| 1 |
// ------------------------------------------------------------------------ |
| 2 |
// |
| 3 |
// SPDX-License-Identifier: LGPL-2.1-or-later |
| 4 |
// Copyright (C) 2020 - 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 |
|
| 16 |
#ifndef dealii_matrix_free_tensor_product_point_kernels_h |
| 17 |
#define dealii_matrix_free_tensor_product_point_kernels_h |
| 18 |
|
| 19 |
#include <deal.II/base/config.h> |
| 20 |
|
| 21 |
#include <deal.II/base/ndarray.h> |
| 22 |
#include <deal.II/base/polynomial.h> |
| 23 |
#include <deal.II/base/utilities.h> |
| 24 |
|
| 25 |
#include <deal.II/matrix_free/shape_info.h> |
| 26 |
|
| 27 |
|
| 28 |
DEAL_II_NAMESPACE_OPEN |
| 29 |
|
| 30 |
|
| 31 |
|
| 32 |
namespace internal |
| 33 |
{ |
| 34 |
/** |
| 35 |
* Struct to avoid using Tensor<1, dim, Point<dim2>> in |
| 36 |
* evaluate_tensor_product_value_and_gradient because a Point cannot be used |
| 37 |
* within Tensor. Instead, a specialization of this struct upcasts the point |
| 38 |
* to a Tensor<1,dim>. |
| 39 |
*/ |
| 40 |
template <typename Number, typename Number2> |
| 41 |
struct ProductTypeNoPoint |
| 42 |
{ |
| 43 |
using type = typename ProductType<Number, Number2>::type; |
| 44 |
}; |
| 45 |
|
| 46 |
template <int dim, typename Number, typename Number2> |
| 47 |
struct ProductTypeNoPoint<Point<dim, Number>, Number2> |
| 48 |
{ |
| 49 |
using type = typename ProductType<Tensor<1, dim, Number>, Number2>::type; |
| 50 |
}; |
| 51 |
|
| 52 |
|
| 53 |
|
| 54 |
/** |
| 55 |
* Compute the values and derivatives of the 1d polynomials @p poly at the |
| 56 |
* specified point @p p and store them in @p shapes. |
| 57 |
*/ |
| 58 |
template <int dim, typename Number> |
| 59 |
inline void |
| 60 |
compute_values_of_array( |
| 61 |
dealii::ndarray<Number, 2, dim> *shapes, |
| 62 |
const std::vector<Polynomials::Polynomial<double>> &poly, |
| 63 |
const Point<dim, Number> &p, |
| 64 |
const unsigned int derivative = 1) |
| 65 |
{ |
| 66 |
const int n_shapes = poly.size(); |
| 67 |
|
| 68 |
// Evaluate 1d polynomials and their derivatives |
| 69 |
std::array<Number, dim> point; |
| 70 |
for (unsigned int d = 0; d < dim; ++d) |
| 71 |
point[d] = p[d]; |
| 72 |
for (int i = 0; i < n_shapes; ++i) |
| 73 |
poly[i].values_of_array(point, derivative, shapes[i].data()); |
| 74 |
} |
| 75 |
|
| 76 |
|
| 77 |
|
| 78 |
/** |
| 79 |
* Specialization of above function for dim = 0. Should not be called. |
| 80 |
*/ |
| 81 |
template <typename Number> |
| 82 |
inline void |
| 83 |
compute_values_of_array(dealii::ndarray<Number, 2, 0> *, |
| 84 |
const std::vector<Polynomials::Polynomial<double>> &, |
| 85 |
const Point<0, Number> &, |
| 86 |
const unsigned int) |
| 87 |
{ |
| 88 |
DEAL_II_ASSERT_UNREACHABLE(); |
| 89 |
} |
| 90 |
|
| 91 |
|
| 92 |
|
| 93 |
/** |
| 94 |
* Evaluate the 1d polynomials @p poly at the two specified points @p p0 and |
| 95 |
* @p p1 and store them in @p shapes. This function can be used as a more |
| 96 |
* efficient alternative to the compute_values_of_array() function, because |
| 97 |
* of reduced overhead when querying the polynomials (which usually have |
| 98 |
* loop bounds that are not known at compile time). |
| 99 |
*/ |
| 100 |
template <int dim, typename Number> |
| 101 |
inline void |
| 102 |
compute_values_of_array_in_pairs( |
| 103 |
dealii::ndarray<Number, 2, dim> *shapes, |
| 104 |
const std::vector<Polynomials::Polynomial<double>> &poly, |
| 105 |
const Point<dim, Number> &p0, |
| 106 |
const Point<dim, Number> &p1) |
| 107 |
{ |
| 108 |
// Use 'int' variable here to let the compiler apply additional |
| 109 |
// optimizations, in particular regarding multiplications and additions in |
| 110 |
// loop increments that are known not to overflow/wrap around (as is the |
| 111 |
// case for unsigned int). |
| 112 |
const int n_shapes = poly.size(); |
| 113 |
|
| 114 |
std::array<Number, 2 * dim> point, result; |
| 115 |
for (unsigned int d = 0; d < dim; ++d) |
| 116 |
point[d] = p0[d]; |
| 117 |
for (unsigned int d = 0; d < dim; ++d) |
| 118 |
point[dim + d] = p1[d]; |
| 119 |
for (int i = 0; i < n_shapes; ++i) |
| 120 |
{ |
| 121 |
poly[i].values_of_array(point, 0, &result); |
| 122 |
for (unsigned int j = 0; j < 2; ++j) |
| 123 |
for (unsigned int d = 0; d < dim; ++d) |
| 124 |
shapes[j * n_shapes + i][0][d] = result[j * dim + d]; |
| 125 |
} |
| 126 |
} |
| 127 |
|
| 128 |
|
| 129 |
|
| 130 |
/** |
| 131 |
* Interpolate inner dimensions of tensor product shape functions. |
| 132 |
*/ |
| 133 |
template <int dim, |
| 134 |
int length, |
| 135 |
typename Number2, |
| 136 |
typename Number, |
| 137 |
int n_values = 1, |
| 138 |
bool do_renumber = true, |
| 139 |
int stride = 1> |
| 140 |
inline |
| 141 |
#ifndef DEBUG |
| 142 |
DEAL_II_ALWAYS_INLINE |
| 143 |
#endif |
| 144 |
std::array<typename ProductTypeNoPoint<Number, Number2>::type, |
| 145 |
2 + n_values> |
| 146 |
do_interpolate_xy(const Number *values, |
| 147 |
const std::vector<unsigned int> &renumber, |
| 148 |
const dealii::ndarray<Number2, 2, dim> *shapes, |
| 149 |
const int n_shapes_runtime, |
| 150 |
int &i) |
| 151 |
{ |
| 152 |
static_assert(0 <= dim && dim <= 3, "Only dim=0,1,2,3 implemented"); |
| 153 |
static_assert(1 <= n_values && n_values <= 2, |
| 154 |
"Only n_values=1,2 implemented"); |
| 155 |
|
| 156 |
const int n_shapes = length > 0 ? length : n_shapes_runtime; |
| 157 |
|
| 158 |
// If n_values > 1, we want to interpolate from a second array, |
| 159 |
// placed in the same array immediately after the main data. This |
| 160 |
// is used to interpolate normal derivatives onto faces. |
| 161 |
const Number *values_2 = |
| 162 |
n_values > 1 ? |
| 163 |
values + stride * (length > 0 ? |
| 164 |
Utilities::pow(length, dim) : |
| 165 |
Utilities::fixed_power<dim>(n_shapes_runtime)) : |
| 166 |
nullptr; |
| 167 |
using Number3 = typename ProductTypeNoPoint<Number, Number2>::type; |
| 168 |
std::array<Number3, 2 + n_values> result = {}; |
| 169 |
for (int i1 = 0; i1 < (dim > 1 ? n_shapes : 1); ++i1) |
| 170 |
{ |
| 171 |
// Interpolation + derivative x direction |
| 172 |
std::array<Number3, 1 + n_values> inner_result = {}; |
| 173 |
|
| 174 |
// Distinguish the inner loop based on whether we have a |
| 175 |
// renumbering or not |
| 176 |
if (do_renumber && !renumber.empty()) |
| 177 |
for (int i0 = 0; i0 < n_shapes; ++i0, ++i) |
| 178 |
{ |
| 179 |
// gradient |
| 180 |
inner_result[0] += |
| 181 |
shapes[i0][1][0] * values[renumber[i] * stride]; |
| 182 |
// values |
| 183 |
inner_result[1] += |
| 184 |
shapes[i0][0][0] * values[renumber[i] * stride]; |
| 185 |
if (n_values > 1) |
| 186 |
inner_result[2] += |
| 187 |
shapes[i0][0][0] * values_2[renumber[i] * stride]; |
| 188 |
} |
| 189 |
else |
| 190 |
for (int i0 = 0; i0 < n_shapes; ++i0, ++i) |
| 191 |
{ |
| 192 |
// gradient |
| 193 |
inner_result[0] += shapes[i0][1][0] * values[i * stride]; |
| 194 |
// values |
| 195 |
inner_result[1] += shapes[i0][0][0] * values[i * stride]; |
| 196 |
if (n_values > 1) |
| 197 |
inner_result[2] += shapes[i0][0][0] * values_2[i * stride]; |
| 198 |
} |
| 199 |
|
| 200 |
if (dim > 1) |
| 201 |
{ |
| 202 |
// Interpolation + derivative in y direction |
| 203 |
// gradient |
| 204 |
result[0] += inner_result[0] * shapes[i1][0][1]; |
| 205 |
result[1] += inner_result[1] * shapes[i1][1][1]; |
| 206 |
// values |
| 207 |
result[2] += inner_result[1] * shapes[i1][0][1]; |
| 208 |
if (n_values > 1) |
| 209 |
result[3] += inner_result[2] * shapes[i1][0][1]; |
