ESPResSo
Extensible Simulation Package for Research on Soft Matter Systems
Loading...
Searching...
No Matches
DiffusiveFluxKernelThermalized_single_precision.cpp
Go to the documentation of this file.
1//======================================================================================================================
2//
3// This file is part of waLBerla. waLBerla is free software: you can
4// redistribute it and/or modify it under the terms of the GNU General Public
5// License as published by the Free Software Foundation, either version 3 of
6// the License, or (at your option) any later version.
7//
8// waLBerla is distributed in the hope that it will be useful, but WITHOUT
9// ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
10// FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
11// for more details.
12//
13// You should have received a copy of the GNU General Public License along
14// with waLBerla (see COPYING.txt). If not, see <http://www.gnu.org/licenses/>.
15//
16//! \\file DiffusiveFluxKernelThermalized_single_precision.cpp
17//! \\author pystencils
18//======================================================================================================================
19
20// kernel generated with pystencils v1.4+1.ge851f4e, lbmpy v1.4+1.ge9efe34, sympy v1.12.1, lbmpy_walberla/pystencils_walberla from waLBerla commit 3247aa7395049ca5bfb69d34d55e45db19fa439c
21
22#include <cmath>
23
24#include "DiffusiveFluxKernelThermalized_single_precision.h"
25#include "core/DataTypes.h"
26#include "core/Macros.h"
27
28#include "philox_rand.h"
29
30#define FUNC_PREFIX
31
32#if (defined WALBERLA_CXX_COMPILER_IS_GNU) || (defined WALBERLA_CXX_COMPILER_IS_CLANG)
33#pragma GCC diagnostic push
34#pragma GCC diagnostic ignored "-Wfloat-equal"
35#pragma GCC diagnostic ignored "-Wshadow"
36#pragma GCC diagnostic ignored "-Wconversion"
37#pragma GCC diagnostic ignored "-Wunused-variable"
38#endif
39
40#if (defined WALBERLA_CXX_COMPILER_IS_INTEL)
41#pragma warning push
42#pragma warning(disable : 1599)
43#endif
44
45using namespace std;
46
47namespace walberla {
48namespace pystencils {
49
50namespace internal_13067439141d91943f586adb1c937d5b {
51static FUNC_PREFIX void diffusivefluxkernelthermalized_single_precision_diffusivefluxkernelthermalized_single_precision(float D, float *RESTRICT const _data_j, float *RESTRICT const _data_rho, int64_t const _size_j_0, int64_t const _size_j_1, int64_t const _size_j_2, int64_t const _stride_j_0, int64_t const _stride_j_1, int64_t const _stride_j_2, int64_t const _stride_j_3, int64_t const _stride_rho_0, int64_t const _stride_rho_1, int64_t const _stride_rho_2, uint32_t block_offset_0, uint32_t block_offset_1, uint32_t block_offset_2, uint32_t field_size_0, uint32_t field_size_1, uint32_t field_size_2, uint32_t seed, uint32_t time_step) {
52#pragma omp parallel
53 {
54#pragma omp for schedule(static)
55 for (int64_t ctr_2 = 0; ctr_2 < _size_j_2; ctr_2 += 1) {
56 for (int64_t ctr_1 = 0; ctr_1 < _size_j_1; ctr_1 += 1) {
57 for (int64_t ctr_0 = 1; ctr_0 < _size_j_0; ctr_0 += 1) {
58 if (ctr_1 > 0 && ctr_2 > 0 && ctr_1 < _size_j_1 - 1 && ctr_2 < _size_j_2 - 1) {
59
60 float random_3_0;
61 float random_3_1;
62 float random_3_2;
63 float random_3_3;
64 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 3, seed, random_3_0, random_3_1, random_3_2, random_3_3);
65
66 float random_2_0;
67 float random_2_1;
68 float random_2_2;
69 float random_2_3;
70 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 2, seed, random_2_0, random_2_1, random_2_2, random_2_3);
71
72 float random_1_0;
73 float random_1_1;
74 float random_1_2;
75 float random_1_3;
76 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 1, seed, random_1_0, random_1_1, random_1_2, random_1_3);
