| 1 |
// ------------------------------------------------------------------------ |
| 2 |
// |
| 3 |
// SPDX-License-Identifier: LGPL-2.1-or-later |
| 4 |
// Copyright (C) 1999 - 2024 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_sparse_vanka_templates_h |
| 16 |
#define dealii_sparse_vanka_templates_h |
| 17 |
|
| 18 |
|
| 19 |
#include <deal.II/base/config.h> |
| 20 |
|
| 21 |
#include <deal.II/base/memory_consumption.h> |
| 22 |
#include <deal.II/base/thread_management.h> |
| 23 |
|
| 24 |
#include <deal.II/lac/full_matrix.h> |
| 25 |
#include <deal.II/lac/sparse_matrix.h> |
| 26 |
#include <deal.II/lac/sparse_vanka.h> |
| 27 |
#include <deal.II/lac/vector.h> |
| 28 |
|
| 29 |
#include <algorithm> |
| 30 |
#include <map> |
| 31 |
|
| 32 |
DEAL_II_NAMESPACE_OPEN |
| 33 |
|
| 34 |
template <typename number> |
| 35 |
SparseVanka<number>::SparseVanka() |
| 36 |
: matrix() |
| 37 |
, selected() |
| 38 |
, inverses() |
| 39 |
, _m(0) |
| 40 |
, _n(0) |
| 41 |
{} |
| 42 |
|
| 43 |
template <typename number> |
| 44 |
SparseVanka<number>::SparseVanka(const SparseMatrix<number> &M, |
| 45 |
const std::vector<bool> &selected_dofs) |
| 46 |
: matrix(&M, typeid(*this).name()) |
| 47 |
, selected(&selected_dofs) |
| 48 |
, inverses(M.m(), nullptr) |
| 49 |
, _m(M.m()) |
| 50 |
, _n(M.n()) |
| 51 |
{ |
| 52 |
Assert(M.m() == M.n(), ExcNotQuadratic()); |
| 53 |
Assert(M.m() == selected->size(), |
| 54 |
ExcDimensionMismatch(M.m(), selected->size())); |
| 55 |
|
| 56 |
compute_inverses(); |
| 57 |
} |
| 58 |
|
| 59 |
|
| 60 |
template <typename number> |
| 61 |
SparseVanka<number>::~SparseVanka() |
| 62 |
{ |
| 63 |
typename std::vector< |
| 64 |
ObserverPointer<FullMatrix<float>, SparseVanka<number>>>::iterator i; |
| 65 |
for (i = inverses.begin(); i != inverses.end(); ++i) |
| 66 |
{ |
| 67 |
FullMatrix<float> *p = *i; |
| 68 |
*i = nullptr; |
| 69 |
if (p != nullptr) |
| 70 |
delete p; |
| 71 |
} |
| 72 |
} |
| 73 |
|
| 74 |
|
| 75 |
template <typename number> |
| 76 |
void |
| 77 |
SparseVanka<number>::initialize(const SparseMatrix<number> &M, |
| 78 |
const AdditionalData &additional_data) |
| 79 |
{ |
| 80 |
matrix = &M; |
| 81 |
selected = &(additional_data.selected); |
| 82 |
inverses.resize(M.m()); |
| 83 |
_m = M.m(); |
| 84 |
_n = M.n(); |
| 85 |
|
| 86 |
Assert(M.m() == M.n(), ExcNotQuadratic()); |
| 87 |
Assert(M.m() == selected->size(), |
| 88 |
ExcDimensionMismatch(M.m(), selected->size())); |
| 89 |
|
| 90 |
compute_inverses(); |
| 91 |
} |
| 92 |
|
| 93 |
template <typename number> |
| 94 |
void |
| 95 |
SparseVanka<number>::compute_inverses() |
| 96 |
{ |
| 97 |
Assert(matrix != nullptr, ExcNotInitialized()); |
| 98 |
Assert(selected != nullptr, ExcNotInitialized()); |
| 99 |
|
| 100 |
const size_type n_inverses = |
| 101 |
std::count(selected->begin(), selected->end(), true); |
| 102 |
// somewhat arbitrarily set up an equal number of tasks as we have threads |
| 103 |
const std::size_t n_tasks = MultithreadInfo::n_threads(); |