| 210 |
} |
| 211 |
else |
| 212 |
{ |
| 213 |
// gradient |
| 214 |
result[0] = inner_result[0]; |
| 215 |
// values |
| 216 |
result[1] = inner_result[1]; |
| 217 |
if (n_values > 1) |
| 218 |
result[2] = inner_result[2]; |
| 219 |
} |
| 220 |
} |
| 221 |
return result; |
| 222 |
} |
| 223 |
|
| 224 |
|
| 225 |
|
| 226 |
/** |
| 227 |
* Interpolates the values and gradients into the points specified in |
| 228 |
* @p compute_values_of_array() with help of the precomputed @p shapes. |
| 229 |
*/ |
| 230 |
template <int dim, |
| 231 |
typename Number, |
| 232 |
typename Number2, |
| 233 |
int n_values = 1, |
| 234 |
bool do_renumber = true, |
| 235 |
int stride = 1> |
| 236 |
inline std::array<typename ProductTypeNoPoint<Number, Number2>::type, |
| 237 |
dim + n_values> |
| 238 |
evaluate_tensor_product_value_and_gradient_shapes( |
| 239 |
const dealii::ndarray<Number2, 2, dim> *shapes, |
| 240 |
const int n_shapes, |
| 241 |
const Number *values, |
| 242 |
const std::vector<unsigned int> &renumber = {}) |
| 243 |
{ |
| 244 |
static_assert(0 <= dim && dim <= 3, "Only dim=0,1,2,3 implemented"); |
| 245 |
static_assert(1 <= n_values && n_values <= 2, |
| 246 |
"Only n_values=1,2 implemented"); |
| 247 |
|
| 248 |
using Number3 = typename ProductTypeNoPoint<Number, Number2>::type; |
| 249 |
|
| 250 |
std::array<Number3, dim + n_values> result = {}; |
| 251 |
if (dim == 0) |
| 252 |
{ |
| 253 |
// We only need the interpolation of the value and normal derivatives on |
| 254 |
// faces of a 1d element. As the interpolation is the value at the |
| 255 |
// point, simply set the result vector accordingly. |
| 256 |
result[0] = values[0]; |
| 257 |
if (n_values > 1) |
| 258 |
result[1] = values[1 * stride]; |
| 259 |
return result; |
| 260 |
} |
| 261 |
|
| 262 |
// Go through the tensor product of shape functions and interpolate |
| 263 |
// with optimal algorithm |
| 264 |
for (int i2 = 0, i = 0; i2 < (dim > 2 ? n_shapes : 1); ++i2) |
| 265 |
{ |
| 266 |
std::array<Number3, 2 + n_values> inner_result; |
| 267 |
// Generate separate code with known loop bounds for the most common |
| 268 |
// cases |
| 269 |
if (n_shapes == 2) |
| 270 |
inner_result = |
| 271 |
do_interpolate_xy<dim, |
| 272 |
2, |
| 273 |
Number2, |
| 274 |
Number, |
| 275 |
n_values, |
| 276 |
do_renumber, |
| 277 |
stride>(values, renumber, shapes, n_shapes, i); |
| 278 |
else if (n_shapes == 3) |
| 279 |
inner_result = |
| 280 |
do_interpolate_xy<dim, |
| 281 |
3, |
| 282 |
Number2, |
| 283 |
Number, |
| 284 |
n_values, |
| 285 |
do_renumber, |
| 286 |
stride>(values, renumber, shapes, n_shapes, i); |
| 287 |
else if (n_shapes == 4) |
| 288 |
inner_result = |
| 289 |
do_interpolate_xy<dim, |
| 290 |
4, |
| 291 |
Number2, |
| 292 |
Number, |
| 293 |
n_values, |
| 294 |
do_renumber, |
| 295 |
stride>(values, renumber, shapes, n_shapes, i); |
| 296 |
else if (n_shapes == 5) |
| 297 |
inner_result = |
| 298 |
do_interpolate_xy<dim, |
| 299 |
5, |
| 300 |
Number2, |
| 301 |
Number, |
| 302 |
n_values, |
| 303 |
do_renumber, |
| 304 |
stride>(values, renumber, shapes, n_shapes, i); |
| 305 |
else if (n_shapes == 6) |
| 306 |
inner_result = |
| 307 |
do_interpolate_xy<dim, |
| 308 |
6, |
| 309 |
Number2, |
| 310 |
Number, |
| 311 |
n_values, |
| 312 |
do_renumber, |
| 313 |
stride>(values, renumber, shapes, n_shapes, i); |
| 314 |
else |
| 315 |
inner_result = |
| 316 |
do_interpolate_xy<dim, |
| 317 |
-1, |
| 318 |
Number2, |
| 319 |
Number, |
| 320 |
n_values, |
| 321 |
do_renumber, |
| 322 |
stride>(values, renumber, shapes, n_shapes, i); |
| 323 |
if (dim == 3) |
| 324 |
{ |
| 325 |
// derivative + interpolation in z direction |
| 326 |
// gradient |
| 327 |
result[0] += inner_result[0] * shapes[i2][0][2]; |
| 328 |
result[1] += inner_result[1] * shapes[i2][0][2]; |
| 329 |
result[2] += inner_result[2] * shapes[i2][1][2]; |
| 330 |
// values |
| 331 |
result[3] += inner_result[2] * shapes[i2][0][2]; |
| 332 |
if (n_values > 1) |
| 333 |
result[4] += inner_result[3] * shapes[i2][0][2]; |
| 334 |
} |
| 335 |
else if (dim == 2) |
| 336 |
{ |
| 337 |
// gradient |
| 338 |
result[0] = inner_result[0]; |
| 339 |
result[1] = inner_result[1]; |
| 340 |
// values |
| 341 |
result[2] = inner_result[2]; |
| 342 |
if (n_values > 1) |
| 343 |
result[3] = inner_result[3]; |
| 344 |
} |
| 345 |
else |
| 346 |
{ |
| 347 |
// gradient |
| 348 |
result[0] = inner_result[0]; |
| 349 |
// values |
| 350 |
result[1] = inner_result[1]; |
| 351 |
if (n_values > 1) |
| 352 |
result[2] = inner_result[2]; |
| 353 |
} |
| 354 |
} |
| 355 |
|
| 356 |
return result; |
| 357 |
} |
| 358 |
|
| 359 |
|
| 360 |
|
| 361 |
/** |
| 362 |
* Specializes @p evaluate_tensor_product_value_and_gradient() for linear |
| 363 |
* polynomials which massively reduces the necessary instructions. |
| 364 |
*/ |
| 365 |
template <int dim, |
| 366 |
typename Number, |
| 367 |
typename Number2, |
| 368 |
int n_values = 1, |
| 369 |
int stride = 1> |
| 370 |
inline std::array<typename ProductTypeNoPoint<Number, Number2>::type, |
| 371 |
dim + n_values> |
| 372 |
evaluate_tensor_product_value_and_gradient_linear( |
| 373 |
const Number *values, |
| 374 |
const Point<dim, Number2> &p) |
| 375 |
{ |
| 376 |
static_assert(0 <= dim && dim <= 3, "Only dim=0,1,2,3 implemented"); |
| 377 |
static_assert(1 <= n_values && n_values <= 2, |
| 378 |
"Only n_values=1,2 implemented"); |
| 379 |
|
| 380 |
using Number3 = typename ProductTypeNoPoint<Number, Number2>::type; |
| 381 |
|
| 382 |
// If n_values > 1, we want to interpolate from a second array, |
| 383 |
// placed in the same array immediately after the main data. This |
| 384 |
// is used to interpolate normal derivatives onto faces. |
| 385 |
|
| 386 |
std::array<Number3, dim + n_values> result; |
| 387 |
if (dim == 0) |
| 388 |
{ |
| 389 |
// we only need the value on faces of a 1d element |
| 390 |
result[0] = values[0]; |
| 391 |
if (n_values > 1) |
| 392 |
result[1] = values[1 * stride]; |
| 393 |
} |
| 394 |
else if (dim == 1) |
| 395 |
{ |
| 396 |
// gradient |
| 397 |
result[0] = Number3(values[stride] - values[0]); |
| 398 |
// values |
| 399 |
result[1] = Number3(values[0]) + p[0] * result[0]; |
| 400 |
if (n_values > 1) |
| 401 |
result[2] = Number3(values[2 * stride]) + |
| 402 |
p[0] * (values[3 * stride] - values[2 * stride]); |
| 403 |
} |
| 404 |
else if (dim == 2) |
| 405 |
{ |
| 406 |
const Number3 val10 = Number3(values[stride] - values[0]); |
| 407 |
const Number3 val32 = Number3(values[3 * stride] - values[2 * stride]); |
| 408 |
const Number3 tmp0 = Number3(values[0]) + p[0] * val10; |
| 409 |
const Number3 tmp1 = Number3(values[2 * stride]) + p[0] * val32; |
| 410 |
|
| 411 |
// gradient |
| 412 |
result[0] = val10 + p[1] * (val32 - val10); |
| 413 |
result[1] = tmp1 - tmp0; |
| 414 |
|
| 415 |
// values |
| 416 |
result[2] = tmp0 + p[1] * result[1]; |
| 417 |
|
| 418 |
if (n_values > 1) |
| 419 |
{ |
| 420 |
const Number3 tmp0_2 = |
| 421 |
Number3(values[4 * stride]) + |
| 422 |
p[0] * (values[5 * stride] - values[4 * stride]); |
| 423 |
const Number3 tmp1_2 = |
| 424 |
Number3(values[6 * stride]) + |
| 425 |
p[0] * (values[7 * stride] - values[6 * stride]); |
| 426 |
result[3] = tmp0_2 + p[1] * (tmp1_2 - tmp0_2); |
| 427 |
} |
| 428 |
} |
| 429 |
else if (dim == 3) |
| 430 |
{ |
| 431 |
const Number3 val10 = Number3(values[stride] - values[0]); |
| 432 |
const Number3 val32 = Number3(values[3 * stride] - values[2 * stride]); |
| 433 |
