| 1 |
// ------------------------------------------------------------------------ |
| 2 |
// |
| 3 |
// SPDX-License-Identifier: LGPL-2.1-or-later |
| 4 |
// Copyright (C) 2008 - 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_chunk_sparse_matrix_templates_h |
| 16 |
#define dealii_chunk_sparse_matrix_templates_h |
| 17 |
|
| 18 |
|
| 19 |
#include <deal.II/base/config.h> |
| 20 |
|
| 21 |
#include <deal.II/base/parallel.h> |
| 22 |
#include <deal.II/base/template_constraints.h> |
| 23 |
|
| 24 |
#include <deal.II/lac/chunk_sparse_matrix.h> |
| 25 |
#include <deal.II/lac/full_matrix.h> |
| 26 |
#include <deal.II/lac/vector.h> |
| 27 |
|
| 28 |
#include <algorithm> |
| 29 |
#include <cmath> |
| 30 |
#include <functional> |
| 31 |
#include <iomanip> |
| 32 |
#include <numeric> |
| 33 |
#include <ostream> |
| 34 |
#include <vector> |
| 35 |
|
| 36 |
DEAL_II_NAMESPACE_OPEN |
| 37 |
|
| 38 |
|
| 39 |
namespace internal |
| 40 |
{ |
| 41 |
// TODO: the goal of the ChunkSparseMatrix class is to stream data and use |
| 42 |
// the vectorization features of modern processors. to make this happen, |
| 43 |
// we will have to vectorize the functions in the following namespace, either |
| 44 |
// by hand or by using, for example, optimized BLAS versions for them. |
| 45 |
namespace ChunkSparseMatrixImplementation |
| 46 |
{ |
| 47 |
/** |
| 48 |
* Declare type for container size. |
| 49 |
*/ |
| 50 |
using size_type = types::global_dof_index; |
| 51 |
|
| 52 |
/** |
| 53 |
* Add the result of multiplying a chunk of size chunk_size times |
| 54 |
* chunk_size by a source vector fragment of size chunk_size to the |
| 55 |
* destination vector fragment. |
| 56 |
*/ |
| 57 |
template <typename MatrixIterator, |
| 58 |
typename SrcIterator, |
| 59 |
typename DstIterator> |
| 60 |
inline void |
| 61 |
chunk_vmult_add(const size_type chunk_size, |
| 62 |
const MatrixIterator matrix, |
| 63 |
const SrcIterator src, |
| 64 |
DstIterator dst) |
| 65 |
{ |
| 66 |
MatrixIterator matrix_row = matrix; |
| 67 |
|
| 68 |
for (size_type i = 0; i < chunk_size; ++i, matrix_row += chunk_size) |
| 69 |
{ |
| 70 |
typename std::iterator_traits<DstIterator>::value_type sum = 0; |
| 71 |
|
| 72 |
for (size_type j = 0; j < chunk_size; ++j) |
| 73 |
sum += matrix_row[j] * src[j]; |
| 74 |
|
| 75 |
dst[i] += sum; |
| 76 |
} |
| 77 |
} |
| 78 |
|
| 79 |
|
| 80 |
|
| 81 |
/** |
| 82 |
* Like the previous function, but subtract. We need this for computing |
| 83 |
* the residual. |
| 84 |
*/ |
| 85 |
template <typename MatrixIterator, |
| 86 |
typename SrcIterator, |
| 87 |
typename DstIterator> |
| 88 |
inline void |
| 89 |
chunk_vmult_subtract(const size_type chunk_size, |
| 90 |
const MatrixIterator matrix, |
| 91 |
const SrcIterator src, |
| 92 |
DstIterator dst) |
| 93 |
{ |
| 94 |
MatrixIterator matrix_row = matrix; |
| 95 |
|
| 96 |
for (size_type i = 0; i < chunk_size; ++i, matrix_row += chunk_size) |
| 97 |
{ |
| 98 |
typename std::iterator_traits<DstIterator>::value_type sum = 0; |
| 99 |
|
| 100 |
for (size_type j = 0; j < chunk_size; ++j) |
| 101 |
sum += matrix_row[j] * src[j]; |
| 102 |
|
| 103 |
dst[i] -= sum; |
| 104 |
} |
| 105 |
} |
| 106 |
|
| 107 |
|
| 108 |
/** |
| 109 |
* Add the result of multiplying the transpose of a chunk of size |
| 110 |
* chunk_size times chunk_size by a source vector fragment of size |
| 111 |
* chunk_size to the destination vector fragment. |
| 112 |
*/ |
| 113 |
template <typename MatrixIterator, |
| 114 |
typename SrcIterator, |
| 115 |
typename DstIterator> |
| 116 |
inline void |
| 117 |
chunk_Tvmult_add(const size_type chunk_size, |
| 118 |
const MatrixIterator matrix, |
| 119 |
const SrcIterator src, |
| 120 |
DstIterator dst) |
| 121 |
{ |
| 122 |
for (size_type i = 0; i < chunk_size; ++i) |
| 123 |
{ |
| 124 |
typename std::iterator_traits<DstIterator>::value_type sum = 0; |
| 125 |
|
| 126 |
for (size_type j = 0; j < chunk_size; ++j) |
| 127 |
sum += matrix[j * chunk_size + i] * src[j]; |
| 128 |
|
| 129 |
dst[i] += sum; |
| 130 |
} |
| 131 |
} |
| 132 |
|
| 133 |
|
| 134 |
/** |
| 135 |
* Produce the result of the matrix scalar product $u^TMv$ for an |
| 136 |
* individual chunk. |
| 137 |
*/ |
| 138 |
template <typename result_type, |
| 139 |
typename MatrixIterator, |
| 140 |
typename SrcIterator1, |
| 141 |
typename SrcIterator2> |
| 142 |
inline result_type |
| 143 |
chunk_matrix_scalar_product(const size_type chunk_size, |
| 144 |
const MatrixIterator matrix, |
| 145 |
const SrcIterator1 u, |
| 146 |
const SrcIterator2 v) |
| 147 |
{ |
| 148 |
result_type result = 0; |
| 149 |
|
| 150 |
MatrixIterator matrix_row = matrix; |
| 151 |
|
| 152 |
for (size_type i = 0; i < chunk_size; ++i, matrix_row += chunk_size) |
| 153 |
{ |
| 154 |
typename std::iterator_traits<SrcIterator2>::value_type sum = 0; |
| 155 |
|
| 156 |
for (size_type j = 0; j < chunk_size; ++j) |
| 157 |
sum += matrix_row[j] * v[j]; |
| 158 |
|
| 159 |
result += u[i] * sum; |
| 160 |
} |
| 161 |
|
| 162 |
return result; |
| 163 |
} |
| 164 |
|
| 165 |
|
| 166 |
|
| 167 |
/** |
| 168 |
* Perform a vmult_add using the ChunkSparseMatrix data structures, but |
| 169 |
* only using a subinterval of the matrix rows. |
| 170 |
* |
| 171 |
* In the sequential case, this function is called on all rows, in the |
| 172 |
* parallel case it may be called on a subrange, at the discretion of the |
| 173 |
* task scheduler. |
| 174 |
*/ |
| 175 |
template <typename number, typename InVector, typename OutVector> |
| 176 |
void |
| 177 |
vmult_add_on_subrange(const ChunkSparsityPattern &cols, |
| 178 |
const unsigned int begin_row, |
| 179 |
const unsigned int end_row, |
| 180 |
const number *values, |
| 181 |
const std::size_t *rowstart, |
| 182 |
const size_type *colnums, |
| 183 |
const InVector &src, |
| 184 |
OutVector &dst) |
| 185 |
{ |
| 186 |
const size_type m = cols.n_rows(); |
| 187 |
const size_type n = cols.n_cols(); |
| 188 |
const size_type chunk_size = cols.get_chunk_size(); |
| 189 |
|
| 190 |
// loop over all chunks. note that we need to treat the last chunk row |
| 191 |
// and column differently if they have padding elements |
| 192 |
const size_type n_filled_last_rows = m % chunk_size; |
| 193 |
const size_type n_filled_last_cols = n % chunk_size; |
| 194 |
|
| 195 |
const size_type last_regular_row = |
| 196 |
n_filled_last_rows > 0 ? |
| 197 |
std::min(m / chunk_size, static_cast<size_type>(end_row)) : |
| 198 |
end_row; |
| 199 |
const size_type irregular_col = n / chunk_size; |
| 200 |
|
| 201 |
typename OutVector::iterator dst_ptr = |
| 202 |
dst.begin() + chunk_size * begin_row; |
| 203 |
const number *val_ptr = |
| 204 |
&values[rowstart[begin_row] * chunk_size * chunk_size]; |
| 205 |
const size_type *colnum_ptr = &colnums[rowstart[begin_row]]; |
| 206 |
for (unsigned int chunk_row = begin_row; chunk_row < last_regular_row; |
| 207 |
++chunk_row) |
| 208 |
{ |
| 209 |
const number *const val_end_of_row = |
| 210 |
&values[rowstart[chunk_row + 1] * chunk_size * chunk_size]; |
| 211 |
while (val_ptr != val_end_of_row) |
| 212 |
{ |
| 213 |
if (*colnum_ptr != irregular_col) |
| 214 |
chunk_vmult_add(chunk_size, |
| 215 |
val_ptr, |
| 216 |
src.begin() + *colnum_ptr * chunk_size, |
| 217 |
dst_ptr); |
| 218 |
else |
| 219 |
// we're at a chunk column that has padding |
| 220 |
for (size_type r = 0; r < chunk_size; ++r) |
| 221 |
for (size_type c = 0; c < n_filled_last_cols; ++c) |
