Performance estimation for embedded systems with data and control dependencies

In this paper we present an approach to performance estimation for hard real-time systems. We consider architectures consisting of multiple processors. The scheduling policy is based on a preemptive strategy with static priorities. Our model of the system captures both data and control dependencies, and the analysis is able to reduce the pessimism of the estimation by using the knowledge about these dependencies. Extensive experiments as well as a real life example demonstrate the efficiency of our approach.