const Number3 tmp0 = Number3(values[0]) + p[0] * val10; |
| 434 |
const Number3 tmp1 = Number3(values[2 * stride]) + p[0] * val32; |
| 435 |
const Number3 tmp10 = tmp1 - tmp0; |
| 436 |
const Number3 tmpy0 = tmp0 + p[1] * tmp10; |
| 437 |
|
| 438 |
const Number3 val54 = Number3(values[5 * stride] - values[4 * stride]); |
| 439 |
const Number3 val76 = Number3(values[7 * stride] - values[6 * stride]); |
| 440 |
const Number3 tmp2 = Number3(values[4 * stride]) + p[0] * val54; |
| 441 |
const Number3 tmp3 = Number3(values[6 * stride]) + p[0] * val76; |
| 442 |
const Number3 tmp32 = tmp3 - tmp2; |
| 443 |
const Number3 tmpy1 = tmp2 + p[1] * tmp32; |
| 444 |
|
| 445 |
// gradient |
| 446 |
result[2] = tmpy1 - tmpy0; |
| 447 |
result[1] = tmp10 + p[2] * (tmp32 - tmp10); |
| 448 |
const Number3 tmpz0 = val10 + p[1] * (val32 - val10); |
| 449 |
result[0] = tmpz0 + p[2] * (val54 + p[1] * (val76 - val54) - tmpz0); |
| 450 |
|
| 451 |
// value |
| 452 |
result[3] = tmpy0 + p[2] * result[2]; |
| 453 |
Assert(n_values == 1, ExcNotImplemented()); |
| 454 |
} |
| 455 |
|
| 456 |
return result; |
| 457 |
} |
| 458 |
|
| 459 |
|
| 460 |
|
| 461 |
/** |
| 462 |
* Compute the polynomial interpolation of a tensor product shape function |
| 463 |
* $\varphi_i$ given a vector of coefficients $u_i$ in the form |
| 464 |
* $u_h(\mathbf{x}) = \sum_{i=1}^{k^d} \varphi_i(\mathbf{x}) u_i$. The shape |
| 465 |
* functions $\varphi_i(\mathbf{x}) = |
| 466 |
* \prod_{d=1}^{\text{dim}}\varphi_{i_d}^\text{1d}(x_d)$ represent a tensor |
| 467 |
* product. The function returns a pair with the value of the interpolation |
| 468 |
* as the first component and the gradient in reference coordinates as the |
| 469 |
* second component. Note that for compound types (e.g. the `values` field |
| 470 |
* begin a Point<spacedim> argument), the components of the gradient are |
| 471 |
* sorted as Tensor<1, dim, Tensor<1, spacedim>> with the derivatives |
| 472 |
* as the first index; this is a consequence of the generic arguments in the |
| 473 |
* function. |
| 474 |
* |
| 475 |
* @param poly The underlying one-dimensional polynomial basis |
| 476 |
* $\{\varphi^{1d}_{i_1}\}$ given as a vector of polynomials. |
| 477 |
* |
| 478 |
* @param values The expansion coefficients $u_i$ of type `Number` in |
| 479 |
* the polynomial interpolation. The coefficients can be simply `double` |
| 480 |
* variables but e.g. also Point<spacedim> in case they define arithmetic |
| 481 |
* operations with the type `Number2`. |
| 482 |
* |
| 483 |
* @param p The position in reference coordinates where the interpolation |
| 484 |
* should be evaluated. |
| 485 |
* |
| 486 |
* @param d_linear Flag to specify whether a d-linear (linear in 1d, |
| 487 |
* bi-linear in 2d, tri-linear in 3d) interpolation should be made, which |
| 488 |
* allows to unroll loops and considerably speed up evaluation. |
| 489 |
* |
| 490 |
* @param renumber Optional parameter to specify a renumbering in the |
| 491 |
* coefficient vector, assuming that `values[renumber[i]]` returns |
| 492 |
* the lexicographic (tensor product) entry of the coefficients. If the |
| 493 |
* vector is entry, the values are assumed to be sorted lexicographically. |
| 494 |
*/ |
| 495 |
template <int dim, typename Number, typename Number2> |
| 496 |
inline std::pair< |
| 497 |
typename ProductTypeNoPoint<Number, Number2>::type, |
| 498 |
Tensor<1, dim, typename ProductTypeNoPoint<Number, Number2>::type>> |
| 499 |
evaluate_tensor_product_value_and_gradient( |
| 500 |
const std::vector<Polynomials::Polynomial<double>> &poly, |
| 501 |
const ArrayView<const Number> &values, |
| 502 |
const Point<dim, Number2> &p, |
| 503 |
const bool d_linear = false, |
| 504 |
const std::vector<unsigned int> &renumber = {}) |
| 505 |
{ |
| 506 |
using Number3 = typename ProductTypeNoPoint<Number, Number2>::type; |
| 507 |
|
| 508 |
std::array<Number3, dim + 1> result; |
| 509 |
if (d_linear) |
| 510 |
{ |
| 511 |
result = |
| 512 |
evaluate_tensor_product_value_and_gradient_linear(values.data(), p); |
| 513 |
} |
| 514 |
else |
| 515 |
{ |
| 516 |
AssertIndexRange(poly.size(), 200); |
| 517 |
std::array<dealii::ndarray<Number2, 2, dim>, 200> shapes; |
| 518 |
compute_values_of_array(shapes.data(), poly, p); |
| 519 |
result = evaluate_tensor_product_value_and_gradient_shapes<dim, |
| 520 |
Number, |
| 521 |
Number2>( |
| 522 |
shapes.data(), poly.size(), values.data(), renumber); |
| 523 |
} |
| 524 |
return std::make_pair(result[dim], |
| 525 |
Tensor<1, dim, Number3>( |
| 526 |
ArrayView<Number3>(result.data(), dim))); |
| 527 |
} |
| 528 |
|
| 529 |
|
| 530 |
|
| 531 |
template <int dim, |
| 532 |
int length, |
| 533 |
typename Number2, |
| 534 |
typename Number, |
| 535 |
bool do_renumber = true, |
| 536 |
int stride = 1> |
| 537 |
inline |
| 538 |
#ifndef DEBUG |
| 539 |
DEAL_II_ALWAYS_INLINE |
| 540 |
#endif |
| 541 |
typename ProductTypeNoPoint<Number, Number2>::type |
| 542 |
do_interpolate_xy_value(const Number *values, |
| 543 |
const std::vector<unsigned int> &renumber, |
| 544 |
const dealii::ndarray<Number2, 2, dim> *shapes, |
| 545 |
const int n_shapes_runtime, |
| 546 |
int &i) |
| 547 |
{ |
| 548 |
const int n_shapes = length > 0 ? length : n_shapes_runtime; |
| 549 |
using Number3 = typename ProductTypeNoPoint<Number, Number2>::type; |
| 550 |
Number3 result = {}; |
| 551 |
for (int i1 = 0; i1 < (dim > 1 ? n_shapes : 1); ++i1) |
| 552 |
{ |
| 553 |
// Interpolation x direction |
| 554 |
Number3 value = {}; |
| 555 |
|
| 556 |
// Distinguish the inner loop based on whether we have a |
| 557 |
// renumbering or not |
| 558 |
if (do_renumber && !renumber.empty()) |
| 559 |
for (int i0 = 0; i0 < n_shapes; ++i0, ++i) |
| 560 |
value += shapes[i0][0][0] * values[renumber[i] * stride]; |
| 561 |
else |
| 562 |
for (int i0 = 0; i0 < n_shapes; ++i0, ++i) |
| 563 |
value += shapes[i0][0][0] * values[i * stride]; |
| 564 |
|
| 565 |
if (dim > 1) |
| 566 |
result += value * shapes[i1][0][1]; |
| 567 |
else |
| 568 |
result = value; |
| 569 |
} |
| 570 |
return result; |
| 571 |
} |
| 572 |
|
| 573 |
|
| 574 |
|
| 575 |
template <int dim, |
| 576 |
typename Number, |
| 577 |
typename Number2, |
| 578 |
bool do_renumber = true, |
| 579 |
int stride = 1> |
| 580 |
inline typename ProductTypeNoPoint<Number, Number2>::type |
| 581 |
evaluate_tensor_product_value_shapes( |
| 582 |
const dealii::ndarray<Number2, 2, dim> *shapes, |
| 583 |
const int n_shapes, |
| 584 |
const Number *values, |
| 585 |
const std::vector<unsigned int> &renumber = {}) |
| 586 |
{ |
| 587 |
static_assert(dim >= 0 && dim <= 3, "Only dim=0,1,2,3 implemented"); |
| 588 |
|
| 589 |
// we only need the value on faces of a 1d element |
| 590 |
if (dim == 0) |
| 591 |
{ |
| 592 |
return values[0]; |
| 593 |
} |
| 594 |
|
| 595 |
using Number3 = typename ProductTypeNoPoint<Number, Number2>::type; |
| 596 |
|
| 597 |
// Go through the tensor product of shape functions and interpolate |
| 598 |
// with optimal algorithm |
| 599 |
Number3 result = {}; |
| 600 |
for (int i2 = 0, i = 0; i2 < (dim > 2 ? n_shapes : 1); ++i2) |
| 601 |
{ |
| 602 |
Number3 inner_result; |
| 603 |
// Generate separate code with known loop bounds for the most common |
| 604 |
// cases |
| 605 |
if (n_shapes == 2) |
| 606 |
inner_result = do_interpolate_xy_value<dim, |
| 607 |
2, |
| 608 |
Number2, |
| 609 |
Number, |
| 610 |
do_renumber, |
| 611 |
stride>( |
| 612 |
values, renumber, shapes, n_shapes, i); |
| 613 |
