| 1 |
// ------------------------------------------------------------------------ |
| 2 |
// |
| 3 |
// SPDX-License-Identifier: LGPL-2.1-or-later |
| 4 |
// Copyright (C) 2005 - 2025 by the deal.II authors |
| 5 |
// |
| 6 |
// This file is part of the deal.II library. |
| 7 |
// |
| 8 |
// Part of the source code is dual licensed under Apache-2.0 WITH |
| 9 |
// LLVM-exception OR LGPL-2.1-or-later. Detailed license information |
| 10 |
// governing the source code and code contributions can be found in |
| 11 |
// LICENSE.md and CONTRIBUTING.md at the top level directory of deal.II. |
| 12 |
// |
| 13 |
// ------------------------------------------------------------------------ |
| 14 |
|
| 15 |
#ifndef dealii_lapack_full_matrix_h |
| 16 |
#define dealii_lapack_full_matrix_h |
| 17 |
|
| 18 |
|
| 19 |
#include <deal.II/base/config.h> |
| 20 |
|
| 21 |
#include <deal.II/base/mutex.h> |
| 22 |
#include <deal.II/base/observer_pointer.h> |
| 23 |
#include <deal.II/base/table.h> |
| 24 |
|
| 25 |
#include <deal.II/lac/lapack_support.h> |
| 26 |
#include <deal.II/lac/vector_memory.h> |
| 27 |
|
| 28 |
#include <complex> |
| 29 |
#include <memory> |
| 30 |
#include <vector> |
| 31 |
|
| 32 |
DEAL_II_NAMESPACE_OPEN |
| 33 |
|
| 34 |
// forward declarations |
| 35 |
#ifndef DOXYGEN |
| 36 |
template <typename number> |
| 37 |
class Vector; |
| 38 |
template <typename number> |
| 39 |
class BlockVector; |
| 40 |
template <typename number> |
| 41 |
class FullMatrix; |
| 42 |
template <typename number> |
| 43 |
class SparseMatrix; |
| 44 |
#endif |
| 45 |
|
| 46 |
/** |
| 47 |
* A variant of FullMatrix using LAPACK functions wherever possible. In order |
| 48 |
* to do this, the matrix is stored in transposed order. The element access |
| 49 |
* functions hide this fact by reverting the transposition. |
| 50 |
* |
| 51 |
* @note In order to perform LAPACK functions, the class contains a lot of |
| 52 |
* auxiliary data in the private section. The names of these data vectors are |
| 53 |
* usually the names chosen for the arguments in the LAPACK documentation. |
| 54 |
* |
| 55 |
* @ingroup Matrix1 |
| 56 |
*/ |
| 57 |
template <typename number> |
| 58 |
class LAPACKFullMatrix : public TransposeTable<number> |
| 59 |
{ |
| 60 |
public: |
| 61 |
/** |
| 62 |
* Declare type for container size. |
| 63 |
*/ |
| 64 |
using size_type = std::make_unsigned_t<types::blas_int>; |
| 65 |
|
| 66 |
/** |
| 67 |
* Constructor. Initialize the matrix as a square matrix with dimension |
| 68 |
* @p size. |
| 69 |
* |
| 70 |
* In order to avoid the implicit conversion of integers and other types to |
| 71 |
* a matrix, this constructor is declared <tt>explicit</tt>. |
| 72 |
* |
| 73 |
* By default, no memory is allocated. |
| 74 |
*/ |
| 75 |
explicit LAPACKFullMatrix(const size_type size = 0); |
| 76 |
|
| 77 |
/** |
| 78 |
* Constructor. Initialize the matrix as a rectangular matrix $\rm{rows} |
| 79 |
* \times \rm{cols}$. |
| 80 |
*/ |
| 81 |
LAPACKFullMatrix(const size_type rows, const size_type cols); |
| 82 |
|
| 83 |
/** |
| 84 |
* Copy constructor. This constructor does a deep copy of the matrix. |
| 85 |
* Therefore, it poses a possible efficiency problem, if for example, |
| 86 |
* function arguments are passed by value rather than by reference. |
| 87 |
* Unfortunately, we can't mark this copy constructor <tt>explicit</tt>, |
| 88 |
* since that prevents the use of this class in containers, such as |
| 89 |
* <code>std::vector</code>. The responsibility to check performance of |
| 90 |
* programs must therefore remain with the user of this class. |
| 91 |
*/ |
| 92 |
LAPACKFullMatrix(const LAPACKFullMatrix &); |
| 93 |
|
| 94 |
/** |
| 95 |
* Assignment operator. |
| 96 |
*/ |
| 97 |
LAPACKFullMatrix<number> & |
| 98 |
operator=(const LAPACKFullMatrix<number> &); |
| 99 |
|
| 100 |
/** |
| 101 |
* Assignment operator from a regular FullMatrix. |
| 102 |
* |
| 103 |
* @note Since LAPACK expects matrices in transposed order, this |
| 104 |
* transposition is included here. |
| 105 |
*/ |
| 106 |
template <typename number2> |
| 107 |
LAPACKFullMatrix<number> & |
| 108 |
operator=(const FullMatrix<number2> &); |
| 109 |
|
| 110 |
/** |
| 111 |
* Assignment operator from a regular SparseMatrix. |
| 112 |
* |
| 113 |
* @note Since LAPACK expects matrices in transposed order, this |
| 114 |
* transposition is included here. |
| 115 |
*/ |
| 116 |
template <typename number2> |
| 117 |
LAPACKFullMatrix<number> & |
| 118 |
operator=(const SparseMatrix<number2> &); |
| 119 |
|
| 120 |
/** |
| 121 |
* This operator assigns a scalar to a matrix. To avoid confusion with |
| 122 |
* constructors, zero (when cast to the @p number type) is the only |
| 123 |
* value allowed for @p d. |
| 124 |
*/ |
| 125 |
LAPACKFullMatrix<number> & |
| 126 |
operator=(const number d); |
| 127 |
|
| 128 |
/** |
| 129 |
* This operator multiplies all entries by a fixed @p factor. |
| 130 |
*/ |
| 131 |
LAPACKFullMatrix<number> & |
| 132 |
operator*=(const number factor); |
| 133 |
|
| 134 |
/** |
| 135 |
* This operator divides all entries by a fixed @p factor. |
| 136 |
*/ |
| 137 |
LAPACKFullMatrix<number> & |
| 138 |
operator/=(const number factor); |
| 139 |
|
| 140 |
/** |
| 141 |
* Set a particular entry of the matrix to a @p value. |
| 142 |
* Thus, calling <code>A.set(1,2,3.141);</code> is entirely equivalent to the |
| 143 |
* operation <code>A(1,2) = 3.141;</code>. This function exists for |
| 144 |
* compatibility with the various sparse matrix objects. |
| 145 |
* |
| 146 |
* @param i The row index of the element to be set. |
| 147 |
* @param j The column index of the element to be set. |
| 148 |
* @param value The value to be written into the element. |
| 149 |
*/ |
| 150 |
void |
| 151 |
set(const size_type i, const size_type j, const number value); |
| 152 |
|
| 153 |
/** |
| 154 |
* Simple addition of a scaled matrix, i.e. $\mathbf A \mathrel{+}= a \, |
| 155 |
* \mathbf B$. |
| 156 |
*/ |
| 157 |
void |
| 158 |
add(const number a, const LAPACKFullMatrix<number> &B); |
| 159 |
|
| 160 |
/** |
| 161 |
* Perform a rank-1 update of a symmetric matrix |
| 162 |
* $ \mathbf A \leftarrow \mathbf A + a \, \mathbf v \mathbf v^T $. |
