Changeset 328 for anr/task-frontend.tex

Timestamp:

Jan 26, 2011, 6:15:22 PM (13 years ago)

Author:

coach

Message:

 

File:

• anr/task-frontend.tex (modified) (1 diff)

anr/task-frontend.tex

@@ -58 +58 @@
     \end{livrable}
 
- \subtask{Parallelism optimization}
-  Extraction of parallelism in polyhedral loops and conversion into a process network.
+ \subtask{Automatic parallelization and memory optimization}
+
+This sub-task aims at providing a source-level optimizer in front the
+HLS back-end tools. The optimization are twofold:
+\begin{itemize}
+\item Extraction of parallelism in polyhedral loops and conversion
+  into a process network.
+\item Minimization of intra-process local memory
+\item Construction of inter-process FIFOs
+\end{itemize}
+We will design these methods by using polyhedral techniques, as we did
+in the past for pure HPC optimizations. The program model is typically
+regular programs with affine loop bound conditions and array index
+functions. In a second part, we will extend the program model by using
+conservative approximations.
    \begin{livrable}
     \itemV{0}{6}{d}{\Slip}{Method, Preliminary Definition}
       Description and specification of a process construction method for programs with 
       polyhedral loops. 
-    \itemL{30}{36}{d}{\Slip}{Process generation method}{10:0:9}
-      Final assessment of the method and improved version of the specification.
     \itemV{6}{12}{x}{\Slip}{Process construction}
       Preliminary implementation in the Syntol framework. 
       At this step the software will just implement a single constructor.
-    \itemV{12}{18}{x}{\Slip} {Arrays and FIFO}
-      Implementation of the array contraction and FIFO construction algorithm. 
-      Conversion of the input and output to the \xcoach format.
+    \itemL{30}{36}{d+x}{\Slip}{Process generation method}{10:0:9}
+      Final assessment of the method and improved version of the specification.
+%
+    \itemV{6}{12}{d}{\Slip} {Arrays and FIFO}
+    Description and specification of the FIFO construction method
+    and local memory optimization algorithms.
+    \itemV{12}{18}{d+x}{\Slip} {Arrays and FIFO}
+    Preliminary implementation in the Bee framework.
+    Conversion of the input and output of Bee to the \xcoach format.
+    At this step, only memory optimizations will be available.
+    \itemL{18}{30}{d+x}{\Slip}{Arrays and FIFO}{10:0:9}
+    Final assessment of the method and improved version of the specification.
+%
     \itemV{18}{30}{d+x}{\Slip}{Non-polyhedral extension}
-      Extension of automatic parallelization and array contraction
+      Extension of automatic parallelization and memory optimization
       to non-polyhedral loops. Implementation in the Bee framework.
-    \itemL{30}{36}{x}{\Slip} {Process/FIFO construction}{10:20:12}
+    \itemL{30}{36}{d+x}{\Slip} {Non-polyhedral extension}{10:20:12}
       Final release taking into account the feedbacks from the 
       demonstrator \STs.