ESPResSo
Extensible Simulation Package for Research on Soft Matter Systems
Loading...
Searching...
No Matches
DiffusiveFluxKernelWithElectrostaticThermalized_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 DiffusiveFluxKernelWithElectrostaticThermalized_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 007e77e077ad9d22b5eed6f3d3118240993e553c
21
22#include <cmath>
23
24#include "DiffusiveFluxKernelWithElectrostaticThermalized_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_e04f3d5b3f93f09e4de6aba968e70d10 {
51static FUNC_PREFIX void diffusivefluxkernelwithelectrostaticthermalized_single_precision_diffusivefluxkernelwithelectrostaticthermalized_single_precision(float D, float *RESTRICT const _data_j, float *RESTRICT const _data_phi, 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_phi_0, int64_t const _stride_phi_1, int64_t const _stride_phi_2, 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, float f_ext_0, float f_ext_1, float f_ext_2, uint32_t field_size_0, uint32_t field_size_1, uint32_t field_size_2, float kT, uint32_t seed, uint32_t time_step, float z) {
52 for (int64_t ctr_2 = 0; ctr_2 < _size_j_2; ctr_2 += 1) {
53 for (int64_t ctr_1 = 0; ctr_1 < _size_j_1; ctr_1 += 1) {
54 for (int64_t ctr_0 = 1; ctr_0 < _size_j_0; ctr_0 += 1) {
55 if (ctr_1 > 0 && ctr_2 > 0 && ctr_1 < _size_j_1 - 1 && ctr_2 < _size_j_2 - 1) {
56
57 float random_7_0;
58 float random_7_1;
59 float random_7_2;
60 float random_7_3;
61 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_7_0, random_7_1, random_7_2, random_7_3);
62
63 float random_6_0;
64 float random_6_1;
65 float random_6_2;
66 float random_6_3;
67 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_6_0, random_6_1, random_6_2, random_6_3);
68
69 float random_5_0;
70 float random_5_1;
71 float random_5_2;
72 float random_5_3;
73 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_5_0, random_5_1, random_5_2, random_5_3);
74
75 float random_4_0;
76 float random_4_1;
77 float random_4_2;
78 float random_4_3;
79 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_4_0, random_4_1, random_4_2, random_4_3);
80
81 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2] = D * (-f_ext_0 * z * (_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]) + kT * (_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]) * 2.0f + z * (_data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2] - _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2]) * (_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])) * 0.081462038946841925f * ((1.0f) / (kT)) + (random_4_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;
82 }
83 if (ctr_1 > 0 && ctr_2 > 0 && ctr_0 < _size_j_0 - 1 && ctr_2 < _size_j_2 - 1) {
84
85 float random_7_0;
86 float random_7_1;
87 float random_7_2;
88 float random_7_3;
89 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_7_0, random_7_1, random_7_2, random_7_3);
90
91 float random_6_0;
92 float random_6_1;
93 float random_6_2;
94 float random_6_3;
95 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_6_0, random_6_1, random_6_2, random_6_3);
96
97 float random_5_0;
98 float random_5_1;
99 float random_5_2;
100 float random_5_3;
101 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_5_0, random_5_1, random_5_2, random_5_3);
102
103 float random_4_0;
104 float random_4_1;
105 float random_4_2;
106 float random_4_3;
107 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_4_0, random_4_1, random_4_2, random_4_3);
108
109 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + _stride_j_3] = D * (-f_ext_1 * z * (_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]) + kT * (_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]) * 2.0f + z * (_data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2] - _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 - _stride_phi_1 + _stride_phi_2 * ctr_2]) * (_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])) * 0.081462038946841925f * ((1.0f) / (kT)) + (random_4_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;
110 }
111 if (ctr_1 > 0 && ctr_2 > 0 && ctr_0 < _size_j_0 - 1 && ctr_1 < _size_j_1 - 1) {
112
113 float random_7_0;
114 float random_7_1;
115 float random_7_2;
116 float random_7_3;
117 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_7_0, random_7_1, random_7_2, random_7_3);
118
119 float random_6_0;
120 float random_6_1;
121 float random_6_2;
122 float random_6_3;
123 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_6_0, random_6_1, random_6_2, random_6_3);