| 222 |
dst_ptr[r] += (val_ptr[r * chunk_size + c] * |
| 223 |
src(*colnum_ptr * chunk_size + c)); |
| 224 |
|
| 225 |
++colnum_ptr; |
| 226 |
val_ptr += chunk_size * chunk_size; |
| 227 |
} |
| 228 |
|
| 229 |
dst_ptr += chunk_size; |
| 230 |
} |
| 231 |
|
| 232 |
// now deal with last chunk row if necessary |
| 233 |
if (n_filled_last_rows > 0 && end_row == (m / chunk_size + 1)) |
| 234 |
{ |
| 235 |
const size_type chunk_row = last_regular_row; |
| 236 |
|
| 237 |
const number *const val_end_of_row = |
| 238 |
&values[rowstart[chunk_row + 1] * chunk_size * chunk_size]; |
| 239 |
while (val_ptr != val_end_of_row) |
| 240 |
{ |
| 241 |
if (*colnum_ptr != irregular_col) |
| 242 |
{ |
| 243 |
// we're at a chunk row but not column that has padding |
| 244 |
for (size_type r = 0; r < n_filled_last_rows; ++r) |
| 245 |
for (size_type c = 0; c < chunk_size; ++c) |
| 246 |
dst_ptr[r] += (val_ptr[r * chunk_size + c] * |
| 247 |
src(*colnum_ptr * chunk_size + c)); |
| 248 |
} |
| 249 |
else |
| 250 |
// we're at a chunk row and column that has padding |
| 251 |
for (size_type r = 0; r < n_filled_last_rows; ++r) |
| 252 |
for (size_type c = 0; c < n_filled_last_cols; ++c) |
| 253 |
dst_ptr[r] += (val_ptr[r * chunk_size + c] * |
| 254 |
src(*colnum_ptr * chunk_size + c)); |
| 255 |
|
| 256 |
++colnum_ptr; |
| 257 |
val_ptr += chunk_size * chunk_size; |
| 258 |
} |
| 259 |
} |
| 260 |
Assert(std::size_t(colnum_ptr - colnums) == rowstart[end_row], |
| 261 |
ExcInternalError()); |
| 262 |
Assert(std::size_t(val_ptr - values) == |
| 263 |
rowstart[end_row] * chunk_size * chunk_size, |
| 264 |
ExcInternalError()); |
| 265 |
} |
| 266 |
} // namespace ChunkSparseMatrixImplementation |
| 267 |
} // namespace internal |
| 268 |
|
| 269 |
|
| 270 |
|
| 271 |
template <typename number> |
| 272 |
ChunkSparseMatrix<number>::ChunkSparseMatrix() |
| 273 |
: cols(nullptr, "ChunkSparseMatrix") |
| 274 |
, val(nullptr) |
| 275 |
, max_len(0) |
| 276 |
{} |
| 277 |
|
| 278 |
|
| 279 |
|
| 280 |
template <typename number> |
| 281 |
ChunkSparseMatrix<number>::ChunkSparseMatrix(const ChunkSparseMatrix &m) |
| 282 |
: EnableObserverPointer(m) |
| 283 |
, cols(nullptr, "ChunkSparseMatrix") |
| 284 |
, val(nullptr) |
| 285 |
, max_len(0) |
| 286 |
{ |
| 287 |
Assert(m.cols == nullptr && m.val == nullptr && m.max_len == 0, |
| 288 |
ExcMessage( |
| 289 |
"This constructor can only be called if the provided argument " |
| 290 |
"is an empty matrix. This constructor can not be used to " |
| 291 |
"copy-construct a non-empty matrix. Use the " |
| 292 |
"ChunkSparseMatrix::copy_from() function for that purpose.")); |
| 293 |
} |
| 294 |
|
| 295 |
|
| 296 |
|
| 297 |
template <typename number> |
| 298 |
ChunkSparseMatrix<number> & |
| 299 |
ChunkSparseMatrix<number>::operator=(const ChunkSparseMatrix<number> &m) |
| 300 |
{ |
| 301 |
Assert(m.cols == nullptr && m.val == nullptr && m.max_len == 0, |
| 302 |
ExcMessage( |
| 303 |
"This operator can only be called if the provided right " |
| 304 |
"hand side is an empty matrix. This operator can not be " |
| 305 |
"used to copy a non-empty matrix. Use the " |
| 306 |
"ChunkSparseMatrix::copy_from() function for that purpose.")); |
| 307 |
|
| 308 |
return *this; |
| 309 |
} |
| 310 |
|
| 311 |
|
| 312 |
|
| 313 |
template <typename number> |
| 314 |
ChunkSparseMatrix<number>::ChunkSparseMatrix(const ChunkSparsityPattern &c) |
| 315 |
: cols(nullptr, "ChunkSparseMatrix") |
| 316 |
, val(nullptr) |
| 317 |
, max_len(0) |
| 318 |
{ |
| 319 |
// virtual functions called in constructors and destructors never use the |
| 320 |
// override in a derived class |
| 321 |
// for clarity be explicit on which function is called |
| 322 |
ChunkSparseMatrix<number>::reinit(c); |
| 323 |
} |
| 324 |
|
| 325 |
|
| 326 |
|
| 327 |
template <typename number> |
| 328 |
ChunkSparseMatrix<number>::ChunkSparseMatrix(const ChunkSparsityPattern &c, |
| 329 |
const IdentityMatrix &id) |
| 330 |
: cols(nullptr, "ChunkSparseMatrix") |
| 331 |
, val(nullptr) |
| 332 |
, max_len(0) |
| 333 |
{ |
| 334 |
Assert(c.n_rows() == id.m(), ExcDimensionMismatch(c.n_rows(), id.m())); |
| 335 |
Assert(c.n_cols() == id.n(), ExcDimensionMismatch(c.n_cols(), id.n())); |
| 336 |
|
| 337 |
// virtual functions called in constructors and destructors never use the |
| 338 |
// override in a derived class |
| 339 |
// for clarity be explicit on which function is called |
| 340 |
ChunkSparseMatrix<number>::reinit(c); |
| 341 |
for (size_type i = 0; i < n(); ++i) |
| 342 |
this->set(i, i, 1.); |
| 343 |
} |
| 344 |
|
| 345 |
|
| 346 |
|
| 347 |
template <typename number> |
| 348 |
ChunkSparseMatrix<number>::~ChunkSparseMatrix() |
| 349 |
{ |
| 350 |
cols = nullptr; |
| 351 |
} |
| 352 |
|
| 353 |
|
| 354 |
|
| 355 |
namespace internal |
| 356 |
{ |
| 357 |
namespace ChunkSparseMatrixImplementation |
| 358 |
{ |
| 359 |
template <typename T> |
| 360 |
void |
| 361 |
zero_subrange(const unsigned int begin, const unsigned int end, T *dst) |
| 362 |
{ |
| 363 |
std::memset(dst + begin, 0, (end - begin) * sizeof(T)); |
| 364 |
} |
| 365 |
} // namespace ChunkSparseMatrixImplementation |
| 366 |
} // namespace internal |
| 367 |
|
| 368 |
|
| 369 |
|
| 370 |
template <typename number> |
| 371 |
ChunkSparseMatrix<number> & |
| 372 |
ChunkSparseMatrix<number>::operator=(const double d) |
| 373 |
{ |
| 374 |
Assert(d == 0, ExcScalarAssignmentOnlyForZeroValue()); |
| 375 |
|
| 376 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 377 |
Assert(cols->sparsity_pattern.compressed || cols->empty(), |
| 378 |
ChunkSparsityPattern::ExcNotCompressed()); |
| 379 |
|
| 380 |
// do initial zeroing of elements in parallel. Try to achieve a similar |
| 381 |
// layout as when doing matrix-vector products, as on some NUMA systems, a |
| 382 |
// memory block is assigned to memory banks where the first access is |
| 383 |
// generated. For sparse matrices, the first operations is usually the |
| 384 |
// operator=. The grain size is chosen to reflect the number of rows in |
| 385 |
// minimum_parallel_grain_size, weighted by the number of nonzero entries |
| 386 |
// per row on average. |
| 387 |
const unsigned int matrix_size = cols->sparsity_pattern.n_nonzero_elements() * |
| 388 |
cols->chunk_size * cols->chunk_size; |
| 389 |
const unsigned int grain_size = |
| 390 |
internal::SparseMatrixImplementation::minimum_parallel_grain_size * |
| 391 |
(matrix_size + m()) / m(); |
| 392 |
if (matrix_size > grain_size) |
| 393 |
parallel::apply_to_subranges( |
| 394 |
0U, |
| 395 |
matrix_size, |
| 396 |
[this](const unsigned int begin, const unsigned int end) { |
| 397 |
internal::ChunkSparseMatrixImplementation::zero_subrange(begin, |
| 398 |
end, |
| 399 |
val.get()); |
| 400 |
}, |
| 401 |
grain_size); |
| 402 |
else if (matrix_size > 0) |
| 403 |
std::memset(val.get(), 0, matrix_size * sizeof(number)); |
| 404 |
|
| 405 |
return *this; |
| 406 |
} |
| 407 |
|
| 408 |
|
| 409 |
|
| 410 |
template <typename number> |
| 411 |
ChunkSparseMatrix<number> & |
| 412 |
ChunkSparseMatrix<number>::operator=(const IdentityMatrix &id) |
| 413 |
{ |
| 414 |
Assert(cols->n_rows() == id.m(), |
| 415 |
ExcDimensionMismatch(cols->n_rows(), id.m())); |
| 416 |
Assert(cols->n_cols() == id.n(), |
| 417 |
ExcDimensionMismatch(cols->n_cols(), id.n())); |
| 418 |
|
| 419 |
*this = 0; |
| 420 |
for (size_type i = 0; i < n(); ++i) |
| 421 |
this->set(i, i, 1.); |
