[289] | 1 | \anrdoc{Preciser:\begin{itemize} |
---|
| 2 | \item positionnement du projet par rapport au contexte developpe precedemment : |
---|
| 3 | vis- a-vis des projets et recherches concurrents, complementaires ou |
---|
| 4 | anterieurs, des brevets et standards... |
---|
| 5 | \item indiquer si le projet s'inscrit dans la continuite de projet(s) anterieurs |
---|
| 6 | deja finances par l'ANR. Dans ce cas, presenter brievement les resultats acquis, |
---|
| 7 | \item positionnement du projet par rapport aux axes thematiques de l'appel a projets, |
---|
| 8 | \item positionnement du projet aux niveaux europeen et international. |
---|
| 9 | \end{itemize}} |
---|
| 10 | |
---|
| 11 | % Relevance of the proposal |
---|
| 12 | %The COACH proposal addresses directly the \emph{Embedded Systems} item of |
---|
| 13 | %the ARPEGE program. |
---|
| 14 | |
---|
| 15 | %PC => IA et ALain |
---|
| 16 | %J'aui déplacé le pargraphe ci dessous en conclusion de la section précédente 2.1 |
---|
| 17 | |
---|
| 18 | %It aims to propose solutions to the societal/economical challenges by |
---|
| 19 | %providing SMEs novel design capabilities enabling them to increase their |
---|
| 20 | %design productivity with design exploration and synthesis methods that are placed on top |
---|
| 21 | %of the state-of-the-art methods. |
---|
| 22 | %This project proposes an open-source framework for mapping multi-tasks software applications |
---|
| 23 | %on Field Programmable Gate Array circuits (FPGA). |
---|
| 24 | %%% |
---|
| 25 | \parlf |
---|
| 26 | COACH will contribute to build an open design and run-time |
---|
| 27 | environment, including communication middleware and tools to support |
---|
| 28 | developers in the production of embedded software, through all phases of the software lifecycle, |
---|
| 29 | from requirements analysis downto deployment and maintenance. |
---|
| 30 | More specifically, COACH focuses on: |
---|
| 31 | \begin{itemize} |
---|
| 32 | \item High level methods and concepts (esp. requirements and architectural level) for system |
---|
| 33 | design, development and integration, addressing complexity aspects and modularity. |
---|
| 34 | \item Open and modular design environments, enabling flexibility and extensibility by |
---|
| 35 | means of new or sector-specific tools and ensuring consistency and traceability along the |
---|
| 36 | development lifecycle. |
---|
| 37 | \item Light/agile methodologies and adaptive workflow providing a dynamic and adaptive |
---|
| 38 | environment, suitable for co-operative and distributed development. |
---|
[297] | 39 | \item \mustbecompleted{IP-XACT: .... MAGILLEM...} |
---|
[289] | 40 | \end{itemize} |
---|
| 41 | COACH outcome will contribute to strengthen Europe's competitive position by developing |
---|
| 42 | technologies and methodologies for product design, focusing (in compliance with the |
---|
| 43 | %scope of the above program) on technologies, engineering methodologies, novel tools, |
---|
| 44 | %methods which facilitate resource use efficiency. The approaches and tools to be developed |
---|
| 45 | %in COACH will enable new and emerging information technologies for the development, |
---|
| 46 | %methods which facilitate resource use efficiency. The COACH approaches and tools |
---|
| 47 | scope of the above program) on technologies, engineering methodologies, novel tools |
---|
| 48 | which facilitate resource use efficiency. The COACH approaches and tools |
---|
| 49 | will enable new and emerging information technologies for the development, |
---|
| 50 | manufacturing and integration of devices and related software into end-products. |
---|
| 51 | %%% |
---|
| 52 | \parlf\noindent |
---|
| 53 | The COACH project will benefit from a number of previous recent projects: |
---|
| 54 | \begin{description} |
---|
| 55 | \item[SOCLIB] |
---|
[297] | 56 | The SoCLib ANR platform (2007-2009) is an open infrastructure |
---|
| 57 | that supports system level virtual prototyping of shared memory, multi-processors |
---|