else if (n_shapes == 3) |
| 614 |
inner_result = do_interpolate_xy_value<dim, |
| 615 |
3, |
| 616 |
Number2, |
| 617 |
Number, |
| 618 |
do_renumber, |
| 619 |
stride>( |
| 620 |
values, renumber, shapes, n_shapes, i); |
| 621 |
else if (n_shapes == 4) |
| 622 |
inner_result = do_interpolate_xy_value<dim, |
| 623 |
4, |
| 624 |
Number2, |
| 625 |
Number, |
| 626 |
do_renumber, |
| 627 |
stride>( |
| 628 |
values, renumber, shapes, n_shapes, i); |
| 629 |
else if (n_shapes == 5) |
| 630 |
inner_result = do_interpolate_xy_value<dim, |
| 631 |
5, |
| 632 |
Number2, |
| 633 |
Number, |
| 634 |
do_renumber, |
| 635 |
stride>( |
| 636 |
values, renumber, shapes, n_shapes, i); |
| 637 |
else if (n_shapes == 6) |
| 638 |
inner_result = do_interpolate_xy_value<dim, |
| 639 |
6, |
| 640 |
Number2, |
| 641 |
Number, |
| 642 |
do_renumber, |
| 643 |
stride>( |
| 644 |
values, renumber, shapes, n_shapes, i); |
| 645 |
else |
| 646 |
inner_result = do_interpolate_xy_value<dim, |
| 647 |
-1, |
| 648 |
Number2, |
| 649 |
Number, |
| 650 |
do_renumber, |
| 651 |
stride>( |
| 652 |
values, renumber, shapes, n_shapes, i); |
| 653 |
if (dim == 3) |
| 654 |
{ |
| 655 |
// Interpolation + derivative in z direction |
| 656 |
result += inner_result * shapes[i2][0][2]; |
| 657 |
} |
| 658 |
else |
| 659 |
{ |
| 660 |
result = inner_result; |
| 661 |
} |
| 662 |
} |
| 663 |
|
| 664 |
return result; |
| 665 |
} |
| 666 |
|
| 667 |
|
| 668 |
|
| 669 |
template <int dim, typename Number, typename Number2, int stride = 1> |
| 670 |
inline typename ProductTypeNoPoint<Number, Number2>::type |
| 671 |
evaluate_tensor_product_value_linear(const Number *values, |
| 672 |
const Point<dim, Number2> &p) |
| 673 |
{ |
| 674 |
static_assert(dim >= 0 && dim <= 3, "Only dim=0,1,2,3 implemented"); |
| 675 |
|
| 676 |
using Number3 = typename ProductTypeNoPoint<Number, Number2>::type; |
| 677 |
|
| 678 |
if (dim == 0) |
| 679 |
{ |
| 680 |
// we only need the value on faces of a 1d element |
| 681 |
return values[0]; |
| 682 |
} |
| 683 |
else if (dim == 1) |
| 684 |
{ |
| 685 |
return Number3(values[0]) + p[0] * Number3(values[stride] - values[0]); |
| 686 |
} |
| 687 |
else if (dim == 2) |
| 688 |
{ |
| 689 |
const Number3 val10 = Number3(values[stride] - values[0]); |
| 690 |
const Number3 val32 = Number3(values[3 * stride] - values[2 * stride]); |
| 691 |
const Number3 tmp0 = Number3(values[0]) + p[0] * val10; |
| 692 |
const Number3 tmp1 = Number3(values[2 * stride]) + p[0] * val32; |
| 693 |
return tmp0 + p[1] * (tmp1 - tmp0); |
| 694 |
} |
| 695 |
else if (dim == 3) |
| 696 |
{ |
| 697 |
const Number3 val10 = Number3(values[stride] - values[0]); |
| 698 |
const Number3 val32 = Number3(values[3 * stride] - values[2 * stride]); |
| 699 |
const Number3 tmp0 = Number3(values[0]) + p[0] * val10; |
| 700 |
const Number3 tmp1 = Number3(values[2 * stride]) + p[0] * val32; |
| 701 |
const Number3 tmpy0 = tmp0 + p[1] * (tmp1 - tmp0); |
| 702 |
|
| 703 |
const Number3 val54 = Number3(values[5 * stride] - values[4 * stride]); |
| 704 |
const Number3 val76 = Number3(values[7 * stride] - values[6 * stride]); |
| 705 |
const Number3 tmp2 = Number3(values[4 * stride]) + p[0] * val54; |
| 706 |
const Number3 tmp3 = Number3(values[6 * stride]) + p[0] * val76; |
| 707 |
const Number3 tmpy1 = tmp2 + p[1] * (tmp3 - tmp2); |
| 708 |
|
| 709 |
return tmpy0 + p[2] * (tmpy1 - tmpy0); |
| 710 |
} |
| 711 |
|
| 712 |
// work around a compile error: missing return statement |
| 713 |
return Number3(); |
| 714 |
} |
| 715 |
|
| 716 |
|
| 717 |
|
| 718 |
template <int dim, typename Number, typename Number2> |
| 719 |
inline typename ProductTypeNoPoint<Number, Number2>::type |
| 720 |
evaluate_tensor_product_value( |
| 721 |
const std::vector<Polynomials::Polynomial<double>> &poly, |
| 722 |
const ArrayView<const Number> &values, |
| 723 |
const Point<dim, Number2> &p, |
| 724 |
const bool d_linear = false, |
| 725 |
const std::vector<unsigned int> &renumber = {}) |
| 726 |
{ |
| 727 |
typename ProductTypeNoPoint<Number, Number2>::type result; |
| 728 |
if (d_linear) |
| 729 |
{ |
| 730 |
result = evaluate_tensor_product_value_linear(values.data(), p); |
| 731 |
} |
| 732 |
else |
| 733 |
{ |
| 734 |
AssertIndexRange(poly.size(), 200); |
| 735 |
std::array<dealii::ndarray<Number2, 2, dim>, 200> shapes; |
| 736 |
const int n_shapes = poly.size(); |
| 737 |
std::array<Number2, dim> point; |
| 738 |
for (unsigned int d = 0; d < dim; ++d) |
| 739 |
point[d] = p[d]; |
| 740 |
for (int i = 0; i < n_shapes; ++i) |
| 741 |
poly[i].values_of_array(point, 0, shapes[i].data()); |
| 742 |
result = evaluate_tensor_product_value_shapes<dim, Number, Number2>( |
| 743 |
shapes.data(), n_shapes, values.data(), renumber); |
| 744 |
} |
| 745 |
return result; |
| 746 |
} |
| 747 |
|
| 748 |
|
| 749 |
|
| 750 |
/** |
| 751 |
* This function computes derivatives of arbitrary orders in 1d, returning a |
| 752 |
* Tensor with the respective derivative |
| 753 |
*/ |
| 754 |
template <int derivative_order, typename Number, typename Number2> |
| 755 |
inline Tensor<1, 1, typename ProductTypeNoPoint<Number, Number2>::type> |
| 756 |
evaluate_tensor_product_higher_derivatives( |
| 757 |
const std::vector<Polynomials::Polynomial<double>> &poly, |
| 758 |
const ArrayView<const Number> &values, |
| 759 |
const Point<1, Number2> &p, |
| 760 |
const std::vector<unsigned int> &renumber = {}) |
| 761 |
{ |
| 762 |
using Number3 = typename ProductTypeNoPoint<Number, Number2>::type; |
| 763 |
|
| 764 |
const int n_shapes = poly.size(); |
| 765 |
AssertDimension(n_shapes, values.size()); |
| 766 |
Assert(renumber.empty() || renumber.size() == values.size(), |
| 767 |
ExcDimensionMismatch(renumber.size(), values.size())); |
| 768 |
|
| 769 |
std::array<Number2, derivative_order + 1> shapes; |
| 770 |
Tensor<1, 1, Number3> result; |
| 771 |
if (renumber.empty()) |
| 772 |
for (int i = 0; i < n_shapes; ++i) |
| 773 |
{ |
| 774 |
poly[i].value(p[0], derivative_order, shapes.data()); |
| 775 |
result[0] += shapes[derivative_order] * values[i]; |
| 776 |
} |
| 777 |
else |
| 778 |
for (int i = 0; i < n_shapes; ++i) |
| 779 |
{ |
| 780 |
poly[i].value(p[0], derivative_order, shapes.data()); |
| 781 |
result[0] += shapes[derivative_order] * values[renumber[i]]; |
| 782 |
} |
| 783 |
return result; |
| 784 |
} |
| 785 |
|
| 786 |
|
| 787 |
|
| 788 |
/** |
| 789 |
* This function computes derivatives of arbitrary orders in 2d, returning a |
| 790 |
* Tensor with the respective derivatives |
| 791 |
*/ |
| 792 |
template <int derivative_order, typename Number, typename Number2> |
| 793 |
inline Tensor<1, |
| 794 |
derivative_order + 1, |
| 795 |
typename ProductTypeNoPoint<Number, Number2>::type> |
| 796 |
evaluate_tensor_product_higher_derivatives( |
| 797 |
const std::vector<Polynomials::Polynomial<double>> &poly, |
| 798 |
const ArrayView<const Number> &values, |
| 799 |
const Point<2, Number2> &p, |
| 800 |
const std::vector<unsigned int> &renumber = {}) |
| 801 |
{ |
| 802 |
using Number3 = typename ProductTypeNoPoint<Number, Number2>::type; |
| 803 |
constexpr int dim = 2; |
| 804 |
|
| 805 |
const int n_shapes = poly.size(); |
| 806 |
AssertDimension(Utilities::pow(n_shapes, 2), values.size()); |
| 807 |
Assert(renumber.empty() || renumber.size() == values.size(), |
| 808 |
ExcDimensionMismatch(renumber.size(), values.size())); |
| 809 |
|
| 810 |
AssertIndexRange(n_shapes, 100); |
| 811 |
dealii::ndarray<Number2, 100, derivative_order + 1, dim> shapes; |
