OPEN-NEXT

In modern industry, data processing systems aggregate and process information from different sources to carry out complex production control and coordination activities. Examples are the real-time monitoring of product quality, automation of production lines, intelligent freight transport systems. The increasingly close integration of sensors in computational platforms has given rise in recent years to the so-called Cyber-Physical Systems (CPS) which are used in different areas, from domotics to the automotive and avionics sectors and, precisely, to industrial and manufacturing sectors (Industry 4.0 and Manufacturing 2.0).

The growing need for data processing from multiple sensors requires considerable computing power that can hardly be provided by traditional single-processor architectures: they have by now exhausted the possibilities of performance scaling and are no longer able to satisfy the new industry needs. At the same time, the reduction in the size of the control devices and the optimization of energy consumption are essential requirements that cannot be met through the simple use of a greater number of computational elements (resource over-provisioning).

At the same time, new industrial applications are appearing on the embedded systems market that impose requirements that are difficult to satisfy with existing technology:

• higher computational loads, for rapid processing and fusion of multiple sensory data;
• reduced energy consumption, to allow the use of smaller batteries associated with renewable energy sources;
• faster and more reliable interaction with the surrounding environment, with a capacity to react in predictable times;
• greater criticality, with systems that participate in safety-critical activities also in close interaction with man: in these systems it is not admissible to aim at high average performances without ensuring compliance with the constraints on response time.

The need for new computational architectures that can provide high performance in a predictable manner on new generation embedded platforms, which require complex operating system stacks to be used optimally, therefore emerges.

Development Goals

OPEN-NEXT will address three technological issues:

• Programming models for multi / many-core heterogeneous architectures with real-time constraints;
• Complex stack of operating systems to support real-time applications on multi / many-core heterogeneous architectures;
• Tools for the build and configuration of complex stacks of operating systems and for the schedulability analysis of the SW modules of a real-time application.

Each of these topics will be addressed in a dedicated OR which will include all the activities related to it, from the analysis and study phase to the implementation and test phase. The technological modules produced by OR2, OR3 and OR4 will provide the basis for the realization of the demonstrators that will be developed in collaboration with the corporate partners within OR1. The creation of these demonstrators will also be an opportunity to transfer the know-how developed by the laboratories to individual companies. The project also envisages a significant dissemination of results that will make a significant contribution to maximizing the impact of the project on the regional industrial system.