DOC: add a benchmarks that compares us to gcc and icc.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170509 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/docs/Vectorizers.rst b/docs/Vectorizers.rst
index 291c76dd2654e55a6913692a2ee7038de1f2ec23..b60e46dbca0b9be92ad1fb211d8b1a9e968bee20 100644 (file)
--- a/docs/Vectorizers.rst
+++ b/docs/Vectorizers.rst
@@ -188,6 +188,19 @@ See the table below for a list of these functions.
 |fma  |trunc|nearbyint|
 +-----+-----+---------+
 
+Performance
+^^^^^^^^^^^
+
+This section shows the the execution time of Clang on a simple benchmark: 
+`gcc-loops <http://llvm.org/viewvc/llvm-project/test-suite/trunk/SingleSource/UnitTests/Vectorizer/>`._
+This benchmarks is a collection of loops from the GCC autovectorization 
+`page <http://gcc.gnu.org/projects/tree-ssa/vectorization.html>` by Dorit Nuzman._
+
+The chart below compares GCC-4.7, ICC-13, and Clang-SVN at -O3, running on a Sandybridge.
+The Y-axis shows time in msec. Lower is better.
+
+.. image:: gcc-loops.png
+
 The Basic Block Vectorizer
 ==========================
 

diff --git a/docs/gcc-loops.png b/docs/gcc-loops.png
new file mode 100644 (file)
index 0000000..e178146
Binary files /dev/null and b/docs/gcc-loops.png differ