| 104 |
const size_type n_inverses_per_task = |
| 105 |
std::max(static_cast<size_type>(n_inverses / n_tasks), |
| 106 |
static_cast<size_type>(1U)); |
| 107 |
|
| 108 |
// set up start and end index |
| 109 |
// for each of the |
| 110 |
// tasks. note that we have |
| 111 |
// to work somewhat to get this |
| 112 |
// appropriate, since the |
| 113 |
// indices for which inverses |
| 114 |
// have to be computed may not |
| 115 |
// be evenly distributed in the |
| 116 |
// vector. as an extreme |
| 117 |
// example consider numbering |
| 118 |
// of DoFs by component, then |
| 119 |
// all indices for which we |
| 120 |
// have to do work will be |
| 121 |
// consecutive, with other |
| 122 |
// consecutive regions where we |
| 123 |
// do not have to do something |
| 124 |
std::vector<std::pair<size_type, unsigned int>> blocking(n_tasks); |
| 125 |
|
| 126 |
unsigned int c = 0; |
| 127 |
unsigned int task_n = 0; |
| 128 |
blocking[0].first = 0; |
| 129 |
|
| 130 |
for (size_type i = 0; (i < matrix->m()) && (task_n + 1 < n_tasks); ++i) |
| 131 |
{ |
| 132 |
if ((*selected)[i] == true) |
| 133 |
++c; |
| 134 |
if (c == n_inverses_per_task) |
| 135 |
{ |
| 136 |
blocking[task_n].second = i; |
| 137 |
blocking[task_n + 1].first = i; |
| 138 |
++task_n; |
| 139 |
|
| 140 |
c = 0; |
| 141 |
} |
| 142 |
} |
| 143 |
blocking[n_tasks - 1].second = matrix->m(); |
| 144 |
|
| 145 |
// Now spawn the tasks |
| 146 |
Threads::TaskGroup<> tasks; |
| 147 |
for (unsigned int i = 0; i < n_tasks; ++i) |
| 148 |
tasks += Threads::new_task([&, i]() { |
| 149 |
this->compute_inverses(blocking[i].first, blocking[i].second); |
| 150 |
}); |
| 151 |
tasks.join_all(); |
| 152 |
} |
| 153 |
|
| 154 |
|
| 155 |
template <typename number> |
| 156 |
void |
| 157 |
SparseVanka<number>::compute_inverses(const size_type begin, |
| 158 |
const size_type end) |
| 159 |
{ |
| 160 |
// set-up the vector that will be used |
| 161 |
// by the functions which we call |
| 162 |
// below. |
| 163 |
std::vector<size_type> local_indices; |
| 164 |
|
| 165 |
// traverse all rows of the matrix |
| 166 |
// which are selected |
| 167 |
for (size_type row = begin; row < end; ++row) |
| 168 |
if ((*selected)[row] == true) |
| 169 |
compute_inverse(row, local_indices); |
| 170 |
} |
| 171 |
|
| 172 |
|
| 173 |
|
| 174 |
template <typename number> |
| 175 |
void |
| 176 |
SparseVanka<number>::compute_inverse(const size_type row, |
| 177 |
std::vector<size_type> &local_indices) |
| 178 |
{ |
| 179 |
Assert(matrix != nullptr, ExcNotInitialized()); |
| 180 |
Assert(selected != nullptr, ExcNotInitialized()); |
| 181 |
|
| 182 |
// first define an alias to the sparsity |
| 183 |
// pattern of the matrix, since this |
| 184 |
// will be used quite often |
| 185 |
const SparsityPattern &structure = matrix->get_sparsity_pattern(); |
| 186 |
|
| 187 |
const size_type row_length = structure.row_length(row); |
| 188 |
|
| 189 |
inverses[row] = new FullMatrix<float>(row_length, row_length); |
| 190 |