| 422 |
|
| 423 |
return *this; |
| 424 |
} |
| 425 |
|
| 426 |
|
| 427 |
|
| 428 |
template <typename number> |
| 429 |
void |
| 430 |
ChunkSparseMatrix<number>::reinit(const ChunkSparsityPattern &sparsity) |
| 431 |
{ |
| 432 |
cols = &sparsity; |
| 433 |
|
| 434 |
if (cols->empty()) |
| 435 |
{ |
| 436 |
val.reset(); |
| 437 |
max_len = 0; |
| 438 |
return; |
| 439 |
} |
| 440 |
|
| 441 |
// allocate not just m() * n() elements but enough so that we can store full |
| 442 |
// chunks. this entails some padding elements |
| 443 |
const size_type chunk_size = cols->get_chunk_size(); |
| 444 |
const size_type N = |
| 445 |
cols->sparsity_pattern.n_nonzero_elements() * chunk_size * chunk_size; |
| 446 |
if (N > max_len || max_len == 0) |
| 447 |
{ |
| 448 |
val = std::make_unique<number[]>(N); |
| 449 |
max_len = N; |
| 450 |
} |
| 451 |
|
| 452 |
// fill with zeros. do not just fill N elements but all that we allocated to |
| 453 |
// ensure that also the padding elements are zero and not left at previous |
| 454 |
// values |
| 455 |
this->operator=(0.); |
| 456 |
} |
| 457 |
|
| 458 |
|
| 459 |
|
| 460 |
template <typename number> |
| 461 |
void |
| 462 |
ChunkSparseMatrix<number>::clear() |
| 463 |
{ |
| 464 |
cols = nullptr; |
| 465 |
val.reset(); |
| 466 |
max_len = 0; |
| 467 |
} |
| 468 |
|
| 469 |
|
| 470 |
|
| 471 |
template <typename number> |
| 472 |
bool |
| 473 |
ChunkSparseMatrix<number>::empty() const |
| 474 |
{ |
| 475 |
if (cols == nullptr) |
| 476 |
return true; |
| 477 |
else |
| 478 |
return cols->empty(); |
| 479 |
} |
| 480 |
|
| 481 |
|
| 482 |
|
| 483 |
template <typename number> |
| 484 |
typename ChunkSparseMatrix<number>::size_type |
| 485 |
ChunkSparseMatrix<number>::n_nonzero_elements() const |
| 486 |
{ |
| 487 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 488 |
return cols->n_nonzero_elements(); |
| 489 |
} |
| 490 |
|
| 491 |
|
| 492 |
|
| 493 |
template <typename number> |
| 494 |
typename ChunkSparseMatrix<number>::size_type |
| 495 |
ChunkSparseMatrix<number>::n_actually_nonzero_elements() const |
| 496 |
{ |
| 497 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 498 |
|
| 499 |
// count those elements that are nonzero, even if they lie in the padding |
| 500 |
// around the matrix. since we have the invariant that padding elements are |
| 501 |
// zero, nothing bad can happen here |
| 502 |
const size_type chunk_size = cols->get_chunk_size(); |
| 503 |
return std::count_if(val.get(), |
| 504 |
val.get() + cols->sparsity_pattern.n_nonzero_elements() * |
| 505 |
chunk_size * chunk_size, |
| 506 |
[](const double element) { return element != 0.; }); |
| 507 |
} |
| 508 |
|
| 509 |
|
| 510 |
|
| 511 |
template <typename number> |
| 512 |
void |
| 513 |
ChunkSparseMatrix<number>::symmetrize() |
| 514 |
{ |
| 515 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 516 |
Assert(cols->rows == cols->cols, ExcNotQuadratic()); |
| 517 |
|
| 518 |
DEAL_II_NOT_IMPLEMENTED(); |
| 519 |
} |
| 520 |
|
| 521 |
|
| 522 |
|
| 523 |
template <typename number> |
| 524 |
template <typename somenumber> |
| 525 |
ChunkSparseMatrix<number> & |
| 526 |
ChunkSparseMatrix<number>::copy_from( |
| 527 |
const ChunkSparseMatrix<somenumber> &matrix) |
| 528 |
{ |
| 529 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 530 |
Assert(val != nullptr, ExcNotInitialized()); |
| 531 |
Assert(cols == matrix.cols, ExcDifferentChunkSparsityPatterns()); |
| 532 |
|
| 533 |
// copy everything, including padding elements |
| 534 |
const size_type chunk_size = cols->get_chunk_size(); |
| 535 |
std::copy(matrix.val.get(), |
| 536 |
matrix.val.get() + cols->sparsity_pattern.n_nonzero_elements() * |
| 537 |
chunk_size * chunk_size, |
| 538 |
val.get()); |
| 539 |
|
| 540 |
return *this; |
| 541 |
} |
| 542 |
|
| 543 |
|
| 544 |
|
| 545 |
template <typename number> |
| 546 |
template <typename somenumber> |
| 547 |
void |
| 548 |
ChunkSparseMatrix<number>::copy_from(const FullMatrix<somenumber> &matrix) |
| 549 |
{ |
| 550 |
// first delete previous content |
| 551 |
*this = 0; |
| 552 |
|
| 553 |
// then copy old matrix |
| 554 |
for (size_type row = 0; row < matrix.m(); ++row) |
| 555 |
for (size_type col = 0; col < matrix.n(); ++col) |
| 556 |
if (matrix(row, col) != 0) |
| 557 |
set(row, col, matrix(row, col)); |
| 558 |
} |
| 559 |
|
| 560 |
|
| 561 |
|
| 562 |
template <typename number> |
| 563 |
template <typename somenumber> |
| 564 |
void |
| 565 |
ChunkSparseMatrix<number>::add(const number factor, |
| 566 |
const ChunkSparseMatrix<somenumber> &matrix) |
| 567 |
{ |
| 568 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 569 |
Assert(val != nullptr, ExcNotInitialized()); |
| 570 |
Assert(cols == matrix.cols, ExcDifferentChunkSparsityPatterns()); |
| 571 |
|
| 572 |
// add everything, including padding elements |
| 573 |
const size_type chunk_size = cols->get_chunk_size(); |
| 574 |
number *val_ptr = val.get(); |
| 575 |
const somenumber *matrix_ptr = matrix.val.get(); |
| 576 |
const number *const end_ptr = |
| 577 |
val.get() + |
| 578 |
cols->sparsity_pattern.n_nonzero_elements() * chunk_size * chunk_size; |
| 579 |
|
| 580 |
while (val_ptr != end_ptr) |
| 581 |
*val_ptr++ += factor * *matrix_ptr++; |
| 582 |
} |
| 583 |
|
| 584 |
|
| 585 |
|
| 586 |
template <typename number> |
| 587 |
void |
| 588 |
ChunkSparseMatrix<number>::extract_row_copy(const size_type row, |
| 589 |
const size_type array_length, |
| 590 |
size_type &row_length, |
| 591 |
size_type *column_indices, |
| 592 |
number *values) const |
| 593 |
{ |
| 594 |
AssertIndexRange(cols->row_length(row), array_length + 1); |
| 595 |
AssertIndexRange(row, m()); |
| 596 |
const unsigned int chunk_size = cols->get_chunk_size(); |
| 597 |
const size_type reduced_row = row / chunk_size; |
| 598 |
|
| 599 |
SparsityPattern::iterator it = cols->sparsity_pattern.begin(reduced_row), |
| 600 |
itend = cols->sparsity_pattern.end(reduced_row); |
| 601 |
const number *val_ptr = |
| 602 |
&val[(it - cols->sparsity_pattern.begin(0)) * chunk_size * chunk_size + |
| 603 |
(row % chunk_size) * chunk_size]; |
| 604 |
|
| 605 |
// find out if we did padding and if this row is affected by it |
| 606 |
if (cols->n_cols() % chunk_size == 0) |
| 607 |
{ |
| 608 |
for (; it < itend; ++it) |
| 609 |
{ |
| 610 |
for (unsigned int c = 0; c < chunk_size; ++c) |
| 611 |
{ |
| 612 |
*values++ = val_ptr[c]; |
| 613 |
*column_indices++ = it->column() * chunk_size + c; |
| 614 |
} |
| 615 |
val_ptr += chunk_size * chunk_size; |
| 616 |
} |
| 617 |
row_length = |
| 618 |
chunk_size * (cols->sparsity_pattern.row_length(reduced_row)); |
| 619 |
} |
| 620 |
else |
| 621 |
{ |
| 622 |
const unsigned int last_chunk_size = cols->n_cols() % chunk_size; |
| 623 |
row_length = 0; |
| 624 |
for (; it < itend; ++it) |
| 625 |
{ |
| 626 |
const unsigned int next_chunk_size = |
| 627 |
(it->column() == cols->sparsity_pattern.n_cols() - 1) ? |
| 628 |
last_chunk_size : |
| 629 |
chunk_size; |
| 630 |
for (unsigned int c = 0; c < next_chunk_size; ++c, ++row_length) |
| 631 |
{ |
| 632 |
*values++ = val_ptr[c]; |
| 633 |
*column_indices++ = it->column() * chunk_size + c; |
| 634 |
} |
| 635 |
val_ptr += chunk_size * chunk_size; |
| 636 |
} |
| 637 |
} |
| 638 |
} |
| 639 |
|
| 640 |
|
| 641 |
|
| 642 |
template <typename number> |
| 643 |
template <class OutVector, class InVector> |
| 644 |
void |
| 645 |