| 812 |
// Evaluate 1d polynomials and their derivatives |
| 813 |
std::array<Number2, dim> point; |
| 814 |
for (unsigned int d = 0; d < dim; ++d) |
| 815 |
point[d] = p[d]; |
| 816 |
for (int i = 0; i < n_shapes; ++i) |
| 817 |
poly[i].values_of_array(point, derivative_order, &shapes[i][0]); |
| 818 |
|
| 819 |
Tensor<1, derivative_order + 1, Number3> result; |
| 820 |
for (int i1 = 0, i = 0; i1 < n_shapes; ++i1) |
| 821 |
{ |
| 822 |
Tensor<1, derivative_order + 1, Number3> result_x; |
| 823 |
if (renumber.empty()) |
| 824 |
for (int i0 = 0; i0 < n_shapes; ++i0, ++i) |
| 825 |
for (unsigned int d = 0; d <= derivative_order; ++d) |
| 826 |
result_x[d] += shapes[i0][d][0] * values[i]; |
| 827 |
else |
| 828 |
for (int i0 = 0; i0 < n_shapes; ++i0, ++i) |
| 829 |
for (unsigned int d = 0; d <= derivative_order; ++d) |
| 830 |
result_x[d] += shapes[i0][d][0] * values[renumber[i]]; |
| 831 |
|
| 832 |
for (unsigned int d = 0; d <= derivative_order; ++d) |
| 833 |
result[d] += shapes[i1][d][1] * result_x[derivative_order - d]; |
| 834 |
} |
| 835 |
return result; |
| 836 |
} |
| 837 |
|
| 838 |
|
| 839 |
|
| 840 |
/** |
| 841 |
* This function computes derivatives of arbitrary orders in 3d, returning a |
| 842 |
* Tensor with the respective derivatives |
| 843 |
*/ |
| 844 |
template <int derivative_order, typename Number, typename Number2> |
| 845 |
inline Tensor<1, |
| 846 |
((derivative_order + 1) * (derivative_order + 2)) / 2, |
| 847 |
typename ProductTypeNoPoint<Number, Number2>::type> |
| 848 |
evaluate_tensor_product_higher_derivatives( |
| 849 |
const std::vector<Polynomials::Polynomial<double>> &poly, |
| 850 |
const ArrayView<const Number> &values, |
| 851 |
const Point<3, Number2> &p, |
| 852 |
const std::vector<unsigned int> &renumber = {}) |
| 853 |
{ |
| 854 |
using Number3 = typename ProductTypeNoPoint<Number, Number2>::type; |
| 855 |
constexpr int dim = 3; |
| 856 |
constexpr int n_derivatives = |
| 857 |
((derivative_order + 1) * (derivative_order + 2)) / 2; |
| 858 |
|
| 859 |
const int n_shapes = poly.size(); |
| 860 |
AssertDimension(Utilities::pow(n_shapes, 3), values.size()); |
| 861 |
Assert(renumber.empty() || renumber.size() == values.size(), |
| 862 |
ExcDimensionMismatch(renumber.size(), values.size())); |
| 863 |
|
| 864 |
AssertIndexRange(n_shapes, 100); |
| 865 |
dealii::ndarray<Number2, 100, derivative_order + 1, dim> shapes; |
| 866 |
// Evaluate 1d polynomials and their derivatives |
| 867 |
std::array<Number2, dim> point; |
| 868 |
for (unsigned int d = 0; d < dim; ++d) |
| 869 |
point[d] = p[d]; |
| 870 |
for (int i = 0; i < n_shapes; ++i) |
| 871 |
poly[i].values_of_array(point, derivative_order, &shapes[i][0]); |
| 872 |
|
| 873 |
Tensor<1, n_derivatives, Number3> result; |
| 874 |
for (int i2 = 0, i = 0; i2 < n_shapes; ++i2) |
| 875 |
{ |
| 876 |
Tensor<1, n_derivatives, Number3> result_xy; |
| 877 |
for (int i1 = 0; i1 < n_shapes; ++i1) |
| 878 |
{ |
| 879 |
// apply x derivatives |
| 880 |
Tensor<1, derivative_order + 1, Number3> result_x; |
| 881 |
if (renumber.empty()) |
| 882 |
for (int i0 = 0; i0 < n_shapes; ++i0, ++i) |
| 883 |
for (unsigned int d = 0; d <= derivative_order; ++d) |
| 884 |
result_x[d] += shapes[i0][d][0] * values[i]; |
| 885 |
else |
| 886 |
for (int i0 = 0; i0 < n_shapes; ++i0, ++i) |
| 887 |
for (unsigned int d = 0; d <= derivative_order; ++d) |
| 888 |
result_x[d] += shapes[i0][d][0] * values[renumber[i]]; |
| 889 |
|
| 890 |
// multiply by y derivatives, sorting them in upper triangular |
| 891 |
// matrix, starting with highest global derivative order, |
| 892 |
// decreasing the combined order of xy derivatives by one in each |
| 893 |
// row, to be combined with z derivatives in the next step |
| 894 |
for (unsigned int d = 0, c = 0; d <= derivative_order; ++d) |
| 895 |
for (unsigned int e = d; e <= derivative_order; ++e, ++c) |
| 896 |
result_xy[c] += |
| 897 |
shapes[i1][e - d][1] * result_x[derivative_order - e]; |
| 898 |
} |
| 899 |
|
| 900 |
// multiply by z derivatives, starting with highest x derivative |
| 901 |
for (unsigned int d = 0, c = 0; d <= derivative_order; ++d) |
| 902 |
for (unsigned int e = d; e <= derivative_order; ++e, ++c) |
| 903 |
result[c] += shapes[i2][d][2] * result_xy[c]; |
| 904 |
} |
| 905 |
return result; |
| 906 |
} |
| 907 |
|
| 908 |
|
| 909 |
|
| 910 |
template <int dim, typename Number, typename Number2> |
| 911 |
SymmetricTensor<2, dim, typename ProductTypeNoPoint<Number, Number2>::type> |
| 912 |
evaluate_tensor_product_hessian( |
| 913 |
const std::vector<Polynomials::Polynomial<double>> &poly, |
| 914 |
const ArrayView<const Number> &values, |
| 915 |
const Point<dim, Number2> &p, |
| 916 |
const std::vector<unsigned int> &renumber = {}) |
| 917 |
{ |
| 918 |
static_assert(dim >= 1 && dim <= 3, "Only dim=1,2,3 implemented"); |
| 919 |
|
| 920 |
const auto hessian = |
| 921 |
evaluate_tensor_product_higher_derivatives<2>(poly, values, p, renumber); |
| 922 |
|
| 923 |
using Number3 = typename ProductTypeNoPoint<Number, Number2>::type; |
| 924 |
SymmetricTensor<2, dim, Number3> result; |
| 925 |
if (dim == 1) |
| 926 |
result[0][0] = hessian[0]; |
| 927 |
else if (dim >= 2) |
| 928 |
{ |
| 929 |
// derivatives in Hessian are xx, xy, yy, xz, yz, zz, so must re-order |
| 930 |
// them for 3D |
| 931 |
for (unsigned int d = 0, c = 0; d < 2; ++d) |
| 932 |
for (unsigned int e = d; e < 2; ++e, ++c) |
| 933 |
result[d][e] = hessian[c]; |
| 934 |
if (dim == 3) |
| 935 |
{ |
| 936 |
for (unsigned int d = 0; d < 2; ++d) |
| 937 |
result[d][2] = hessian[3 + d]; |
| 938 |
result[2][2] = hessian[5]; |
| 939 |
} |
| 940 |
} |
| 941 |
|
| 942 |
return result; |
| 943 |
} |
| 944 |
|
| 945 |
|
| 946 |
|
| 947 |
/** |
| 948 |
* Test inner dimensions of tensor product shape functions and accumulate. |
| 949 |
*/ |
| 950 |
template <int dim, |
| 951 |
int length, |
| 952 |
typename Number2, |
| 953 |
typename Number, |
| 954 |
bool add, |
| 955 |
int n_values = 1> |
| 956 |
inline |
| 957 |
#ifndef DEBUG |
| 958 |
DEAL_II_ALWAYS_INLINE |
| 959 |
#endif |
| 960 |
void |
| 961 |
do_apply_test_functions_xy( |
| 962 |
Number2 *values, |
| 963 |
const dealii::ndarray<Number, 2, dim> *shapes, |
| 964 |
const std::array<Number2, 2 + n_values> &test_grads_value, |
| 965 |
const int n_shapes_runtime, |
| 966 |
int &i) |
| 967 |
{ |
| 968 |
static_assert(0 <= dim && dim <= 3, "Only dim=0,1,2,3 implemented"); |
| 969 |
static_assert(1 <= n_values && n_values <= 2, |
| 970 |
"Only n_values=1,2 implemented"); |
| 971 |
|
| 972 |
// Note that 'add' is a template argument, so the compiler will remove |
| 973 |
// these checks |
| 974 |
if (length > 0) |
| 975 |
{ |
| 976 |
constexpr unsigned int array_size = length > 0 ? length : 1; |
| 977 |
std::array<Number, array_size> shape_values_x; |
| 978 |
std::array<Number, array_size> shape_derivs_x; |
| 979 |
for (unsigned int j = 0; j < array_size; ++j) |
| 980 |
{ |
| 981 |
shape_values_x[j] = shapes[j][0][0]; |
| 982 |
shape_derivs_x[j] = shapes[j][1][0]; |
| 983 |
} |
| 984 |
for (int i1 = 0; i1 < (dim > 1 ? length : 1); ++i1) |
| 985 |
{ |
| 986 |
const Number2 test_value_y = |
| 987 |
dim > 1 ? (test_grads_value[2] * shapes[i1][0][1] + |
| 988 |
test_grads_value[1] * shapes[i1][1][1]) : |
| 989 |
test_grads_value[2]; |
| 990 |
const Number2 test_grad_xy = |
| 991 |
dim > 1 ? test_grads_value[0] * shapes[i1][0][1] : |
| 992 |
test_grads_value[0]; |
| 993 |
Number2 test_value_y_2; |