|
| 191 |
// collect the dofs that couple |
| 192 |
// with @p row |
| 193 |
local_indices.resize(row_length); |
| 194 |
for (size_type i = 0; i < row_length; ++i) |
| 195 |
local_indices[i] = structure.column_number(row, i); |
| 196 |
|
| 197 |
// Build local matrix |
| 198 |
inverses[row]->extract_submatrix_from(*matrix, local_indices, local_indices); |
| 199 |
|
| 200 |
// Compute inverse |
| 201 |
inverses[row]->gauss_jordan(); |
| 202 |
} |
| 203 |
|
| 204 |
|
| 205 |
template <typename number> |
| 206 |
template <typename number2> |
| 207 |
void |
| 208 |
SparseVanka<number>::vmult(Vector<number2> &dst, |
| 209 |
const Vector<number2> &src) const |
| 210 |
{ |
| 211 |
Assert(matrix != nullptr, ExcNotInitialized()); |
| 212 |
Assert(selected != nullptr, ExcNotInitialized()); |
| 213 |
|
| 214 |
// first set output vector to zero |
| 215 |
dst = 0; |
| 216 |
// then pass on to the function |
| 217 |
// that actually does the work |
| 218 |
apply_preconditioner(dst, src, false); |
| 219 |
} |
| 220 |
|
| 221 |
template <typename number> |
| 222 |
template <typename number2> |
| 223 |
void |
| 224 |
SparseVanka<number>::Tvmult(Vector<number2> &dst, |
| 225 |
const Vector<number2> &src) const |
| 226 |
{ |
| 227 |
Assert(matrix != nullptr, ExcNotInitialized()); |
| 228 |
Assert(selected != nullptr, ExcNotInitialized()); |
| 229 |
|
| 230 |
// first set output vector to zero |
| 231 |
dst = 0; |
| 232 |
// then pass on to the function |
| 233 |
// that actually does the work |
| 234 |
apply_preconditioner(dst, src, true); |
| 235 |
} |
| 236 |
|
| 237 |
|
| 238 |
template <typename number> |
| 239 |
void |
| 240 |
SparseVanka<number>::clear() |
| 241 |
{ // Clear the inverses vector and deallocate memory |
| 242 |
inverses.clear(); |
| 243 |
|
| 244 |
// Reset the matrix pointer |
| 245 |
matrix = nullptr; |
| 246 |
|
| 247 |
// Reset the selected pointer |
| 248 |
selected = nullptr; |
| 249 |
|
| 250 |
// Reset the sizes |
| 251 |
_m = 0; |
| 252 |
_n = 0; |
| 253 |
} |
| 254 |
|
| 255 |
template <typename number> |
| 256 |
template <typename number2> |
| 257 |
void |
| 258 |
SparseVanka<number>::apply_preconditioner( |
| 259 |
Vector<number2> &dst, |
| 260 |
const Vector<number2> &src, |
| 261 |
const bool transpose, |
| 262 |
const std::vector<bool> *const dof_mask) const |
| 263 |
{ |
| 264 |
Assert(dst.size() == src.size(), |
| 265 |
ExcDimensionMismatch(dst.size(), src.size())); |
| 266 |
Assert(dst.size() == matrix->m(), |
| 267 |
ExcDimensionMismatch(dst.size(), src.size())); |
| 268 |
|
| 269 |
// first define an alias to the sparsity |
| 270 |
// pattern of the matrix, since this |
| 271 |
// will be used quite often |
| 272 |
const SparsityPattern &structure = matrix->get_sparsity_pattern(); |
| 273 |
|
| 274 |
|
| 275 |
// store whether we shall work on |
| 276 |
// the whole matrix, or only on |
| 277 |
// blocks. this variable is used to |
| 278 |
// optimize access to vectors a |
| 279 |
// little bit. |
| 280 |