77
78 float random_0_0;
79 float random_0_1;
80 float random_0_2;
81 float random_0_3;
82 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 0, seed, random_0_0, random_0_1, random_0_2, random_0_3);
83
84 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2] = D * (_data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] - _data_rho[_stride_rho_0 * ctr_0 - _stride_rho_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2]) * 0.16292407789368385f + (random_0_0 - 0.5f) * powf(D * (0.5f * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] + 0.5f * _data_rho[_stride_rho_0 * ctr_0 - _stride_rho_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2]), 0.5f) * 1.977416969040271f;
85 }
86 if (ctr_1 > 0 && ctr_2 > 0 && ctr_0 < _size_j_0 - 1 && ctr_2 < _size_j_2 - 1) {
87
88 float random_3_0;
89 float random_3_1;
90 float random_3_2;
91 float random_3_3;
92 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 3, seed, random_3_0, random_3_1, random_3_2, random_3_3);
93
94 float random_2_0;
95 float random_2_1;
96 float random_2_2;
97 float random_2_3;
98 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 2, seed, random_2_0, random_2_1, random_2_2, random_2_3);
99
100 float random_1_0;
101 float random_1_1;
102 float random_1_2;
103 float random_1_3;
104 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 1, seed, random_1_0, random_1_1, random_1_2, random_1_3);
105
106 float random_0_0;
107 float random_0_1;
108 float random_0_2;
109 float random_0_3;
110 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 0, seed, random_0_0, random_0_1, random_0_2, random_0_3);
111
112 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + _stride_j_3] = D * (_data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] - _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 - _stride_rho_1 + _stride_rho_2 * ctr_2]) * 0.16292407789368385f + (random_0_1 - 0.5f) * powf(D * (0.5f * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] + 0.5f * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 - _stride_rho_1 + _stride_rho_2 * ctr_2]), 0.5f) * 1.977416969040271f;
113 }
114 if (ctr_1 > 0 && ctr_2 > 0 && ctr_0 < _size_j_0 - 1 && ctr_1 < _size_j_1 - 1) {
115
116 float random_3_0;
117 float random_3_1;
118 float random_3_2;
119 float random_3_3;
120 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 3, seed, random_3_0, random_3_1, random_3_2, random_3_3);
121
122 float random_2_0;
123 float random_2_1;
124 float random_2_2;
125 float random_2_3;
126 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 2, seed, random_2_0, random_2_1, random_2_2, random_2_3);
127
128 float random_1_0;
129 float random_1_1;
130 float random_1_2;
131 float random_1_3;
132 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 1, seed, random_1_0, random_1_1, random_1_2, random_1_3);
133
134 float random_0_0;
135 float random_0_1;
136 float random_0_2;
137 float random_0_3;
138 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 0, seed, random_0_0, random_0_1, random_0_2, random_0_3);
139
140 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 2 * _stride_j_3] = D * (-_data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2 - _stride_rho_2] + _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2]) * 0.16292407789368385f + (random_0_2 - 0.5f) * powf(D * (0.5f * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2 - _stride_rho_2] + 0.5f * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2]), 0.5f) * 1.977416969040271f;
141 }
142 if (ctr_1 > 0 && ctr_2 > 0 && ctr_2 < _size_j_2 - 1) {
143
144 float random_3_0;
145 float random_3_1;
146 float random_3_2;
147 float random_3_3;
