* add bench/benchVecAdd.cpp by Gael, fix crash (ei_pload on non-aligned)

* introduce packet(int), make use of it in linear vectorized paths
  --> completely fixes the slowdown noticed in benchVecAdd.
* generalize coeff(int) to linear-access xprs
* clarify the access flag bits
* rework api dox in Coeffs.h and util/Constants.h
* improve certain expressions's flags, allowing more vectorization
* fix bug in Block: start(int) and end(int) returned dyn*dyn size
* fix bug in Block: just because the Eval type has packet access
  doesn't imply the block xpr should have it too.

1 files changed, 6 insertions, 6 deletions

diff --git a/Eigen/src/Core/IO.h b/Eigen/src/Core/IO.h
index f7094a4a1..762e1fb31 100644
--- a/Eigen/src/Core/IO.h
+++ b/Eigen/src/Core/IO.h
@@ -31,14 +31,14 @@
   */
 template<typename Derived>
 std::ostream & operator <<
-( std::ostream & s,
-  const MatrixBase<Derived> & m )
+(std::ostream & s,
+ const MatrixBase<Derived> & m)
 {
-  for( int i = 0; i < m.rows(); i++ )
+  for(int i = 0; i < m.rows(); i++)
   {
-    s << m( i, 0 );
-    for (int j = 1; j < m.cols(); j++ )
-      s << " " << m( i, j );
+    s << m.coeff(i, 0);
+    for(int j = 1; j < m.cols(); j++)
+      s << " " << m.coeff(i, j);
     if( i < m.rows() - 1)
       s << "\n";
   }