source: anr-2010/section-1.tex

Last change on this file was 269, checked in by coach, 14 years ago

IA: finale

File size: 10.0 KB
Line 
1% les objectifs globaux,
2The market of digital systems is about 4,600 M\$ today and is estimated to
35,600 M\$ in 2012. However the ever growing applications complexity involves
4integration of heterogeneous technologies and requires the design of
5complex Multi-Processors System on Chip (MPSoC).
6\\
7During the last decade, the design of ASICs (Application Specific
8Integrated Circuits) appeared to be more and more reserved to high volume markets, because
9the design and fabrication costs of such components exploded, due to increasing NRE (Non
10Recurring-Engineering) costs.
11Fortunately, FPGA (Field Programmable Gate Array) components, such as the
12Virtex5 family from \xilinx or the Stratix4 family from \altera, can nowadays
13implement a complete MPSoC with multiple processors and several dedicated
14coprocessors for a few Keuros per device. Many applications are initially captured
15algorithmically in High-Level Languages (HLLs) such as C/C++. This has led to growing interest
16in tools that can provide an implementation path directly from HLLs to hardware.
17Thus, Electronic System Level (ESL) design methodologies (Virtual Prototyping,
18Co-design, High-Level Synthesis...) are now mature and allow the automation of
19a system-level design flow. Unfortunately, ESL tool development to date has primarily focused
20on the design of hard-wired devices i.e. ASICs and ASSPs (Application Specific Standard Product).
21However, the increasing sophistication of FPGAs has accelerated the need for FPGA-based ESL design
22methodologies. ESL methodologies hold the promise of streamlining the design approach by accepting
23designs written in C/C++ language and implementing the function straight into FPGA.
24We believe that coupling FPGA technologies and ESL methodologies
25will allow both SMEs (Small and Medium Enterprise) and
26major companies to design innovative devices and to enter new, low and
27medium volume markets.
28\parlf
29The objective of COACH is to provide an integrated design flow, based on the
30SoCLib infrastructure~\cite{soclib}, and optimized for the design of
31multi-processors digital systems targeting FPGA devices.
32Such digital systems are generally integrated
33into one or several chips, and there are two types of applications:
34They can be embedded (autonomous) applications
35such as personal digital assistants (PDA), ambiant computing components,
36or wireless sensor networks (WSN).
37They can also be extension boards connected to a PC to accelerate a specific computation,
38as in High-Performance Computing (HPC) or High-Speed Signal Processing (HSSP).
39\parlf
40%verrous scientifiques et techniques
41The COACH environment will integrate several hardware and software technologies:
42\begin{description}
43\item[Design Space Exploration:]
44
45    The COACH environment will allow to describe an application as a process
46        network i.e. a set of tasks communicating through FIFO channels.
47        COACH will allow to map the application on a shared-memory, MPSoC architecture.
48    It will permit to easily explore the design space to help the system designer
49        to define the proper hardware/software partitioning of the application.
50    For each point in the design space, metrics such as throughput, latency, power
51    consumption, silicon area, memory allocation and data locality will be provided.
52    These criteria will be evaluated by using the SoCLib virtual prototyping infrastructure
53    and high-level estimation methodologies.
54       
55\item[Hardware Accelerators Synthesis (HAS):]
56    COACH will allow the automatic generation of hardware accelerators when required.
57    Hence, High-Level Synthesis (HLS) tools, Application Specific Instruction Processor
58    (ASIP) design environment and source-level transformation tools (loop transformations
59    and memory optimisation) will be provided.
60    This will allow further exploration of the micro-architectural design space.
61    HLS tools are sensitive to the coding style of the input specification and the domain
62    they target (control vs. data dominated).
63    The HLS tools of COACH will support a common language and coding style to avoid
64    re-engineering by the designer.
65\item[Platform based design:] 
66    COACH will handle both \altera and \xilinx FPGA devices.
67    COACH will define architectural templates that can be customized by adding
68    dedicated coprocessors and ASIPs and by fixing template parameters such as
69    the number of embedded processors, the number of sizes of embedded memory banks
70    or the embedded the operating system.
71    However, the specification of the application will be independant of both the
72    architectural template and the target FPGA device.
73    Basically, the following three architectural templates will be provided:
74    \begin{enumerate}
75    \item A Neutral architectural template based on the SoCLib IP core library and the
76      VCI/OCP communication infrastructure.
77    \item An \altera architectural template based on the \altera IP core library, the
78      AVALON system bus and the NIOS processor.
79    \item A \xilinx architectural template based on the Xilinx IP core library, the PLB