148 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 3, seed, random_3_0, random_3_1, random_3_2, random_3_3);
149
150 float random_2_0;
151 float random_2_1;
152 float random_2_2;
153 float random_2_3;
154 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 2, seed, random_2_0, random_2_1, random_2_2, random_2_3);
155
156 float random_1_0;
157 float random_1_1;
158 float random_1_2;
159 float random_1_3;
160 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 1, seed, random_1_0, random_1_1, random_1_2, random_1_3);
161
162 float random_0_0;
163 float random_0_1;
164 float random_0_2;
165 float random_0_3;
166 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 0, seed, random_0_0, random_0_1, random_0_2, random_0_3);
167
168 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 3 * _stride_j_3] = D * (_data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] - _data_rho[_stride_rho_0 * ctr_0 - _stride_rho_0 + _stride_rho_1 * ctr_1 - _stride_rho_1 + _stride_rho_2 * ctr_2]) * 0.11520472029718914f + (random_0_3 - 0.5f) * powf(D * (0.5f * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] + 0.5f * _data_rho[_stride_rho_0 * ctr_0 - _stride_rho_0 + _stride_rho_1 * ctr_1 - _stride_rho_1 + _stride_rho_2 * ctr_2]), 0.5f) * 1.6628028407278295f;
169 }
170 if (ctr_2 > 0 && ctr_1 < _size_j_1 - 1 && ctr_2 < _size_j_2 - 1) {
171
172 float random_3_0;
173 float random_3_1;
174 float random_3_2;
175 float random_3_3;
176 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 3, seed, random_3_0, random_3_1, random_3_2, random_3_3);
177
178 float random_2_0;
179 float random_2_1;
180 float random_2_2;
181 float random_2_3;
182 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 2, seed, random_2_0, random_2_1, random_2_2, random_2_3);
183
184 float random_1_0;
185 float random_1_1;
186 float random_1_2;
187 float random_1_3;
188 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 1, seed, random_1_0, random_1_1, random_1_2, random_1_3);
189
190 float random_0_0;
191 float random_0_1;
192 float random_0_2;
193 float random_0_3;
194 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 0, seed, random_0_0, random_0_1, random_0_2, random_0_3);
195
196 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 4 * _stride_j_3] = D * (_data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] - _data_rho[_stride_rho_0 * ctr_0 - _stride_rho_0 + _stride_rho_1 * ctr_1 + _stride_rho_1 + _stride_rho_2 * ctr_2]) * 0.11520472029718914f + (random_1_0 - 0.5f) * powf(D * (0.5f * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] + 0.5f * _data_rho[_stride_rho_0 * ctr_0 - _stride_rho_0 + _stride_rho_1 * ctr_1 + _stride_rho_1 + _stride_rho_2 * ctr_2]), 0.5f) * 1.6628028407278295f;
197 }
198 if (ctr_1 > 0 && ctr_2 > 0 && ctr_1 < _size_j_1 - 1) {
199
200 float random_3_0;
201 float random_3_1;
202 float random_3_2;
203 float random_3_3;
204 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 3, seed, random_3_0, random_3_1, random_3_2, random_3_3);
205
206 float random_2_0;
207 float random_2_1;
208 float random_2_2;
209 float random_2_3;
210 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 2, seed, random_2_0, random_2_1, random_2_2, random_2_3);
211
212 float random_1_0;
213 float random_1_1;
214 float random_1_2;
215 float random_1_3;
216 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 1, seed, random_1_0, random_1_1, random_1_2, random_1_3);
217
218 float random_0_0;
219 float random_0_1;
220 float random_0_2;
221 float random_0_3;
222 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 0, seed, random_0_0, random_0_1, random_0_2, random_0_3);
223
