source: anr/task-3.tex @ 279

Last change on this file since 279 was 278, checked in by coach, 14 years ago

Reduced the task number. Suppressed xilinx, navtel and flexra. Added mds.

File size: 4.2 KB
RevLine 
[26]1\begin{taskinfo}
2\let\LIP\leader
3\let\IRISA\enable
[126]4\let\UBS\enable
5\let\UPMC\enable
6\let\TIMA\enable
[26]7\end{taskinfo}
8%
9\begin{objectif}
[41]10The objective of this task is to convert the input specification of
11an hardware accelerator, which must be written in a familiar language
12(C/C++) with as few constraints as possible, into a form suitable for
[109]13the HLS tools (i.e. HAS back-end tools of the COACH project). If the
14target is an ASIP, the frontend has to extract
[41]15patterns from the source code and convert them into the definition
16of an extensible processor. If the target is a process network, the
17front end has to distribute the workload and the data sets as fairly
18as possible, identify communication channels, and output an \xcoach
19description.
[26]20\end{objectif}
21%
[52]22\begin{workpackage}
[278]23  \subtask{ASIP compiler}
24  This sub-task aims at providing compiler support for custom instructions
[85]25  within the HAS front-end. It will take as input the COACH intermediate
[86]26  representation, and will output an annotated COACH IR containing the custom
27  instructions definitions along with their occurrence in the application.
[26]28    \begin{livrable}
[152]29      \itemV{0}{18}{x}{\Sirisa}{ASIP compilation flow}
[85]30        In this first version of the software, the computations patterns corresponding to
[121]31        custom instructions are specified by the user, and then automatically extracted (when
[86]32        beneficial) from the application intermediate representation.
[152]33      \itemL{18}{24}{x}{\Sirisa}{ASIP compilation flow}{6:9:0}
[86]34        In this second version, the software will also be able to automatically identify
[85]35        interesting pattern candidates in the application code, and use them as custom
36        instructions. 
[26]37    \end{livrable}
[85]38 
[278]39 \subtask{Micro-architectural template models for ASIP}
40 In this sub-task, we provide micro-architectural template models for the two target
[121]41 processor architectures (NIOS-II and MIPS) supported within the COACH-ASIP design flow.
[85]42 For each processor, we provide a simulation model (System-C) and a synthesizable model (VHDL)
43 of the architecture, along with its architectural extensions
[26]44    \begin{livrable}
[152]45      \itemV{0}{12}{x}{\Sirisa}{SystemC for extensible MIPS }
[121]46      { A SystemC simulation model for a simple extensible MIPS architectural template }
[152]47      \itemL{12}{20}{x}{\Sirisa}{SystemC for extensible MIPS}{2:3:0}
[121]48      {A SystemC simulation model for an extensible MIPS with a tight architectural integration of
[93]49      its instruction set extensions}
[267]50      \itemV{3}{18}{h}{\Sirisa}{VHDL for an extensible MIPS}
[121]51      {A synthesizable VHDL model for a simple extensible MIPS architectural template}
[217]52      \itemL{18}{24}{h}{\Sirisa}{VHDL for extensible MIPS}{9:12:0}
[121]53      {A synthesizable VHDL model for an extensible MIPS with a tight architectural integration of
[93]54      its instruction set extensions}
[152]55      \itemL{24}{36}{d}{\Sirisa}{Evaluation report }{0:0:2}
[121]56      {An evaluation report with quantitative analysis of the performance/area trade-off induced by
[93]57      the different approaches}
[26]58    \end{livrable}
[85]59
[278]60 \subtask{Parallelism optimization}
61  Extraction of parallelism in polyhedral loops and conversion into a process network.
[41]62   \begin{livrable}
[52]63    \itemV{0}{6}{d}{\Slip}{Method, Preliminary Definition}
[237]64      Description and specification of a process construction method for programs with
[178]65      polyhedral loops.
[224]66    \itemL{30}{36}{d}{\Slip}{Process generation method}{10:0:9}
[178]67      Final assessment of the method and improved version of the specification.
[110]68    \itemV{6}{12}{x}{\Slip}{Process construction}
[83]69      Preliminary implementation in the Syntol framework.
[86]70      At this step the software will just implement a single constructor.
[83]71    \itemV{12}{18}{x}{\Slip} {Arrays and FIFO}
72      Implementation of the array contraction and FIFO construction algorithm.
73      Conversion of the input and output to the \xcoach format.
[87]74    \itemV{18}{30}{d+x}{\Slip}{Non-polyhedral extension}
[84]75      Extension of automatic parallelization and array contraction
[87]76      to non-polyhedral loops. Implementation in the Bee framework.
[224]77    \itemL{30}{36}{x}{\Slip} {Process/FIFO construction}{10:20:12}
[83]78      Final release taking into account the feedbacks from the
79      demonstrator \STs.
[41]80   \end{livrable}
[83]81
[41]82\end{workpackage}
83   
Note: See TracBrowser for help on using the repository browser.