| 163 |
* |
| 164 |
* This function also works for Cholesky factorization. |
| 165 |
* In that case, updating ($a>0$) is |
| 166 |
* performed via Givens rotations, whereas downdating ($a<0$) via hyperbolic |
| 167 |
* rotations. Note that the latter case might lead to a negative definite |
| 168 |
* matrix in which case the error will be thrown (because Cholesky |
| 169 |
* factorizations are only valid for symmetric and positive definite |
| 170 |
* matrices). |
| 171 |
*/ |
| 172 |
void |
| 173 |
rank1_update(const number a, const Vector<number> &v); |
| 174 |
|
| 175 |
/** |
| 176 |
* Apply <a href="https://en.wikipedia.org/wiki/Givens_rotation">Givens |
| 177 |
* rotation</a> |
| 178 |
* @p csr (a triplet of cosine, sine and radius, see |
| 179 |
* Utilities::LinearAlgebra::givens_rotation() for the definition of the |
| 180 |
* rotation matrix $\mathbf G$) |
| 181 |
* to this matrix in the plane spanned by the @p i'th and @p k'th unit vectors. |
| 182 |
* If @p left is <code>true</code>, the rotation is applied from left |
| 183 |
* $\mathbf A \leftarrow \mathbf G \mathbf A$ |
| 184 |
* and only rows @p i and @p k are affected. |
| 185 |
* Otherwise, transpose of the rotation matrix is applied from right |
| 186 |
* $\mathbf A \leftarrow \mathbf A \mathbf G^T$ |
| 187 |
* and only columns @p i and @p k are affected. |
| 188 |
*/ |
| 189 |
void |
| 190 |
apply_givens_rotation(const std::array<number, 3> &csr, |
| 191 |
const size_type i, |
| 192 |
const size_type k, |
| 193 |
const bool left = true); |
| 194 |
|
| 195 |
/** |
| 196 |
* Assignment from different matrix classes, performing the usual conversion |
| 197 |
* to the transposed format expected by LAPACK. This assignment operator |
| 198 |
* uses iterators of the typename MatrixType. Therefore, sparse matrices are |
| 199 |
* possible sources. |
| 200 |
*/ |
| 201 |
template <typename MatrixType> |
| 202 |
void |
| 203 |
copy_from(const MatrixType &); |
| 204 |
|
| 205 |
/** |
| 206 |
* Regenerate the current matrix by one that has the same properties as if |
| 207 |
* it were created by the constructor of this class with the same argument |
| 208 |
* list as this present function. |
| 209 |
*/ |
| 210 |
void |
| 211 |
reinit(const size_type size); |
| 212 |
|
| 213 |
/** |
| 214 |
* Same as above but will preserve the values of matrix upon resizing. |
| 215 |
* The original values |
| 216 |
* of the matrix are kept on increasing the size |
| 217 |
* \f[ |
| 218 |
* \mathbf A \rightarrow |
| 219 |
* \left( |
| 220 |
* \begin{array}{cc} |
| 221 |
* \mathbf A & \mathbf 0 \\ |
| 222 |
* \mathbf 0 & \mathbf 0 |
| 223 |
* \end{array} |
| 224 |
* \right) |
| 225 |
* \f] |
| 226 |
* Whereas if the new size is smaller, the matrix will contain the upper left |
| 227 |
* block of the original one \f[ \left( \begin{array}{cc} |
| 228 |
* \mathbf A_{11} & \mathbf A_{12} \\ |
| 229 |
* \mathbf A_{21} & \mathbf A_{22} |
| 230 |
* \end{array} |
| 231 |
* \right) |
| 232 |
* \rightarrow \mathbf A_{11} |
| 233 |
* \f] |
| 234 |
*/ |
| 235 |
void |
| 236 |
grow_or_shrink(const size_type size); |
| 237 |
|
| 238 |
/** |
| 239 |
* Remove row @p row and column @p col from the matrix. |
| 240 |
* \f[ |
| 241 |
* \left( |
| 242 |
* \begin{array}{ccc} |
| 243 |
* \mathbf A_{11} & \mathbf a_{12} & \mathbf A_{13} \\ |
| 244 |
* \mathbf a_{21}^T & a_{22} & \mathbf a_{23}^T \\ |
| 245 |
* \mathbf A_{31} & \mathbf a_{32} & \mathbf A_{33} |
| 246 |
* \end{array} |
| 247 |
* \right) |
| 248 |
* \rightarrow |
| 249 |
* \left( |
| 250 |
* \begin{array}{cc} |
| 251 |
* \mathbf A_{11} & \mathbf A_{13} \\ |
| 252 |
* \mathbf A_{31} & \mathbf A_{33} |
| 253 |
* \end{array} |
| 254 |
* \right) |
| 255 |
* \f] |
| 256 |
*/ |
| 257 |
void |
| 258 |
remove_row_and_column(const size_type row, const size_type col); |
| 259 |
|
| 260 |
/** |
| 261 |
* Regenerate the current matrix by one that has the same properties as if |
| 262 |
* it were created by the constructor of this class with the same argument |
| 263 |
* list as this present function. |
| 264 |
*/ |
| 265 |
void |
| 266 |
reinit(const size_type rows, const size_type cols); |
| 267 |
|
| 268 |
/** |
| 269 |
* Assign @p property to this matrix. |
| 270 |
*/ |
| 271 |
void |
| 272 |
set_property(const LAPACKSupport::Property property); |
| 273 |
|
| 274 |
/** |
| 275 |
* Return the dimension of the codomain (or range) space. |
| 276 |
* |
| 277 |
* @note The matrix is of dimension $m \times n$. |
| 278 |
*/ |
| 279 |
size_type |
| 280 |
m() const; |
| 281 |
|
| 282 |
/** |
| 283 |
* Return the dimension of the domain space. |
| 284 |
* |
| 285 |
* @note The matrix is of dimension $m \times n$. |
| 286 |
*/ |
| 287 |
size_type |
| 288 |
n() const; |
| 289 |
|
| 290 |
/** |
| 291 |
* Fill rectangular block. |
| 292 |
* |
| 293 |
* A rectangular block of the matrix <tt>src</tt> is copied into |
| 294 |
* <tt>this</tt>. The upper left corner of the block being copied is |
| 295 |
* <tt>(src_offset_i,src_offset_j)</tt>. The upper left corner of the |
| 296 |
* copied block is <tt>(dst_offset_i,dst_offset_j)</tt>. The size of the |
| 297 |
* rectangular block being copied is the maximum size possible, determined |
| 298 |
* either by the size of <tt>this</tt> or <tt>src</tt>. |
| 299 |
* |
| 300 |
* The final two arguments allow to enter a multiple of the source or its |
| 301 |
* transpose. |
| 302 |
*/ |
| 303 |
template <typename MatrixType> |
| 304 |
void |
| 305 |
fill(const MatrixType &src, |
| 306 |
const size_type dst_offset_i = 0, |
| 307 |
const size_type dst_offset_j = 0, |
| 308 |
const size_type src_offset_i = 0, |
| 309 |
const size_type src_offset_j = 0, |
| 310 |
const number factor = 1., |
| 311 |
const bool transpose = false); |
| 312 |
|
| 313 |
|
| 314 |
/** |
| 315 |
* Matrix-vector-multiplication. |
| 316 |
* |
| 317 |
* Depending on previous transformations recorded in #state, the result of |
| 318 |
* this function is one of |
| 319 |
* <ul> |
| 320 |
* <li> If #state is LAPACKSupport::matrix or LAPACKSupport::inverse_matrix, |
| 321 |
* this will be a regular matrix vector product using LAPACK gemv(). |
| 322 |
* <li> If #state is LAPACKSupport::svd or LAPACKSupport::inverse_svd, this |
