Customised and low power computing

Specific Challenge: A key structural change overtaking computing is the move towards a low-power computing continuum spanning embedded systems, mobile devices, desktops, data centres, etc. The demand for low-power multi/many-core computing systems is intensifying across all market segments.

Capitalising on Europe's industrial and technology strengths in low power computing and embedded and cyber-physical systems, the objective is to strengthen European competitiveness in the key parts of the emerging computing value chain. With the wider diffusion of embedded ICT and cyber-physical systems, security becomes increasingly important to be addressed across all levels starting from secure and trusted zones supported on hardware and software level.

Scope:

a.      Research & Innovation  Actions should cover one or both of the following themes:

         Next generation servers, micro-server and highly parallel embedded computing systems based on ultra-low power architectures: The target is highly performing low-power low-cost micro-servers, using cutting-edge technologies like, for example, optical interconnects, 3D integrated system on chip, innovative power management,  which can be deployed across the full spectrum of home, embedded, and business applications. Focus is on integration of hardware and software components into fully working prototypes and including validation under real-life workloads from various application areas. Specific emphasis is given on low-power, low-cost, high-density, secure, reliable, scalable small form-factor datacentres (""datacentre-in-a-box""). Proposals requesting a Large contribution are expected.

         New cross-layer programming approaches empowering developers to effectively master and exploit the full potential of the next generations of computing systems based on heterogeneous parallel architectures and constituting the computing continuum. Beyond performance, optimisation should include energy efficiency, time-criticality, dependability, data movement, security and cost-effectiveness. Research should also aim at radically increasing the productivity in programming and maintaining intrinsically parallel code by marginalising the need for dual expertise - application engineering and computer system engineering. Focus is on holistic approaches hiding the complexity between the computing HW component level and the level of application families. Proposals requesting a small contribution are expected.

b.      Innovation Actions: Activities aim at stimulating broad adoption of customised low power computing technologies. They should cover one or both of the following themes:

         Towards platforms and ecosystems: Establish reference architectures and platforms for customised low-power heterogeneous computing systems delivering high-performance functionality under real-time constraints across several sectors and application domains. Activities should be use-case driven and include industrial consensus building, pre-normative activities, reference implementations, proof-of concept demonstration and validation in key application domains. The users' perspective will be paid due attention. Proposals requesting a small contribution are expected.

         Connecting innovators across value chains: Driven by the requirements of users, application experiments must bring together all actors along the value chain to customise and use advanced low power computing systems in cyber-physical systems. With special emphasis on SMEs and mid-caps, experiments are expected to be clustered in large scale projects driven by networks of European centres of excellence to achieve critical mass and to better exploit EU-added value.

Proposals requesting a Large contribution are expected. The action may involve financial support to third parties in line with the conditions set out in Part K of the General Annexes. The consortium will define the selection process of additional users and suppliers running the experiments for which financial support will be granted (typically in the order of EUR 50.000 – 150.000[1] per party).  Maximum 50% of the EU funding requested by the proposal should be allocated to this purpose.

c.       Support Actions for cross-sectorial platform-building, for clustering of related research projects, for structuring the European academic and industrial research communities, for dissemination of programme achievements and impact analysis and for constituency building and road-mapping for future research and innovation agendas.

Expected impact:

         Reinforce and broaden Europe's strong position in low-power computing in traditional and new market segments by strengthening the technology competences of European suppliers and the academic community.

         Reduction of energy consumption of servers by 2 orders of magnitude as compared to state of the art in 2013.

         Double the productivity in efficiently programming and maintaining advanced computing systems powering cyber-physical systems as compared to state of the art in programming embedded systems in 2013.

         Increase the adoption of form-factor data-centres and heterogeneous highly parallel computing systems.

         Higher involvement of SMEs, both on the supply and the demand-side.

         Increased adoption of concurrency in applications across all sectors; higher degree of parallelism in applications; increased public trust in embedded applications due to secure and reliable architectures.

Types of action:

a.       Research & Innovation Actions – A mix of proposals requesting Small and Large contributions is expected

b.      Innovation Actions – A mix of proposals requesting Small and Large contributions is expected

c.       Coordination and Support Actions

[1]     In line with the Rules for Participation Article 19 (7) the amounts referred to in Article 137 of the Financial Regulation may be exceeded where it is necessary to achieve the objectives of the action.