|
Anasazi Version of the Day
|
|
Anasazi Version of the Day
|
#include <Tsqr_CacheBlocker.hpp>
Public Member Functions | |
| CacheBlocker (const Ordinal num_rows, const Ordinal num_cols, const CacheBlockingStrategy< Ordinal, Scalar > &strategy) | |
| CacheBlocker (const CacheBlocker &rhs) | |
| Copy constructor. | |
| CacheBlocker & | operator= (const CacheBlocker &rhs) |
| Assignment operator. | |
| size_t | cache_block_size () const |
| Cache block size in bytes. | |
| Ordinal | nrows () const |
| Number of rows in the matrix corresponding to the cache blocking scheme. | |
| Ordinal | ncols () const |
| Number of columns in the matrix corresponding to the cache blocking scheme. | |
| template<class MatrixViewType > | |
| MatrixViewType | split_top_block (MatrixViewType &A, const bool contiguous_cache_blocks) const |
| template<class MatrixViewType > | |
| MatrixViewType | top_block (const MatrixViewType &A, const bool contiguous_cache_blocks) const |
| template<class MatrixViewType > | |
| void | fill_with_zeros (MatrixViewType A, const bool contiguous_cache_blocks) const |
| void | cache_block (const Ordinal num_rows, const Ordinal num_cols, Scalar A_out[], const Scalar A_in[], const Ordinal lda_in) const |
| Cache-block the given A_in matrix into A_out. | |
| void | un_cache_block (const Ordinal num_rows, const Ordinal num_cols, Scalar A_out[], const Ordinal lda_out, const Scalar A_in[]) const |
A CacheBlocker uses a particular cache blocking strategy ("class CBS") to know how to separate an nrows by ncols matrix into cache blocks, which in this case are row blocks. We can use this strategy to cache block any matrix of nrows rows, using the same distribution of rows to blocks, regardless of whether that latter matrix has a different number of columns than ncols.
Definition at line 64 of file Tsqr_CacheBlocker.hpp.
| TSQR::CacheBlocker< Ordinal, Scalar >::CacheBlocker | ( | const Ordinal | num_rows, |
| const Ordinal | num_cols, | ||
| const CacheBlockingStrategy< Ordinal, Scalar > & | strategy | ||
| ) | [inline] |
Constructor
| num_rows | Number of rows in the matrix corresponding to the cache blocking scheme |
| num_cols | Number of columns in the matrix corresponding to the cache blocking scheme |
| strategy | Cache blocking strategy object |
Definition at line 90 of file Tsqr_CacheBlocker.hpp.
| TSQR::CacheBlocker< Ordinal, Scalar >::CacheBlocker | ( | const CacheBlocker< Ordinal, Scalar > & | rhs | ) | [inline] |
Copy constructor.
Definition at line 115 of file Tsqr_CacheBlocker.hpp.
| CacheBlocker& TSQR::CacheBlocker< Ordinal, Scalar >::operator= | ( | const CacheBlocker< Ordinal, Scalar > & | rhs | ) | [inline] |
Assignment operator.
Definition at line 122 of file Tsqr_CacheBlocker.hpp.
| size_t TSQR::CacheBlocker< Ordinal, Scalar >::cache_block_size | ( | ) | const [inline] |
Cache block size in bytes.
Definition at line 130 of file Tsqr_CacheBlocker.hpp.
| Ordinal TSQR::CacheBlocker< Ordinal, Scalar >::nrows | ( | ) | const [inline] |
Number of rows in the matrix corresponding to the cache blocking scheme.
Definition at line 133 of file Tsqr_CacheBlocker.hpp.
| Ordinal TSQR::CacheBlocker< Ordinal, Scalar >::ncols | ( | ) | const [inline] |
Number of columns in the matrix corresponding to the cache blocking scheme.
Definition at line 136 of file Tsqr_CacheBlocker.hpp.
| MatrixViewType TSQR::CacheBlocker< Ordinal, Scalar >::split_top_block | ( | MatrixViewType & | A, |
| const bool | contiguous_cache_blocks | ||
| ) | const [inline] |
Return the topmost cache block of A, where the number of rows in each cache block is chosen according to the number of columns with which this CacheBlocker was set up (rather than the number of columns in A, which may not be the same). The idea is to have the number and distribution of rows in the cache blocks be the same as the original nrows() by ncols() matrix with which this CacheBlocker was initialized.
Definition at line 147 of file Tsqr_CacheBlocker.hpp.
| MatrixViewType TSQR::CacheBlocker< Ordinal, Scalar >::top_block | ( | const MatrixViewType & | A, |
| const bool | contiguous_cache_blocks | ||
| ) | const [inline] |
Return the topmost cache block of A. A is copied so it won't be modified.
Definition at line 161 of file Tsqr_CacheBlocker.hpp.
| void TSQR::CacheBlocker< Ordinal, Scalar >::fill_with_zeros | ( | MatrixViewType | A, |
| const bool | contiguous_cache_blocks | ||
| ) | const [inline] |
Fill the entries of A with Scalar(0).
Definition at line 193 of file Tsqr_CacheBlocker.hpp.
| void TSQR::CacheBlocker< Ordinal, Scalar >::cache_block | ( | const Ordinal | num_rows, |
| const Ordinal | num_cols, | ||
| Scalar | A_out[], | ||
| const Scalar | A_in[], | ||
| const Ordinal | lda_in | ||
| ) | const [inline] |
Cache-block the given A_in matrix into A_out.
Given an nrows by ncols (with nrows >= ncols) matrix A_in, stored in column-major order with leading dimension lda_in (>= nrows), copy it into A_out in a cache-blocked row block format. Each cache block is a matrix in column-major order, and the elements of a cache block are stored consecutively in A_out. The number of rows in each cache block depends on the cache-blocking strategy that this CacheBlocker uses.
| num_rows | [in] Total number of rows in the matrices A_in and A_out |
| num_cols | [in] Number of columns in the matrices A_in and A_out |
| A_out | [out] nrows*ncols contiguous storage into which to write the cache-blocked output matrix. |
| A_in | [in] nrows by ncols matrix, stored in column-major order with leading dimension lda_in >= nrows |
| lda_in | [in] Leading dimension of the matrix A_in |
Definition at line 227 of file Tsqr_CacheBlocker.hpp.
| void TSQR::CacheBlocker< Ordinal, Scalar >::un_cache_block | ( | const Ordinal | num_rows, |
| const Ordinal | num_cols, | ||
| Scalar | A_out[], | ||
| const Ordinal | lda_out, | ||
| const Scalar | A_in[] | ||
| ) | const [inline] |
"Un"-cache-block the given A_in matrix, writing the results to A_out.
Definition at line 260 of file Tsqr_CacheBlocker.hpp.
1.7.4