const bool range_is_restricted = (dof_mask != nullptr); |
| 281 |
|
| 282 |
// space to be used for local |
| 283 |
// systems. allocate as much memory |
| 284 |
// as is the maximum. this |
| 285 |
// eliminates the need to |
| 286 |
// re-allocate memory inside the |
| 287 |
// loop. |
| 288 |
FullMatrix<float> local_matrix(structure.max_entries_per_row(), |
| 289 |
structure.max_entries_per_row()); |
| 290 |
Vector<float> b(structure.max_entries_per_row()); |
| 291 |
Vector<float> x(structure.max_entries_per_row()); |
| 292 |
|
| 293 |
std::map<size_type, size_type> local_index; |
| 294 |
|
| 295 |
// traverse all rows of the matrix |
| 296 |
// which are selected |
| 297 |
const size_type n = matrix->m(); |
| 298 |
for (size_type row = 0; row < n; ++row) |
| 299 |
if (((*selected)[row] == true) && |
| 300 |
((range_is_restricted == false) || ((*dof_mask)[row] == true))) |
| 301 |
{ |
| 302 |
const size_type row_length = structure.row_length(row); |
| 303 |
|
| 304 |
b.reinit(row_length); |
| 305 |
x.reinit(row_length); |
| 306 |
// mapping between: |
| 307 |
// 1 column number of all |
| 308 |
// entries in this row, and |
| 309 |
// 2 the position within this |
| 310 |
// row (as stored in the |
| 311 |
// SparsityPattern object |
| 312 |
// |
| 313 |
// since we do not explicitly |
| 314 |
// consider nonsymmetric sparsity |
| 315 |
// patterns, the first element |
| 316 |
// of each entry simply denotes |
| 317 |
// all degrees of freedom that |
| 318 |
// couple with @p row. |
| 319 |
local_index.clear(); |
| 320 |
for (size_type i = 0; i < row_length; ++i) |
| 321 |
local_index.insert( |
| 322 |
std::pair<size_type, size_type>(structure.column_number(row, i), |
| 323 |
i)); |
| 324 |
|
| 325 |
// Build local matrix and rhs |
| 326 |
for (std::map<size_type, size_type>::const_iterator is = |
| 327 |
local_index.begin(); |
| 328 |
is != local_index.end(); |
| 329 |
++is) |
| 330 |
{ |
| 331 |
// irow loops over all DoFs that |
| 332 |
// couple with the present DoF |
| 333 |
const size_type irow = is->first; |
| 334 |
// index of DoF irow in the matrix |
| 335 |
// row corresponding to DoF @p row. |
| 336 |
// runs between 0 and row_length |
| 337 |
const size_type i = is->second; |
| 338 |
|
| 339 |
// copy rhs |
| 340 |
b(i) = src(irow); |
| 341 |
|
| 342 |
// for all the DoFs that irow |
| 343 |
// couples with |
| 344 |
// number of DoFs coupling to |
| 345 |
// irow (including irow itself) |
| 346 |
for (typename SparseMatrix<number>::const_iterator p = |
| 347 |
matrix->begin(irow); |
| 348 |
p != matrix->end(irow); |
| 349 |
++p) |
| 350 |
{ |
| 351 |
// find out whether this DoF |
| 352 |
// (that couples with @p irow, |
| 353 |
// which itself couples with |
| 354 |
// @p row) also couples with |
| 355 |
// @p row. |
| 356 |
const std::map<size_type, size_type>::const_iterator js = |
| 357 |
local_index.find(p->column()); |
| 358 |
// if not, then still use |
| 359 |
// this dof to modify the rhs |
| 360 |
// |
| 361 |
// note that if so, we already |
