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 difficult 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 identification is usually performed in an ad hoc manner using hints provided by human designers. We present a systematic, schedulability-aware approach that can help mapping real time object oriented models to multithreaded implementations. In our approach, a task contains a group of mutually exclusive transactions that may possess different 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 difficulty of the task derivation problem and the utility of the automated synthesis of implementation.