[289] | 58 | architectures, and provides tools to map multi-tasks software application on these |
---|
| 59 | architectures, for reliable performance evaluation. |
---|
| 60 | The core of this platform is a library of SystemC simulation models for |
---|
[297] | 61 | general purpose IP cores. |
---|
| 62 | It provides also embedded operating systems and software/hardware |
---|
[289] | 63 | communication middleware. |
---|
| 64 | \item[ROMA] The ROMA ANR project \cite{roma} |
---|
| 65 | involving IRISA (CAIRN team), LIRMM, CEA List, THOMSON France R\&D, |
---|
| 66 | proposes to develop a reconfigurable processor, exhibiting high |
---|
| 67 | silicon density and power efficiency, able to adapt its computing |
---|
| 68 | structure to computation patterns that can be speed-up and/or |
---|
| 69 | power efficient. %The ROMA project study a pipeline of |
---|
| 70 | %evolved low-power coarse grain reconfigurable operators to avoid |
---|
| 71 | %traditional overhead, in reconfigurable devices, related to the |
---|
| 72 | %interconnection network. |
---|
| 73 | The project will borrow from the ROMA |
---|
| 74 | ANR project and the ongoing joint INRIA-STMicro |
---|
| 75 | Nano2012 project to adapt existing pattern extraction algorithms |
---|
| 76 | and datapath merging techniques to ASIP synthesis. |
---|
| 77 | % and datapath merging techniques to the synthesis of customized |
---|
| 78 | % ASIP processors. |
---|
| 79 | \item[TSAR] |
---|
| 80 | The TSAR MEDEA+ project (2008-2010) involving BULL, THALES and \upmc targets the design of a |
---|
| 81 | % The TSAR MEDEA+ project (2008-2010) targets the design of a |
---|
| 82 | scalable, coherent shared memory, multi-cores processor architecture, and uses the SoCLib |
---|
| 83 | plaform for virtual prototyping. COACH will benefit from the synthesizable VHDL |
---|
| 84 | models developped in the framework of TSAR (MIPS32 processor core, and RING interconnect). |
---|
| 85 | \item[BioWic] |
---|
| 86 | On the HPC application side, we also hope to benefit from the experience in |
---|
| 87 | hardware acceleration of bioinformatic algorithms/workfows gathered by the |
---|
| 88 | CAIRN group in the context of the ANR BioWic project (2009-2011), so as to |
---|
| 89 | be able to validate the framework on real-life HPC applications. |
---|
[297] | 90 | \item[SoCket] \mustbecompleted{...... MAGILEM ......} |
---|
| 91 | \item[HOSPI] \mustbecompleted{...... MAGILEM ......} |
---|
| 92 | \item[SoftSoc] \mustbecompleted{...... MAGILEM ......} |
---|
[289] | 93 | \end{description} |
---|
| 94 | %%% |
---|
| 95 | \parlf\noindent |
---|
[297] | 96 | The partners involved in the COACH project have a well established expertise |
---|
| 97 | in the following domains: |
---|
[289] | 98 | \begin{itemize} |
---|
| 99 | \item |
---|
| 100 | In the field of High Level Synthesis (HLS), the project |
---|
| 101 | leverages on know-how acquired over the last 15 years with the GAUT~\cite{gaut08} project |
---|
[297] | 102 | developed by the \ubs laboratory, and with the UGH~\cite{ugh08} project developed |
---|
[289] | 103 | by the \upmc and \tima laboratories. |
---|
| 104 | \item |
---|
| 105 | Regarding system level architecture, the project is based on the know-how |
---|
| 106 | acquired by \upmc and \tima in the framework of various projects |
---|
| 107 | in the field of communication architectures for shared memory multi-processors systems |
---|
| 108 | (COSY~\cite{cosy}, DISYDENT~\cite{disydent05} or DSPIN~\cite{dspin08} of MEDEA-MESA). |
---|
| 109 | As an example, the DSPIN project is now used in the TSAR project. |
---|
| 110 | \item |
---|
| 111 | Regarding Application Specific Instruction Processor (ASIP) design, the |
---|
| 112 | CAIRN group at INRIA Rennes -- Bretagne Atlantique benefits from several years of |
---|
| 113 | expertise in the domain of retargetable compiler |
---|
| 114 | (Armor/Calife~\cite{CODES99} since 1996, and the Gecos |
---|
| 115 | compilers~\cite{ASAP05} since 2002). |
---|
[297] | 116 | \item |
---|
[289] | 117 | In the field of compilers, the \lip Compsys group was founded in 2002 |
