The DreamCloud Project

The main objective addressed by DreamCloud is to enable dynamic resource allocation in many- core embedded and high performance systems while providing appropriate guarantees on performance and energy efficiency.

DreamCloud will address techniques to allocate computation and communication workloads onto computing platforms during run-time whilst respecting performance and energy budget requirements. To achieve this, DreamCloud brings together teams from embedded computing and high- performance computing (HPC) to address these common ambitious yet achievable goals:

  • Provide complex embedded systems with cloud-like capabilities such as those available in today’s high-performance computing, allowing them to dynamically tune resource usage but without sacrificing critical application-specific constraints in performance and energy.
  • Enable HPC and cloud computing systems to balance workload and manage resources so that they can offer more meaningful guarantees in terms of performance and energy, focussing not only on improving average behaviour but also on reducing variability and upper bounds of timing and energy metrics.

DreamCloud brings together industrial partners from deeply embedded systems (e.g. automotive), consumer embedded systems (e.g. household media), and high performance computing (e.g. HPC platforms); academic partners from embedded systems, real-time systems and HPC. This will enable DreamCloud to develop better approaches by  cross-fertilising  expertise  and  experience from  multiple  industrial  domains  and  academic  communities.

News

  • Invited talk at the International Workshop on Dependable Many-Core Computing (DMCC 2015)

    Leandro Soares Indrusiak gave an invited talk at the International Workshop on Dependable Many-Core Computing (DMCC) in Amsterdam, describing some of the resource allocation techniques used within the DreamCloud project to guarantee time-predictable performance in embedded many-core systems. The talk, entitled "Real-Time Mixed-Criticality Network-on-Chip Resource Allocation", addressed the specific resource allocation challenges for many-cores based on Network-on-Chip technology. It was the…

    Read more…
    Started by Leandro Soares Indrusiak 0 Replies
  • Paper accepted in FDL'2015

    Our paper entitled "An Integrated Framework for Model-Based Design and Analysis of Automotive Multi-Core Systems" has been accepted for presentation at the Forum on specification and Design Languages (FDL’2015) that will hold in Barcelona (Spain), from September 14th 2015 to September 16th 2015 -- see http://www.ecsi.org/fdl. FDL’2015 is a well established international forum devoted to dissemination of research results, practical experiences and new ideas in the application of specification,…

    Read more…
    Started by Abdoulaye Gamatié 0 Replies
  • DreamCloud presented at LIRMM lab scientific day

    Abdoulaye Gamatie, from CNRS/LIRMM, gave an invited talk entitled "For a Design Continuum to Build Next Generation Energy-Efficient Compute Nodes" (see abstract in the program of this event here: agenda.pdf) on July 1st 2015 in Montpellier (France), during the annual Scientific Day of the LIRMM Lab to which around 160 persons registered. He presented part of ongoing work in DreamCloud project regarding the efficient resource allocation for optimizing both performance and energy of multicore and…

    Read more…
    Started by Abdoulaye Gamatié 0 Replies
  • DreamCloud simulator demo at ReCoSoC'2015

    A live demo of one DreamCloud simulator, developed at CNRS/LIRMM, for embedded multicore systems has been presented during ReCoSoC’2015 Symposium (June 29th 2015 - July 1st 2015) in Bremen (Germany). This demo, entitled "Automotive Multi-Core System Design Exploration Framework in DreamCloud European project" showed how our simulator seamlessly implements a complete design flow starting from Amalthea automotive application models to performance and energy numbers characterizing different…

    Read more…
    Started by Abdoulaye Gamatié 0 Replies

DreamCloud is a Specific Targeted Research Project (STREP) of the Seventh Framework Programme for research and technological development (FP7) - the European Union's chief instrument for funding research projects that commence over the period 2007 to 2013.


FP7 ICT News

Photos

Project Partners