124
125 float random_5_0;
126 float random_5_1;
127 float random_5_2;
128 float random_5_3;
129 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_5_0, random_5_1, random_5_2, random_5_3);
130
131 float random_4_0;
132 float random_4_1;
133 float random_4_2;
134 float random_4_3;
135 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_4_0, random_4_1, random_4_2, random_4_3);
136
137 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 2 * _stride_j_3] = D * (f_ext_2 * z * (_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]) + kT * (_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]) * 2.0f + z * (_data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2 - _stride_phi_2] - _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2]) * (_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])) * -0.081462038946841925f * ((1.0f) / (kT)) + (random_4_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;
138 }
139 if (ctr_1 > 0 && ctr_2 > 0 && ctr_2 < _size_j_2 - 1) {
140
141 float random_7_0;
142 float random_7_1;
143 float random_7_2;
144 float random_7_3;
145 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_7_0, random_7_1, random_7_2, random_7_3);
146
147 float random_6_0;
148 float random_6_1;
149 float random_6_2;
150 float random_6_3;
151 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_6_0, random_6_1, random_6_2, random_6_3);
152
153 float random_5_0;
154 float random_5_1;
155 float random_5_2;
156 float random_5_3;
157 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_5_0, random_5_1, random_5_2, random_5_3);
158
159 float random_4_0;
160 float random_4_1;
161 float random_4_2;
162 float random_4_3;
163 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_4_0, random_4_1, random_4_2, random_4_3);
164
165 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 3 * _stride_j_3] = D * (f_ext_0 * z * (_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]) * -2.0f + f_ext_1 * z * (_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]) * -2.0f + kT * (_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]) * 4.0f + z * (_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]) * (_data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2] - _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 - _stride_phi_1 + _stride_phi_2 * ctr_2] + _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2] - _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 - _stride_phi_1 + _stride_phi_2 * ctr_2]) + z * (_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]) * (_data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2] + _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 - _stride_phi_1 + _stride_phi_2 * ctr_2] - _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2] - _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 - _stride_phi_1 + _stride_phi_2 * ctr_2])) * 0.028801180074297286f * ((1.0f) / (kT)) + (random_4_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;
166 }
167 if (ctr_2 > 0 && ctr_1 < _size_j_1 - 1 && ctr_2 < _size_j_2 - 1) {
168
169 float random_7_0;
170 float random_7_1;
171 float random_7_2;
172 float random_7_3;
173 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_7_0, random_7_1, random_7_2, random_7_3);
174
175 float random_6_0;
176 float random_6_1;
177 float random_6_2;
178 float random_6_3;
179 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_6_0, random_6_1, random_6_2, random_6_3);
180
181 float random_5_0;
182 float random_5_1;
183 float random_5_2;
184 float random_5_3;
185 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_5_0, random_5_1, random_5_2, random_5_3);
186
187 float random_4_0;
188 float random_4_1;
189 float random_4_2;
190 float random_4_3;
191 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_4_0, random_4_1, random_4_2, random_4_3);
192
193 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 4 * _stride_j_3] = D * (f_ext_0 * z * (_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]) * -2.0f + f_ext_1 * z * (_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]) * 2.0f + kT * (_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]) * 4.0f + z * (_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]) * (-_data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_1 + _stride_phi_2 * ctr_2] + _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2] - _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 + _stride_phi_1 + _stride_phi_2 * ctr_2] + _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2]) + z * (_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]) * (_data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_1 + _stride_phi_2 * ctr_2] + _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2] - _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 + _stride_phi_1 + _stride_phi_2 * ctr_2] - _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2])) * 0.028801180074297286f * ((1.0f) / (kT)) + (random_5_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;