| 994 |
if (n_values > 1) |
| 995 |
test_value_y_2 = dim > 1 ? |
| 996 |
test_grads_value[3] * shapes[i1][0][1] : |
| 997 |
test_grads_value[3]; |
| 998 |
|
| 999 |
Number2 *values_ptr = values + i + i1 * length; |
| 1000 |
Number2 *values_ptr_2 = |
| 1001 |
n_values > 1 ? values_ptr + Utilities::pow(length, dim) : nullptr; |
| 1002 |
for (int i0 = 0; i0 < length; ++i0) |
| 1003 |
{ |
| 1004 |
if (add) |
| 1005 |
values_ptr[i0] += shape_values_x[i0] * test_value_y; |
| 1006 |
else |
| 1007 |
values_ptr[i0] = shape_values_x[i0] * test_value_y; |
| 1008 |
values_ptr[i0] += shape_derivs_x[i0] * test_grad_xy; |
| 1009 |
if (n_values > 1) |
| 1010 |
{ |
| 1011 |
if (add) |
| 1012 |
values_ptr_2[i0] += shape_values_x[i0] * test_value_y_2; |
| 1013 |
else |
| 1014 |
values_ptr_2[i0] = shape_values_x[i0] * test_value_y_2; |
| 1015 |
} |
| 1016 |
} |
| 1017 |
} |
| 1018 |
i += (dim > 1 ? length * length : length); |
| 1019 |
} |
| 1020 |
else |
| 1021 |
{ |
| 1022 |
for (int i1 = 0; i1 < (dim > 1 ? n_shapes_runtime : 1); ++i1) |
| 1023 |
{ |
| 1024 |
const Number2 test_value_y = |
| 1025 |
dim > 1 ? (test_grads_value[2] * shapes[i1][0][1] + |
| 1026 |
test_grads_value[1] * shapes[i1][1][1]) : |
| 1027 |
test_grads_value[2]; |
| 1028 |
const Number2 test_grad_xy = |
| 1029 |
dim > 1 ? test_grads_value[0] * shapes[i1][0][1] : |
| 1030 |
test_grads_value[0]; |
| 1031 |
Number2 test_value_y_2; |
| 1032 |
if (n_values > 1) |
| 1033 |
test_value_y_2 = dim > 1 ? |
| 1034 |
test_grads_value[3] * shapes[i1][0][1] : |
| 1035 |
test_grads_value[3]; |
| 1036 |
|
| 1037 |
Number2 *values_ptr = values + i + i1 * n_shapes_runtime; |
| 1038 |
Number2 *values_ptr_2 = |
| 1039 |
n_values > 1 ? |
| 1040 |
values_ptr + Utilities::fixed_power<dim>(n_shapes_runtime) : |
| 1041 |
nullptr; |
| 1042 |
for (int i0 = 0; i0 < n_shapes_runtime; ++i0) |
| 1043 |
{ |
| 1044 |
if (add) |
| 1045 |
values_ptr[i0] += shapes[i0][0][0] * test_value_y; |
| 1046 |
else |
| 1047 |
values_ptr[i0] = shapes[i0][0][0] * test_value_y; |
| 1048 |
values_ptr[i0] += shapes[i0][1][0] * test_grad_xy; |
| 1049 |
if (n_values > 1) |
| 1050 |
{ |
| 1051 |
if (add) |
| 1052 |
values_ptr_2[i0] += shapes[i0][0][0] * test_value_y_2; |
| 1053 |
else |
| 1054 |
values_ptr_2[i0] = shapes[i0][0][0] * test_value_y_2; |
| 1055 |
} |
| 1056 |
} |
| 1057 |
} |
| 1058 |
i += (dim > 1 ? n_shapes_runtime * n_shapes_runtime : n_shapes_runtime); |
| 1059 |
} |
| 1060 |
} |
| 1061 |
|
| 1062 |
|
| 1063 |
|
| 1064 |
/** |
| 1065 |
* Same as evaluate_tensor_product_value_and_gradient_shapes() but for |
| 1066 |
* integration. |
| 1067 |
*/ |
| 1068 |
template <int dim, |
| 1069 |
typename Number, |
| 1070 |
typename Number2, |
| 1071 |
bool add, |
| 1072 |
int n_values = 1> |
| 1073 |
inline void |
| 1074 |
integrate_add_tensor_product_value_and_gradient_shapes( |
| 1075 |
const dealii::ndarray<Number, 2, dim> *shapes, |
| 1076 |
const int n_shapes, |
| 1077 |
const Number2 *value, |
| 1078 |
const Tensor<1, dim, Number2> &gradient, |
| 1079 |
Number2 *values) |
| 1080 |
{ |
| 1081 |
static_assert(0 <= dim && dim <= 3, "Only dim=0,1,2,3 implemented"); |
| 1082 |
static_assert(1 <= n_values && n_values <= 2, |
| 1083 |
"Only n_values=1,2 implemented"); |
| 1084 |
|
| 1085 |
// Note that 'add' is a template argument, so the compiler will remove |
| 1086 |
// these checks |
| 1087 |
if (dim == 0) |
| 1088 |
{ |
| 1089 |
if (add) |
| 1090 |
values[0] += value[0]; |
| 1091 |
else |
| 1092 |
values[0] = value[0]; |
| 1093 |
if (n_values > 1) |
| 1094 |
{ |
| 1095 |
if (add) |
| 1096 |
values[1] += value[1]; |
| 1097 |
else |
| 1098 |
values[1] = value[1]; |
| 1099 |
} |
| 1100 |
return; |
| 1101 |
} |
| 1102 |
|
| 1103 |
// Implement the transpose of the function above |
| 1104 |
// as in evaluate, use `int` type to produce better code in this context |
| 1105 |
std::array<Number2, 2 + n_values> test_grads_value; |
| 1106 |
for (int i2 = 0, i = 0; i2 < (dim > 2 ? n_shapes : 1); ++i2) |
| 1107 |
{ |
| 1108 |
// test grad x |
| 1109 |
test_grads_value[0] = |
| 1110 |
dim > 2 ? gradient[0] * shapes[i2][0][2] : gradient[0]; |
| 1111 |
// test grad y |
| 1112 |
test_grads_value[1] = dim > 2 ? gradient[1] * shapes[i2][0][2] : |
| 1113 |
(dim > 1 ? gradient[1] : Number2()); |
| 1114 |
// test value z |
| 1115 |
test_grads_value[2] = |
| 1116 |
dim > 2 ? |
| 1117 |
(value[0] * shapes[i2][0][2] + gradient[2] * shapes[i2][1][2]) : |
| 1118 |
value[0]; |
| 1119 |
|
| 1120 |
if (n_values > 1) |
| 1121 |
test_grads_value[3] = |
| 1122 |
dim > 2 ? value[1] * shapes[i2][0][2] : value[1]; |
| 1123 |
// Generate separate code with known loop bounds for the most common |
| 1124 |
// cases |
| 1125 |
if (n_shapes == 2) |
| 1126 |
do_apply_test_functions_xy<dim, 2, Number2, Number, add, n_values>( |
| 1127 |
values, shapes, test_grads_value, n_shapes, i); |
| 1128 |
else if (n_shapes == 3) |
| 1129 |
do_apply_test_functions_xy<dim, 3, Number2, Number, add, n_values>( |
| 1130 |
values, shapes, test_grads_value, n_shapes, i); |
| 1131 |
else if (n_shapes == 4) |
| 1132 |
do_apply_test_functions_xy<dim, 4, Number2, Number, add, n_values>( |
| 1133 |
values, shapes, test_grads_value, n_shapes, i); |
| 1134 |
else if (n_shapes == 5) |
| 1135 |
do_apply_test_functions_xy<dim, 5, Number2, Number, add, n_values>( |
| 1136 |
values, shapes, test_grads_value, n_shapes, i); |
| 1137 |
else if (n_shapes == 6) |
| 1138 |
do_apply_test_functions_xy<dim, 6, Number2, Number, add, n_values>( |
| 1139 |
values, shapes, test_grads_value, n_shapes, i); |
| 1140 |
else |
| 1141 |
do_apply_test_functions_xy<dim, -1, Number2, Number, add, n_values>( |
| 1142 |
values, shapes, test_grads_value, n_shapes, i); |
| 1143 |
} |
| 1144 |
} |
| 1145 |
|
| 1146 |
|
| 1147 |
|
| 1148 |
/** |
| 1149 |
* Specializes @p integrate_add_tensor_product_value_and_gradient_shapes() for linear |
| 1150 |
* polynomials which massively reduces the necessary instructions. |
| 1151 |
*/ |
| 1152 |
template <int dim, |
| 1153 |
typename Number, |
| 1154 |
typename Number2, |
| 1155 |
bool add, |
| 1156 |
int n_values = 1> |
| 1157 |
inline void |
| 1158 |
integrate_add_tensor_product_value_and_gradient_linear( |
| 1159 |
const Number2 *value, |
| 1160 |
const Tensor<1, dim, Number2> &gradient, |
| 1161 |
Number2 *values, |
| 1162 |
const Point<dim, Number> &p) |
| 1163 |
{ |
| 1164 |
static_assert(0 <= dim && dim <= 3, "Only dim=0,1,2,3 implemented"); |
| 1165 |
static_assert(1 <= n_values && n_values <= 2, |
| 1166 |
"Only n_values=1,2 implemented"); |
| 1167 |
|
| 1168 |
// Note that 'add' is a template argument, so the compiler will remove |
| 1169 |
// these checks |
| 1170 |
if (dim == 0) |
| 1171 |
{ |
| 1172 |
if (add) |
| 1173 |
values[0] += value[0]; |
| 1174 |
else |
| 1175 |
values[0] = value[0]; |
| 1176 |
if (n_values > 1) |
| 1177 |
{ |
| 1178 |
if (add) |
| 1179 |
values[1] += value[1]; |
| 1180 |
else |
| 1181 |
values[1] = value[1]; |
| 1182 |
} |
| 1183 |
} |
| 1184 |
else if (dim == 1) |
| 1185 |
{ |
| 1186 |
const Number2 difference = value[0] * p[0] + gradient[0]; |
| 1187 |
if (add) |
| 1188 |
{ |
| 1189 |
values[0] += value[0] - difference; |
| 1190 |
values[1] += difference; |
| 1191 |
} |
| 1192 |
else |
| 1193 |
{ |
| 1194 |
values[0] = value[0] - difference; |
| 1195 |
values[1] = difference; |
| 1196 |
} |
| 1197 |
if (n_values > 1) |
| 1198 |
{ |
| 1199 |
const Number2 product = value[1] * p[0]; |
| 1200 |
if (add) |
| 1201 |
{ |
| 1202 |
