* Big change in Block and Map:

- added a MapBase base xpr on top of which Map and the specialization
    of Block are implemented
  - MapBase forces both aligned loads (and aligned stores, see below) in expressions
    such as "x.block(...) += other_expr"
* Significant vectorization improvement:
 - added a AlignedBit flag meaning the first coeff/packet is aligned,
   this allows to not generate extra code to deal with the first unaligned part
 - removed all unaligned stores when no unrolling
 - removed unaligned loads in Sum when the input as the DirectAccessBit flag
* Some code simplification in CacheFriendly product
* Some minor documentation improvements
This commit is contained in:
Gael Guennebaud
2008-08-09 18:41:24 +00:00
parent becbeda50a
commit 4fa40367e9
17 changed files with 397 additions and 296 deletions

View File

@@ -43,8 +43,8 @@ template<typename ExpressionType, unsigned int Added, unsigned int Removed> clas
template<typename ExpressionType> class NestByValue;
template<typename ExpressionType> class SwapWrapper;
template<typename MatrixType> class Minor;
template<typename MatrixType, int BlockRows=Dynamic, int BlockCols=Dynamic,
int DirectAccessStatus = ei_traits<MatrixType>::Flags&DirectAccessBit> class Block;
template<typename MatrixType, int BlockRows=Dynamic, int BlockCols=Dynamic, int PacketAccess=Unaligned,
int _DirectAccessStatus = ei_traits<MatrixType>::Flags&DirectAccessBit> class Block;
template<typename MatrixType> class Transpose;
template<typename MatrixType> class Conjugate;
template<typename NullaryOp, typename MatrixType> class CwiseNullaryOp;
@@ -53,7 +53,7 @@ template<typename BinaryOp, typename Lhs, typename Rhs> class CwiseBinaryOp;
template<typename Lhs, typename Rhs, int ProductMode> class Product;
template<typename CoeffsVectorType> class DiagonalMatrix;
template<typename MatrixType> class DiagonalCoeffs;
template<typename MatrixType, int Alignment = Unaligned> class Map;
template<typename MatrixType, int PacketAccess = Unaligned> class Map;
template<typename MatrixType, unsigned int Mode> class Part;
template<typename MatrixType, unsigned int Mode> class Extract;
template<typename ExpressionType> class Cwise;