224 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 5 * _stride_j_3] = D * (_data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] - _data_rho[_stride_rho_0 * ctr_0 - _stride_rho_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2 - _stride_rho_2]) * 0.11520472029718914f + (random_1_1 - 0.5f) * powf(D * (0.5f * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] + 0.5f * _data_rho[_stride_rho_0 * ctr_0 - _stride_rho_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2 - _stride_rho_2]), 0.5f) * 1.6628028407278295f;
225 }
226 if (ctr_1 > 0 && ctr_1 < _size_j_1 - 1 && ctr_2 < _size_j_2 - 1) {
227
228 float random_3_0;
229 float random_3_1;
230 float random_3_2;
231 float random_3_3;
232 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 3, seed, random_3_0, random_3_1, random_3_2, random_3_3);
233
234 float random_2_0;
235 float random_2_1;
236 float random_2_2;
237 float random_2_3;
238 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 2, seed, random_2_0, random_2_1, random_2_2, random_2_3);
239
240 float random_1_0;
241 float random_1_1;
242 float random_1_2;
243 float random_1_3;
244 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 1, seed, random_1_0, random_1_1, random_1_2, random_1_3);
245
246 float random_0_0;
247 float random_0_1;
248 float random_0_2;
249 float random_0_3;
250 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 0, seed, random_0_0, random_0_1, random_0_2, random_0_3);
251
252 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 6 * _stride_j_3] = D * (_data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] - _data_rho[_stride_rho_0 * ctr_0 - _stride_rho_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2 + _stride_rho_2]) * 0.11520472029718914f + (random_1_2 - 0.5f) * powf(D * (0.5f * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] + 0.5f * _data_rho[_stride_rho_0 * ctr_0 - _stride_rho_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2 + _stride_rho_2]), 0.5f) * 1.6628028407278295f;
253 }
254 if (ctr_1 > 0 && ctr_2 > 0 && ctr_0 < _size_j_0 - 1) {
255
256 float random_3_0;
257 float random_3_1;
258 float random_3_2;
259 float random_3_3;
260 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 3, seed, random_3_0, random_3_1, random_3_2, random_3_3);
261
262 float random_2_0;
263 float random_2_1;
264 float random_2_2;
265 float random_2_3;
266 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 2, seed, random_2_0, random_2_1, random_2_2, random_2_3);
267
268 float random_1_0;
269 float random_1_1;
270 float random_1_2;
271 float random_1_3;
272 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 1, seed, random_1_0, random_1_1, random_1_2, random_1_3);
273
274 float random_0_0;
275 float random_0_1;
276 float random_0_2;
277 float random_0_3;
278 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 0, seed, random_0_0, random_0_1, random_0_2, random_0_3);
279
280 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 7 * _stride_j_3] = D * (_data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] - _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 - _stride_rho_1 + _stride_rho_2 * ctr_2 - _stride_rho_2]) * 0.11520472029718914f + (random_1_3 - 0.5f) * powf(D * (0.5f * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] + 0.5f * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 - _stride_rho_1 + _stride_rho_2 * ctr_2 - _stride_rho_2]), 0.5f) * 1.6628028407278295f;
281 }
282 if (ctr_1 > 0 && ctr_0 < _size_j_0 - 1 && ctr_2 < _size_j_2 - 1) {
283
284 float random_3_0;
285 float random_3_1;
286 float random_3_2;
287 float random_3_3;
288 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 3, seed, random_3_0, random_3_1, random_3_2, random_3_3);
289
290 float random_2_0;
291 float random_2_1;
292 float random_2_2;
293 float random_2_3;