194 }
195 if (ctr_1 > 0 && ctr_2 > 0 && ctr_1 < _size_j_1 - 1) {
196
197 float random_7_0;
198 float random_7_1;
199 float random_7_2;
200 float random_7_3;
201 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_7_0, random_7_1, random_7_2, random_7_3);
202
203 float random_6_0;
204 float random_6_1;
205 float random_6_2;
206 float random_6_3;
207 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_6_0, random_6_1, random_6_2, random_6_3);
208
209 float random_5_0;
210 float random_5_1;
211 float random_5_2;
212 float random_5_3;
213 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_5_0, random_5_1, random_5_2, random_5_3);
214
215 float random_4_0;
216 float random_4_1;
217 float random_4_2;
218 float random_4_3;
219 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_4_0, random_4_1, random_4_2, random_4_3);
220
221 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 5 * _stride_j_3] = D * (f_ext_0 * z * (_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]) * 2.0f + f_ext_2 * z * (_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]) * 2.0f + kT * (-_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]) * 4.0f + z * (_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]) * (_data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2 - _stride_phi_2] - _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2] + _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2 - _stride_phi_2] - _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2]) - z * (_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]) * (_data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2 - _stride_phi_2] + _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2] - _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2 - _stride_phi_2] - _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2])) * -0.028801180074297286f * ((1.0f) / (kT)) + (random_5_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;
222 }
223 if (ctr_1 > 0 && ctr_1 < _size_j_1 - 1 && ctr_2 < _size_j_2 - 1) {
224
225 float random_7_0;
226 float random_7_1;
227 float random_7_2;
228 float random_7_3;
229 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_7_0, random_7_1, random_7_2, random_7_3);
230
231 float random_6_0;
232 float random_6_1;
233 float random_6_2;
234 float random_6_3;
235 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_6_0, random_6_1, random_6_2, random_6_3);
236
237 float random_5_0;
238 float random_5_1;
239 float random_5_2;
240 float random_5_3;
241 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_5_0, random_5_1, random_5_2, random_5_3);
242
243 float random_4_0;
244 float random_4_1;
245 float random_4_2;
246 float random_4_3;
247 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_4_0, random_4_1, random_4_2, random_4_3);
248
249 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 6 * _stride_j_3] = D * (f_ext_0 * z * (_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]) * -2.0f + f_ext_2 * z * (_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]) * 2.0f + kT * (_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]) * 4.0f + z * (_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]) * (-_data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2 + _stride_phi_2] + _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2] - _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2 + _stride_phi_2] + _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2]) + z * (_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]) * (_data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2 + _stride_phi_2] + _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2] - _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2 + _stride_phi_2] - _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2])) * 0.028801180074297286f * ((1.0f) / (kT)) + (random_5_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;
250 }
251 if (ctr_1 > 0 && ctr_2 > 0 && ctr_0 < _size_j_0 - 1) {