| 323 |
* function first multiplies with the right transformation matrix, then with |
| 324 |
* the diagonal matrix of singular values or their reciprocal values, and |
| 325 |
* finally with the left transformation matrix. |
| 326 |
* </ul> |
| 327 |
* |
| 328 |
* The optional parameter @p adding determines, whether the result is |
| 329 |
* stored in the vector |
| 330 |
* $\mathbf w = \mathbf A \cdot \mathbf v$ |
| 331 |
* or added to it |
| 332 |
* $\mathbf w \mathrel{+}= \mathbf A \cdot \mathbf v$. |
| 333 |
* |
| 334 |
* @note Source and destination must not be the same vector. |
| 335 |
* |
| 336 |
* @note The template with @p number2 only exists for compile-time |
| 337 |
* compatibility with FullMatrix. Only the case @p number2 = @p number is |
| 338 |
* implemented due to limitations in the underlying LAPACK interface. All |
| 339 |
* other variants throw an error upon invocation. |
| 340 |
*/ |
| 341 |
template <typename number2> |
| 342 |
void |
| 343 |
vmult(Vector<number2> &w, |
| 344 |
const Vector<number2> &v, |
| 345 |
const bool adding = false) const; |
| 346 |
|
| 347 |
/** |
| 348 |
* Specialization of above function for compatible Vector::value_type. |
| 349 |
*/ |
| 350 |
void |
| 351 |
vmult(Vector<number> &w, |
| 352 |
const Vector<number> &v, |
| 353 |
const bool adding = false) const; |
| 354 |
|
| 355 |
/** |
| 356 |
* Adding Matrix-vector-multiplication $\mathbf w \mathrel{+}= \mathbf A \cdot |
| 357 |
* \mathbf v$. |
| 358 |
* |
| 359 |
* See the documentation of vmult() for details on the implementation. |
| 360 |
*/ |
| 361 |
template <typename number2> |
| 362 |
void |
| 363 |
vmult_add(Vector<number2> &w, const Vector<number2> &v) const; |
| 364 |
|
| 365 |
/** |
| 366 |
* Specialization of above function for compatible Vector::value_type. |
| 367 |
*/ |
| 368 |
void |
| 369 |
vmult_add(Vector<number> &w, const Vector<number> &v) const; |
| 370 |
|
| 371 |
/** |
| 372 |
* Transpose matrix-vector-multiplication. |
| 373 |
* |
| 374 |
* The optional parameter @p adding determines, whether the result is |
| 375 |
* stored in the vector |
| 376 |
* $\mathbf w = \mathbf A^T \cdot \mathbf v$ |
| 377 |
* or added to it |
| 378 |
* $\mathbf w \mathrel{+}= \mathbf A^T \cdot \mathbf v$. |
| 379 |
* |
| 380 |
* See the documentation of vmult() for details on the implementation. |
| 381 |
*/ |
| 382 |
template <typename number2> |
| 383 |
void |
| 384 |
Tvmult(Vector<number2> &w, |
| 385 |
const Vector<number2> &v, |
| 386 |
const bool adding = false) const; |
| 387 |
|
| 388 |
/** |
| 389 |
* Specialization of above function for compatible Vector::value_type. |
| 390 |
*/ |
| 391 |
void |
| 392 |
Tvmult(Vector<number> &w, |
| 393 |
const Vector<number> &v, |
| 394 |
const bool adding = false) const; |
| 395 |
|
| 396 |
/** |
| 397 |
* Adding transpose matrix-vector-multiplication $\mathbf w \mathrel{+}= |
| 398 |
* \mathbf A^T \cdot \mathbf v$. |
| 399 |
* |
| 400 |
* See the documentation of vmult() for details on the implementation. |
| 401 |
*/ |
| 402 |
template <typename number2> |
| 403 |
void |
| 404 |
Tvmult_add(Vector<number2> &w, const Vector<number2> &v) const; |
| 405 |
|
| 406 |
/** |
| 407 |
* Specialization of above function for compatible Vector::value_type. |
| 408 |
*/ |
| 409 |
void |
| 410 |
Tvmult_add(Vector<number> &w, const Vector<number> &v) const; |
| 411 |
|
| 412 |
|
| 413 |
/** |
| 414 |
* Matrix-matrix-multiplication. |
| 415 |
* |
| 416 |
* The optional parameter @p adding determines, whether the result is |
| 417 |
* stored in the matrix |
| 418 |
* $\mathbf C = \mathbf A \cdot \mathbf B$ |
| 419 |
* or added to it |
| 420 |
* $\mathbf C \mathrel{+}= \mathbf A \cdot \mathbf B$. |
| 421 |
* |
| 422 |
* @note It is assumed that @p A and @p B have compatible sizes and that |
| 423 |
* @p C already has the right size. |
| 424 |
* |
| 425 |
* @p This function uses the BLAS function Xgemm. |
| 426 |
*/ |
| 427 |
void |
| 428 |
mmult(LAPACKFullMatrix<number> &C, |
| 429 |
const LAPACKFullMatrix<number> &B, |
| 430 |
const bool adding = false) const; |
| 431 |
|
| 432 |
/** |
| 433 |
* Same as before, but stores the result in a FullMatrix, not in a |
| 434 |
* LAPACKFullMatrix. |
| 435 |
*/ |
| 436 |
void |
| 437 |
mmult(FullMatrix<number> &C, |
| 438 |
const LAPACKFullMatrix<number> &B, |
| 439 |
const bool adding = false) const; |
| 440 |
|
| 441 |
/** |
| 442 |
* Matrix-matrix-multiplication using transpose of <tt>this</tt>. |
| 443 |
* |
| 444 |
* The optional parameter @p adding determines, whether the result is |
| 445 |
* stored in the matrix |
| 446 |
* $\mathbf C = \mathbf A^T \cdot \mathbf B$ |
| 447 |
* or added to it |
| 448 |
* $\mathbf C \mathrel{+}= \mathbf A^T \cdot \mathbf B$. |
| 449 |
* |
| 450 |
* @note It is assumed that @p A and @p B have compatible sizes and that |
| 451 |
* @p C already has the right size. |
| 452 |
* |
| 453 |
* @note This function uses the BLAS function Xgemm. |
| 454 |
*/ |
| 455 |
void |
| 456 |
Tmmult(LAPACKFullMatrix<number> &C, |
| 457 |
const LAPACKFullMatrix<number> &B, |
| 458 |
const bool adding = false) const; |
| 459 |
|
| 460 |
/** |
| 461 |
* Same as before, but stores the result in a FullMatrix, not in a |
| 462 |
* LAPACKFullMatrix. |
| 463 |
*/ |
| 464 |
void |
| 465 |
Tmmult(FullMatrix<number> &C, |
| 466 |
const LAPACKFullMatrix<number> &B, |
| 467 |
const bool adding = false) const; |
| 468 |
|
| 469 |
/** |
| 470 |
* Matrix-matrix-multiplication using transpose of <tt>this</tt> and a |
| 471 |
* diagonal vector @p V. |
| 472 |
* |
| 473 |
* If the <code>adding=false</code> then the result is stored in the matrix |
| 474 |
* $\mathbf C = \mathbf A^T \cdot \rm{diag}(\mathbf V) \cdot \mathbf B$ |
| 475 |
* otherwise it is added $\mathbf C \mathrel{+}= \mathbf A^T \cdot |
| 476 |
* \rm{diag}(\mathbf V) \cdot \mathbf B$. |
| 477 |
* |
| 478 |
* @note It is assumed that @p A, @p B and @p V have compatible sizes and that |
| 479 |
* @p C already has the right size. |
| 480 |
* |
| 481 |
* @note This function is not provided by LAPACK. The function first forms |
| 482 |
* $\rm{diag}(\mathbf V) \cdot \mathbf B$ product and then uses the Xgemm |