---|
| 118 | by several senior researchers with experience in |
---|
| 119 | high performance computing and automatic parallelization. They have been |
---|
| 120 | among the initiators of the polyhedral model, a theory which serve to |
---|
| 121 | unify many parallelism detection and exploitation techniques for regular |
---|
| 122 | programs. It is expected that the techniques developped by \lip for |
---|
| 123 | parallelism detection, scheduling \cite{Feau:92aa,Feau:92bb}, |
---|
| 124 | process construction \cite{Feau:96} and memory management \cite{bee} |
---|
| 125 | will be very useful as a front-end for HLS tools. |
---|
[297] | 126 | \item |
---|
| 127 | Regarding \mustbecompleted{.... MAGILLEM ... IP-XACT} |
---|
[289] | 128 | \end{itemize} |
---|
| 129 | %%% |
---|
| 130 | \parlf\noindent |
---|
[297] | 131 | The COACH project totally fulfills the objectives of the axis 2 "METHODES, |
---|
| 132 | OUTILS ET TECHNOLOGIES POUR LES SYSTEMES EMBARQUES". |
---|
| 133 | \mustbecompleted{BEGIN-FIXME} |
---|
[289] | 134 | COACH will address new embedded systems architectures by allowing the design of |
---|
| 135 | Multi-Core Systems-on-Chip (possibly heterogeneous) on FPGA according to the design |
---|
| 136 | constraints and objectives (real-time, low-power). It will permit designing complex SoC |
---|
| 137 | based on IP cores (memory, peripherals...), |
---|
| 138 | running Embedded Software, as well as an Operating System with associated middleware and |
---|
| 139 | API and using hardware accelerator automatically generated. It will also permit to use |
---|
| 140 | efficiently different dynamic system management techniques and re-configuration mechanisms. |
---|
[297] | 141 | \\ |
---|
[289] | 142 | COACH will address High-Performance Computing (HPC) by helping designers to accelerate an |
---|
| 143 | application running on a PC. |
---|
| 144 | By providing tools that translate high level language programs to FPGA |
---|
| 145 | configurations, COACH will allow to easily migrate critical parts into an FPGA plugged to the |
---|
| 146 | PC bus (through a communication link like PCI/X). |
---|
[297] | 147 | \mustbecompleted{END-FIXME} |
---|
| 148 | \parlf |
---|
| 149 | The COACH project well fits also the axis 5 "USAGES". |
---|
| 150 | \mustbecompleted{BEGIN-FIXME} |
---|
[289] | 151 | COACH will address robotic and control applications by |
---|
| 152 | allowing to design complex systems based on MPSoC architecture. |
---|
| 153 | Like in the consumer electronics domain, future control applications |
---|
| 154 | will employ more and more SoC for safety and security applications. |
---|
| 155 | Application domains for such systems are for example automotive |
---|
| 156 | or avionics domains (e.g. collision-detection, intelligent navigation...). |
---|
| 157 | Manufacturing technology will also increasingly need high-end vision analysis and high-speed |
---|
| 158 | robot control. |
---|
[297] | 159 | % |
---|
[289] | 160 | The results of the COACH project will help users to build cryptographic secure systems implemented in |
---|
| 161 | hardware or both in software/hardware in an effective way, substantially enhancing the |
---|
| 162 | process productivity of the cryptographic algorithms hardware synthesis, improving the |
---|
| 163 | quality and reducing the design time and the cost of synthesised cryptographic devices. |
---|
[297] | 164 | \mustbecompleted{END-FIXME} |
---|
| 165 | \parlf |
---|
[289] | 166 | Finally, it is worth to note that this project covers priorities defined by the commission |
---|
| 167 | experts in the field of Information Technolgies Society (IST) for Embedded |
---|
| 168 | Systems: \textit{ $<<$Concepts, methods and tools for designing systems dealing with systems complexity |
---|
| 169 | and allowing to apply efficiently applications and various products on embedded platforms, |
---|
| 170 | considering resources constraints (delays, power, memory, etc.), security and quality |
---|
| 171 | services$>>$}. |
---|