252
253 float random_7_0;
254 float random_7_1;
255 float random_7_2;
256 float random_7_3;
257 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_7_0, random_7_1, random_7_2, random_7_3);
258
259 float random_6_0;
260 float random_6_1;
261 float random_6_2;
262 float random_6_3;
263 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_6_0, random_6_1, random_6_2, random_6_3);
264
265 float random_5_0;
266 float random_5_1;
267 float random_5_2;
268 float random_5_3;
269 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_5_0, random_5_1, random_5_2, random_5_3);
270
271 float random_4_0;
272 float random_4_1;
273 float random_4_2;
274 float random_4_3;
275 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_4_0, random_4_1, random_4_2, random_4_3);
276
277 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 7 * _stride_j_3] = D * (f_ext_1 * z * (_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]) * 2.0f + f_ext_2 * z * (_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]) * 2.0f + kT * (-_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]) * 4.0f + z * (_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]) * (_data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2 - _stride_phi_2] - _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2] + _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 - _stride_phi_1 + _stride_phi_2 * ctr_2 - _stride_phi_2] - _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 - _stride_phi_1 + _stride_phi_2 * ctr_2]) - z * (_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]) * (_data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2 - _stride_phi_2] + _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2] - _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 - _stride_phi_1 + _stride_phi_2 * ctr_2 - _stride_phi_2] - _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 - _stride_phi_1 + _stride_phi_2 * ctr_2])) * -0.028801180074297286f * ((1.0f) / (kT)) + (random_5_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;
278 }
279 if (ctr_1 > 0 && ctr_0 < _size_j_0 - 1 && ctr_2 < _size_j_2 - 1) {
280
281 float random_7_0;
282 float random_7_1;
283 float random_7_2;
284 float random_7_3;
285 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_7_0, random_7_1, random_7_2, random_7_3);
286
287 float random_6_0;
288 float random_6_1;
289 float random_6_2;
290 float random_6_3;
291 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_6_0, random_6_1, random_6_2, random_6_3);
292
293 float random_5_0;
294 float random_5_1;
295 float random_5_2;
296 float random_5_3;
297 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_5_0, random_5_1, random_5_2, random_5_3);
298
299 float random_4_0;
300 float random_4_1;
301 float random_4_2;
302 float random_4_3;
303 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_4_0, random_4_1, random_4_2, random_4_3);
304
305 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 8 * _stride_j_3] = D * (f_ext_1 * z * (_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]) * -2.0f + f_ext_2 * z * (_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]) * 2.0f + kT * (_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]) * 4.0f + z * (_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]) * (-_data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2 + _stride_phi_2] + _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2] - _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 - _stride_phi_1 + _stride_phi_2 * ctr_2 + _stride_phi_2] + _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 - _stride_phi_1 + _stride_phi_2 * ctr_2]) + z * (_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]) * (_data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2 + _stride_phi_2] + _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2] - _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 - _stride_phi_1 + _stride_phi_2 * ctr_2 + _stride_phi_2] - _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 - _stride_phi_1 + _stride_phi_2 * ctr_2])) * 0.028801180074297286f * ((1.0f) / (kT)) + (random_6_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;
306 }
307 if (ctr_1 > 0 && ctr_2 > 0) {
308
309 float random_7_0;
310 float random_7_1;
311 float random_7_2;
312 float random_7_3;
313 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_7_0, random_7_1, random_7_2, random_7_3);
314
315 float random_6_0;
316 float random_6_1;
317 float random_6_2;
318 float random_6_3;