ChunkSparseMatrix<number>::vmult(OutVector &dst, const InVector &src) const |
| 646 |
{ |
| 647 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 648 |
Assert(val != nullptr, ExcNotInitialized()); |
| 649 |
Assert(m() == dst.size(), ExcDimensionMismatch(m(), dst.size())); |
| 650 |
Assert(n() == src.size(), ExcDimensionMismatch(n(), src.size())); |
| 651 |
|
| 652 |
Assert(!PointerComparison::equal(&src, &dst), ExcSourceEqualsDestination()); |
| 653 |
|
| 654 |
// set the output vector to zero and then add to it the contributions of |
| 655 |
// vmults from individual chunks. this is what vmult_add does |
| 656 |
dst = 0; |
| 657 |
vmult_add(dst, src); |
| 658 |
} |
| 659 |
|
| 660 |
|
| 661 |
|
| 662 |
template <typename number> |
| 663 |
template <class OutVector, class InVector> |
| 664 |
void |
| 665 |
ChunkSparseMatrix<number>::Tvmult(OutVector &dst, const InVector &src) const |
| 666 |
{ |
| 667 |
Assert(val != nullptr, ExcNotInitialized()); |
| 668 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 669 |
Assert(n() == dst.size(), ExcDimensionMismatch(n(), dst.size())); |
| 670 |
Assert(m() == src.size(), ExcDimensionMismatch(m(), src.size())); |
| 671 |
|
| 672 |
Assert(!PointerComparison::equal(&src, &dst), ExcSourceEqualsDestination()); |
| 673 |
|
| 674 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 675 |
Assert(val != nullptr, ExcNotInitialized()); |
| 676 |
Assert(m() == dst.size(), ExcDimensionMismatch(m(), dst.size())); |
| 677 |
Assert(n() == src.size(), ExcDimensionMismatch(n(), src.size())); |
| 678 |
|
| 679 |
Assert(!PointerComparison::equal(&src, &dst), ExcSourceEqualsDestination()); |
| 680 |
|
| 681 |
// set the output vector to zero and then add to it the contributions of |
| 682 |
// vmults from individual chunks. this is what vmult_add does |
| 683 |
dst = 0; |
| 684 |
Tvmult_add(dst, src); |
| 685 |
} |
| 686 |
|
| 687 |
|
| 688 |
|
| 689 |
template <typename number> |
| 690 |
template <class OutVector, class InVector> |
| 691 |
void |
| 692 |
ChunkSparseMatrix<number>::vmult_add(OutVector &dst, const InVector &src) const |
| 693 |
{ |
| 694 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 695 |
Assert(val != nullptr, ExcNotInitialized()); |
| 696 |
Assert(m() == dst.size(), ExcDimensionMismatch(m(), dst.size())); |
| 697 |
Assert(n() == src.size(), ExcDimensionMismatch(n(), src.size())); |
| 698 |
|
| 699 |
Assert(!PointerComparison::equal(&src, &dst), ExcSourceEqualsDestination()); |
| 700 |
parallel::apply_to_subranges( |
| 701 |
0U, |
| 702 |
cols->sparsity_pattern.n_rows(), |
| 703 |
[this, &src, &dst](const unsigned int begin_row, |
| 704 |
const unsigned int end_row) { |
| 705 |
internal::ChunkSparseMatrixImplementation::vmult_add_on_subrange( |
| 706 |
*cols, |
| 707 |
begin_row, |
| 708 |
end_row, |
| 709 |
val.get(), |
| 710 |
cols->sparsity_pattern.rowstart.get(), |
| 711 |
cols->sparsity_pattern.colnums.get(), |
| 712 |
src, |
| 713 |
dst); |
| 714 |
}, |
| 715 |
internal::SparseMatrixImplementation::minimum_parallel_grain_size / |
| 716 |
cols->chunk_size + |
| 717 |
1); |
| 718 |
} |
| 719 |
|
| 720 |
|
| 721 |
template <typename number> |
| 722 |
template <class OutVector, class InVector> |
| 723 |
void |
| 724 |
ChunkSparseMatrix<number>::Tvmult_add(OutVector &dst, const InVector &src) const |
| 725 |
{ |
| 726 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 727 |
Assert(val != nullptr, ExcNotInitialized()); |
| 728 |
Assert(m() == dst.size(), ExcDimensionMismatch(m(), dst.size())); |
| 729 |
Assert(n() == src.size(), ExcDimensionMismatch(n(), src.size())); |
| 730 |
|
| 731 |
Assert(!PointerComparison::equal(&src, &dst), ExcSourceEqualsDestination()); |
| 732 |
|
| 733 |
const size_type n_chunk_rows = cols->sparsity_pattern.n_rows(); |
| 734 |
|
| 735 |
// loop over all chunks. note that we need to treat the last chunk row and |
| 736 |
// column differently if they have padding elements |
| 737 |
const bool rows_have_padding = (m() % cols->chunk_size != 0), |
| 738 |
cols_have_padding = (n() % cols->chunk_size != 0); |
| 739 |
|
| 740 |
const size_type n_regular_chunk_rows = |
| 741 |
(rows_have_padding ? n_chunk_rows - 1 : n_chunk_rows); |
| 742 |
|
| 743 |
// like in vmult_add, but don't keep an iterator into dst around since we're |
| 744 |
// not traversing it sequentially this time |
| 745 |
const number *val_ptr = val.get(); |
| 746 |
const size_type *colnum_ptr = cols->sparsity_pattern.colnums.get(); |
| 747 |
|
| 748 |
for (size_type chunk_row = 0; chunk_row < n_regular_chunk_rows; ++chunk_row) |
| 749 |
{ |
| 750 |
const number *const val_end_of_row = |
| 751 |
&val[cols->sparsity_pattern.rowstart[chunk_row + 1] * cols->chunk_size * |
| 752 |
cols->chunk_size]; |
| 753 |
while (val_ptr != val_end_of_row) |
| 754 |
{ |
| 755 |
if ((cols_have_padding == false) || |
| 756 |
(*colnum_ptr != cols->sparsity_pattern.n_cols() - 1)) |
| 757 |
internal::ChunkSparseMatrixImplementation::chunk_Tvmult_add( |
| 758 |
cols->chunk_size, |
| 759 |
val_ptr, |
| 760 |
src.begin() + chunk_row * cols->chunk_size, |
| 761 |
dst.begin() + *colnum_ptr * cols->chunk_size); |
| 762 |
else |
| 763 |
// we're at a chunk column that has padding |
| 764 |
for (size_type r = 0; r < cols->chunk_size; ++r) |
| 765 |
for (size_type c = 0; c < n() % cols->chunk_size; ++c) |
| 766 |
dst(*colnum_ptr * cols->chunk_size + c) += |
| 767 |
(val_ptr[r * cols->chunk_size + c] * |
| 768 |
src(chunk_row * cols->chunk_size + r)); |
| 769 |
|
| 770 |
++colnum_ptr; |
| 771 |
val_ptr += cols->chunk_size * cols->chunk_size; |
| 772 |
} |
| 773 |
} |
| 774 |
|
| 775 |
// now deal with last chunk row if necessary |
| 776 |
if (rows_have_padding) |
| 777 |
{ |
| 778 |
const size_type chunk_row = n_chunk_rows - 1; |
| 779 |
|
| 780 |
const number *const val_end_of_row = |
| 781 |
&val[cols->sparsity_pattern.rowstart[chunk_row + 1] * cols->chunk_size * |
| 782 |
cols->chunk_size]; |
| 783 |
while (val_ptr != val_end_of_row) |
| 784 |
{ |
| 785 |
if ((cols_have_padding == false) || |
| 786 |
(*colnum_ptr != cols->sparsity_pattern.n_cols() - 1)) |
| 787 |
{ |
| 788 |
// we're at a chunk row but not column that has padding |
| 789 |
for (size_type r = 0; r < m() % cols->chunk_size; ++r) |
| 790 |
for (size_type c = 0; c < cols->chunk_size; ++c) |
| 791 |
dst(*colnum_ptr * cols->chunk_size + c) += |
| 792 |
(val_ptr[r * cols->chunk_size + c] * |
| 793 |
src(chunk_row * cols->chunk_size + r)); |
| 794 |
} |
| 795 |
else |
| 796 |
// we're at a chunk row and column that has padding |
| 797 |
for (size_type r = 0; r < m() % cols->chunk_size; ++r) |
| 798 |
for (size_type c = 0; c < n() % cols->chunk_size; ++c) |
| 799 |
dst(*colnum_ptr * cols->chunk_size + c) += |
| 800 |
(val_ptr[r * cols->chunk_size + c] * |
| 801 |
src(chunk_row * cols->chunk_size + r)); |
| 802 |
|
| 803 |
++colnum_ptr; |
| 804 |
val_ptr += cols->chunk_size * cols->chunk_size; |
| 805 |
} |
| 806 |
} |
| 807 |
} |
| 808 |
|
| 809 |
|
| 810 |
template <typename number> |
| 811 |
template <typename somenumber> |
| 812 |
somenumber |
| 813 |
ChunkSparseMatrix<number>::matrix_norm_square(const Vector<somenumber> &v) const |
| 814 |
{ |
| 815 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 816 |
Assert(val != nullptr, ExcNotInitialized()); |
| 817 |
Assert(m() == v.size(), ExcDimensionMismatch(m(), v.size())); |
| 818 |
Assert(n() == v.size(), ExcDimensionMismatch(n(), v.size())); |
| 819 |
|
| 820 |
somenumber result = 0; |