80      system bus and the Microblaze processor.
81    \end{enumerate}
82\item[Hardware/Software communication middleware:]
83    COACH will implement an homogeneous HW/SW communication infrastructure and
84    communication APIs (Application Programming Interface), that will be used for
85    communications between software tasks running on embedded processors and
86    dedicated hardware coprocessors.
87\end{description}
88The COACH design flow will be dedicated to system designers, and will as
89much as possible hide the hardware characteristics to the end-user.
90%From the end user point of view, the specification of the application will be
91%independant from both the architectural template and from the selected FPGA
92%family.
93\parlf
94% le programme de travail
95%The COACH project targets fundamental issues related to design methodologies for
96%digital systems by providing estimation, exploration and design tools targeting both
97%performance and power optimization at all the abstraction levels of the flow (system,
98%architecture, algorithm and logic).
99To reach this ambitious goal, the project will rely on the experience and the
100complementariness of partners in the following domains:
101Operating system and communication middleware (\tima, \upmc),
102MPSoC architectures (\tima, \ubs, \upmc),
103ASIP architectures (\irisa),
104High Level Synthesis (\tima, \ubs, \upmc), and compilation (\lip).
105\\
106The COACH project does not start from scratch.
107It stronly relies on the SoCLib virtual prototyping platform~\cite{soclib} for prototyping, (DSX, component library), operating systems (MUTEKH, DNA/OS).
108It also leverages on  several existing technologies:
109on the GAUT~\cite{gaut08} and UGH~\cite{ugh08} tools for HLS,
110on the ROMA~\cite{roma} project for ASIP,
111on the SYNTOL~\cite{syntol} and BEE~\cite{bee} tools for source-level analysis and transformations
112and on the \xilinx and \altera IP core libraries.
113Finally it will use the \xilinx and \altera logic and physical synthesis tools to generate the FPGA configuration
114bitstreams.
115\parlf
116The COACH proposal has been prepared during one year by a technical working group
117involving the 5 academic partners (one monthly meeting from january 2009 to february
1182010). The objective was to analyse the issues of integrating
119and enhancing the existing tools and tecnnologies into a unique framework.
120Most of the general software architecture of the proposed design flow (including the
121exchange format specification) has been define by this working group.
122Because the COACH project leanes on the ANR SoCLib platform, it may be described as an
123extension of the SoCLib platform.
124%The main development steps of the COACH project are:
125%\begin{enumerate}
126%   \item Definition of the end user inputs:
127%    The coarse grain parallelism of the application will be described as a communicating
128%    task graph, each task being described in C language.
129%    Similarly the architectural templates with their parameters and the design constraints
130%    will be specified.
131%  \item Definition of an internal format for representing task.
132%  \item Development of the GCC pluggin for generating the internal format of a
133%    C task.
134%  \item Adaptation of the existing HAS tools (BEE, SYNTOL, UGH, GAUT) to read and write
135%    the internal format. This will allow to swap from one tool to another one, and to
136%    chain them if necessary.
137%  \item Modification of the DSX tool (Design Space eXplorer) of the SocLib
138%    platform to generate the bitstream for the various FPGA families and architectural
139%    templates.
140%  \item Development of new tools such as ASIP compiler, HPC design environment and
141%    dynamic reconfiguration of FPGA devices.
142%\end{enumerate}
143\parlf
144Two major FPGA companies are involved in the project: \xilinx will contribute
145as a contractual partner providing documentation and manpower; \altera will contribute as
146a supporter (see letter page \pageref{supp:1})
147providing documentation and development boards. These two companies are strongly motivated
148to help the COACH project to generate efficient bitsreams for both FPGA families.
149The role of the industrial partners \bull, \thales, \navtel and \zied is to provide
150real use cases to benchmark the COACH design environment and to analyze the designer productivity
151improvements.
152\parlf
153Following the general policy of the SoCLib platform, the COACH project will be an open
154infrastructure, available in the framework of the SoCLib server.
155The architectural templates, and the COACH software tools will be distributed under the
156GPL license. The VHDL synthesizable models for the neutral architectural template (SoCLib
157IP core library) will be freely available for non commercial use. For industrial exploitation
158the technology providers are ready to propose commercial licenses, directly to the end user,
159or through a third party.
160\parlf
161Finally, the COACH project is already supported by a large number of PMEs, as demonstrated by the
162"letters of interest" (see Annex B), that have collected during the preparation of the project :
163ADACSYS, MDS, INPIXAL, CAMKA System, ATEME, ALSIM, SILICOMP-AQL,
164ABOUND Logic, EADS-ASTRIUM.
165
Note: See TracBrowser for help on using the repository browser.