319 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_6_0, random_6_1, random_6_2, random_6_3);
320
321 float random_5_0;
322 float random_5_1;
323 float random_5_2;
324 float random_5_3;
325 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_5_0, random_5_1, random_5_2, random_5_3);
326
327 float random_4_0;
328 float random_4_1;
329 float random_4_2;
330 float random_4_3;
331 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_4_0, random_4_1, random_4_2, random_4_3);
332
333 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 9 * _stride_j_3] = D * (-f_ext_0 * z * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] - f_ext_0 * z * _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] - f_ext_1 * z * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] - f_ext_1 * z * _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] - f_ext_2 * z * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] - f_ext_2 * z * _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] + kT * -2.0f * _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] + kT * 2.0f * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] + z * _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2] * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] + z * _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_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] - z * _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 - _stride_phi_1 + _stride_phi_2 * ctr_2 - _stride_phi_2] * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] - z * _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 - _stride_phi_1 + _stride_phi_2 * ctr_2 - _stride_phi_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]) * 0.04703213011469496f * ((1.0f) / (kT)) + (random_6_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;
334 }
335 if (ctr_1 > 0 && ctr_2 < _size_j_2 - 1) {
336
337 float random_7_0;
338 float random_7_1;
339 float random_7_2;
340 float random_7_3;
341 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_7_0, random_7_1, random_7_2, random_7_3);
342
343 float random_6_0;
344 float random_6_1;
345 float random_6_2;
346 float random_6_3;
347 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_6_0, random_6_1, random_6_2, random_6_3);
348
349 float random_5_0;
350 float random_5_1;
351 float random_5_2;
352 float random_5_3;
353 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_5_0, random_5_1, random_5_2, random_5_3);
354
355 float random_4_0;
356 float random_4_1;
357 float random_4_2;
358 float random_4_3;
359 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_4_0, random_4_1, random_4_2, random_4_3);
360
361 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 10 * _stride_j_3] = D * (-f_ext_0 * z * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] - f_ext_0 * z * _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] - f_ext_1 * z * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] - f_ext_1 * z * _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] + f_ext_2 * z * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] + f_ext_2 * z * _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] + kT * -2.0f * _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] + kT * 2.0f * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] + z * _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2] * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] + z * _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_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] - z * _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 - _stride_phi_1 + _stride_phi_2 * ctr_2 + _stride_phi_2] * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] - z * _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 - _stride_phi_1 + _stride_phi_2 * ctr_2 + _stride_phi_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]) * 0.04703213011469496f * ((1.0f) / (kT)) + (random_6_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;
362 }
363 if (ctr_2 > 0 && ctr_1 < _size_j_1 - 1) {
364
365 float random_7_0;
366 float random_7_1;
367 float random_7_2;
368 float random_7_3;
369 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_7_0, random_7_1, random_7_2, random_7_3);
370
371 float random_6_0;
372 float random_6_1;
373 float random_6_2;
374 float random_6_3;
375 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_6_0, random_6_1, random_6_2, random_6_3);
376
377 float random_5_0;
378 float random_5_1;
379 float random_5_2;