| 821 |
|
| 822 |
//////////////// |
| 823 |
// like matrix_scalar_product, except that the two vectors are now the same |
| 824 |
|
| 825 |
const size_type n_chunk_rows = cols->sparsity_pattern.n_rows(); |
| 826 |
|
| 827 |
// loop over all chunks. note that we need to treat the last chunk row and |
| 828 |
// column differently if they have padding elements |
| 829 |
const bool rows_have_padding = (m() % cols->chunk_size != 0), |
| 830 |
cols_have_padding = (n() % cols->chunk_size != 0); |
| 831 |
|
| 832 |
const size_type n_regular_chunk_rows = |
| 833 |
(rows_have_padding ? n_chunk_rows - 1 : n_chunk_rows); |
| 834 |
|
| 835 |
const number *val_ptr = val.get(); |
| 836 |
const size_type *colnum_ptr = cols->sparsity_pattern.colnums.get(); |
| 837 |
typename Vector<somenumber>::const_iterator v_ptr = v.begin(); |
| 838 |
|
| 839 |
for (size_type chunk_row = 0; chunk_row < n_regular_chunk_rows; ++chunk_row) |
| 840 |
{ |
| 841 |
const number *const val_end_of_row = |
| 842 |
&val[cols->sparsity_pattern.rowstart[chunk_row + 1] * cols->chunk_size * |
| 843 |
cols->chunk_size]; |
| 844 |
while (val_ptr != val_end_of_row) |
| 845 |
{ |
| 846 |
if ((cols_have_padding == false) || |
| 847 |
(*colnum_ptr != cols->sparsity_pattern.n_cols() - 1)) |
| 848 |
result += internal::ChunkSparseMatrixImplementation:: |
| 849 |
chunk_matrix_scalar_product<somenumber>(cols->chunk_size, |
| 850 |
val_ptr, |
| 851 |
v_ptr, |
| 852 |
v.begin() + |
| 853 |
*colnum_ptr * |
| 854 |
cols->chunk_size); |
| 855 |
else |
| 856 |
// we're at a chunk column that has padding |
| 857 |
for (size_type r = 0; r < cols->chunk_size; ++r) |
| 858 |
for (size_type c = 0; c < n() % cols->chunk_size; ++c) |
| 859 |
result += v(chunk_row * cols->chunk_size + r) * |
| 860 |
(val_ptr[r * cols->chunk_size + c] * |
| 861 |
v(*colnum_ptr * cols->chunk_size + c)); |
| 862 |
|
| 863 |
++colnum_ptr; |
| 864 |
val_ptr += cols->chunk_size * cols->chunk_size; |
| 865 |
} |
| 866 |
|
| 867 |
|
| 868 |
v_ptr += cols->chunk_size; |
| 869 |
} |
| 870 |
|
| 871 |
// now deal with last chunk row if necessary |
| 872 |
if (rows_have_padding) |
| 873 |
{ |
| 874 |
const size_type chunk_row = n_chunk_rows - 1; |
| 875 |
|
| 876 |
const number *const val_end_of_row = |
| 877 |
&val[cols->sparsity_pattern.rowstart[chunk_row + 1] * cols->chunk_size * |
| 878 |
cols->chunk_size]; |
| 879 |
while (val_ptr != val_end_of_row) |
| 880 |
{ |
| 881 |
if ((cols_have_padding == false) || |
| 882 |
(*colnum_ptr != cols->sparsity_pattern.n_cols() - 1)) |
| 883 |
{ |
| 884 |
// we're at a chunk row but not column that has padding |
| 885 |
for (size_type r = 0; r < m() % cols->chunk_size; ++r) |
| 886 |
for (size_type c = 0; c < cols->chunk_size; ++c) |
| 887 |
result += v(chunk_row * cols->chunk_size + r) * |
| 888 |
(val_ptr[r * cols->chunk_size + c] * |
| 889 |
v(*colnum_ptr * cols->chunk_size + c)); |
| 890 |
} |
| 891 |
else |
| 892 |
// we're at a chunk row and column that has padding |
| 893 |
for (size_type r = 0; r < m() % cols->chunk_size; ++r) |
| 894 |
for (size_type c = 0; c < n() % cols->chunk_size; ++c) |
| 895 |
result += v(chunk_row * cols->chunk_size + r) * |
| 896 |
(val_ptr[r * cols->chunk_size + c] * |
| 897 |
v(*colnum_ptr * cols->chunk_size + c)); |
| 898 |
|
| 899 |
++colnum_ptr; |
| 900 |
val_ptr += cols->chunk_size * cols->chunk_size; |
| 901 |
} |
| 902 |
} |
| 903 |
|
| 904 |
return result; |
| 905 |
} |
| 906 |
|
| 907 |
|
| 908 |
|
| 909 |
template <typename number> |
| 910 |
template <typename somenumber> |
| 911 |
somenumber |
| 912 |
ChunkSparseMatrix<number>::matrix_scalar_product( |
| 913 |
const Vector<somenumber> &u, |
| 914 |
const Vector<somenumber> &v) const |
| 915 |
{ |
| 916 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 917 |
Assert(val != nullptr, ExcNotInitialized()); |
| 918 |
Assert(m() == u.size(), ExcDimensionMismatch(m(), u.size())); |
| 919 |
Assert(n() == v.size(), ExcDimensionMismatch(n(), v.size())); |
| 920 |
|
| 921 |
// the following works like the vmult_add function |
| 922 |
somenumber result = 0; |
| 923 |
|
| 924 |
const size_type n_chunk_rows = cols->sparsity_pattern.n_rows(); |
| 925 |
|
| 926 |
// loop over all chunks. note that we need to treat the last chunk row and |
| 927 |
// column differently if they have padding elements |
| 928 |
const bool rows_have_padding = (m() % cols->chunk_size != 0), |
| 929 |
cols_have_padding = (n() % cols->chunk_size != 0); |
| 930 |
|
| 931 |
const size_type n_regular_chunk_rows = |
| 932 |
(rows_have_padding ? n_chunk_rows - 1 : n_chunk_rows); |
| 933 |
|
| 934 |
const number *val_ptr = val.get(); |
| 935 |
const size_type *colnum_ptr = cols->sparsity_pattern.colnums.get(); |
| 936 |
typename Vector<somenumber>::const_iterator u_ptr = u.begin(); |
| 937 |
|
| 938 |
for (size_type chunk_row = 0; chunk_row < n_regular_chunk_rows; ++chunk_row) |
| 939 |
{ |
| 940 |
const number *const val_end_of_row = |
| 941 |
&val[cols->sparsity_pattern.rowstart[chunk_row + 1] * cols->chunk_size * |
| 942 |
cols->chunk_size]; |
| 943 |
while (val_ptr != val_end_of_row) |
| 944 |
{ |
| 945 |
if ((cols_have_padding == false) || |
| 946 |
(*colnum_ptr != cols->sparsity_pattern.n_cols() - 1)) |
| 947 |
result += internal::ChunkSparseMatrixImplementation:: |
| 948 |
chunk_matrix_scalar_product<somenumber>(cols->chunk_size, |
| 949 |
val_ptr, |
| 950 |
u_ptr, |
| 951 |
v.begin() + |
| 952 |
*colnum_ptr * |
| 953 |
cols->chunk_size); |
| 954 |
else |
| 955 |
// we're at a chunk column that has padding |
| 956 |
for (size_type r = 0; r < cols->chunk_size; ++r) |
| 957 |
for (size_type c = 0; c < n() % cols->chunk_size; ++c) |
| 958 |
result += u(chunk_row * cols->chunk_size + r) * |
| 959 |
(val_ptr[r * cols->chunk_size + c] * |
| 960 |
v(*colnum_ptr * cols->chunk_size + c)); |
| 961 |
|
| 962 |
++colnum_ptr; |
| 963 |
val_ptr += cols->chunk_size * cols->chunk_size; |
| 964 |
} |
| 965 |
|
| 966 |
|
| 967 |
u_ptr += cols->chunk_size; |
| 968 |
} |
| 969 |
|
| 970 |
// now deal with last chunk row if necessary |
| 971 |
if (rows_have_padding) |
| 972 |
{ |
| 973 |
const size_type chunk_row = n_chunk_rows - 1; |
| 974 |
|
| 975 |
const number *const val_end_of_row = |
| 976 |
&val[cols->sparsity_pattern.rowstart[chunk_row + 1] * cols->chunk_size * |
| 977 |
cols->chunk_size]; |
| 978 |
while (val_ptr != val_end_of_row) |
| 979 |
{ |
| 980 |
if ((cols_have_padding == false) || |
| 981 |
(*colnum_ptr != cols->sparsity_pattern.n_cols() - 1)) |
| 982 |
{ |
| 983 |
// we're at a chunk row but not column that has padding |
| 984 |
for (size_type r = 0; r < m() % cols->chunk_size; ++r) |
| 985 |
for (size_type c = 0; c < cols->chunk_size; ++c) |
| 986 |
result += u(chunk_row * cols->chunk_size + r) * |
| 987 |
(val_ptr[r * cols->chunk_size + c] * |
| 988 |
v(*colnum_ptr * cols->chunk_size + c)); |
| 989 |
} |
| 990 |
else |
| 991 |
// we're at a chunk row and column that has padding |
| 992 |
for (size_type r = 0; r < m() % cols->chunk_size; ++r) |
| 993 |
for (size_type c = 0; c < n() % cols->chunk_size; ++c) |
| 994 |
result += u(chunk_row * cols->chunk_size + r) * |
| 995 |
(val_ptr[r * cols->chunk_size + c] * |
| 996 |
v(*colnum_ptr * cols->chunk_size + c)); |
| 997 |
|
| 998 |
++colnum_ptr; |
| 999 |
val_ptr += cols->chunk_size * cols->chunk_size; |
| 1000 |
} |
| 1001 |
} |
| 1002 |
|
| 1003 |
return result; |
| 1004 |
} |
| 1005 |
|
| 1006 |
|
| 1007 |
|
| 1008 |