| 483 |
* function. |
| 484 |
*/ |
| 485 |
void |
| 486 |
Tmmult(LAPACKFullMatrix<number> &C, |
| 487 |
const LAPACKFullMatrix<number> &B, |
| 488 |
const Vector<number> &V, |
| 489 |
const bool adding = false) const; |
| 490 |
|
| 491 |
/** |
| 492 |
* Matrix-matrix-multiplication using transpose of @p B. |
| 493 |
* |
| 494 |
* The optional parameter @p adding determines, whether the result is |
| 495 |
* stored in the matrix |
| 496 |
* $\mathbf C = \mathbf A \cdot \mathbf B^T$ |
| 497 |
* or added to it |
| 498 |
* $\mathbf C \mathrel{+}= \mathbf A \cdot \mathbf B^T$. |
| 499 |
* |
| 500 |
* @note It is assumed that @p A and @p B have compatible sizes and that |
| 501 |
* @p C already has the right size. |
| 502 |
* |
| 503 |
* @note This function uses the BLAS function Xgemm. |
| 504 |
*/ |
| 505 |
void |
| 506 |
mTmult(LAPACKFullMatrix<number> &C, |
| 507 |
const LAPACKFullMatrix<number> &B, |
| 508 |
const bool adding = false) const; |
| 509 |
|
| 510 |
/** |
| 511 |
* Same as before, but stores the result in a FullMatrix, not in a |
| 512 |
* LAPACKFullMatrix. |
| 513 |
*/ |
| 514 |
void |
| 515 |
mTmult(FullMatrix<number> &C, |
| 516 |
const LAPACKFullMatrix<number> &B, |
| 517 |
const bool adding = false) const; |
| 518 |
|
| 519 |
/** |
| 520 |
* Matrix-matrix-multiplication using transpose of <tt>this</tt> and |
| 521 |
* @p B. |
| 522 |
* |
| 523 |
* The optional parameter @p adding determines, whether the result is |
| 524 |
* stored in the matrix |
| 525 |
* $\mathbf C = \mathbf A^T \cdot \mathbf B^T$ |
| 526 |
* or added to it |
| 527 |
* $\mathbf C \mathrel{+}= \mathbf A^T \cdot \mathbf B^T$. |
| 528 |
* |
| 529 |
* @note It is assumed that @p A and @p B have compatible sizes and that |
| 530 |
* @p C already has the right size. |
| 531 |
* |
| 532 |
* @note This function uses the BLAS function Xgemm. |
| 533 |
*/ |
| 534 |
void |
| 535 |
TmTmult(LAPACKFullMatrix<number> &C, |
| 536 |
const LAPACKFullMatrix<number> &B, |
| 537 |
const bool adding = false) const; |
| 538 |
|
| 539 |
/** |
| 540 |
* Same as before, but stores the result in a FullMatrix, not in a |
| 541 |
* LAPACKFullMatrix. |
| 542 |
*/ |
| 543 |
void |
| 544 |
TmTmult(FullMatrix<number> &C, |
| 545 |
const LAPACKFullMatrix<number> &B, |
| 546 |
const bool adding = false) const; |
| 547 |
|
| 548 |
/** |
| 549 |
* Performs out-place transposition. |
| 550 |
* Matrix @p B should be appropriately sized. |
| 551 |
* |
| 552 |
* @note for complex number types, conjugate transpose will be performed. |
| 553 |
* |
| 554 |
* @note If deal.II is configured with Intel-MKL, `mkl_?omatcopy` will be used, |
| 555 |
* otherwise transposition is done element by element. |
| 556 |
*/ |
| 557 |
void |
| 558 |
transpose(LAPACKFullMatrix<number> &B) const; |
| 559 |
|
| 560 |
/** |
| 561 |
* Scale rows of this matrix by @p V . This is equivalent to premultiplication |
| 562 |
* with a diagonal matrix $\mathbf A\leftarrow {\rm diag}(\mathbf V)\mathbf |
| 563 |
* A$. |
| 564 |
*/ |
| 565 |
void |
| 566 |
scale_rows(const Vector<number> &V); |
| 567 |
|
| 568 |
/** |
| 569 |
* Compute the LU factorization of the matrix using LAPACK function Xgetrf. |
| 570 |
*/ |
| 571 |
void |
| 572 |
compute_lu_factorization(); |
| 573 |
|
| 574 |
/** |
| 575 |
* Compute the Cholesky factorization of the matrix using LAPACK function |
| 576 |
* Xpotrf. |
| 577 |
* |
| 578 |
* @note The factorization is stored in the lower-triangular part of the matrix. |
| 579 |
*/ |
| 580 |
void |
| 581 |
compute_cholesky_factorization(); |
| 582 |
|
| 583 |
/** |
| 584 |
* Estimate the reciprocal of the condition number $1/k(\mathbf A)$ in $L_1$ |
| 585 |
* norm ($1/(||\mathbf A||_1 \, ||\mathbf A^{-1}||_1)$) of a symmetric |
| 586 |
* positive definite matrix using Cholesky factorization. This function can |
| 587 |
* only be called if the matrix is already factorized. |
| 588 |
* |
| 589 |
* @note The condition number $k(\mathbf A)$ can be used to estimate the numerical |
| 590 |
* error related to the matrix inversion or the solution of the |
| 591 |
* system of linear algebraic equations as |
| 592 |
* <code>error = std::numeric_limits<Number>::epsilon * k</code>. |
| 593 |
* Alternatively one can get the number of accurate digits |
| 594 |
* <code>std::floor(std::log10(k))</code>. |
| 595 |
* |
| 596 |
* @note The function computes reciprocal of the condition number to |
| 597 |
* avoid possible overflow if the matrix is nearly singular. |
| 598 |
* |
| 599 |
* @param[in] l1_norm Is the $L_1$ norm of the matrix before calling Cholesky |
| 600 |
* factorization. It can be obtained by calling l1_norm(). |
| 601 |
*/ |
| 602 |
number |
| 603 |
reciprocal_condition_number(const number l1_norm) const; |
| 604 |
|
| 605 |
/** |
| 606 |
* Estimate the reciprocal of the condition number $1/k(\mathbf A)$ in $L_1$ |
| 607 |
* norm for triangular matrices. The matrix has to have the |
| 608 |
* LAPACKSupport::Property set to either |
| 609 |
* LAPACKSupport::Property::upper_triangular or |
| 610 |
* LAPACKSupport::Property::lower_triangular, see set_property(). |
| 611 |
*/ |
| 612 |
number |
| 613 |
reciprocal_condition_number() const; |
| 614 |
|
| 615 |
/** |
| 616 |
* Compute the determinant of a matrix. As it requires the LU factorization of |
| 617 |
* the matrix, this function can only be called after |
| 618 |
* compute_lu_factorization() has been called. |
| 619 |
*/ |
| 620 |
number |
| 621 |
determinant() const; |
| 622 |
|
| 623 |
/** |
| 624 |
* Compute $L_1$ norm. |
| 625 |
*/ |
| 626 |
number |
| 627 |
l1_norm() const; |
| 628 |
|
| 629 |
/** |
| 630 |
* Compute $L_\infty$ norm. |
| 631 |
*/ |
| 632 |
number |
| 633 |
linfty_norm() const; |
| 634 |
|
| 635 |
/** |
| 636 |
* Compute Frobenius norm |
| 637 |
*/ |
| 638 |
number |
| 639 |
frobenius_norm() const; |
| 640 |
|
| 641 |
/** |
| 642 |
* Compute trace of the matrix, i.e. the sum of the diagonal values. |
| 643 |
* Obviously, the matrix needs to be quadratic for this function. |
| 644 |
*/ |
| 645 |
number |
| 646 |
trace() const; |
| 647 |
|
| 648 |
/** |
| 649 |
* Invert the matrix by first computing an LU/Cholesky factorization with the |
| 650 |