380 float random_5_3;
381 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_5_0, random_5_1, random_5_2, random_5_3);
382
383 float random_4_0;
384 float random_4_1;
385 float random_4_2;
386 float random_4_3;
387 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_4_0, random_4_1, random_4_2, random_4_3);
388
389 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 11 * _stride_j_3] = D * (-f_ext_0 * z * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] - f_ext_0 * z * _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] + f_ext_1 * z * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] + f_ext_1 * z * _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] - f_ext_2 * z * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] - f_ext_2 * z * _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] + kT * -2.0f * _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] + kT * 2.0f * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] + z * _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2] * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] + z * _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_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] - z * _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 + _stride_phi_1 + _stride_phi_2 * ctr_2 - _stride_phi_2] * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] - z * _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 + _stride_phi_1 + _stride_phi_2 * ctr_2 - _stride_phi_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]) * 0.04703213011469496f * ((1.0f) / (kT)) + (random_6_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;
390 }
391 if (ctr_1 < _size_j_1 - 1 && ctr_2 < _size_j_2 - 1) {
392
393 float random_7_0;
394 float random_7_1;
395 float random_7_2;
396 float random_7_3;
397 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_7_0, random_7_1, random_7_2, random_7_3);
398
399 float random_6_0;
400 float random_6_1;
401 float random_6_2;
402 float random_6_3;
403 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_6_0, random_6_1, random_6_2, random_6_3);
404
405 float random_5_0;
406 float random_5_1;
407 float random_5_2;
408 float random_5_3;
409 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_5_0, random_5_1, random_5_2, random_5_3);
410
411 float random_4_0;
412 float random_4_1;
413 float random_4_2;
414 float random_4_3;
415 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_4_0, random_4_1, random_4_2, random_4_3);
416
417 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 12 * _stride_j_3] = D * (f_ext_0 * z * (_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]) * -2.0f + f_ext_1 * z * (_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]) * 2.0f + f_ext_2 * z * (_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]) * 2.0f + kT * (_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]) * 4.0f + z * (_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]) * (-_data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_1 + _stride_phi_2 * ctr_2 + _stride_phi_2] + _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_1 + _stride_phi_2 * ctr_2] - _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2 + _stride_phi_2] + _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2]) - z * (_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]) * (_data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_1 + _stride_phi_2 * ctr_2 + _stride_phi_2] - _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2 + _stride_phi_2] + _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 + _stride_phi_1 + _stride_phi_2 * ctr_2] - _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2]) + z * (_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]) * (_data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_1 + _stride_phi_2 * ctr_2] + _data_phi[_stride_phi_0 * ctr_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2 + _stride_phi_2] - _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 + _stride_phi_1 + _stride_phi_2 * ctr_2] - _data_phi[_stride_phi_0 * ctr_0 - _stride_phi_0 + _stride_phi_1 * ctr_1 + _stride_phi_2 * ctr_2 + _stride_phi_2])) * 0.02351606505734748f * ((1.0f) / (kT)) + (random_7_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;
418 }
419 }
420 }
421 }
422}
423} // namespace internal_e04f3d5b3f93f09e4de6aba968e70d10
424
425void DiffusiveFluxKernelWithElectrostaticThermalized_single_precision::run(IBlock *block) {
426 if (!this->configured_)
