[www] r290897 - Add DawnCC to the project page

[Mehdi Amini via llvm-commits]

Author: mehdi_amini
Date: Tue Jan  3 12:08:06 2017
New Revision: 290897

URL: http://llvm.org/viewvc/llvm-project?rev=290897&view=rev
Log:
Add DawnCC to the project page

Modified:
    www/trunk/ProjectsWithLLVM/index.html

Modified: www/trunk/ProjectsWithLLVM/index.html
URL: http://llvm.org/viewvc/llvm-project/www/trunk/ProjectsWithLLVM/index.html?rev=290897&r1=290896&r2=290897&view=diff
==============================================================================
--- www/trunk/ProjectsWithLLVM/index.html (original)
+++ www/trunk/ProjectsWithLLVM/index.html Tue Jan  3 12:08:06 2017
@@ -36,6 +36,7 @@
 <div class="www_text">
 
 <ul>
+<li><a href="#dawncc">DawnCC</a></li>
 <li><a href="#terralang">Terra Lang</a></li>
 <li><a href="#codasip">Codasip Studio</a></li>
 <li><a href="#pony">Pony Programming Language</a></li>
@@ -79,6 +80,40 @@
 </div>
 
 <!--=========================================================================-->
+<div class="www_subsection">
+  <a name="dawncc">Automatic Insertion of Copy Annotation in Data-Parallel 
+	  Programs</a>
+</div>
+
+<div class="www_subsubsection">
+  By Gleison Mendonca, Breno Campos Ferreira Guimaraes, Péricles Alves, 
+  Marcio Machado Pereira, Guido Araéujo, and Fernando Magno Quintao 
+  Pereira.<br/>
+  See Dawn project <a href="http://cuda.dcc.ufmg.br/dawn/">webpage</a>.
+</div>
+
+<div class="www_text">
+  <p>
+  Directive-based programming models, such as OpenACC and OpenMP arise today as
+  promising techniques to support the development of parallel applications.
+  These systems allow developers to convert a sequential program into a parallel
+  one with minimum human intervention. However, inserting pragmas into
+  production code is a difficult and error-prone task, often requiring
+  familiarity with the target program. This difficulty restricts the ability of
+  developers to annotate code that they have not written themselves. This paper
+  provides one fundamental component in the solution of this problem. We
+  introduce a static program analysis that infers the bounds of memory regions
+  referenced in source code. Such bounds allow us to automatically insert
+  data-transfer primitives, which are needed when the parallelized code is meant
+  to be executed in an accelerator device, such as a GPU. To validate our ideas,
+  we have applied them onto Polybench, using two different architectures: Nvidia
+  and Qualcomm-based. We have successfully analyzed 98% of all the memory
+  accesses in Polybench. This result has enabled us to insert automatic
+  annotations into those benchmarks leading to speedups of over 100x.
+  </p>
+</div>
+
+<!--=========================================================================-->
 <div class="www_subsection">
   <a name="terralang">Terra: A low-level counterpart to Lua</a>
 </div>