* LAPACK function Xgetrf/Xpotrf and then building the actual inverse using |
| 651 |
* Xgetri/Xpotri. |
| 652 |
*/ |
| 653 |
void |
| 654 |
invert(); |
| 655 |
|
| 656 |
/** |
| 657 |
* Solve the linear system with right hand side @p v and put the solution |
| 658 |
* back to @p v. The matrix should be either triangular or LU/Cholesky |
| 659 |
* factorization should be previously computed. |
| 660 |
* |
| 661 |
* The flag transposed indicates whether the solution of the transposed |
| 662 |
* system is to be performed. |
| 663 |
*/ |
| 664 |
void |
| 665 |
solve(Vector<number> &v, const bool transposed = false) const; |
| 666 |
|
| 667 |
/** |
| 668 |
* Same as above but for multiple right hand sides (as many as there |
| 669 |
* are columns in the matrix @p B). |
| 670 |
*/ |
| 671 |
void |
| 672 |
solve(LAPACKFullMatrix<number> &B, const bool transposed = false) const; |
| 673 |
|
| 674 |
/** |
| 675 |
* Compute eigenvalues of the matrix. After this routine has been called, |
| 676 |
* eigenvalues can be retrieved using the eigenvalue() function. The matrix |
| 677 |
* itself will be LAPACKSupport::unusable after this operation. |
| 678 |
* |
| 679 |
* The optional arguments allow to compute left and right eigenvectors as |
| 680 |
* well. |
| 681 |
* |
| 682 |
* Note that the function does not return the computed eigenvalues right |
| 683 |
* away since that involves copying data around between the output arrays of |
| 684 |
* the LAPACK functions and any return array. This is often unnecessary |
| 685 |
* since one may not be interested in all eigenvalues at once, but for |
| 686 |
* example only the extreme ones. In that case, it is cheaper to just have |
| 687 |
* this function compute the eigenvalues and have a separate function that |
| 688 |
* returns whatever eigenvalue is requested. |
| 689 |
* |
| 690 |
* @note Calls the LAPACK function Xgeev. |
| 691 |
*/ |
| 692 |
void |
| 693 |
compute_eigenvalues(const bool right_eigenvectors = false, |
| 694 |
const bool left_eigenvectors = false); |
| 695 |
|
| 696 |
/** |
| 697 |
* Compute eigenvalues and eigenvectors of a real symmetric matrix. Only |
| 698 |
* eigenvalues in the interval $(\rm{lower\_bound}, \rm{upper\_bound}]$ are |
| 699 |
* computed with the absolute tolerance $\rm abs\_accuracy$. An approximate |
| 700 |
* eigenvalue is accepted as converged when it is determined to lie in an |
| 701 |
* interval $[a,b]$ of width less than or equal to $\rm{abs\_accuracy} + eps * |
| 702 |
* \rm{max}(|a|,|b|)$, where $eps$ is the machine precision. If |
| 703 |
* $\rm{abs\_accuracy}$ is less than or equal to zero, then |
| 704 |
* $eps\,|\mathbf{T}|_1$ will be used in its place, where $|\mathbf{T}|_1$ is |
| 705 |
* the 1-norm of the tridiagonal matrix obtained by reducing $\mathbf A$ to |
| 706 |
* tridiagonal form. Eigenvalues will be computed most accurately when |
| 707 |
* $\rm{abs\_accuracy}$ is set to twice the underflow threshold, not zero. |
| 708 |
* After this routine has been called, all eigenvalues in $(\rm{lower\_bound}, |
| 709 |
* \rm{upper\_bound}]$ will be stored in eigenvalues and the corresponding |
| 710 |
* eigenvectors will be stored in the columns of eigenvectors, whose dimension |
| 711 |
* is set accordingly. |
| 712 |
* |
| 713 |
* @note Calls the LAPACK function Xsyevx. |
| 714 |
*/ |
| 715 |
void |
| 716 |
compute_eigenvalues_symmetric(const number lower_bound, |
| 717 |
const number upper_bound, |
| 718 |
const number abs_accuracy, |
| 719 |
Vector<number> &eigenvalues, |
| 720 |
FullMatrix<number> &eigenvectors); |
| 721 |
|
| 722 |
/** |
| 723 |
* Compute generalized eigenvalues and eigenvectors of a real generalized |
| 724 |
* symmetric eigenproblem of the form |
| 725 |
* - itype = 1: $\mathbf A \cdot \mathbf x=\lambda \mathbf B \cdot \mathbf x$ |
| 726 |
* - itype = 2: $\mathbf A \cdot \mathbf B \cdot \mathbf x=\lambda \mathbf x$ |
| 727 |
* - itype = 3: $\mathbf B \cdot \mathbf A \cdot \mathbf x=\lambda \mathbf x$ |
| 728 |
* |
| 729 |
* where $\mathbf A$ is this matrix. $\mathbf A$ |
| 730 |
* and $\mathbf B$ are assumed to be symmetric, and $\mathbf B$ has to be |
| 731 |
* positive definite. Only eigenvalues in the interval $(\rm{lower\_bound}, |
| 732 |
* \rm{upper\_bound}]$ are computed with the absolute tolerance |
| 733 |
* $\rm{abs\_accuracy}$. An approximate eigenvalue is accepted as converged |
| 734 |
* when it is determined to lie in an interval $[a,b]$ of width less than or |
| 735 |
* equal to $\rm{abs\_accuracy} + eps * \rm{max}( |a|,|b| )$, where $eps$ is |
| 736 |
* the machine precision. If $\rm{abs\_accuracy}$ is less than or equal to |
| 737 |
* zero, then $eps \, |\mathbf{T}|_1$ will be used in its place, where |
| 738 |
* $|\mathbf{T}|_1$ is the 1-norm of the tridiagonal matrix obtained by |
| 739 |
* reducing $\mathbf A$ to tridiagonal form. Eigenvalues will be computed most |
| 740 |
* accurately when $\rm{abs\_accuracy}$ is set to twice the underflow |
| 741 |
* threshold, not zero. After this routine has been called, all eigenvalues in |
| 742 |
* $(\rm{lower\_bound}, \rm{upper\_bound}]$ will be stored in eigenvalues and |
| 743 |
* the corresponding eigenvectors will be stored in eigenvectors, whose |
| 744 |
* dimension is set accordingly. |
| 745 |
* |
| 746 |
* @note Calls the LAPACK function Xsygvx. |
| 747 |
*/ |
| 748 |
void |
| 749 |
compute_generalized_eigenvalues_symmetric( |
| 750 |
LAPACKFullMatrix<number> &B, |
| 751 |
const number lower_bound, |
| 752 |
const number upper_bound, |
| 753 |
const number abs_accuracy, |
| 754 |
Vector<number> &eigenvalues, |
| 755 |
std::vector<Vector<number>> &eigenvectors, |
| 756 |
const types::blas_int itype = 1); |
| 757 |
|
| 758 |
/** |
| 759 |
* Same as the other compute_generalized_eigenvalues_symmetric function |
| 760 |
* except that all eigenvalues are computed and the tolerance is set |
| 761 |
* automatically. Note that this function does not return the computed |
| 762 |
* eigenvalues right away since that involves copying data around between |
| 763 |
* the output arrays of the LAPACK functions and any return array. This is |
| 764 |
* often unnecessary since one may not be interested in all eigenvalues at |
| 765 |
