ESPResSo
Extensible Simulation Package for Research on Soft Matter Systems
Loading...
Searching...
No Matches
ReactionKernelIndexed_4_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 ReactionKernelIndexed_4_single_precision.cpp
17//! \\author pystencils
18//======================================================================================================================
19
20// kernel generated with pystencils v1.3.3, lbmpy v1.3.3, lbmpy_walberla/pystencils_walberla from waLBerla commit b0842e1a493ce19ef1bbb8d2cf382fc343970a7f
21
23#include "core/DataTypes.h"
24#include "core/Macros.h"
25
26#define FUNC_PREFIX
27
28using namespace std;
29
30namespace walberla {
31namespace pystencils {
32
33#ifdef __GNUC__
34#pragma GCC diagnostic push
35#pragma GCC diagnostic ignored "-Wstrict-aliasing"
36#pragma GCC diagnostic ignored "-Wunused-variable"
37#pragma GCC diagnostic ignored "-Wconversion"
38#endif
39
40#ifdef __CUDACC__
41#pragma push
42#ifdef __NVCC_DIAG_PRAGMA_SUPPORT__
43#pragma nv_diag_suppress 177
44#else
45#pragma diag_suppress 177
46#endif
47#endif
48// NOLINTBEGIN(readability-non-const-parameter*)
49namespace internal_62195c7636fc531694c87493561447d7 {
50static FUNC_PREFIX void reactionkernelindexed_4_single_precision_boundary_ReactionKernelIndexed_4_single_precision(uint8_t *RESTRICT const _data_indexVector, float *RESTRICT _data_rho_0, float *RESTRICT _data_rho_1, float *RESTRICT _data_rho_2, float *RESTRICT _data_rho_3, int64_t const _stride_rho_0_0, int64_t const _stride_rho_0_1, int64_t const _stride_rho_0_2, int64_t const _stride_rho_1_0, int64_t const _stride_rho_1_1, int64_t const _stride_rho_1_2, int64_t const _stride_rho_2_0, int64_t const _stride_rho_2_1, int64_t const _stride_rho_2_2, int64_t const _stride_rho_3_0, int64_t const _stride_rho_3_1, int64_t const _stride_rho_3_2, int32_t indexVectorSize, float order_0, float order_1, float order_2, float order_3, float rate_coefficient, float stoech_0, float stoech_1, float stoech_2, float stoech_3) {
51 for (int64_t ctr_0 = 0; ctr_0 < indexVectorSize; ctr_0 += 1) {
52 const int32_t x = *((int32_t *)(&_data_indexVector[12 * ctr_0]));
53 const int32_t y = *((int32_t *)(&_data_indexVector[12 * ctr_0 + 4]));
54 const int32_t z = *((int32_t *)(&_data_indexVector[12 * ctr_0 + 8]));
55
56 const int32_t cx[] = {0};
57 const int32_t cy[] = {0};
58 const int32_t cz[] = {0};
59 const int32_t invdir[] = {0};
60
61 const float local_rho_0 = _data_rho_0[_stride_rho_0_0 * x + _stride_rho_0_1 * y + _stride_rho_0_2 * z];
62 const float local_rho_1 = _data_rho_1[_stride_rho_1_0 * x + _stride_rho_1_1 * y + _stride_rho_1_2 * z];
63 const float local_rho_2 = _data_rho_2[_stride_rho_2_0 * x + _stride_rho_2_1 * y + _stride_rho_2_2 * z];
64 const float local_rho_3 = _data_rho_3[_stride_rho_3_0 * x + _stride_rho_3_1 * y + _stride_rho_3_2 * z];
65 const float rate_factor = rate_coefficient * powf(local_rho_0, order_0) * powf(local_rho_1, order_1) * powf(local_rho_2, order_2) * powf(local_rho_3, order_3);
66 _data_rho_0[_stride_rho_0_0 * x + _stride_rho_0_1 * y + _stride_rho_0_2 * z] = local_rho_0 + rate_factor * stoech_0;
67 _data_rho_1[_stride_rho_1_0 * x + _stride_rho_1_1 * y + _stride_rho_1_2 * z] = local_rho_1 + rate_factor * stoech_1;
68 _data_rho_2[_stride_rho_2_0 * x + _stride_rho_2_1 * y + _stride_rho_2_2 * z] = local_rho_2 + rate_factor * stoech_2;
69 _data_rho_3[_stride_rho_3_0 * x + _stride_rho_3_1 * y + _stride_rho_3_2 * z] = local_rho_3 + rate_factor * stoech_3;
70 }
71}
72} // namespace internal_62195c7636fc531694c87493561447d7
73
74// NOLINTEND(readability-non-const-parameter*)
75#ifdef __GNUC__
76#pragma GCC diagnostic pop
77#endif
78
79#ifdef __CUDACC__
80#pragma pop
81#endif
82
83void ReactionKernelIndexed_4_single_precision::run_impl(IBlock *block, IndexVectors::Type type) {
84 auto *indexVectors = block->uncheckedFastGetData<IndexVectors>(indexVectorID);