294 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 2, seed, random_2_0, random_2_1, random_2_2, random_2_3);
295
296 float random_1_0;
297 float random_1_1;
298 float random_1_2;
299 float random_1_3;
300 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 1, seed, random_1_0, random_1_1, random_1_2, random_1_3);
301
302 float random_0_0;
303 float random_0_1;
304 float random_0_2;
305 float random_0_3;
306 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 0, seed, random_0_0, random_0_1, random_0_2, random_0_3);
307
308 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 8 * _stride_j_3] = D * (_data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] - _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 - _stride_rho_1 + _stride_rho_2 * ctr_2 + _stride_rho_2]) * 0.11520472029718914f + (random_2_0 - 0.5f) * powf(D * (0.5f * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] + 0.5f * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 - _stride_rho_1 + _stride_rho_2 * ctr_2 + _stride_rho_2]), 0.5f) * 1.6628028407278295f;
309 }
310 if (ctr_1 > 0 && ctr_2 > 0) {
311
312 float random_3_0;
313 float random_3_1;
314 float random_3_2;
315 float random_3_3;
316 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 3, seed, random_3_0, random_3_1, random_3_2, random_3_3);
317
318 float random_2_0;
319 float random_2_1;
320 float random_2_2;
321 float random_2_3;
322 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 2, seed, random_2_0, random_2_1, random_2_2, random_2_3);
323
324 float random_1_0;
325 float random_1_1;
326 float random_1_2;
327 float random_1_3;
328 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 1, seed, random_1_0, random_1_1, random_1_2, random_1_3);
329
330 float random_0_0;
331 float random_0_1;
332 float random_0_2;
333 float random_0_3;
334 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 0, seed, random_0_0, random_0_1, random_0_2, random_0_3);
335
336 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 9 * _stride_j_3] = D * (_data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] - _data_rho[_stride_rho_0 * ctr_0 - _stride_rho_0 + _stride_rho_1 * ctr_1 - _stride_rho_1 + _stride_rho_2 * ctr_2 - _stride_rho_2]) * 0.09406426022938992f + (random_2_1 - 0.5f) * powf(D * (0.5f * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] + 0.5f * _data_rho[_stride_rho_0 * ctr_0 - _stride_rho_0 + _stride_rho_1 * ctr_1 - _stride_rho_1 + _stride_rho_2 * ctr_2 - _stride_rho_2]), 0.5f) * 1.5025119784898082f;
337 }
338 if (ctr_1 > 0 && ctr_2 < _size_j_2 - 1) {
339
340 float random_3_0;
341 float random_3_1;
342 float random_3_2;
343 float random_3_3;
344 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 3, seed, random_3_0, random_3_1, random_3_2, random_3_3);
345
346 float random_2_0;
347 float random_2_1;
348 float random_2_2;
349 float random_2_3;
350 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 2, seed, random_2_0, random_2_1, random_2_2, random_2_3);
351
352 float random_1_0;
353 float random_1_1;
354 float random_1_2;
355 float random_1_3;
356 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 1, seed, random_1_0, random_1_1, random_1_2, random_1_3);
357
358 float random_0_0;
359 float random_0_1;
360 float random_0_2;
361 float random_0_3;
362 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 0, seed, random_0_0, random_0_1, random_0_2, random_0_3);
363
364 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 10 * _stride_j_3] = D * (_data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] - _data_rho[_stride_rho_0 * ctr_0 - _stride_rho_0 + _stride_rho_1 * ctr_1 - _stride_rho_1 + _stride_rho_2 * ctr_2 + _stride_rho_2]) * 0.09406426022938992f + (random_2_2 - 0.5f) * powf(D * (0.5f * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] + 0.5f * _data_rho[_stride_rho_0 * ctr_0 - _stride_rho_0 + _stride_rho_1 * ctr_1 - _stride_rho_1 + _stride_rho_2 * ctr_2 + _stride_rho_2]), 0.5f) * 1.5025119784898082f;