| 362 |
// have copied the entry above |
| 363 |
if (js == local_index.end()) |
| 364 |
{ |
| 365 |
if (!range_is_restricted || |
| 366 |
((*dof_mask)[p->column()] == true)) |
| 367 |
b(i) -= p->value() * dst(p->column()); |
| 368 |
} |
| 369 |
} |
| 370 |
} |
| 371 |
|
| 372 |
// apply preconditioner |
| 373 |
if (transpose) |
| 374 |
inverses[row]->Tvmult(x, b); |
| 375 |
else |
| 376 |
inverses[row]->vmult(x, b); |
| 377 |
|
| 378 |
// Distribute new values |
| 379 |
for (std::map<size_type, size_type>::const_iterator is = |
| 380 |
local_index.begin(); |
| 381 |
is != local_index.end(); |
| 382 |
++is) |
| 383 |
{ |
| 384 |
const size_type irow = is->first; |
| 385 |
const size_type i = is->second; |
| 386 |
|
| 387 |
if (!range_is_restricted || ((*dof_mask)[irow] == true)) |
| 388 |
dst(irow) = x(i); |
| 389 |
// do nothing if not in |
| 390 |
// the range |
| 391 |
} |
| 392 |
} |
| 393 |
} |
| 394 |
|
| 395 |
|
| 396 |
|
| 397 |
template <typename number> |
| 398 |
std::size_t |
| 399 |
SparseVanka<number>::memory_consumption() const |
| 400 |
{ |
| 401 |
std::size_t mem = |
| 402 |
(sizeof(*this) + MemoryConsumption::memory_consumption(*selected)); |
| 403 |
for (size_type i = 0; i < inverses.size(); ++i) |
| 404 |
mem += MemoryConsumption::memory_consumption(*inverses[i]); |
| 405 |
|
| 406 |
return mem; |
| 407 |
} |
| 408 |
|
| 409 |
|
| 410 |
|
| 411 |
template <typename number> |
| 412 |
SparseVanka<number>::AdditionalData::AdditionalData( |
| 413 |
const std::vector<bool> &selected) |
| 414 |
: selected(selected) |
| 415 |
{} |
| 416 |
|
| 417 |
|
| 418 |
//--------------------------------------------------------------------------- |
| 419 |
|
| 420 |
|
| 421 |
template <typename number> |
| 422 |
SparseBlockVanka<number>::SparseBlockVanka( |
| 423 |
const SparseMatrix<number> &M, |
| 424 |
const std::vector<bool> &selected, |
| 425 |
const unsigned int n_blocks, |
| 426 |
const BlockingStrategy blocking_strategy) |
| 427 |
: SparseVanka<number>(M, selected) |
| 428 |
, n_blocks(n_blocks) |
| 429 |
, dof_masks(n_blocks, std::vector<bool>(M.m(), false)) |
| 430 |
{ |
| 431 |
compute_dof_masks(M, selected, blocking_strategy); |
| 432 |
} |
| 433 |
|
| 434 |
|
| 435 |
template <typename number> |
| 436 |
void |
| 437 |
SparseBlockVanka<number>::compute_dof_masks( |
| 438 |
const SparseMatrix<number> &M, |
| 439 |
const std::vector<bool> &selected, |
| 440 |
const BlockingStrategy blocking_strategy) |
| 441 |
{ |
| 442 |
Assert(n_blocks > 0, ExcInternalError()); |
| 443 |
|
| 444 |
const size_type n_inverses = |
| 445 |
std::count(selected.begin(), selected.end(), true); |
| 446 |
|
| 447 |
const size_type n_inverses_per_block = |
| 448 |
std::max(n_inverses / n_blocks, static_cast<size_type>(1U)); |
| 449 |
|
| 450 |
// precompute the splitting points |
| 451 |
std::vector<std::pair<size_type, size_type>> intervals(n_blocks); |
| 452 |
|
| 453 |
// set up start and end index for |
| 454 |
// each of the blocks. note that |