85 int32_t indexVectorSize = int32_c(indexVectors->indexVector(type).size());
86 if (indexVectorSize == 0)
87 return;
88
89 auto pointer = indexVectors->pointerCpu(type);
90
91 uint8_t *_data_indexVector = reinterpret_cast<uint8_t *>(pointer);
92
93 auto rho_3 = block->getData<field::GhostLayerField<float, 1>>(rho_3ID);
94 auto rho_1 = block->getData<field::GhostLayerField<float, 1>>(rho_1ID);
95 auto rho_2 = block->getData<field::GhostLayerField<float, 1>>(rho_2ID);
96 auto rho_0 = block->getData<field::GhostLayerField<float, 1>>(rho_0ID);
97
98 auto &order_1 = order_1_;
99 auto &order_0 = order_0_;
100 auto &order_2 = order_2_;
101 auto &stoech_0 = stoech_0_;
102 auto &stoech_1 = stoech_1_;
103 auto &order_3 = order_3_;
104 auto &stoech_2 = stoech_2_;
105 auto &rate_coefficient = rate_coefficient_;
106 auto &stoech_3 = stoech_3_;
107 WALBERLA_ASSERT_GREATER_EQUAL(0, -int_c(rho_0->nrOfGhostLayers()))
108 float *RESTRICT _data_rho_0 = rho_0->dataAt(0, 0, 0, 0);
109 WALBERLA_ASSERT_GREATER_EQUAL(0, -int_c(rho_1->nrOfGhostLayers()))
110 float *RESTRICT _data_rho_1 = rho_1->dataAt(0, 0, 0, 0);
111 WALBERLA_ASSERT_GREATER_EQUAL(0, -int_c(rho_2->nrOfGhostLayers()))
112 float *RESTRICT _data_rho_2 = rho_2->dataAt(0, 0, 0, 0);
113 WALBERLA_ASSERT_GREATER_EQUAL(0, -int_c(rho_3->nrOfGhostLayers()))
114 float *RESTRICT _data_rho_3 = rho_3->dataAt(0, 0, 0, 0);
115 const int64_t _stride_rho_0_0 = int64_t(rho_0->xStride());
116 const int64_t _stride_rho_0_1 = int64_t(rho_0->yStride());
117 const int64_t _stride_rho_0_2 = int64_t(rho_0->zStride());
118 const int64_t _stride_rho_1_0 = int64_t(rho_1->xStride());
119 const int64_t _stride_rho_1_1 = int64_t(rho_1->yStride());
120 const int64_t _stride_rho_1_2 = int64_t(rho_1->zStride());
121 const int64_t _stride_rho_2_0 = int64_t(rho_2->xStride());
122 const int64_t _stride_rho_2_1 = int64_t(rho_2->yStride());
123 const int64_t _stride_rho_2_2 = int64_t(rho_2->zStride());
124 const int64_t _stride_rho_3_0 = int64_t(rho_3->xStride());
125 const int64_t _stride_rho_3_1 = int64_t(rho_3->yStride());
126 const int64_t _stride_rho_3_2 = int64_t(rho_3->zStride());
127 internal_62195c7636fc531694c87493561447d7::reactionkernelindexed_4_single_precision_boundary_ReactionKernelIndexed_4_single_precision(_data_indexVector, _data_rho_0, _data_rho_1, _data_rho_2, _data_rho_3, _stride_rho_0_0, _stride_rho_0_1, _stride_rho_0_2, _stride_rho_1_0, _stride_rho_1_1, _stride_rho_1_2, _stride_rho_2_0, _stride_rho_2_1, _stride_rho_2_2, _stride_rho_3_0, _stride_rho_3_1, _stride_rho_3_2, indexVectorSize, order_0, order_1, order_2, order_3, rate_coefficient, stoech_0, stoech_1, stoech_2, stoech_3);
128}
129
133
137
141
142} // namespace pystencils
143} // namespace walberla
#define FUNC_PREFIX
\file AdvectiveFluxKernel_double_precision.cpp \author pystencils
#define RESTRICT
\file AdvectiveFluxKernel_double_precision.h \author pystencils
static double * block(double *p, std::size_t index, std::size_t size)
Definition elc.cpp:172
static FUNC_PREFIX void reactionkernelindexed_4_single_precision_boundary_ReactionKernelIndexed_4_single_precision(uint8_t *RESTRICT const _data_indexVector, float *RESTRICT _data_rho_0, float *RESTRICT _data_rho_1, float *RESTRICT _data_rho_2, float *RESTRICT _data_rho_3, int64_t const _stride_rho_0_0, int64_t const _stride_rho_0_1, int64_t const _stride_rho_0_2, int64_t const _stride_rho_1_0, int64_t const _stride_rho_1_1, int64_t const _stride_rho_1_2, int64_t const _stride_rho_2_0, int64_t const _stride_rho_2_1, int64_t const _stride_rho_2_2, int64_t const _stride_rho_3_0, int64_t const _stride_rho_3_1, int64_t const _stride_rho_3_2, int32_t indexVectorSize, float order_0, float order_1, float order_2, float order_3, float rate_coefficient, float stoech_0, float stoech_1, float stoech_2, float stoech_3)
\file PackInfoPdfDoublePrecision.cpp \author pystencils