values[2] += value[1] - product; |
| 1203 |
values[3] += product; |
| 1204 |
} |
| 1205 |
else |
| 1206 |
{ |
| 1207 |
values[2] = value[1] - product; |
| 1208 |
values[3] = product; |
| 1209 |
} |
| 1210 |
} |
| 1211 |
} |
| 1212 |
else if (dim == 2) |
| 1213 |
{ |
| 1214 |
const Number2 test_value_y1 = value[0] * p[1] + gradient[1]; |
| 1215 |
const Number2 test_value_y0 = value[0] - test_value_y1; |
| 1216 |
const Number2 test_grad_xy1 = gradient[0] * p[1]; |
| 1217 |
const Number2 test_grad_xy0 = gradient[0] - test_grad_xy1; |
| 1218 |
const Number2 value0 = p[0] * test_value_y0 + test_grad_xy0; |
| 1219 |
const Number2 value1 = p[0] * test_value_y1 + test_grad_xy1; |
| 1220 |
|
| 1221 |
if (add) |
| 1222 |
{ |
| 1223 |
values[0] += test_value_y0 - value0; |
| 1224 |
values[1] += value0; |
| 1225 |
values[2] += test_value_y1 - value1; |
| 1226 |
values[3] += value1; |
| 1227 |
} |
| 1228 |
else |
| 1229 |
{ |
| 1230 |
values[0] = test_value_y0 - value0; |
| 1231 |
values[1] = value0; |
| 1232 |
values[2] = test_value_y1 - value1; |
| 1233 |
values[3] = value1; |
| 1234 |
} |
| 1235 |
|
| 1236 |
if (n_values > 1) |
| 1237 |
{ |
| 1238 |
const Number2 test_value_y1_2 = value[1] * p[1]; |
| 1239 |
const Number2 test_value_y0_2 = value[1] - test_value_y1_2; |
| 1240 |
const Number2 value0_2 = p[0] * test_value_y0_2; |
| 1241 |
const Number2 value1_2 = p[0] * test_value_y1_2; |
| 1242 |
|
| 1243 |
if (add) |
| 1244 |
{ |
| 1245 |
values[4] += test_value_y0_2 - value0_2; |
| 1246 |
values[5] += value0_2; |
| 1247 |
values[6] += test_value_y1_2 - value1_2; |
| 1248 |
values[7] += value1_2; |
| 1249 |
} |
| 1250 |
else |
| 1251 |
{ |
| 1252 |
values[4] = test_value_y0_2 - value0_2; |
| 1253 |
values[5] = value0_2; |
| 1254 |
values[6] = test_value_y1_2 - value1_2; |
| 1255 |
values[7] = value1_2; |
| 1256 |
} |
| 1257 |
} |
| 1258 |
} |
| 1259 |
else if (dim == 3) |
| 1260 |
{ |
| 1261 |
Assert(n_values == 1, ExcNotImplemented()); |
| 1262 |
|
| 1263 |
const Number2 test_value_z1 = value[0] * p[2] + gradient[2]; |
| 1264 |
const Number2 test_value_z0 = value[0] - test_value_z1; |
| 1265 |
const Number2 test_grad_x1 = gradient[0] * p[2]; |
| 1266 |
const Number2 test_grad_x0 = gradient[0] - test_grad_x1; |
| 1267 |
const Number2 test_grad_y1 = gradient[1] * p[2]; |
| 1268 |
const Number2 test_grad_y0 = gradient[1] - test_grad_y1; |
| 1269 |
|
| 1270 |
const Number2 test_value_y01 = test_value_z0 * p[1] + test_grad_y0; |
| 1271 |
const Number2 test_value_y00 = test_value_z0 - test_value_y01; |
| 1272 |
const Number2 test_grad_xy01 = test_grad_x0 * p[1]; |
| 1273 |
const Number2 test_grad_xy00 = test_grad_x0 - test_grad_xy01; |
| 1274 |
const Number2 test_value_y11 = test_value_z1 * p[1] + test_grad_y1; |
| 1275 |
const Number2 test_value_y10 = test_value_z1 - test_value_y11; |
| 1276 |
const Number2 test_grad_xy11 = test_grad_x1 * p[1]; |
| 1277 |
const Number2 test_grad_xy10 = test_grad_x1 - test_grad_xy11; |
| 1278 |
|
| 1279 |
const Number2 value00 = p[0] * test_value_y00 + test_grad_xy00; |
| 1280 |
const Number2 value01 = p[0] * test_value_y01 + test_grad_xy01; |
| 1281 |
const Number2 value10 = p[0] * test_value_y10 + test_grad_xy10; |
| 1282 |
const Number2 value11 = p[0] * test_value_y11 + test_grad_xy11; |
| 1283 |
|
| 1284 |
if (add) |
| 1285 |
{ |
| 1286 |
values[0] += test_value_y00 - value00; |
| 1287 |
values[1] += value00; |
| 1288 |
values[2] += test_value_y01 - value01; |
| 1289 |
values[3] += value01; |
| 1290 |
values[4] += test_value_y10 - value10; |
| 1291 |
values[5] += value10; |
| 1292 |
values[6] += test_value_y11 - value11; |
| 1293 |
values[7] += value11; |
| 1294 |
} |
| 1295 |
else |
| 1296 |
{ |
| 1297 |
values[0] = test_value_y00 - value00; |
| 1298 |
values[1] = value00; |
| 1299 |
values[2] = test_value_y01 - value01; |
| 1300 |
values[3] = value01; |
| 1301 |
values[4] = test_value_y10 - value10; |
| 1302 |
values[5] = value10; |
| 1303 |
values[6] = test_value_y11 - value11; |
| 1304 |
values[7] = value11; |
| 1305 |
} |
| 1306 |
} |
| 1307 |
} |
| 1308 |
|
| 1309 |
|
| 1310 |
|
| 1311 |
/** |
| 1312 |
* Calls the correct @p integrate_add_tensor_product_value_and_gradient_...() |
| 1313 |
* function depending on if values should be added to or set and if |
| 1314 |
* polynomials are linear. |
| 1315 |
*/ |
| 1316 |
template <bool is_linear, |
| 1317 |
int dim, |
| 1318 |
typename Number, |
| 1319 |
typename Number2, |
| 1320 |
int n_values = 1> |
| 1321 |
inline void |
| 1322 |
integrate_tensor_product_value_and_gradient( |
| 1323 |
const dealii::ndarray<Number, 2, dim> *shapes, |
| 1324 |
const unsigned int n_shapes, |
| 1325 |
const Number2 *value, |
| 1326 |
const Tensor<1, dim, Number2> &gradient, |
| 1327 |
Number2 *values, |
| 1328 |
const Point<dim, Number> &p, |
| 1329 |
const bool do_add) |
| 1330 |
{ |
| 1331 |
if (do_add) |
| 1332 |
{ |
| 1333 |
if (is_linear) |
| 1334 |
internal::integrate_add_tensor_product_value_and_gradient_linear< |
| 1335 |
dim, |
| 1336 |
Number, |
| 1337 |
Number2, |
| 1338 |
true, |
| 1339 |
n_values>(value, gradient, values, p); |
| 1340 |
else |
| 1341 |
internal::integrate_add_tensor_product_value_and_gradient_shapes< |
| 1342 |
dim, |
| 1343 |
Number, |
| 1344 |
Number2, |
| 1345 |
true, |
| 1346 |
n_values>(shapes, n_shapes, value, gradient, values); |
| 1347 |
} |
| 1348 |
else |
| 1349 |
{ |
| 1350 |
if (is_linear) |
| 1351 |
internal::integrate_add_tensor_product_value_and_gradient_linear< |
| 1352 |
dim, |
| 1353 |
Number, |
| 1354 |
Number2, |
| 1355 |
false, |
| 1356 |
n_values>(value, gradient, values, p); |
| 1357 |
else |
| 1358 |
internal::integrate_add_tensor_product_value_and_gradient_shapes< |
| 1359 |
dim, |
| 1360 |
Number, |
| 1361 |
Number2, |
| 1362 |
false, |
| 1363 |
n_values>(shapes, n_shapes, value, gradient, values); |
| 1364 |
} |
| 1365 |
} |
| 1366 |
|
| 1367 |
|
| 1368 |
|
| 1369 |
/** |
| 1370 |
* Test inner dimensions of tensor product shape functions and accumulate. |
| 1371 |
*/ |
| 1372 |
template <int dim, int length, typename Number2, typename Number, bool add> |
| 1373 |
inline |
| 1374 |
#ifndef DEBUG |
| 1375 |
DEAL_II_ALWAYS_INLINE |
| 1376 |
#endif |
| 1377 |
void |
| 1378 |
do_apply_test_functions_xy_value( |
| 1379 |
Number2 *values, |
| 1380 |
const dealii::ndarray<Number, 2, dim> *shapes, |
| 1381 |
const Number2 &test_value, |
| 1382 |
const int n_shapes_runtime, |
| 1383 |
int &i) |
| 1384 |
{ |
| 1385 |
if (length > 0) |
| 1386 |
{ |
| 1387 |
constexpr unsigned int array_size = length > 0 ? length : 1; |
| 1388 |
std::array<Number, array_size> shape_values_x; |
| 1389 |
for (unsigned int i1 = 0; i1 < array_size; ++i1) |
| 1390 |
shape_values_x[i1] = shapes[i1][0][0]; |
| 1391 |
for (int i1 = 0; i1 < (dim > 1 ? length : 1); ++i1) |
| 1392 |
{ |
| 1393 |
const Number2 test_value_y = |
| 1394 |
dim > 1 ? test_value * shapes[i1][0][1] : test_value; |
| 1395 |
|
| 1396 |
Number2 *values_ptr = values + i + i1 * length; |
| 1397 |
for (int i0 = 0; i0 < length; ++i0) |
| 1398 |
{ |
| 1399 |
if (add) |
| 1400 |
values_ptr[i0] += shape_values_x[i0] * test_value_y; |
| 1401 |
else |
| 1402 |
values_ptr[i0] = shape_values_x[i0] * test_value_y; |
| 1403 |
} |
| 1404 |
} |
| 1405 |
i += (dim > 1 ? length * length : length); |
| 1406 |
} |
| 1407 |
else |
| 1408 |
{ |
| 1409 |
for (int i1 = 0; i1 < (dim > 1 ? n_shapes_runtime : 1); ++i1) |
| 1410 |
{ |
| 1411 |
const Number2 test_value_y = |
| 1412 |
dim > 1 ? test_value * shapes[i1][0][1] : test_value; |