* once, but for example only the extreme ones. In that case, it is cheaper |
| 766 |
* to just have this function compute the eigenvalues and have a separate |
| 767 |
* function that returns whatever eigenvalue is requested. Eigenvalues can |
| 768 |
* be retrieved using the eigenvalue() function. The number of computed |
| 769 |
* eigenvectors is equal to `eigenvectors.size()`. |
| 770 |
* |
| 771 |
* @note Calls the LAPACK function Xsygv. |
| 772 |
*/ |
| 773 |
void |
| 774 |
compute_generalized_eigenvalues_symmetric( |
| 775 |
LAPACKFullMatrix<number> &B, |
| 776 |
std::vector<Vector<number>> &eigenvectors, |
| 777 |
const types::blas_int itype = 1); |
| 778 |
|
| 779 |
/** |
| 780 |
* Compute the singular value decomposition of the matrix using LAPACK |
| 781 |
* function Xgesdd. |
| 782 |
* |
| 783 |
* Requires that the #state is LAPACKSupport::matrix, fills the data members |
| 784 |
* #wr, #svd_u, and #svd_vt, and leaves the object in the #state |
| 785 |
* LAPACKSupport::svd. |
| 786 |
* |
| 787 |
* The singular value decomposition factorizes the provided matrix (A) into |
| 788 |
* three parts: U, sigma, and the transpose of V (V^T), such that A = U sigma |
| 789 |
* V^T. Sigma is a MxN matrix which contains the singular values of A on |
| 790 |
* the diagonal while all the other elements are zero. U is a MxM orthogonal |
| 791 |
* matrix containing the left singular vectors corresponding to the singular |
| 792 |
* values of A. V is a NxN orthonal matrix containing the right singular |
| 793 |
* vectors corresponding the singular values of A. |
| 794 |
* |
| 795 |
* Note that the variable #svd_vt contains the transpose of V and can be |
| 796 |
* accessed by get_svd_vt(), while U is accessed with get_svd_u(). |
| 797 |
*/ |
| 798 |
void |
| 799 |
compute_svd(); |
| 800 |
|
| 801 |
/** |
| 802 |
* Compute the inverse of the matrix by singular value decomposition. |
| 803 |
* |
| 804 |
* Requires that #state is either LAPACKSupport::matrix or |
| 805 |
* LAPACKSupport::svd. In the first case, this function calls compute_svd(). |
| 806 |
* After this function, the object will have the #state |
| 807 |
* LAPACKSupport::inverse_svd. |
| 808 |
* |
| 809 |
* For a singular value decomposition, the inverse is simply computed by |
| 810 |
* replacing all singular values by their reciprocal values. If the matrix |
| 811 |
* does not have maximal rank, singular values 0 are not touched, thus |
| 812 |
* computing the minimal norm right inverse of the matrix. |
| 813 |
* |
| 814 |
* The parameter @p threshold determines, when a singular value should |
| 815 |
* be considered zero. It is the ratio of the smallest to the largest |
| 816 |
* nonzero singular value $s_{max}$. Thus, the inverses of all |
| 817 |
* singular values less than $s_{max}/\rm{threshold}$ will |
| 818 |
* be set to zero. |
| 819 |
*/ |
| 820 |
void |
| 821 |
compute_inverse_svd(const double threshold = 0.); |
| 822 |
|
| 823 |
/** |
| 824 |
* Same as above but provide the size of the kernel instead of a threshold, |
| 825 |
* i.e. the @p kernel_size smallest eigenvalues. |
| 826 |
*/ |
| 827 |
void |
| 828 |
compute_inverse_svd_with_kernel(const unsigned int kernel_size); |
| 829 |
|
| 830 |
/** |
| 831 |
* Retrieve eigenvalue after compute_eigenvalues() was called. The return |
| 832 |
* type is always a complex number: In case the underlying matrix is |
| 833 |
* real-valued, the type `std::complex<number>` is returned, whereas |
| 834 |
* `number` is returned for complex numbers. |
| 835 |
*/ |
| 836 |
std::complex<typename numbers::NumberTraits<number>::real_type> |
| 837 |
eigenvalue(const size_type i) const; |
| 838 |
|
| 839 |
/** |
| 840 |
* After a call to compute_eigenvalues(), this function returns the $n\times |
| 841 |
* n$ matrix of (right) eigenvectors in a decomposition of the form $A V = V |
| 842 |
* \Lambda$. Note that this function constructs the associated matrix on the |
| 843 |
* fly, since LAPACK packs complex-conjugate eigenvalue/eigenvector pairs of |
| 844 |
* real-valued matrices into a real-valued return matrix. This call only |
| 845 |
* succeeds in case the respective flag `right_eigenvectors` in |
| 846 |
* compute_eigenvalues() has been set to true. |
| 847 |
*/ |
| 848 |
FullMatrix<std::complex<typename numbers::NumberTraits<number>::real_type>> |
| 849 |
get_right_eigenvectors() const; |
| 850 |
|
| 851 |
/** |
| 852 |
* Return the matrix of left eigenvectors after a call to |
| 853 |
* compute_eigenvalues(), following the same principles as |
| 854 |
* get_right_eigenvectors(). |
| 855 |
*/ |
| 856 |
FullMatrix<std::complex<typename numbers::NumberTraits<number>::real_type>> |
| 857 |
get_left_eigenvectors() const; |
| 858 |
|
| 859 |
/** |
| 860 |
* Retrieve singular values after compute_svd() or compute_inverse_svd() was |
| 861 |
* called. |
| 862 |
*/ |
| 863 |
number |
| 864 |
singular_value(const size_type i) const; |
| 865 |
|
| 866 |
/** |
| 867 |
* Retrieve the matrix #svd_u after compute_svd() or compute_inverse_svd() was |
| 868 |
* called. |
| 869 |
*/ |
| 870 |
inline const LAPACKFullMatrix<number> & |
| 871 |
get_svd_u() const; |
| 872 |
|
| 873 |
/** |
| 874 |
* Retrieve the matrix #svd_vt after compute_svd() or compute_inverse_svd() |
| 875 |
* was called. |
| 876 |
*/ |
| 877 |
inline const LAPACKFullMatrix<number> & |
| 878 |
get_svd_vt() const; |
| 879 |
|
| 880 |
/** |
| 881 |
* Print the matrix and allow formatting of entries. |
| 882 |
* |
| 883 |
* The parameters allow for a flexible setting of the output format: |
| 884 |
* |
| 885 |
* @param out This specifies the stream to write to. |
| 886 |
* |
| 887 |
* @param precision denotes the number of trailing digits. |
| 888 |
* |
| 889 |
* @param scientific is used to determine the number format, where |
| 890 |
* <code>scientific = false</code> means fixed point notation. |
| 891 |
* |
| 892 |
* @param width denotes the with of each column. A zero entry for |
| 893 |
* @p width makes the function compute a width, but it may be changed |
| 894 |
* to a positive value, if output is crude. |
| 895 |
* |
| 896 |
* @param zero_string specifies a string printed for zero entries. |
| 897 |
* |
| 898 |