template <typename number> |
| 1009 |
typename ChunkSparseMatrix<number>::real_type |
| 1010 |
ChunkSparseMatrix<number>::l1_norm() const |
| 1011 |
{ |
| 1012 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 1013 |
Assert(val != nullptr, ExcNotInitialized()); |
| 1014 |
|
| 1015 |
const size_type n_chunk_rows = cols->sparsity_pattern.n_rows(); |
| 1016 |
|
| 1017 |
// loop over all rows and columns; it is safe to also loop over the padding |
| 1018 |
// elements (they are zero) if we make sure that the vector into which we |
| 1019 |
// sum column sums is large enough |
| 1020 |
Vector<real_type> column_sums(cols->sparsity_pattern.n_cols() * |
| 1021 |
cols->chunk_size); |
| 1022 |
|
| 1023 |
for (size_type chunk_row = 0; chunk_row < n_chunk_rows; ++chunk_row) |
| 1024 |
for (size_type j = cols->sparsity_pattern.rowstart[chunk_row]; |
| 1025 |
j < cols->sparsity_pattern.rowstart[chunk_row + 1]; |
| 1026 |
++j) |
| 1027 |
for (size_type r = 0; r < cols->chunk_size; ++r) |
| 1028 |
for (size_type s = 0; s < cols->chunk_size; ++s) |
| 1029 |
column_sums(cols->sparsity_pattern.colnums[j] * cols->chunk_size + |
| 1030 |
s) += |
| 1031 |
numbers::NumberTraits<number>::abs( |
| 1032 |
val[j * cols->chunk_size * cols->chunk_size + |
| 1033 |
r * cols->chunk_size + s]); |
| 1034 |
|
| 1035 |
return column_sums.linfty_norm(); |
| 1036 |
} |
| 1037 |
|
| 1038 |
|
| 1039 |
|
| 1040 |
template <typename number> |
| 1041 |
typename ChunkSparseMatrix<number>::real_type |
| 1042 |
ChunkSparseMatrix<number>::linfty_norm() const |
| 1043 |
{ |
| 1044 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 1045 |
Assert(val != nullptr, ExcNotInitialized()); |
| 1046 |
|
| 1047 |
// this function works like l1_norm(). it can be made more efficient |
| 1048 |
// (without allocating a temporary vector) as is done in the SparseMatrix |
| 1049 |
// class but since it is rarely called in time critical places it is |
| 1050 |
// probably not worth it |
| 1051 |
const size_type n_chunk_rows = cols->sparsity_pattern.n_rows(); |
| 1052 |
|
| 1053 |
// loop over all rows and columns; it is safe to also loop over the padding |
| 1054 |
// elements (they are zero) if we make sure that the vector into which we |
| 1055 |
// sum column sums is large enough |
| 1056 |
Vector<real_type> row_sums(cols->sparsity_pattern.n_rows() * |
| 1057 |
cols->chunk_size); |
| 1058 |
|
| 1059 |
for (size_type chunk_row = 0; chunk_row < n_chunk_rows; ++chunk_row) |
| 1060 |
for (size_type j = cols->sparsity_pattern.rowstart[chunk_row]; |
| 1061 |
j < cols->sparsity_pattern.rowstart[chunk_row + 1]; |
| 1062 |
++j) |
| 1063 |
for (size_type r = 0; r < cols->chunk_size; ++r) |
| 1064 |
for (size_type s = 0; s < cols->chunk_size; ++s) |
| 1065 |
row_sums(chunk_row * cols->chunk_size + r) += |
| 1066 |
numbers::NumberTraits<number>::abs( |
| 1067 |
val[j * cols->chunk_size * cols->chunk_size + |
| 1068 |
r * cols->chunk_size + s]); |
| 1069 |
|
| 1070 |
return row_sums.linfty_norm(); |
| 1071 |
} |
| 1072 |
|
| 1073 |
|
| 1074 |
|
| 1075 |
template <typename number> |
| 1076 |
typename ChunkSparseMatrix<number>::real_type |
| 1077 |
ChunkSparseMatrix<number>::frobenius_norm() const |
| 1078 |
{ |
| 1079 |
// simply add up all entries in the sparsity pattern, without taking any |
| 1080 |
// reference to rows or columns |
| 1081 |
// |
| 1082 |
// padding elements are zero, so we can add them up as well |
| 1083 |
real_type norm_sqr = 0; |
| 1084 |
for (const number *ptr = val.get(); ptr != val.get() + max_len; ++ptr) |
| 1085 |
norm_sqr += numbers::NumberTraits<number>::abs_square(*ptr); |
| 1086 |
|
| 1087 |
return std::sqrt(norm_sqr); |
| 1088 |
} |
| 1089 |
|
| 1090 |
|
| 1091 |
|
| 1092 |
template <typename number> |
| 1093 |
template <typename somenumber> |
| 1094 |
somenumber |
| 1095 |
ChunkSparseMatrix<number>::residual(Vector<somenumber> &dst, |
| 1096 |
const Vector<somenumber> &u, |
| 1097 |
const Vector<somenumber> &b) const |
| 1098 |
{ |
| 1099 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 1100 |
Assert(val != nullptr, ExcNotInitialized()); |
| 1101 |
Assert(m() == dst.size(), ExcDimensionMismatch(m(), dst.size())); |
| 1102 |
Assert(m() == b.size(), ExcDimensionMismatch(m(), b.size())); |
| 1103 |
Assert(n() == u.size(), ExcDimensionMismatch(n(), u.size())); |
| 1104 |
|
| 1105 |
Assert(&u != &dst, ExcSourceEqualsDestination()); |
| 1106 |
|
| 1107 |
// set dst=b, then subtract the result of A*u from it. since the purpose of |
| 1108 |
// the current class is to promote streaming of data rather than more random |
| 1109 |
// access patterns, breaking things up into two loops may be reasonable |
| 1110 |
dst = b; |
| 1111 |
|
| 1112 |
///////// |
| 1113 |
// the rest of this function is like vmult_add, except that we subtract |
| 1114 |
// rather than add A*u |
| 1115 |
///////// |
| 1116 |
const size_type n_chunk_rows = cols->sparsity_pattern.n_rows(); |
| 1117 |
|
| 1118 |
// loop over all chunks. note that we need to treat the last chunk row and |
| 1119 |
// column differently if they have padding elements |
| 1120 |
const bool rows_have_padding = (m() % cols->chunk_size != 0), |
| 1121 |
cols_have_padding = (n() % cols->chunk_size != 0); |
| 1122 |
|
| 1123 |
const size_type n_regular_chunk_rows = |
| 1124 |
(rows_have_padding ? n_chunk_rows - 1 : n_chunk_rows); |
| 1125 |
|
| 1126 |
const number *val_ptr = val.get(); |
| 1127 |
const size_type *colnum_ptr = cols->sparsity_pattern.colnums.get(); |
| 1128 |
typename Vector<somenumber>::iterator dst_ptr = dst.begin(); |
| 1129 |
|
| 1130 |
for (size_type chunk_row = 0; chunk_row < n_regular_chunk_rows; ++chunk_row) |
| 1131 |
{ |
| 1132 |
const number *const val_end_of_row = |
| 1133 |
&val[cols->sparsity_pattern.rowstart[chunk_row + 1] * cols->chunk_size * |
| 1134 |
cols->chunk_size]; |
| 1135 |
while (val_ptr != val_end_of_row) |
| 1136 |
{ |
| 1137 |
if ((cols_have_padding == false) || |
| 1138 |
(*colnum_ptr != cols->sparsity_pattern.n_cols() - 1)) |
| 1139 |
internal::ChunkSparseMatrixImplementation::chunk_vmult_subtract( |
| 1140 |
cols->chunk_size, |
| 1141 |
val_ptr, |
| 1142 |
u.begin() + *colnum_ptr * cols->chunk_size, |
| 1143 |
dst_ptr); |
| 1144 |
else |
| 1145 |
// we're at a chunk column that has padding |
| 1146 |
for (size_type r = 0; r < cols->chunk_size; ++r) |
| 1147 |
for (size_type c = 0; c < n() % cols->chunk_size; ++c) |
| 1148 |
dst(chunk_row * cols->chunk_size + r) -= |
| 1149 |
(val_ptr[r * cols->chunk_size + c] * |
| 1150 |
u(*colnum_ptr * cols->chunk_size + c)); |
| 1151 |
|
| 1152 |
++colnum_ptr; |
| 1153 |
val_ptr += cols->chunk_size * cols->chunk_size; |
| 1154 |
} |
| 1155 |
|
| 1156 |
|
| 1157 |
dst_ptr += cols->chunk_size; |
| 1158 |
} |
| 1159 |
|
| 1160 |
// now deal with last chunk row if necessary |
| 1161 |
if (rows_have_padding) |
| 1162 |
{ |
| 1163 |
const size_type chunk_row = n_chunk_rows - 1; |
| 1164 |
|
| 1165 |
const number *const val_end_of_row = |
| 1166 |
&val[cols->sparsity_pattern.rowstart[chunk_row + 1] * cols->chunk_size * |
| 1167 |
cols->chunk_size]; |
| 1168 |
while (val_ptr != val_end_of_row) |
| 1169 |
{ |
| 1170 |
if ((cols_have_padding == false) || |
| 1171 |
(*colnum_ptr != cols->sparsity_pattern.n_cols() - 1)) |
| 1172 |
{ |
| 1173 |
// we're at a chunk row but not column that has padding |
| 1174 |
for (size_type r = 0; r < m() % cols->chunk_size; ++r) |
| 1175 |
for (size_type c = 0; c < cols->chunk_size; ++c) |