| 455 |
// we have to work somewhat to get |
| 456 |
// this appropriate, since the |
| 457 |
// indices for which inverses have |
| 458 |
// to be computed may not be evenly |
| 459 |
// distributed in the vector. as an |
| 460 |
// extreme example consider |
| 461 |
// numbering of DoFs by component, |
| 462 |
// then all indices for which we |
| 463 |
// have to do work will be |
| 464 |
// consecutive, with other |
| 465 |
// consecutive regions where we do |
| 466 |
// not have to do something |
| 467 |
{ |
| 468 |
unsigned int c = 0; |
| 469 |
unsigned int block = 0; |
| 470 |
intervals[0].first = 0; |
| 471 |
|
| 472 |
for (size_type i = 0; (i < M.m()) && (block + 1 < n_blocks); ++i) |
| 473 |
{ |
| 474 |
if (selected[i] == true) |
| 475 |
++c; |
| 476 |
if (c == n_inverses_per_block) |
| 477 |
{ |
| 478 |
intervals[block].second = i; |
| 479 |
intervals[block + 1].first = i; |
| 480 |
++block; |
| 481 |
|
| 482 |
c = 0; |
| 483 |
} |
| 484 |
} |
| 485 |
intervals[n_blocks - 1].second = M.m(); |
| 486 |
} |
| 487 |
|
| 488 |
// now transfer the knowledge on |
| 489 |
// the splitting points into the |
| 490 |
// vector<bool>s that the base |
| 491 |
// class wants to see. the way how |
| 492 |
// we do this depends on the |
| 493 |
// requested blocking strategy |
| 494 |
switch (blocking_strategy) |
| 495 |
{ |
| 496 |
case index_intervals: |
| 497 |
{ |
| 498 |
for (unsigned int block = 0; block < n_blocks; ++block) |
| 499 |
std::fill_n(dof_masks[block].begin() + intervals[block].first, |
| 500 |
intervals[block].second - intervals[block].first, |
| 501 |
true); |
| 502 |
break; |
| 503 |
} |
| 504 |
|
| 505 |
case adaptive: |
| 506 |
{ |
| 507 |
// the splitting points for |
| 508 |
// the DoF have been computed |
| 509 |
// above already, but we will |
| 510 |
// only use them to split the |
| 511 |
// Lagrange dofs into |
| 512 |
// blocks. splitting the |
| 513 |
// remaining dofs will be |
| 514 |
// done now. |
| 515 |
|
| 516 |
// first count how often the |
| 517 |
// Lagrange dofs of each |
| 518 |
// block access the different |
| 519 |
// dofs |
| 520 |
Table<2, size_type> access_count(n_blocks, M.m()); |
| 521 |
|
| 522 |
// set-up the map that will |
| 523 |
// be used to store the |
| 524 |
// indices each Lagrange dof |
| 525 |
// accesses |
| 526 |
const SparsityPattern &structure = M.get_sparsity_pattern(); |
| 527 |
|
| 528 |
for (size_type row = 0; row < M.m(); ++row) |
| 529 |
if (selected[row] == true) |
| 530 |
{ |
| 531 |
// first find out to |
| 532 |
// which block the |
| 533 |
// present row belongs |
| 534 |
unsigned int block_number = 0; |
| 535 |
while (row >= intervals[block_number].second) |
| 536 |
++block_number; |
| 537 |
Assert(block_number < n_blocks, ExcInternalError()); |
| 538 |
|
| 539 |
// now traverse the |
| 540 |
// matrix structure to |
| 541 |
// find out to which |
| 542 |
// dofs number the |
| 543 |
// present index wants |
| 544 |
// to write |
| 545 |