* @param denominator Multiply the whole matrix by this common |
| 899 |
* denominator to get nicer numbers. |
| 900 |
* |
| 901 |
* @param threshold all entries with absolute value smaller than |
| 902 |
* this are considered zero. |
| 903 |
* |
| 904 |
* @param separator specifies a string printed to separate row entries. |
| 905 |
* |
| 906 |
* @note The entries stored resemble a matrix only if the state is either |
| 907 |
* LAPACKSupport::matrix or LAPACK::inverse_matrix. Otherwise, calling this |
| 908 |
* function is not allowed. |
| 909 |
*/ |
| 910 |
void |
| 911 |
print_formatted(std::ostream &out, |
| 912 |
const unsigned int precision = 3, |
| 913 |
const bool scientific = true, |
| 914 |
const unsigned int width = 0, |
| 915 |
const char *zero_string = " ", |
| 916 |
const double denominator = 1., |
| 917 |
const double threshold = 0., |
| 918 |
const char *separator = " ") const; |
| 919 |
|
| 920 |
/** |
| 921 |
* Return current state after the last operation here. |
| 922 |
*/ |
| 923 |
LAPACKSupport::State |
| 924 |
get_state() const; |
| 925 |
|
| 926 |
private: |
| 927 |
/** |
| 928 |
* Internal function to compute various norms. |
| 929 |
*/ |
| 930 |
number |
| 931 |
norm(const char type) const; |
| 932 |
|
| 933 |
/** |
| 934 |
* Since LAPACK operations notoriously change the meaning of the matrix |
| 935 |
* entries, we record the current state after the last operation here. |
| 936 |
*/ |
| 937 |
LAPACKSupport::State state; |
| 938 |
|
| 939 |
/** |
| 940 |
* Additional property of the matrix which may help to select more |
| 941 |
* efficient LAPACK functions. |
| 942 |
*/ |
| 943 |
LAPACKSupport::Property property; |
| 944 |
|
| 945 |
/** |
| 946 |
* The working array used for some LAPACK functions. |
| 947 |
*/ |
| 948 |
mutable std::vector<number> work; |
| 949 |
|
| 950 |
/** |
| 951 |
* Integer working array used for some LAPACK functions. |
| 952 |
*/ |
| 953 |
mutable std::vector<types::blas_int> iwork; |
| 954 |
|
| 955 |
/** |
| 956 |
* The vector storing the permutations applied for pivoting in the LU- |
| 957 |
* factorization. |
| 958 |
* |
| 959 |
* Also used as the scratch array IWORK for LAPACK functions needing it. |
| 960 |
*/ |
| 961 |
std::vector<types::blas_int> ipiv; |
| 962 |
|
| 963 |
/** |
| 964 |
* Workspace for calculating the inverse matrix from an LU factorization. |
| 965 |
*/ |
| 966 |
std::vector<number> inv_work; |
| 967 |
|
| 968 |
/** |
| 969 |
* Real parts of eigenvalues or the singular values. Filled by |
| 970 |
* compute_eigenvalues() or compute_svd(). |
| 971 |
*/ |
| 972 |
std::vector<typename numbers::NumberTraits<number>::real_type> wr; |
| 973 |
|
| 974 |
/** |
| 975 |
* Imaginary parts of eigenvalues, or, in the complex scalar case, the |
| 976 |
* eigenvalues themselves. Filled by compute_eigenvalues. |
| 977 |
*/ |
| 978 |
std::vector<number> wi; |
| 979 |
|
| 980 |
/** |
| 981 |
* Space where left eigenvectors can be stored. |
| 982 |
*/ |
| 983 |
std::vector<number> vl; |
| 984 |
|
| 985 |
/** |
| 986 |
* Space where right eigenvectors can be stored. |
| 987 |
*/ |
| 988 |
std::vector<number> vr; |
| 989 |
|
| 990 |
/** |
| 991 |
* The matrix $\mathbf U$ in the singular value decomposition |
| 992 |
* $\mathbf U \cdot \mathbf S \cdot \mathbf V^T$. |
| 993 |
*/ |
| 994 |
std::unique_ptr<LAPACKFullMatrix<number>> svd_u; |
| 995 |
|
| 996 |
/** |
| 997 |
* The matrix $\mathbf V^T$ in the singular value decomposition |
| 998 |
* $\mathbf U \cdot \mathbf S \cdot \mathbf V^T$. |
| 999 |
*/ |
| 1000 |
std::unique_ptr<LAPACKFullMatrix<number>> svd_vt; |
| 1001 |
|
| 1002 |
/** |
| 1003 |
* Thread mutex. |
| 1004 |
*/ |
| 1005 |
mutable Threads::Mutex mutex; |
| 1006 |
}; |
| 1007 |
|
| 1008 |
|
| 1009 |
|
| 1010 |
/** |
| 1011 |
* A preconditioner based on the LU-factorization of LAPACKFullMatrix. |
| 1012 |
* |
| 1013 |
* @ingroup Preconditioners |
| 1014 |
*/ |
| 1015 |
template <typename number> |
| 1016 |
class PreconditionLU : public EnableObserverPointer |
| 1017 |
{ |
| 1018 |
public: |
| 1019 |
void |
| 1020 |
initialize(const LAPACKFullMatrix<number> &); |
| 1021 |
void |
| 1022 |
initialize(const LAPACKFullMatrix<number> &, VectorMemory<Vector<number>> &); |
| 1023 |
void |
| 1024 |
vmult(Vector<number> &, const Vector<number> &) const; |
| 1025 |
void |
| 1026 |
Tvmult(Vector<number> &, const Vector<number> &) const; |
| 1027 |
void |
| 1028 |
vmult(BlockVector<number> &, const BlockVector<number> &) const; |
| 1029 |
void |
| 1030 |
Tvmult(BlockVector<number> &, const BlockVector<number> &) const; |
| 1031 |
|
| 1032 |
private: |
| 1033 |
ObserverPointer<const LAPACKFullMatrix<number>, PreconditionLU<number>> |
| 1034 |
matrix; |
| 1035 |
ObserverPointer<VectorMemory<Vector<number>>, PreconditionLU<number>> mem; |
| 1036 |
}; |
| 1037 |
|
| 1038 |
/*---------------------- Inline functions -----------------------------------*/ |
| 1039 |
|
| 1040 |
template <typename number> |
| 1041 |
inline void |
| 1042 |
LAPACKFullMatrix<number>::set(const size_type i, |
| 1043 |
const size_type j, |
| 1044 |
const number value) |
| 1045 |
{ |
| 1046 |
(*this)(i, j) = value; |
| 1047 |
} |
| 1048 |
|
| 1049 |
|
| 1050 |
|
| 1051 |
template <typename number> |
| 1052 |
inline typename LAPACKFullMatrix<number>::size_type |
| 1053 |
LAPACKFullMatrix<number>::m() const |
| 1054 |
{ |
| 1055 |
return static_cast<size_type>(this->n_rows()); |
| 1056 |
} |
| 1057 |
|
| 1058 |
|
| 1059 |
|
| 1060 |
template <typename number> |
| 1061 |
inline typename LAPACKFullMatrix<number>::size_type |
| 1062 |
LAPACKFullMatrix<number>::n() const |
| 1063 |
{ |
| 1064 |
return static_cast<size_type>(this->n_cols()); |
| 1065 |
} |
| 1066 |
|
| 1067 |
|
| 1068 |
|
| 1069 |
template <typename number> |
| 1070 |
template <typename MatrixType> |
| 1071 |
inline void |
| 1072 |
LAPACKFullMatrix<number>::copy_from(const MatrixType &M) |
| 1073 |
{ |
| 1074 |
this->reinit(M.m(), M.n()); |
| 1075 |
|
| 1076 |
// loop over the elements of the argument matrix row by row, as suggested |
| 1077 |
// in the documentation of the sparse matrix iterator class, and |
| 1078 |
// copy them into the current object |
| 1079 |
for (size_type row = 0; row < M.m(); ++row) |
