization. In this thesis, the Parameterized Polyhedral Process Network (P3N) MoC has been developed to model adaptive streaming applications with parameter reconfiguration. An approach to verify the functional property of the P3N MoC has been devised. Finally, implementation of the P3N MoC on a MPSoC platform has shown that run-time performance penalty due to parameter reconfiguration is negligible. Show less