Design of embedded mixed-criticality CONTRol systems under consideration of EXtra-functional properties

Up to now mission & safety critical services of SoS (Systems of Systems) have been running on dedicated and often custom designed HW/SW platforms. In the near future such systems will be accessible, connected with or executed on devices comprising off-the-shelf HW/SW components. Significant improvements have been achieved supporting the design of mixed-critical systems by developing predictable computing platforms and mechanisms for segregation between applications of different criticalities sharing computing resources. Such platforms enable techniques for the compositional certification of applications’ correctness, run-time properties and reliability.

CONTREX will complement these important activities with an analysis and segregation along the extra-functional properties real-time, power, temperature and reliability. These properties will be a major cost roadblocks when

  1. scaling up the number of applications per platform and the number of cores per chip,
  2. in battery powered devices or
  3. switching to smaller technology nodes.

CONTREX will enable energy efficient and cost aware design through analysis and optimisation of real-time, power, temperature and reliability with regard to application demands at different criticality levels. To reinforce European leadership and industrial competiveness the CONTREX approach will be integrated into existing model-based design methods that can be customized for different application domains and target platforms. CONTREX will focus on the requirements derived from the automotive, aeronautics and telecommunications domain and evaluate its effectiveness and drive integration into existing standards for the design and certification based on three industrial demonstrators. Valuable feed-back to the industrial design practice, standards, and certification procedures is pursued.

Our economic goal is to improve energy efficiency by 20 % and to reduce cost per system by 30 % due to a more efficient use of the computing platform.