| 1413 |
|
| 1414 |
Number2 *values_ptr = values + i + i1 * n_shapes_runtime; |
| 1415 |
for (int i0 = 0; i0 < n_shapes_runtime; ++i0) |
| 1416 |
{ |
| 1417 |
if (add) |
| 1418 |
values_ptr[i0] += shapes[i0][0][0] * test_value_y; |
| 1419 |
else |
| 1420 |
values_ptr[i0] = shapes[i0][0][0] * test_value_y; |
| 1421 |
} |
| 1422 |
} |
| 1423 |
i += (dim > 1 ? n_shapes_runtime * n_shapes_runtime : n_shapes_runtime); |
| 1424 |
} |
| 1425 |
} |
| 1426 |
|
| 1427 |
|
| 1428 |
|
| 1429 |
/** |
| 1430 |
* Same as evaluate_tensor_product_value_shapes() but for integration. |
| 1431 |
*/ |
| 1432 |
template <int dim, typename Number, typename Number2, bool add> |
| 1433 |
inline void |
| 1434 |
integrate_add_tensor_product_value_shapes( |
| 1435 |
const dealii::ndarray<Number, 2, dim> *shapes, |
| 1436 |
const int n_shapes, |
| 1437 |
const Number2 &value, |
| 1438 |
Number2 *values) |
| 1439 |
{ |
| 1440 |
static_assert(dim >= 0 && dim <= 3, "Only dim=0,1,2,3 implemented"); |
| 1441 |
|
| 1442 |
// as in evaluate, use `int` type to produce better code in this context |
| 1443 |
|
| 1444 |
if (dim == 0) |
| 1445 |
{ |
| 1446 |
if (add) |
| 1447 |
values[0] += value; |
| 1448 |
else |
| 1449 |
values[0] = value; |
| 1450 |
return; |
| 1451 |
} |
| 1452 |
|
| 1453 |
// Implement the transpose of the function above |
| 1454 |
Number2 test_value; |
| 1455 |
for (int i2 = 0, i = 0; i2 < (dim > 2 ? n_shapes : 1); ++i2) |
| 1456 |
{ |
| 1457 |
// test value z |
| 1458 |
test_value = dim > 2 ? value * shapes[i2][0][2] : value; |
| 1459 |
|
| 1460 |
// Generate separate code with known loop bounds for the most common |
| 1461 |
// cases |
| 1462 |
if (n_shapes == 2) |
| 1463 |
do_apply_test_functions_xy_value<dim, 2, Number2, Number, add>( |
| 1464 |
values, shapes, test_value, n_shapes, i); |
| 1465 |
else if (n_shapes == 3) |
| 1466 |
do_apply_test_functions_xy_value<dim, 3, Number2, Number, add>( |
| 1467 |
values, shapes, test_value, n_shapes, i); |
| 1468 |
else if (n_shapes == 4) |
| 1469 |
do_apply_test_functions_xy_value<dim, 4, Number2, Number, add>( |
| 1470 |
values, shapes, test_value, n_shapes, i); |
| 1471 |
else if (n_shapes == 5) |
| 1472 |
do_apply_test_functions_xy_value<dim, 5, Number2, Number, add>( |
| 1473 |
values, shapes, test_value, n_shapes, i); |
| 1474 |
else if (n_shapes == 6) |
| 1475 |
do_apply_test_functions_xy_value<dim, 6, Number2, Number, add>( |
| 1476 |
values, shapes, test_value, n_shapes, i); |
| 1477 |
else |
| 1478 |
do_apply_test_functions_xy_value<dim, -1, Number2, Number, add>( |
| 1479 |
values, shapes, test_value, n_shapes, i); |
| 1480 |
} |
| 1481 |
} |
| 1482 |
|
| 1483 |
|
| 1484 |
|
| 1485 |
/** |
| 1486 |
* Specializes @p integrate_tensor_product_value_shapes() for linear |
| 1487 |
* polynomials which massively reduces the necessary instructions. |
| 1488 |
*/ |
| 1489 |
template <int dim, typename Number, typename Number2, bool add> |
| 1490 |
inline void |
| 1491 |
integrate_add_tensor_product_value_linear(const Number2 &value, |
| 1492 |
Number2 *values, |
| 1493 |
const Point<dim, Number> &p) |
| 1494 |
{ |
| 1495 |
static_assert(dim >= 0 && dim <= 3, "Only dim=0,1,2,3 implemented"); |
| 1496 |
|
| 1497 |
if (dim == 0) |
| 1498 |
{ |
| 1499 |
if (add) |
| 1500 |
values[0] += value; |
| 1501 |
else |
| 1502 |
values[0] = value; |
| 1503 |
} |
| 1504 |
else if (dim == 1) |
| 1505 |
{ |
| 1506 |
const auto x0 = Number(1.) - p[0], x1 = p[0]; |
| 1507 |
|
| 1508 |
if (add) |
| 1509 |
{ |
| 1510 |
values[0] += value * x0; |
| 1511 |
values[1] += value * x1; |
| 1512 |
} |
| 1513 |
else |
| 1514 |
{ |
| 1515 |
values[0] = value * x0; |
| 1516 |
values[1] = value * x1; |
| 1517 |
} |
| 1518 |
} |
| 1519 |
else if (dim == 2) |
| 1520 |
{ |
| 1521 |
const auto x0 = Number(1.) - p[0], x1 = p[0], y0 = Number(1.) - p[1], |
| 1522 |
y1 = p[1]; |
| 1523 |
|
| 1524 |
const auto test_value_y0 = value * y0; |
| 1525 |
const auto test_value_y1 = value * y1; |
| 1526 |
|
| 1527 |
if (add) |
| 1528 |
{ |
| 1529 |
values[0] += x0 * test_value_y0; |
| 1530 |
values[1] += x1 * test_value_y0; |
| 1531 |
values[2] += x0 * test_value_y1; |
| 1532 |
values[3] += x1 * test_value_y1; |
| 1533 |
} |
| 1534 |
else |
| 1535 |
{ |
| 1536 |
values[0] = x0 * test_value_y0; |
| 1537 |
values[1] = x1 * test_value_y0; |
| 1538 |
values[2] = x0 * test_value_y1; |
| 1539 |
values[3] = x1 * test_value_y1; |
| 1540 |
} |
| 1541 |
} |
| 1542 |
else if (dim == 3) |
| 1543 |
{ |
| 1544 |
const auto x0 = Number(1.) - p[0], x1 = p[0], y0 = Number(1.) - p[1], |
| 1545 |
y1 = p[1], z0 = Number(1.) - p[2], z1 = p[2]; |
| 1546 |
|
| 1547 |
const auto test_value_z0 = value * z0; |
| 1548 |
const auto test_value_z1 = value * z1; |
| 1549 |
|
| 1550 |
const auto test_value_y00 = test_value_z0 * y0; |
| 1551 |
const auto test_value_y01 = test_value_z0 * y1; |
| 1552 |
const auto test_value_y10 = test_value_z1 * y0; |
| 1553 |
const auto test_value_y11 = test_value_z1 * y1; |
| 1554 |
|
| 1555 |
if (add) |
| 1556 |
{ |
| 1557 |
values[0] += x0 * test_value_y00; |
| 1558 |
values[1] += x1 * test_value_y00; |
| 1559 |
values[2] += x0 * test_value_y01; |
| 1560 |
values[3] += x1 * test_value_y01; |
| 1561 |
values[4] += x0 * test_value_y10; |
| 1562 |
values[5] += x1 * test_value_y10; |
| 1563 |
values[6] += x0 * test_value_y11; |
| 1564 |
values[7] += x1 * test_value_y11; |
| 1565 |
} |
| 1566 |
else |
| 1567 |
{ |
| 1568 |
values[0] = x0 * test_value_y00; |
| 1569 |
values[1] = x1 * test_value_y00; |
| 1570 |
values[2] = x0 * test_value_y01; |
| 1571 |
values[3] = x1 * test_value_y01; |
| 1572 |
values[4] = x0 * test_value_y10; |
| 1573 |
values[5] = x1 * test_value_y10; |
| 1574 |
values[6] = x0 * test_value_y11; |
| 1575 |
values[7] = x1 * test_value_y11; |
| 1576 |
} |
| 1577 |
} |
| 1578 |
} |
| 1579 |
|
| 1580 |
|
| 1581 |
|
| 1582 |
/** |
| 1583 |
* Calls the correct @p integrate_add_tensor_product_value_...() |
| 1584 |
* function depending on if values should be added to or set and if |
| 1585 |
* polynomials are linear. |
| 1586 |
*/ |
| 1587 |
template <bool is_linear, int dim, typename Number, typename Number2> |
| 1588 |
inline void |
| 1589 |
integrate_tensor_product_value(const dealii::ndarray<Number, 2, dim> *shapes, |
| 1590 |
const unsigned int n_shapes, |
| 1591 |
const Number2 &value, |
| 1592 |
Number2 *values, |
| 1593 |
const Point<dim, Number> &p, |
| 1594 |
const bool do_add) |
| 1595 |
{ |
| 1596 |
if (do_add) |
| 1597 |
{ |
| 1598 |
if (is_linear) |
| 1599 |
internal::integrate_add_tensor_product_value_linear<dim, |
| 1600 |
Number, |
| 1601 |
Number2, |
| 1602 |
true>(value, |
| 1603 |
values, |
| 1604 |
p); |
| 1605 |
else |
| 1606 |
internal::integrate_add_tensor_product_value_shapes<dim, |
| 1607 |
Number, |
| 1608 |
Number2, |
| 1609 |
true>(shapes, |
| 1610 |
n_shapes, |
| 1611 |
value, |
| 1612 |
values); |
| 1613 |
} |
| 1614 |
else |
| 1615 |
{ |
| 1616 |
if (is_linear) |
| 1617 |
internal::integrate_add_tensor_product_value_linear<dim, |
| 1618 |
Number, |
| 1619 |
Number2, |
| 1620 |
false>(value, |
| 1621 |
values, |
| 1622 |
p); |
| 1623 |
else |
| 1624 |
internal::integrate_add_tensor_product_value_shapes<dim, |
| 1625 |
Number, |
| 1626 |
Number2, |
| 1627 |
false>(shapes, |
| 1628 |
n_shapes, |
| 1629 |
value, |
| 1630 |
values); |
| 1631 |
} |
| 1632 |
} |
| 1633 |
} // end of namespace internal |
| 1634 |
|
| 1635 |
|
| 1636 |
DEAL_II_NAMESPACE_CLOSE |
| 1637 |
|
| 1638 |
#endif |