source: anr/section-3.2.tex @ 248

% les objectifs scientifiques/techniques du projet.
The objectives of the COACH project are to develop a complete framework to HPC
(accelerating solutions for existing software applications) and embedded
applications (implementing an application on a low power standalone
device).  The design steps are presented figure~\ref{coach-flow}.
\begin{figure}[hbtp]\leavevmode\center
  \includegraphics[width=.8\linewidth]{flow}
  \caption{\label{coach-flow} COACH design flow}
\end{figure}
\begin{description}
\item[HPC setup:] During this step, the user splits the application into 2 parts: the host application
which remains on a PC and the SoC application which is mapped on the FPGA. 
COACH will allow to automatically translate high level language programs to FPGA configurations.
In addition, it will provide a SystemC simulation model of the whole system (PC+communication+FPGA-SoC) 
which will allow performance evaluation of the partitioning.
\item[SoC design:] In this phase, 
COACH will allow the user to obtain simulators for the SoC at different abstraction levels by giving to the COACH framework a SoC description.  
This description will consist of a process network corresponding to the application, 
an OS, an instance of a generic hardware platform
and a mapping of processes on the platform components. COACH will offer different targets to map the processes:  
software (the process runs on a SoC processor),
ASIP (the process runs on a SoC processor enhanced with dedicated instructions),
and hardware (the process runs into a coprocessor that is generated by HLS and plugged on the SoC bus).
\item[Application compilation:] Once the SoC description is validated through performances analysis, COACH will generate automatically
an FPGA bitstream containing the hardware platform with the SoC application software and 
an executable containing the host application. The user will be able to launch the application by
loading the bitstream on an FPGA and running the executable on PC.
\end{description}
 
% l'avancee scientifique attendue. Preciser l'originalite et le caractere 
% ambitieux du projet. 
%FIXME == {NON ceci n'est pas une contribution scientifique. A re-ecrire}

%The main scientific contribution of the project is to unify various synthesis techniques
%(same input and output formats) allowing the user to swap without engineering effort
%from one to another and even to chain them. For instance, it will be possible to run loop transformations before synthesis.
%Another advantage of this framework is to provide different abstraction levels from
%a single description.
%Finally, this description is device family independent and its hardware implementation
%is automatically generated.

% Detailler les verrous scientifiques et techniques a lever par la realisation du projet.
System design is a very complex task and in this project we will try to simplify it
as much as possible. For this purpose the following scientific and technological barriers
have to be addressed.

\begin{description}
\item[Design Space Exploration:]
    The COACH environment will allow to easily map an application described by using a process 
        network Model of Computation (MoC) on a shared-memory, MPSoC architecture. COACH will
        permit to explore the design space by allowing system designer to select and 
        parameterize the target architecture, and to define the best hardware/software 
        partitioning of the application.

\item[High-Level Synthesis:]
    COACH will allow the automatic generation of hardware accelerators when required
        by using High-Level Synthesis (HLS) tools.
        HLS will thus be fully integrated into a complete system-level design environment.
        Moreover, COACH will support both data and control dominated applications. 
    Indeed, the HLS tools of COACH will support a common language and coding style 
        to avoid re-engineering by the designer.
    COACH will provide a tool which will automatically explore the micro-architectural 
        design space of coprocessor.

\item[High-level code transformation:]
    COACH will allow to optimize the memory usage, to enhance the parallelism through 
        loop transformations and parallelization. The challenge is to identify the coarse 
        grained parallelism and to generate,
        from a sequential algorithm, application containing multiple communicating
        tasks. To this aim, one may adapt techniques which were developed in the 1990 for 
        the construction of distributed programs. However, in the context of HLS, there are 
        still several original problems to be solved, mainly to do with the construction of 
        FIFO communication channels and with memory optimization.
        Additionnal preprocessing, source-level transformations, are thus
        required to improve the process.
        Particularly, this includes parallelism exposure and efficient memory mapping.
        COACH will support code transformation by providing a source to source C2C tool.

\item[Platform based design:] 
    COACH will define architectural templates that can be customized by adding
    dedicated coprocessors and ASIPs and by fixing template parameters such as
    the number of embedded processors, the number of sizes of embedded memory banks
    or the embedded the operating system.
    However, the specification of the application will be independant of both the
    architectural template and the target FPGA device.

\item[Hardware/Software communication middleware:]
    COACH will implement an homogeneous HW/SW communication infrastructure and
    communication APIs (Application Programming Interface), that will be used for 
    communications between software tasks running on embedded processors and 
    dedicated hardware coprocessors. This will allow explore the design space by 
        mapping the tasks of application (described as a process network) on a 
        shared-memory, MPSoC architecture.

\item[Processor customization:]
ASIP design will be addressed by the COACH project. COACH will allow system designers to explore 
the various level of interactions between the original CPU micro-architecture and its
  extension. It will also allow to retarget the compiler instruction-selection pass. Finally,
 COACH will integrate ASIP design in a complete System-level design framework.

\item [High-Performance Computing:] The main problem in HPC is the communication 
between the PC and the SoC. This problem has 2 aspects. The first one is the run-time 
efficiency. The second is its engineering  cost, especially if one want to refine an 
implementation at several abstract levels.
COACH will 

%\item The COACH design flow has a top-down approach. In such a case,
%the required performance of a coprocessor (clock frequency, maximum cycles for
%a given computation, power consumption, etc) are imposed by the other system
%components. The challenge is to allow the user to control accurately the synthesis
%process. For instance, the clock frequency must not be a result of the RTL synthesis
%but a strict synthesis constraint.

\end{description}




%Presenter les resultats escomptes en proposant si possible des criteres de reussite 
%et d'evaluation adaptes au type de projet, permettant d'evaluer les resultats en 
%fin de projet.
The main result is the framework. It is composed concretely of: 
a communication middleware for HPC, 
5 HAS tools (control dominated HLS, data dominated HLS, Coarse grained HLS, 
Memory optimisation HLS and ASIP),
3 architectural templates that are synthesizable and that can be prototyped,
one design space exploration tool,
2 operating systems (DNA/OS and MUTEKH).
\\
The framework fonctionality will be demonstrated with the demonstrators
(see task-7 page~\pageref{task-7}) and the tutorial example (see task-8
page~\ref{subtask-tutorial}).