* 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, 22 insertions, 0 deletions

diff --git a/Eigen/src/Core/NestByValue.h b/Eigen/src/Core/NestByValue.h
index 0c6cdb114..a63202dfd 100644
--- a/Eigen/src/Core/NestByValue.h
+++ b/Eigen/src/Core/NestByValue.h
@@ -76,6 +76,16 @@ template<typename ExpressionType> class NestByValue
       return m_expression.const_cast_derived().coeffRef(row, col);
     }
 
+    inline const Scalar _coeff(int index) const
+    {
+      return m_expression.coeff(index);
+    }
+
+    inline Scalar& _coeffRef(int index)
+    {
+      return m_expression.const_cast_derived().coeffRef(index);
+    }
+
     template<int LoadMode>
     inline const PacketScalar _packet(int row, int col) const
     {
@@ -88,6 +98,18 @@ template<typename ExpressionType> class NestByValue
       m_expression.const_cast_derived().template writePacket<LoadMode>(row, col, x);
     }
 
+    template<int LoadMode>
+    inline const PacketScalar _packet(int index) const
+    {
+      return m_expression.template packet<LoadMode>(index);
+    }
+
+    template<int LoadMode>
+    inline void _writePacket(int index, const PacketScalar& x)
+    {
+      m_expression.const_cast_derived().template writePacket<LoadMode>(index, x);
+    }
+
   protected:
     const ExpressionType m_expression;
 };