The implementation of critical applications on multi/many-core platforms is a hot topic in real-time research community. The interferences on shared resources such as shared memory, impacts the execution of critical tasks and their timing analysis. We focus on applications modeled by a direct acyclic graph (DAG) of tasks where edges represent precedence constraints and communications. Our previous work revisits the link between timing analysis and implementation with a collaboration of code orchestration, mapping/scheduling, interference analysis and schedulability. We consider the DAG as a periodic application with one global period. However, applications described by DAGs are generally multi-periodic or subject to execution modes. The idea is to analyze and integrate the execution mode to our implementation/analyses.
The topics that may be explored are:
- Semantic analysis: extraction of execution modes from high-level code (SCADE/Lustre like),
- Code Orchestration: extend our tool for additional platforms,
- Interference analysis: hardware model to estimate interference delays for the additional platforms,
- Scheduling/ schedulability/mapping: extend our algorithms and equations to incorporate mode analysis.
The candidate must have knowledge on formal methods, real-time systems (OS), static timing analysis or Synchronous DAG applications. Low-level development is not a mandatory skill, but would be a plus. This postdoc is funded by the ANR project CAOTIC
Collaborators: Claire Maiza and Pascal Raymond
