Schedulability-aware mapping of real-time object-oriented models to multi-threaded implementations

The object-oriented design methods and their CASE tools are widely used in practice by many real-time software developers. However, object-oriented CASE tools require an additional step of identifying tasks from a given design model. Unfortunately, it is diicult to automate this step for a couple of reasons: (1) there are inherent discrepancies between objects and tasks; and (2) it is hard to derive tasks while maximizing real-time schedulability since this problem makes a non-trivial optimization problem. As a result, in practical object-oriented CASE tools, task identiication is usually performed in an ad-hoc manner using hints provided by human designers. In this paper, we present a systematic , schedulability-aware approach that can help mapping real-time object-oriented models to multi-threaded implementations. In our approach, a task contains a group of mutually exclusive transactions that may possess diierent periods and deadline. For this new task model, we provide a schedulability analysis algorithm. We also show how the run-time system is implemented and how executable code is generated in our framework. We have performed a case study. It shows the diiculty of task derivation problem and the utility of the automated synthesis of implemenation.