365 }
366 if (ctr_2 > 0 && ctr_1 < _size_j_1 - 1) {
367
368 float random_3_0;
369 float random_3_1;
370 float random_3_2;
371 float random_3_3;
372 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 3, seed, random_3_0, random_3_1, random_3_2, random_3_3);
373
374 float random_2_0;
375 float random_2_1;
376 float random_2_2;
377 float random_2_3;
378 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 2, seed, random_2_0, random_2_1, random_2_2, random_2_3);
379
380 float random_1_0;
381 float random_1_1;
382 float random_1_2;
383 float random_1_3;
384 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 1, seed, random_1_0, random_1_1, random_1_2, random_1_3);
385
386 float random_0_0;
387 float random_0_1;
388 float random_0_2;
389 float random_0_3;
390 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 0, seed, random_0_0, random_0_1, random_0_2, random_0_3);
391
392 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 11 * _stride_j_3] = D * (_data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] - _data_rho[_stride_rho_0 * ctr_0 - _stride_rho_0 + _stride_rho_1 * ctr_1 + _stride_rho_1 + _stride_rho_2 * ctr_2 - _stride_rho_2]) * 0.09406426022938992f + (random_2_3 - 0.5f) * powf(D * (0.5f * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] + 0.5f * _data_rho[_stride_rho_0 * ctr_0 - _stride_rho_0 + _stride_rho_1 * ctr_1 + _stride_rho_1 + _stride_rho_2 * ctr_2 - _stride_rho_2]), 0.5f) * 1.5025119784898082f;
393 }
394 if (ctr_1 < _size_j_1 - 1 && ctr_2 < _size_j_2 - 1) {
395
396 float random_3_0;
397 float random_3_1;
398 float random_3_2;
399 float random_3_3;
400 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 3, seed, random_3_0, random_3_1, random_3_2, random_3_3);
401
402 float random_2_0;
403 float random_2_1;
404 float random_2_2;
405 float random_2_3;
406 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 2, seed, random_2_0, random_2_1, random_2_2, random_2_3);
407
408 float random_1_0;
409 float random_1_1;
410 float random_1_2;
411 float random_1_3;
412 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 1, seed, random_1_0, random_1_1, random_1_2, random_1_3);
413
414 float random_0_0;
415 float random_0_1;
416 float random_0_2;
417 float random_0_3;
418 philox_float4(time_step, (block_offset_0 + ctr_0) % field_size_0, (block_offset_1 + ctr_1) % field_size_1, (block_offset_2 + ctr_2) % field_size_2, 0, seed, random_0_0, random_0_1, random_0_2, random_0_3);
419
420 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 12 * _stride_j_3] = D * (_data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] - _data_rho[_stride_rho_0 * ctr_0 - _stride_rho_0 + _stride_rho_1 * ctr_1 + _stride_rho_1 + _stride_rho_2 * ctr_2 + _stride_rho_2]) * 0.09406426022938992f + (random_3_0 - 0.5f) * powf(D * (0.5f * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] + 0.5f * _data_rho[_stride_rho_0 * ctr_0 - _stride_rho_0 + _stride_rho_1 * ctr_1 + _stride_rho_1 + _stride_rho_2 * ctr_2 + _stride_rho_2]), 0.5f) * 1.5025119784898082f;
421 }
422 }
423 }
424 }
425 }
426}
427} // namespace internal_13067439141d91943f586adb1c937d5b
428
429void DiffusiveFluxKernelThermalized_single_precision::run(IBlock *block) {
430 if (!this->configured_)
431 WALBERLA_ABORT("This Sweep contains a configure function that needs to be called manually")
432
433 auto j = block->getData<field::GhostLayerField<float, 13>>(jID);
434 auto rho = block->getData<field::GhostLayerField<float, 1>>(rhoID);
435
436 auto &field_size_1 = this->field_size_1_;
437 auto &seed = this->seed_;