| 1176 |
dst(chunk_row * cols->chunk_size + r) -= |
| 1177 |
(val_ptr[r * cols->chunk_size + c] * |
| 1178 |
u(*colnum_ptr * cols->chunk_size + c)); |
| 1179 |
} |
| 1180 |
else |
| 1181 |
// we're at a chunk row and column that has padding |
| 1182 |
for (size_type r = 0; r < m() % cols->chunk_size; ++r) |
| 1183 |
for (size_type c = 0; c < n() % cols->chunk_size; ++c) |
| 1184 |
dst(chunk_row * cols->chunk_size + r) -= |
| 1185 |
(val_ptr[r * cols->chunk_size + c] * |
| 1186 |
u(*colnum_ptr * cols->chunk_size + c)); |
| 1187 |
|
| 1188 |
++colnum_ptr; |
| 1189 |
val_ptr += cols->chunk_size * cols->chunk_size; |
| 1190 |
} |
| 1191 |
|
| 1192 |
|
| 1193 |
dst_ptr += cols->chunk_size; |
| 1194 |
} |
| 1195 |
|
| 1196 |
// finally compute the norm |
| 1197 |
return dst.l2_norm(); |
| 1198 |
} |
| 1199 |
|
| 1200 |
|
| 1201 |
|
| 1202 |
template <typename number> |
| 1203 |
template <typename somenumber> |
| 1204 |
void |
| 1205 |
ChunkSparseMatrix<number>::precondition_Jacobi(Vector<somenumber> &dst, |
| 1206 |
const Vector<somenumber> &src, |
| 1207 |
const number /*om*/) const |
| 1208 |
{ |
| 1209 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 1210 |
Assert(val != nullptr, ExcNotInitialized()); |
| 1211 |
Assert(m() == n(), |
| 1212 |
ExcMessage("This operation is only valid on square matrices.")); |
| 1213 |
|
| 1214 |
Assert(dst.size() == n(), ExcDimensionMismatch(dst.size(), n())); |
| 1215 |
Assert(src.size() == n(), ExcDimensionMismatch(src.size(), n())); |
| 1216 |
|
| 1217 |
DEAL_II_NOT_IMPLEMENTED(); |
| 1218 |
} |
| 1219 |
|
| 1220 |
|
| 1221 |
|
| 1222 |
template <typename number> |
| 1223 |
template <typename somenumber> |
| 1224 |
void |
| 1225 |
ChunkSparseMatrix<number>::precondition_SSOR(Vector<somenumber> &dst, |
| 1226 |
const Vector<somenumber> &src, |
| 1227 |
const number /*om*/) const |
| 1228 |
{ |
| 1229 |
// to understand how this function works you may want to take a look at the |
| 1230 |
// CVS archives to see the original version which is much clearer... |
| 1231 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 1232 |
Assert(val != nullptr, ExcNotInitialized()); |
| 1233 |
Assert(m() == n(), |
| 1234 |
ExcMessage("This operation is only valid on square matrices.")); |
| 1235 |
|
| 1236 |
Assert(dst.size() == n(), ExcDimensionMismatch(dst.size(), n())); |
| 1237 |
Assert(src.size() == n(), ExcDimensionMismatch(src.size(), n())); |
| 1238 |
|
| 1239 |
DEAL_II_NOT_IMPLEMENTED(); |
| 1240 |
} |
| 1241 |
|
| 1242 |
|
| 1243 |
template <typename number> |
| 1244 |
template <typename somenumber> |
| 1245 |
void |
| 1246 |
ChunkSparseMatrix<number>::precondition_SOR(Vector<somenumber> &dst, |
| 1247 |
const Vector<somenumber> &src, |
| 1248 |
const number om) const |
| 1249 |
{ |
| 1250 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 1251 |
Assert(val != nullptr, ExcNotInitialized()); |
| 1252 |
Assert(m() == n(), |
| 1253 |
ExcMessage("This operation is only valid on square matrices.")); |
| 1254 |
|
| 1255 |
|
| 1256 |
dst = src; |
| 1257 |
SOR(dst, om); |
| 1258 |
} |
| 1259 |
|
| 1260 |
|
| 1261 |
template <typename number> |
| 1262 |
template <typename somenumber> |
| 1263 |
void |
| 1264 |
ChunkSparseMatrix<number>::precondition_TSOR(Vector<somenumber> &dst, |
| 1265 |
const Vector<somenumber> &src, |
| 1266 |
const number om) const |
| 1267 |
{ |
| 1268 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 1269 |
Assert(val != nullptr, ExcNotInitialized()); |
| 1270 |
Assert(m() == n(), |
| 1271 |
ExcMessage("This operation is only valid on square matrices.")); |
| 1272 |
|
| 1273 |
|
| 1274 |
dst = src; |
| 1275 |
TSOR(dst, om); |
| 1276 |
} |
| 1277 |
|
| 1278 |
|
| 1279 |
template <typename number> |
| 1280 |
template <typename somenumber> |
| 1281 |
void |
| 1282 |
ChunkSparseMatrix<number>::SOR(Vector<somenumber> &dst, |
| 1283 |
const number /*om*/) const |
| 1284 |
{ |
| 1285 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 1286 |
Assert(val != nullptr, ExcNotInitialized()); |
| 1287 |
Assert(m() == n(), |
| 1288 |
ExcMessage("This operation is only valid on square matrices.")); |
| 1289 |
Assert(m() == dst.size(), ExcDimensionMismatch(m(), dst.size())); |
| 1290 |
|
| 1291 |
DEAL_II_NOT_IMPLEMENTED(); |
| 1292 |
} |
| 1293 |
|
| 1294 |
|
| 1295 |
template <typename number> |
| 1296 |
template <typename somenumber> |
| 1297 |
void |
| 1298 |
ChunkSparseMatrix<number>::TSOR(Vector<somenumber> &dst, |
| 1299 |
const number /*om*/) const |
| 1300 |
{ |
| 1301 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 1302 |
Assert(val != nullptr, ExcNotInitialized()); |
| 1303 |
Assert(m() == n(), |
| 1304 |
ExcMessage("This operation is only valid on square matrices.")); |
| 1305 |
Assert(m() == dst.size(), ExcDimensionMismatch(m(), dst.size())); |
| 1306 |
|
| 1307 |
DEAL_II_NOT_IMPLEMENTED(); |
| 1308 |
} |
| 1309 |
|
| 1310 |
|
| 1311 |
template <typename number> |
| 1312 |
template <typename somenumber> |
| 1313 |
void |
| 1314 |
ChunkSparseMatrix<number>::PSOR( |
| 1315 |
Vector<somenumber> &dst, |
| 1316 |
const std::vector<size_type> &permutation, |
| 1317 |
const std::vector<size_type> &inverse_permutation, |
| 1318 |
const number /*om*/) const |
| 1319 |
{ |
| 1320 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 1321 |
Assert(val != nullptr, ExcNotInitialized()); |
| 1322 |
Assert(m() == n(), |
| 1323 |
ExcMessage("This operation is only valid on square matrices.")); |
| 1324 |
|
| 1325 |
Assert(m() == dst.size(), ExcDimensionMismatch(m(), dst.size())); |
| 1326 |
Assert(m() == permutation.size(), |
| 1327 |
ExcDimensionMismatch(m(), permutation.size())); |
| 1328 |
Assert(m() == inverse_permutation.size(), |
| 1329 |
ExcDimensionMismatch(m(), inverse_permutation.size())); |
| 1330 |
|
| 1331 |
DEAL_II_NOT_IMPLEMENTED(); |
| 1332 |
} |
| 1333 |
|
| 1334 |
|
| 1335 |
template <typename number> |
| 1336 |
template <typename somenumber> |
| 1337 |
void |
| 1338 |
ChunkSparseMatrix<number>::TPSOR( |
| 1339 |
Vector<somenumber> &dst, |
| 1340 |
const std::vector<size_type> &permutation, |
| 1341 |
const std::vector<size_type> &inverse_permutation, |
| 1342 |
const number /*om*/) const |
| 1343 |
{ |
| 1344 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 1345 |
Assert(val != nullptr, ExcNotInitialized()); |
| 1346 |
Assert(m() == n(), |
| 1347 |
ExcMessage("This operation is only valid on square matrices.")); |
| 1348 |
|
| 1349 |
Assert(m() == dst.size(), ExcDimensionMismatch(m(), dst.size())); |
| 1350 |
Assert(m() == permutation.size(), |
| 1351 |
ExcDimensionMismatch(m(), permutation.size())); |
| 1352 |
Assert(m() == inverse_permutation.size(), |
| 1353 |
ExcDimensionMismatch(m(), inverse_permutation.size())); |
| 1354 |
|
| 1355 |
DEAL_II_NOT_IMPLEMENTED(); |
| 1356 |
} |
| 1357 |
|
| 1358 |
|
| 1359 |
|
| 1360 |
template <typename number> |
| 1361 |
template <typename somenumber> |
| 1362 |
void |
| 1363 |
ChunkSparseMatrix<number>::SOR_step(Vector<somenumber> &v, |
| 1364 |
const Vector<somenumber> &b, |
| 1365 |
const number /*om*/) const |
| 1366 |
{ |
| 1367 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 1368 |
Assert(val != nullptr, ExcNotInitialized()); |
| 1369 |
Assert(m() == n(), |
| 1370 |
ExcMessage("This operation is only valid on square matrices.")); |
| 1371 |
|
| 1372 |
Assert(m() == v.size(), ExcDimensionMismatch(m(), v.size())); |
| 1373 |