427 WALBERLA_ABORT("This Sweep contains a configure function that needs to be called manually")
428
429 auto j = block->getData<field::GhostLayerField<float, 13>>(jID);
430 auto rho = block->getData<field::GhostLayerField<float, 1>>(rhoID);
431 auto phi = block->getData<field::GhostLayerField<float, 1>>(phiID);
432
433 auto &f_ext_1 = this->f_ext_1_;
434 auto &field_size_1 = this->field_size_1_;
435 auto &seed = this->seed_;
436 auto &f_ext_2 = this->f_ext_2_;
437 auto &field_size_0 = this->field_size_0_;
438 auto &field_size_2 = this->field_size_2_;
439 auto &block_offset_2 = this->block_offset_2_;
440 auto &block_offset_1 = this->block_offset_1_;
441 auto &D = this->D_;
442 auto &kT = this->kT_;
443 auto &time_step = this->time_step_;
444 auto &f_ext_0 = this->f_ext_0_;
445 auto &block_offset_0 = this->block_offset_0_;
446 auto &z = this->z_;
447 WALBERLA_ASSERT_GREATER_EQUAL(-1, -int_c(j->nrOfGhostLayers()))
448 float *RESTRICT const _data_j = j->dataAt(-1, -1, -1, 0);
449 WALBERLA_ASSERT_GREATER_EQUAL(-1, -int_c(phi->nrOfGhostLayers()))
450 float *RESTRICT const _data_phi = phi->dataAt(-1, -1, -1, 0);
451 WALBERLA_ASSERT_GREATER_EQUAL(-1, -int_c(rho->nrOfGhostLayers()))
452 float *RESTRICT const _data_rho = rho->dataAt(-1, -1, -1, 0);
453 WALBERLA_ASSERT_GREATER_EQUAL(j->xSizeWithGhostLayer(), int64_t(int64_c(j->xSize()) + 2))
454 const int64_t _size_j_0 = int64_t(int64_c(j->xSize()) + 2);
455 WALBERLA_ASSERT_GREATER_EQUAL(j->ySizeWithGhostLayer(), int64_t(int64_c(j->ySize()) + 2))
456 const int64_t _size_j_1 = int64_t(int64_c(j->ySize()) + 2);
457 WALBERLA_ASSERT_GREATER_EQUAL(j->zSizeWithGhostLayer(), int64_t(int64_c(j->zSize()) + 2))
458 const int64_t _size_j_2 = int64_t(int64_c(j->zSize()) + 2);
459 const int64_t _stride_j_0 = int64_t(j->xStride());
460 const int64_t _stride_j_1 = int64_t(j->yStride());
461 const int64_t _stride_j_2 = int64_t(j->zStride());
462 const int64_t _stride_j_3 = int64_t(1 * int64_t(j->fStride()));
463 const int64_t _stride_phi_0 = int64_t(phi->xStride());
464 const int64_t _stride_phi_1 = int64_t(phi->yStride());
465 const int64_t _stride_phi_2 = int64_t(phi->zStride());
466 const int64_t _stride_rho_0 = int64_t(rho->xStride());
467 const int64_t _stride_rho_1 = int64_t(rho->yStride());
468 const int64_t _stride_rho_2 = int64_t(rho->zStride());
469 internal_e04f3d5b3f93f09e4de6aba968e70d10::diffusivefluxkernelwithelectrostaticthermalized_single_precision_diffusivefluxkernelwithelectrostaticthermalized_single_precision(D, _data_j, _data_phi, _data_rho, _size_j_0, _size_j_1, _size_j_2, _stride_j_0, _stride_j_1, _stride_j_2, _stride_j_3, _stride_phi_0, _stride_phi_1, _stride_phi_2, _stride_rho_0, _stride_rho_1, _stride_rho_2, block_offset_0, block_offset_1, block_offset_2, f_ext_0, f_ext_1, f_ext_2, field_size_0, field_size_1, field_size_2, kT, seed, time_step, z);
470}
471
472void DiffusiveFluxKernelWithElectrostaticThermalized_single_precision::runOnCellInterval(const shared_ptr<StructuredBlockStorage> &blocks, const CellInterval &globalCellInterval, cell_idx_t ghostLayers, IBlock *block) {
473 if (!this->configured_)
474 WALBERLA_ABORT("This Sweep contains a configure function that needs to be called manually")
475
476 CellInterval ci = globalCellInterval;
477 CellInterval blockBB = blocks->getBlockCellBB(*block);
478 blockBB.expand(ghostLayers);
479 ci.intersect(blockBB);
480 blocks->transformGlobalToBlockLocalCellInterval(ci, *block);
481 if (ci.empty())
482 return;
483
484 auto j = block->getData<field::GhostLayerField<float, 13>>(jID);
485 auto rho = block->getData<field::GhostLayerField<float, 1>>(rhoID);
486 auto phi = block->getData<field::GhostLayerField<float, 1>>(phiID);
487
488 auto &f_ext_1 = this->f_ext_1_;
489 auto &field_size_1 = this->field_size_1_;
490 auto &seed = this->seed_;
491 auto &f_ext_2 = this->f_ext_2_;
492 auto &field_size_0 = this->field_size_0_;
493 auto &field_size_2 = this->field_size_2_;
494 auto &block_offset_2 = this->block_offset_2_;
495 auto &block_offset_1 = this->block_offset_1_;
496 auto &D = this->D_;
497 auto &kT = this->kT_;
498 auto &time_step = this->time_step_;
499 auto &f_ext_0 = this->f_ext_0_;
500 auto &block_offset_0 = this->block_offset_0_;
501 auto &z = this->z_;
502 WALBERLA_ASSERT_GREATER_EQUAL(ci.xMin() - 1, -int_c(j->nrOfGhostLayers()))
503 WALBERLA_ASSERT_GREATER_EQUAL(ci.yMin() - 1, -int_c(j->nrOfGhostLayers()))
504 WALBERLA_ASSERT_GREATER_EQUAL(ci.zMin() - 1, -int_c(j->nrOfGhostLayers()))