438 auto &field_size_0 = this->field_size_0_;
439 auto &field_size_2 = this->field_size_2_;
440 auto &block_offset_2 = this->block_offset_2_;
441 auto &block_offset_1 = this->block_offset_1_;
442 auto &D = this->D_;
443 auto &time_step = this->time_step_;
444 auto &block_offset_0 = this->block_offset_0_;
445 WALBERLA_ASSERT_GREATER_EQUAL(-1, -int_c(j->nrOfGhostLayers()))
446 float *RESTRICT const _data_j = j->dataAt(-1, -1, -1, 0);
447 WALBERLA_ASSERT_GREATER_EQUAL(-1, -int_c(rho->nrOfGhostLayers()))
448 float *RESTRICT const _data_rho = rho->dataAt(-1, -1, -1, 0);
449 WALBERLA_ASSERT_GREATER_EQUAL(j->xSizeWithGhostLayer(), int64_t(int64_c(j->xSize()) + 2))
450 const int64_t _size_j_0 = int64_t(int64_c(j->xSize()) + 2);
451 WALBERLA_ASSERT_GREATER_EQUAL(j->ySizeWithGhostLayer(), int64_t(int64_c(j->ySize()) + 2))
452 const int64_t _size_j_1 = int64_t(int64_c(j->ySize()) + 2);
453 WALBERLA_ASSERT_GREATER_EQUAL(j->zSizeWithGhostLayer(), int64_t(int64_c(j->zSize()) + 2))
454 const int64_t _size_j_2 = int64_t(int64_c(j->zSize()) + 2);
455 const int64_t _stride_j_0 = int64_t(j->xStride());
456 const int64_t _stride_j_1 = int64_t(j->yStride());
457 const int64_t _stride_j_2 = int64_t(j->zStride());
458 const int64_t _stride_j_3 = int64_t(1 * int64_t(j->fStride()));
459 const int64_t _stride_rho_0 = int64_t(rho->xStride());
460 const int64_t _stride_rho_1 = int64_t(rho->yStride());
461 const int64_t _stride_rho_2 = int64_t(rho->zStride());
462 internal_13067439141d91943f586adb1c937d5b::diffusivefluxkernelthermalized_single_precision_diffusivefluxkernelthermalized_single_precision(D, _data_j, _data_rho, _size_j_0, _size_j_1, _size_j_2, _stride_j_0, _stride_j_1, _stride_j_2, _stride_j_3, _stride_rho_0, _stride_rho_1, _stride_rho_2, block_offset_0, block_offset_1, block_offset_2, field_size_0, field_size_1, field_size_2, seed, time_step);
463}
464
465void DiffusiveFluxKernelThermalized_single_precision::runOnCellInterval(const shared_ptr<StructuredBlockStorage> &blocks, const CellInterval &globalCellInterval, cell_idx_t ghostLayers, IBlock *block) {
466 if (!this->configured_)
467 WALBERLA_ABORT("This Sweep contains a configure function that needs to be called manually")
468
469 CellInterval ci = globalCellInterval;
470 CellInterval blockBB = blocks->getBlockCellBB(*block);
471 blockBB.expand(ghostLayers);
472 ci.intersect(blockBB);
473 blocks->transformGlobalToBlockLocalCellInterval(ci, *block);
474 if (ci.empty())
475 return;
476
477 auto j = block->getData<field::GhostLayerField<float, 13>>(jID);
478 auto rho = block->getData<field::GhostLayerField<float, 1>>(rhoID);
479
480 auto &field_size_1 = this->field_size_1_;
481 auto &seed = this->seed_;
482 auto &field_size_0 = this->field_size_0_;
483 auto &field_size_2 = this->field_size_2_;
484 auto &block_offset_2 = this->block_offset_2_;
485 auto &block_offset_1 = this->block_offset_1_;
486 auto &D = this->D_;
487 auto &time_step = this->time_step_;
488 auto &block_offset_0 = this->block_offset_0_;
489 WALBERLA_ASSERT_GREATER_EQUAL(ci.xMin() - 1, -int_c(j->nrOfGhostLayers()))
490 WALBERLA_ASSERT_GREATER_EQUAL(ci.yMin() - 1, -int_c(j->nrOfGhostLayers()))
491 WALBERLA_ASSERT_GREATER_EQUAL(ci.zMin() - 1, -int_c(j->nrOfGhostLayers()))
492 float *RESTRICT const _data_j = j->dataAt(ci.xMin() - 1, ci.yMin() - 1, ci.zMin() - 1, 0);
493 WALBERLA_ASSERT_GREATER_EQUAL(ci.xMin() - 1, -int_c(rho->nrOfGhostLayers()))
494 WALBERLA_ASSERT_GREATER_EQUAL(ci.yMin() - 1, -int_c(rho->nrOfGhostLayers()))
495 WALBERLA_ASSERT_GREATER_EQUAL(ci.zMin() - 1, -int_c(rho->nrOfGhostLayers()))
496 float *RESTRICT const _data_rho = rho->dataAt(ci.xMin() - 1, ci.yMin() - 1, ci.zMin() - 1, 0);
