Compositional Temporal Analysis Method for Fixed Priority Pre-emptive Scheduled Modal Stream Processing Applications

Abstract

Modal real-time stream processing applications often contain cyclic dependencies and are typically executed on multiprocessor systems with processor sharing. Most real-time operating system kernels for these systems support Static Priority Pre-emptive (SPP) scheduling, however there is currently no suitable temporal analysis technique available for this type of systems. In this paper, we present a compositional temporal analysis approach for modal and cyclic stream processing applications executed on SPP scheduled multiprocessor systems. In this approach, locks and barriers are added such that the temporal behavior of modes can be characterized independently. As a result, the composition of modes does not change their characterization. This enables the use of an existing Structured Variable-Rate Phased Dataflow (SVPDF) model based dataflow analysis technique to determine the worst-case temporal behavior. The SVPDF model and the parallel implementation including locks and barriers are generated by a multiprocessor compiler. The applicability of the analysis approach is demonstrated using a WLAN 802.11p application. Conditions under which pipelined execution can be achieved are identified. The analysis results are verified with a dataflow simulator that supports sharing of resources.