1 | \definecolor{gtcBoxHeavy}{rgb}{0.10,0.10,0.90} |
---|
2 | \definecolor{gtcBoxLight}{rgb}{0.9,0.90,0.99} |
---|
3 | \definecolor{gtcTaskBG0} {rgb}{0.99,0.90,0.7} |
---|
4 | \definecolor{gtcTaskBG1} {rgb}{0.90,0.99,0.7} |
---|
5 | \definecolor{gtcMilestone}{rgb}{0.9,0.4,0.4} |
---|
6 | \immediate\write\ganttdata{ML=6 ML=12 ML=18 ML=24} |
---|
7 | \def\ganttlabelstyle#1{\begin{small}#1\end{small}} |
---|
8 | \def\gantttitlestyle#1{\begin{scriptsize}\textit{#1}\end{scriptsize}} |
---|
9 | |
---|
10 | %\begin{figure}\leavevmode\center |
---|
11 | %\hspace*{-.6cm} |
---|
12 | %\input{gantt.tex} |
---|
13 | %\caption{\label{gantt}Gantt diagram of delivrables} |
---|
14 | %\end{figure} |
---|
15 | |
---|
16 | \begin{figure}\leavevmode\center |
---|
17 | \hspace*{-.6cm}\vspace{-1.5cm} |
---|
18 | \input{gantt1.tex} |
---|
19 | \caption{\label{gantt1}Gantt diagram of delivrables (task-1 to task-4)} |
---|
20 | \end{figure} |
---|
21 | |
---|
22 | \begin{figure}\leavevmode\center |
---|
23 | \hspace*{-.6cm}\vspace{-1.5cm} |
---|
24 | \input{gantt2.tex} |
---|
25 | \caption{\label{gantt2}Gantt diagram of delivrables (task-5 to task-8)} |
---|
26 | \end{figure} |
---|
27 | |
---|
28 | The figures~\ref{gantt1}~\&~\ref{gantt2} present the Gantt diagram of the project. |
---|
29 | Before the final release (T0+36), there are 4 milestones (red lines on the figures) at |
---|
30 | $T0+6$, $T0+12$, $T0+18$ and $T0+24$ that are rendez-vous points of the precedent |
---|
31 | delivrables. |
---|
32 | \begin{description} |
---|
33 | \item[Milestone 1 ($T0+6$)] Specification of COACH inputs, of the \xcoach format and of |
---|
34 | the demonstatrors as a reference software. |
---|
35 | \item[Milestone 2 ($T0+12$)] The first COACH release. At this step the demonstrators are |
---|
36 | written in the COACH input format. This COACH release allows to prototype and to generate the FPGA-SoC. |
---|
37 | The main restrictions are: |
---|
38 | 1) only the COACH architectural template is supported, |
---|
39 | 2) HAS is not available (but prototyping with virtual coprocessors is available), |
---|
40 | 3) Enhanced communication schemes are not available. |
---|
41 | \item[Milestone 3 ($T0+18$)] The second COACH release. At this step most of the COACH |
---|
42 | features are availables. |
---|
43 | The main restriction is that COACH can not yet generate FPGA-SoC for ALTERA and XILINX |
---|
44 | architectural templates. |
---|
45 | The others restriction is that the HAS tools are not yet fully operational. |
---|
46 | \item[Milestone 4 ($T0+24$)] The pre-release of the COACH project. The full design flow is |
---|
47 | supported. |
---|
48 | The main restriction are: |
---|
49 | 1) The HAS tools have not been yet enhanced, |
---|
50 | 2) dynamic partial reconfiguration is not supported, |
---|
51 | 3) \mustbecompleted{FIXME:ALL .....} |
---|
52 | \item[Final Release ($T0+36$)] |
---|
53 | \end{description} |
---|
54 | This organisation allows to advance globally the project step by step mixing development |
---|
55 | and demonstrator delivrables. |
---|
56 | Hence, demonstrator feed-back will arrive early and so the risk to point out incompatibility |
---|
57 | at the integration phase is significantly reduced. |
---|
58 | \par |
---|
59 | The project has several critical issues: |
---|
60 | \begin{description} |
---|
61 | \item[\xcoachplus format (\novers{\specXcoachDoc}, \novers{\specXcoachToCA})] |
---|
62 | Because all the HAS tools rely on it, it is a |
---|
63 | crucial task. There are no work-arround but as mentionned in |
---|
64 | section~\ref{xcoach-problem} (page~\pageref{xcoach-problem}) we have worked on it |
---|
65 | for a year and are confident. |
---|
66 | \item[\xcoachplus format (\novers{\specXcoachDoc}, |
---|
67 | \novers{\specXcoachToSystemC}, \novers{\specXcoachToVhdl})] |
---|
68 | Its aim is the generation of the coprocessors (hardware \& prototyping model). |
---|
69 | By centralizing the coprocessor generation, it guarantees their functioning |
---|
70 | independently of the used HAS tools. |
---|
71 | Our experience with UGH and GAUT give us confidence in the succes of this |
---|
72 | task. |
---|
73 | \item[prototyping of ALTERA \& XILINX architectural templates ({\csgAlteraSystemC}, |
---|
74 | {\csgXilinxSystemC}] |
---|
75 | The SocLib component library contains most of the SystemC models used for the |
---|
76 | prototyping description of the ALTERA and XILINX architectural templates. |
---|
77 | Nevertheless, at this time we do not know how many are missing and if the existing |
---|
78 | are really useables. |
---|
79 | If the work of theses tasks is too important, they will be abandoned. |
---|
80 | In this case the work-arround to prototype the XILINX and ALTERA architectural |
---|
81 | templates is to use the COACH one. These architectures being very similar, the |
---|
82 | simulation results must be proportional. Theses tasks will be changed by measuring |
---|
83 | the deviance. |
---|
84 | \item[VCI/AVALON \& VCI/PLB bridges (\novers{\hpcAvalonBridge}, \novers{\hpcPlbBridge})] |
---|
85 | If one of these tasks is impossible or too important or leads to inefficiency, |
---|
86 | it will be abandoned. |
---|
87 | In this case, the COACH architectural template will not be available for HPC and |
---|
88 | a SystemC VCI model corresponding to the PCI/X IP will be developped to allow |
---|
89 | prototyping. |
---|
90 | \end{description} |
---|
91 | |
---|