| 1080 |
{ |
| 1081 |
const typename MatrixType::const_iterator end_row = M.end(row); |
| 1082 |
for (typename MatrixType::const_iterator entry = M.begin(row); |
| 1083 |
entry != end_row; |
| 1084 |
++entry) |
| 1085 |
this->el(row, entry->column()) = entry->value(); |
| 1086 |
} |
| 1087 |
|
| 1088 |
state = LAPACKSupport::matrix; |
| 1089 |
} |
| 1090 |
|
| 1091 |
|
| 1092 |
|
| 1093 |
template <typename number> |
| 1094 |
template <typename MatrixType> |
| 1095 |
inline void |
| 1096 |
LAPACKFullMatrix<number>::fill(const MatrixType &M, |
| 1097 |
const size_type dst_offset_i, |
| 1098 |
const size_type dst_offset_j, |
| 1099 |
const size_type src_offset_i, |
| 1100 |
const size_type src_offset_j, |
| 1101 |
const number factor, |
| 1102 |
const bool transpose) |
| 1103 |
{ |
| 1104 |
// loop over the elements of the argument matrix row by row, as suggested |
| 1105 |
// in the documentation of the sparse matrix iterator class |
| 1106 |
for (size_type row = src_offset_i; row < M.m(); ++row) |
| 1107 |
{ |
| 1108 |
const typename MatrixType::const_iterator end_row = M.end(row); |
| 1109 |
for (typename MatrixType::const_iterator entry = M.begin(row); |
| 1110 |
entry != end_row; |
| 1111 |
++entry) |
| 1112 |
{ |
| 1113 |
const size_type i = transpose ? entry->column() : row; |
| 1114 |
const size_type j = transpose ? row : entry->column(); |
| 1115 |
|
| 1116 |
const size_type dst_i = dst_offset_i + i - src_offset_i; |
| 1117 |
const size_type dst_j = dst_offset_j + j - src_offset_j; |
| 1118 |
if (dst_i < this->n_rows() && dst_j < this->n_cols()) |
| 1119 |
(*this)(dst_i, dst_j) = factor * entry->value(); |
| 1120 |
} |
| 1121 |
} |
| 1122 |
|
| 1123 |
state = LAPACKSupport::matrix; |
| 1124 |
} |
| 1125 |
|
| 1126 |
|
| 1127 |
|
| 1128 |
template <typename number> |
| 1129 |
template <typename number2> |
| 1130 |
void |
| 1131 |
LAPACKFullMatrix<number>::vmult(Vector<number2> &, |
| 1132 |
const Vector<number2> &, |
| 1133 |
const bool) const |
| 1134 |
{ |
| 1135 |
Assert(false, |
| 1136 |
ExcMessage("LAPACKFullMatrix<number>::vmult must be called with a " |
| 1137 |
"matching Vector<double> vector type.")); |
| 1138 |
} |
| 1139 |
|
| 1140 |
|
| 1141 |
|
| 1142 |
template <typename number> |
| 1143 |
template <typename number2> |
| 1144 |
void |
| 1145 |
LAPACKFullMatrix<number>::vmult_add(Vector<number2> &, |
| 1146 |
const Vector<number2> &) const |
| 1147 |
{ |
| 1148 |
Assert(false, |
| 1149 |
ExcMessage("LAPACKFullMatrix<number>::vmult_add must be called with a " |
| 1150 |
"matching Vector<double> vector type.")); |
| 1151 |
} |
| 1152 |
|
| 1153 |
|
| 1154 |
|
| 1155 |
template <typename number> |
| 1156 |
template <typename number2> |
| 1157 |
void |
| 1158 |
LAPACKFullMatrix<number>::Tvmult(Vector<number2> &, |
| 1159 |
const Vector<number2> &, |
| 1160 |
const bool) const |
| 1161 |
{ |
| 1162 |
Assert(false, |
| 1163 |
ExcMessage("LAPACKFullMatrix<number>::Tvmult must be called with a " |
| 1164 |
"matching Vector<double> vector type.")); |
| 1165 |
} |
| 1166 |
|
| 1167 |
|
| 1168 |
|
| 1169 |
template <typename number> |
| 1170 |
template <typename number2> |
| 1171 |
void |
| 1172 |
LAPACKFullMatrix<number>::Tvmult_add(Vector<number2> &, |
| 1173 |
const Vector<number2> &) const |
| 1174 |
{ |
| 1175 |
Assert(false, |
| 1176 |
ExcMessage("LAPACKFullMatrix<number>::Tvmult_add must be called " |
| 1177 |
"with a matching Vector<double> vector type.")); |
| 1178 |
} |
| 1179 |
|
| 1180 |
|
| 1181 |
|
| 1182 |
namespace internal |
| 1183 |
{ |
| 1184 |
namespace LAPACKFullMatrixImplementation |
| 1185 |
{ |
| 1186 |
template <typename RealNumber> |
| 1187 |
std::complex<RealNumber> |
| 1188 |
pack_complex(const RealNumber &real_part, const RealNumber &imaginary_part) |
| 1189 |
{ |
| 1190 |
return std::complex<RealNumber>(real_part, imaginary_part); |
| 1191 |
} |
| 1192 |
|
| 1193 |
// The eigenvalues in LAPACKFullMatrix with complex-valued matrices are |
| 1194 |
// contained in the 'wi' array, ignoring the 'wr' array. |
| 1195 |
template <typename Number> |
| 1196 |
std::complex<Number> |
| 1197 |
pack_complex(const Number &, const std::complex<Number> &complex_number) |
| 1198 |
{ |
| 1199 |
return complex_number; |
| 1200 |
} |
| 1201 |
} // namespace LAPACKFullMatrixImplementation |
| 1202 |
} // namespace internal |
| 1203 |
|
| 1204 |
|
| 1205 |
|
| 1206 |
template <typename number> |
| 1207 |
inline std::complex<typename numbers::NumberTraits<number>::real_type> |
| 1208 |
LAPACKFullMatrix<number>::eigenvalue(const size_type i) const |
| 1209 |
{ |
| 1210 |
Assert(state & LAPACKSupport::eigenvalues, ExcInvalidState()); |
| 1211 |
Assert(wr.size() == this->n_rows(), ExcInternalError()); |
| 1212 |
Assert(wi.size() == this->n_rows(), ExcInternalError()); |
| 1213 |
AssertIndexRange(i, this->n_rows()); |
| 1214 |
|
| 1215 |
return internal::LAPACKFullMatrixImplementation::pack_complex(wr[i], wi[i]); |
| 1216 |
} |
| 1217 |
|
| 1218 |
|
| 1219 |
|
| 1220 |
template <typename number> |
| 1221 |
inline number |
| 1222 |
LAPACKFullMatrix<number>::singular_value(const size_type i) const |
| 1223 |
{ |
| 1224 |
Assert(state == LAPACKSupport::svd || state == LAPACKSupport::inverse_svd, |
| 1225 |
LAPACKSupport::ExcState(state)); |
| 1226 |
AssertIndexRange(i, wr.size()); |
| 1227 |
|
| 1228 |
return wr[i]; |
| 1229 |
} |
| 1230 |
|
| 1231 |
|
| 1232 |
|
| 1233 |
template <typename number> |
| 1234 |
inline const LAPACKFullMatrix<number> & |
| 1235 |
LAPACKFullMatrix<number>::get_svd_u() const |
| 1236 |
{ |
| 1237 |
Assert(state == LAPACKSupport::svd || state == LAPACKSupport::inverse_svd, |
| 1238 |
LAPACKSupport::ExcState(state)); |
| 1239 |
|
| 1240 |
return *svd_u; |
| 1241 |
} |
| 1242 |
|
| 1243 |
|
| 1244 |
|
| 1245 |
template <typename number> |
| 1246 |
inline const LAPACKFullMatrix<number> & |
| 1247 |
LAPACKFullMatrix<number>::get_svd_vt() const |
| 1248 |
{ |
| 1249 |
Assert(state == LAPACKSupport::svd || state == LAPACKSupport::inverse_svd, |
| 1250 |
LAPACKSupport::ExcState(state)); |
| 1251 |
|
| 1252 |
return *svd_vt; |
| 1253 |
} |
| 1254 |
|
| 1255 |
|
| 1256 |
|
| 1257 |
DEAL_II_NAMESPACE_CLOSE |
| 1258 |
|
| 1259 |
#endif |