497 WALBERLA_ASSERT_GREATER_EQUAL(j->xSizeWithGhostLayer(), int64_t(int64_c(ci.xSize()) + 2))
498 const int64_t _size_j_0 = int64_t(int64_c(ci.xSize()) + 2);
499 WALBERLA_ASSERT_GREATER_EQUAL(j->ySizeWithGhostLayer(), int64_t(int64_c(ci.ySize()) + 2))
500 const int64_t _size_j_1 = int64_t(int64_c(ci.ySize()) + 2);
501 WALBERLA_ASSERT_GREATER_EQUAL(j->zSizeWithGhostLayer(), int64_t(int64_c(ci.zSize()) + 2))
502 const int64_t _size_j_2 = int64_t(int64_c(ci.zSize()) + 2);
503 const int64_t _stride_j_0 = int64_t(j->xStride());
504 const int64_t _stride_j_1 = int64_t(j->yStride());
505 const int64_t _stride_j_2 = int64_t(j->zStride());
506 const int64_t _stride_j_3 = int64_t(1 * int64_t(j->fStride()));
507 const int64_t _stride_rho_0 = int64_t(rho->xStride());
508 const int64_t _stride_rho_1 = int64_t(rho->yStride());
509 const int64_t _stride_rho_2 = int64_t(rho->zStride());
510 internal_13067439141d91943f586adb1c937d5b::diffusivefluxkernelthermalized_single_precision_diffusivefluxkernelthermalized_single_precision(D, _data_j, _data_rho, _size_j_0, _size_j_1, _size_j_2, _stride_j_0, _stride_j_1, _stride_j_2, _stride_j_3, _stride_rho_0, _stride_rho_1, _stride_rho_2, block_offset_0, block_offset_1, block_offset_2, field_size_0, field_size_1, field_size_2, seed, time_step);
511}
512
513} // namespace pystencils
514} // namespace walberla
515
516#if (defined WALBERLA_CXX_COMPILER_IS_GNU) || (defined WALBERLA_CXX_COMPILER_IS_CLANG)
517#pragma GCC diagnostic pop
518#endif
519
520#if (defined WALBERLA_CXX_COMPILER_IS_INTEL)
521#pragma warning pop
522#endif
FUNC_PREFIX
#define FUNC_PREFIX
\file AdvectiveFluxKernel_double_precision.cpp \author pystencils
Definition AdvectiveFluxKernel_double_precision.cpp:28
RESTRICT
#define RESTRICT
\file AdvectiveFluxKernel_double_precision.h \author pystencils
Definition AdvectiveFluxKernel_double_precision.h:40
DiffusiveFluxKernelThermalized_single_precision.h
walberla::pystencils::DiffusiveFluxKernelThermalized_single_precision::run
void run(IBlock *block)
Definition DiffusiveFluxKernelThermalized_single_precision.cpp:429
walberla::pystencils::DiffusiveFluxKernelThermalized_single_precision::runOnCellInterval
void runOnCellInterval(const shared_ptr< StructuredBlockStorage > &blocks, const CellInterval &globalCellInterval, cell_idx_t ghostLayers, IBlock *block)
Definition DiffusiveFluxKernelThermalized_single_precision.cpp:465
block
static double * block(double *p, std::size_t index, std::size_t size)
Definition elc.cpp:175
philox_float4
QUALIFIERS void philox_float4(uint32 ctr0, uint32 ctr1, uint32 ctr2, uint32 ctr3, uint32 key0, uint32 key1, float &rnd1, float &rnd2, float &rnd3, float &rnd4)
Definition electrokinetics/generated_kernels/philox_rand.h:218
philox_rand.h
Philox counter-based RNG from .
std
STL namespace.
walberla::pystencils::internal_13067439141d91943f586adb1c937d5b::diffusivefluxkernelthermalized_single_precision_diffusivefluxkernelthermalized_single_precision
static FUNC_PREFIX void diffusivefluxkernelthermalized_single_precision_diffusivefluxkernelthermalized_single_precision(float D, float *RESTRICT const _data_j, float *RESTRICT const _data_rho, int64_t const _size_j_0, int64_t const _size_j_1, int64_t const _size_j_2, int64_t const _stride_j_0, int64_t const _stride_j_1, int64_t const _stride_j_2, int64_t const _stride_j_3, int64_t const _stride_rho_0, int64_t const _stride_rho_1, int64_t const _stride_rho_2, uint32_t block_offset_0, uint32_t block_offset_1, uint32_t block_offset_2, uint32_t field_size_0, uint32_t field_size_1, uint32_t field_size_2, uint32_t seed, uint32_t time_step)
Definition DiffusiveFluxKernelThermalized_single_precision.cpp:51
walberla
\file PackInfoPdfDoublePrecision.cpp \author pystencils
Definition EKWalberla.hpp:38