const size_type row_length = structure.row_length(row); |
| 546 |
for (size_type i = 0; i < row_length; ++i) |
| 547 |
++access_count[block_number][structure.column_number(row, i)]; |
| 548 |
} |
| 549 |
|
| 550 |
// now we know that block @p i |
| 551 |
// wants to write to DoF @p j |
| 552 |
// as often as |
| 553 |
// <tt>access_count[i][j]</tt> |
| 554 |
// times. Let @p j be allotted |
| 555 |
// to the block which |
| 556 |
// accesses it most often. |
| 557 |
// |
| 558 |
// if it is a Lagrange dof, |
| 559 |
// the of course we leave it |
| 560 |
// to the block we put it |
| 561 |
// into in the first place |
| 562 |
for (size_type row = 0; row < M.m(); ++row) |
| 563 |
if (selected[row] == true) |
| 564 |
{ |
| 565 |
unsigned int block_number = 0; |
| 566 |
while (row >= intervals[block_number].second) |
| 567 |
++block_number; |
| 568 |
|
| 569 |
dof_masks[block_number][row] = true; |
| 570 |
} |
| 571 |
else |
| 572 |
{ |
| 573 |
// find out which block |
| 574 |
// accesses this dof |
| 575 |
// the most often |
| 576 |
size_type max_accesses = 0; |
| 577 |
unsigned int max_access_block = 0; |
| 578 |
for (unsigned int block = 0; block < n_blocks; ++block) |
| 579 |
if (access_count[block][row] > max_accesses) |
| 580 |
{ |
| 581 |
max_accesses = access_count[block][row]; |
| 582 |
max_access_block = block; |
| 583 |
} |
| 584 |
dof_masks[max_access_block][row] = true; |
| 585 |
} |
| 586 |
|
| 587 |
break; |
| 588 |
} |
| 589 |
|
| 590 |
default: |
| 591 |
DEAL_II_ASSERT_UNREACHABLE(); |
| 592 |
} |
| 593 |
} |
| 594 |
|
| 595 |
|
| 596 |
|
| 597 |
template <typename number> |
| 598 |
template <typename number2> |
| 599 |
void |
| 600 |
SparseBlockVanka<number>::vmult(Vector<number2> &dst, |
| 601 |
const Vector<number2> &src) const |
| 602 |
{ |
| 603 |
dst = 0; |
| 604 |
|
| 605 |
Threads::TaskGroup<> tasks; |
| 606 |
for (unsigned int block = 0; block < n_blocks; ++block) |
| 607 |
tasks += Threads::new_task([&, block] { |
| 608 |
this->apply_preconditioner(dst, src, false, &dof_masks[block]); |
| 609 |
}); |
| 610 |
tasks.join_all(); |
| 611 |
} |
| 612 |
|
| 613 |
template <typename number> |
| 614 |
template <typename number2> |
| 615 |
void |
| 616 |
SparseBlockVanka<number>::Tvmult(Vector<number2> &dst, |
| 617 |
const Vector<number2> &src) const |
| 618 |
{ |
| 619 |
dst = 0; |
| 620 |
|
| 621 |
Threads::TaskGroup<> tasks; |
| 622 |
for (unsigned int block = 0; block < n_blocks; ++block) |
| 623 |
tasks += Threads::new_task([&, block] { |
| 624 |
this->apply_preconditioner(dst, src, true, &dof_masks[block]); |
| 625 |
}); |
| 626 |
tasks.join_all(); |
| 627 |
} |
| 628 |
|
| 629 |
|
| 630 |
|
| 631 |
template <typename number> |
| 632 |
std::size_t |
| 633 |
SparseBlockVanka<number>::memory_consumption() const |
| 634 |
{ |
| 635 |
return SparseVanka<number>::memory_consumption() + |
| 636 |
MemoryConsumption::memory_consumption(dof_masks); |
| 637 |
} |
| 638 |
|
| 639 |
|
| 640 |
|
| 641 |
DEAL_II_NAMESPACE_CLOSE |
| 642 |
|
| 643 |
#endif |