Assert(m() == b.size(), ExcDimensionMismatch(m(), b.size())); |
| 1374 |
|
| 1375 |
DEAL_II_NOT_IMPLEMENTED(); |
| 1376 |
} |
| 1377 |
|
| 1378 |
|
| 1379 |
|
| 1380 |
template <typename number> |
| 1381 |
template <typename somenumber> |
| 1382 |
void |
| 1383 |
ChunkSparseMatrix<number>::TSOR_step(Vector<somenumber> &v, |
| 1384 |
const Vector<somenumber> &b, |
| 1385 |
const number /*om*/) const |
| 1386 |
{ |
| 1387 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 1388 |
Assert(val != nullptr, ExcNotInitialized()); |
| 1389 |
Assert(m() == n(), |
| 1390 |
ExcMessage("This operation is only valid on square matrices.")); |
| 1391 |
|
| 1392 |
Assert(m() == v.size(), ExcDimensionMismatch(m(), v.size())); |
| 1393 |
Assert(m() == b.size(), ExcDimensionMismatch(m(), b.size())); |
| 1394 |
|
| 1395 |
DEAL_II_NOT_IMPLEMENTED(); |
| 1396 |
} |
| 1397 |
|
| 1398 |
|
| 1399 |
|
| 1400 |
template <typename number> |
| 1401 |
template <typename somenumber> |
| 1402 |
void |
| 1403 |
ChunkSparseMatrix<number>::SSOR_step(Vector<somenumber> &v, |
| 1404 |
const Vector<somenumber> &b, |
| 1405 |
const number om) const |
| 1406 |
{ |
| 1407 |
SOR_step(v, b, om); |
| 1408 |
TSOR_step(v, b, om); |
| 1409 |
} |
| 1410 |
|
| 1411 |
|
| 1412 |
|
| 1413 |
template <typename number> |
| 1414 |
template <typename somenumber> |
| 1415 |
void |
| 1416 |
ChunkSparseMatrix<number>::SSOR(Vector<somenumber> &dst, |
| 1417 |
const number /*om*/) const |
| 1418 |
{ |
| 1419 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 1420 |
Assert(val != nullptr, ExcNotInitialized()); |
| 1421 |
Assert(m() == n(), |
| 1422 |
ExcMessage("This operation is only valid on square matrices.")); |
| 1423 |
|
| 1424 |
Assert(m() == dst.size(), ExcDimensionMismatch(m(), dst.size())); |
| 1425 |
|
| 1426 |
DEAL_II_NOT_IMPLEMENTED(); |
| 1427 |
} |
| 1428 |
|
| 1429 |
|
| 1430 |
|
| 1431 |
template <typename number> |
| 1432 |
void |
| 1433 |
ChunkSparseMatrix<number>::print(std::ostream &out) const |
| 1434 |
{ |
| 1435 |
AssertThrow(out.fail() == false, ExcIO()); |
| 1436 |
|
| 1437 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 1438 |
Assert(val != nullptr, ExcNotInitialized()); |
| 1439 |
|
| 1440 |
DEAL_II_NOT_IMPLEMENTED(); |
| 1441 |
|
| 1442 |
AssertThrow(out.fail() == false, ExcIO()); |
| 1443 |
} |
| 1444 |
|
| 1445 |
|
| 1446 |
template <typename number> |
| 1447 |
void |
| 1448 |
ChunkSparseMatrix<number>::print_formatted(std::ostream &out, |
| 1449 |
const unsigned int precision, |
| 1450 |
const bool scientific, |
| 1451 |
const unsigned int width_, |
| 1452 |
const char *zero_string, |
| 1453 |
const double denominator, |
| 1454 |
const char *separator) const |
| 1455 |
{ |
| 1456 |
AssertThrow(out.fail() == false, ExcIO()); |
| 1457 |
|
| 1458 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 1459 |
Assert(val != nullptr, ExcNotInitialized()); |
| 1460 |
|
| 1461 |
unsigned int width = width_; |
| 1462 |
|
| 1463 |
DEAL_II_NOT_IMPLEMENTED(); |
| 1464 |
|
| 1465 |
std::ios::fmtflags old_flags = out.flags(); |
| 1466 |
unsigned int old_precision = out.precision(precision); |
| 1467 |
|
| 1468 |
if (scientific) |
| 1469 |
{ |
| 1470 |
out.setf(std::ios::scientific, std::ios::floatfield); |
| 1471 |
if (width == 0u) |
| 1472 |
width = precision + 7; |
| 1473 |
} |
| 1474 |
else |
| 1475 |
{ |
| 1476 |
out.setf(std::ios::fixed, std::ios::floatfield); |
| 1477 |
if (width == 0u) |
| 1478 |
width = precision + 2; |
| 1479 |
} |
| 1480 |
|
| 1481 |
for (size_type i = 0; i < m(); ++i) |
| 1482 |
{ |
| 1483 |
for (size_type j = 0; j < n(); ++j) |
| 1484 |
if (cols->sparsity_pattern(i, j) != SparsityPattern::invalid_entry) |
| 1485 |
out << std::setw(width) |
| 1486 |
<< val[cols->sparsity_pattern(i, j)] * denominator << separator; |
| 1487 |
else |
| 1488 |
out << std::setw(width) << zero_string << separator; |
| 1489 |
out << std::endl; |
| 1490 |
}; |
| 1491 |
AssertThrow(out.fail() == false, ExcIO()); |
| 1492 |
|
| 1493 |
// reset output format |
| 1494 |
out.precision(old_precision); |
| 1495 |
out.flags(old_flags); |
| 1496 |
} |
| 1497 |
|
| 1498 |
|
| 1499 |
|
| 1500 |
template <typename number> |
| 1501 |
void |
| 1502 |
ChunkSparseMatrix<number>::print_pattern(std::ostream &out, |
| 1503 |
const double threshold) const |
| 1504 |
{ |
| 1505 |
AssertThrow(out.fail() == false, ExcIO()); |
| 1506 |
|
| 1507 |
Assert(cols != nullptr, ExcNeedsSparsityPattern()); |
| 1508 |
Assert(val != nullptr, ExcNotInitialized()); |
| 1509 |
|
| 1510 |
const size_type chunk_size = cols->get_chunk_size(); |
| 1511 |
|
| 1512 |
// loop over all chunk rows and columns, and each time we find something |
| 1513 |
// repeat it chunk_size times in both directions |
| 1514 |
for (size_type i = 0; i < cols->sparsity_pattern.n_rows(); ++i) |
| 1515 |
{ |
| 1516 |
for (size_type d = 0; d < chunk_size; ++d) |
| 1517 |
for (size_type j = 0; j < cols->sparsity_pattern.n_cols(); ++j) |
| 1518 |
if (cols->sparsity_pattern(i, j) == SparsityPattern::invalid_entry) |
| 1519 |
{ |
| 1520 |
for (size_type e = 0; e < chunk_size; ++e) |
| 1521 |
out << '.'; |
| 1522 |
} |
| 1523 |
else if (std::fabs(val[cols->sparsity_pattern(i, j)]) > threshold) |
| 1524 |
{ |
| 1525 |
for (size_type e = 0; e < chunk_size; ++e) |
| 1526 |
out << '*'; |
| 1527 |
} |
| 1528 |
else |
| 1529 |
{ |
| 1530 |
for (size_type e = 0; e < chunk_size; ++e) |
| 1531 |
out << ':'; |
| 1532 |
} |
| 1533 |
out << std::endl; |
| 1534 |
} |
| 1535 |
|
| 1536 |
AssertThrow(out.fail() == false, ExcIO()); |
| 1537 |
} |
| 1538 |
|
| 1539 |
|
| 1540 |
|
| 1541 |
template <typename number> |
| 1542 |
void |
| 1543 |
ChunkSparseMatrix<number>::block_write(std::ostream &out) const |
| 1544 |
{ |
| 1545 |
AssertThrow(out.fail() == false, ExcIO()); |
| 1546 |
|
| 1547 |
// first the simple objects, bracketed in [...] |
| 1548 |
out << '[' << max_len << "]["; |
| 1549 |
// then write out real data |
| 1550 |
out.write(reinterpret_cast<const char *>(val.get()), |
| 1551 |
reinterpret_cast<const char *>(val.get() + max_len) - |
| 1552 |
reinterpret_cast<const char *>(val.get())); |
| 1553 |
out << ']'; |
| 1554 |
|
| 1555 |
AssertThrow(out.fail() == false, ExcIO()); |
| 1556 |
} |
| 1557 |
|
| 1558 |
|
| 1559 |
|
| 1560 |
template <typename number> |
| 1561 |
void |
| 1562 |
ChunkSparseMatrix<number>::block_read(std::istream &in) |
| 1563 |
{ |
| 1564 |
AssertThrow(in.fail() == false, ExcIO()); |
| 1565 |
|
| 1566 |
char c; |
| 1567 |
|
| 1568 |
// first read in simple data |
| 1569 |
in >> c; |
| 1570 |
AssertThrow(c == '[', ExcIO()); |
| 1571 |
in >> max_len; |
| 1572 |
|
| 1573 |
in >> c; |
| 1574 |
AssertThrow(c == ']', ExcIO()); |
| 1575 |
in >> c; |
| 1576 |
AssertThrow(c == '[', ExcIO()); |
| 1577 |
|
| 1578 |
// reallocate space |
| 1579 |
val = std::make_unique<number[]>(max_len); |
| 1580 |
|
| 1581 |
// then read data |
| 1582 |
in.read(reinterpret_cast<char *>(val.get()), |
| 1583 |
reinterpret_cast<char *>(val.get() + max_len) - |
| 1584 |
reinterpret_cast<char *>(val.get())); |
| 1585 |
in >> c; |
| 1586 |
AssertThrow(c == ']', ExcIO()); |
| 1587 |
} |
| 1588 |
|
| 1589 |
|
| 1590 |
|
| 1591 |
template <typename number> |
| 1592 |
std::size_t |
| 1593 |
ChunkSparseMatrix<number>::memory_consumption() const |
| 1594 |
{ |
| 1595 |
return sizeof(*this) + max_len * sizeof(number); |
| 1596 |
} |
| 1597 |
|
| 1598 |
|
| 1599 |
DEAL_II_NAMESPACE_CLOSE |
| 1600 |
|
| 1601 |
#endif |