505 float *RESTRICT const _data_j = j->dataAt(ci.xMin() - 1, ci.yMin() - 1, ci.zMin() - 1, 0);
506 WALBERLA_ASSERT_GREATER_EQUAL(ci.xMin() - 1, -int_c(phi->nrOfGhostLayers()))
507 WALBERLA_ASSERT_GREATER_EQUAL(ci.yMin() - 1, -int_c(phi->nrOfGhostLayers()))
508 WALBERLA_ASSERT_GREATER_EQUAL(ci.zMin() - 1, -int_c(phi->nrOfGhostLayers()))
509 float *RESTRICT const _data_phi = phi->dataAt(ci.xMin() - 1, ci.yMin() - 1, ci.zMin() - 1, 0);
510 WALBERLA_ASSERT_GREATER_EQUAL(ci.xMin() - 1, -int_c(rho->nrOfGhostLayers()))
511 WALBERLA_ASSERT_GREATER_EQUAL(ci.yMin() - 1, -int_c(rho->nrOfGhostLayers()))
512 WALBERLA_ASSERT_GREATER_EQUAL(ci.zMin() - 1, -int_c(rho->nrOfGhostLayers()))
513 float *RESTRICT const _data_rho = rho->dataAt(ci.xMin() - 1, ci.yMin() - 1, ci.zMin() - 1, 0);
514 WALBERLA_ASSERT_GREATER_EQUAL(j->xSizeWithGhostLayer(), int64_t(int64_c(ci.xSize()) + 2))
515 const int64_t _size_j_0 = int64_t(int64_c(ci.xSize()) + 2);
516 WALBERLA_ASSERT_GREATER_EQUAL(j->ySizeWithGhostLayer(), int64_t(int64_c(ci.ySize()) + 2))
517 const int64_t _size_j_1 = int64_t(int64_c(ci.ySize()) + 2);
518 WALBERLA_ASSERT_GREATER_EQUAL(j->zSizeWithGhostLayer(), int64_t(int64_c(ci.zSize()) + 2))
519 const int64_t _size_j_2 = int64_t(int64_c(ci.zSize()) + 2);
520 const int64_t _stride_j_0 = int64_t(j->xStride());
521 const int64_t _stride_j_1 = int64_t(j->yStride());
522 const int64_t _stride_j_2 = int64_t(j->zStride());
523 const int64_t _stride_j_3 = int64_t(1 * int64_t(j->fStride()));
524 const int64_t _stride_phi_0 = int64_t(phi->xStride());
525 const int64_t _stride_phi_1 = int64_t(phi->yStride());
526 const int64_t _stride_phi_2 = int64_t(phi->zStride());
527 const int64_t _stride_rho_0 = int64_t(rho->xStride());
528 const int64_t _stride_rho_1 = int64_t(rho->yStride());
529 const int64_t _stride_rho_2 = int64_t(rho->zStride());
530 internal_e04f3d5b3f93f09e4de6aba968e70d10::diffusivefluxkernelwithelectrostaticthermalized_single_precision_diffusivefluxkernelwithelectrostaticthermalized_single_precision(D, _data_j, _data_phi, _data_rho, _size_j_0, _size_j_1, _size_j_2, _stride_j_0, _stride_j_1, _stride_j_2, _stride_j_3, _stride_phi_0, _stride_phi_1, _stride_phi_2, _stride_rho_0, _stride_rho_1, _stride_rho_2, block_offset_0, block_offset_1, block_offset_2, f_ext_0, f_ext_1, f_ext_2, field_size_0, field_size_1, field_size_2, kT, seed, time_step, z);
531}
532
533} // namespace pystencils
534} // namespace walberla
535
536#if (defined WALBERLA_CXX_COMPILER_IS_GNU) || (defined WALBERLA_CXX_COMPILER_IS_CLANG)
537#pragma GCC diagnostic pop
538#endif
539
540#if (defined WALBERLA_CXX_COMPILER_IS_INTEL)
541#pragma warning pop
542#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
DiffusiveFluxKernelWithElectrostaticThermalized_single_precision.h
walberla::pystencils::DiffusiveFluxKernelWithElectrostaticThermalized_single_precision::runOnCellInterval
void runOnCellInterval(const shared_ptr< StructuredBlockStorage > &blocks, const CellInterval &globalCellInterval, cell_idx_t ghostLayers, IBlock *block)
Definition DiffusiveFluxKernelWithElectrostaticThermalized_single_precision.cpp:472
walberla::pystencils::DiffusiveFluxKernelWithElectrostaticThermalized_single_precision::run
void run(IBlock *block)
Definition DiffusiveFluxKernelWithElectrostaticThermalized_single_precision.cpp:425
stream
cudaStream_t stream[1]
CUDA streams for parallel computing on CPU and GPU.
Definition common_cuda.cu:34
block
static double * block(double *p, std::size_t index, std::size_t size)
Definition elc.cpp:177
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_e04f3d5b3f93f09e4de6aba968e70d10::diffusivefluxkernelwithelectrostaticthermalized_single_precision_diffusivefluxkernelwithelectrostaticthermalized_single_precision
static FUNC_PREFIX void diffusivefluxkernelwithelectrostaticthermalized_single_precision_diffusivefluxkernelwithelectrostaticthermalized_single_precision(float D, float *RESTRICT const _data_j, float *RESTRICT const _data_phi, 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_phi_0, int64_t const _stride_phi_1, int64_t const _stride_phi_2, 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, float f_ext_0, float f_ext_1, float f_ext_2, uint32_t field_size_0, uint32_t field_size_1, uint32_t field_size_2, float kT, uint32_t seed, uint32_t time_step, float z)
Definition DiffusiveFluxKernelWithElectrostaticThermalized_single_precision.cpp:51
walberla
\file PackInfoPdfDoublePrecision.cpp \author pystencils
Definition EKWalberla.hpp:38