ESPResSo
Extensible Simulation Package for Research on Soft Matter Systems
Loading...
Searching...
No Matches
FrictionCouplingKernel_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 FrictionCouplingKernel_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 "FrictionCouplingKernel_single_precision.h"
25#include "core/DataTypes.h"
26#include "core/Macros.h"
27
28#define FUNC_PREFIX
29
30#if (defined WALBERLA_CXX_COMPILER_IS_GNU) || (defined WALBERLA_CXX_COMPILER_IS_CLANG)
31#pragma GCC diagnostic push
32#pragma GCC diagnostic ignored "-Wfloat-equal"
33#pragma GCC diagnostic ignored "-Wshadow"
34#pragma GCC diagnostic ignored "-Wconversion"
35#pragma GCC diagnostic ignored "-Wunused-variable"
36#endif
37
38#if (defined WALBERLA_CXX_COMPILER_IS_INTEL)
39#pragma warning push
40#pragma warning(disable : 1599)
41#endif
42
43using namespace std;
44
45namespace walberla {
46namespace pystencils {
47
48namespace internal_910e9429dc8b77dbed969a16d3f227fb {
49static FUNC_PREFIX void frictioncouplingkernel_single_precision_frictioncouplingkernel_single_precision(float D, float *RESTRICT _data_f, float *RESTRICT const _data_j, int64_t const _size_f_0, int64_t const _size_f_1, int64_t const _size_f_2, int64_t const _stride_f_0, int64_t const _stride_f_1, int64_t const _stride_f_2, int64_t const _stride_f_3, int64_t const _stride_j_0, int64_t const _stride_j_1, int64_t const _stride_j_2, int64_t const _stride_j_3, float kT, float rho_lb) {
50#pragma omp parallel
51 {
52#pragma omp for schedule(static)
53 for (int64_t ctr_2 = 1; ctr_2 < _size_f_2 - 1; ctr_2 += 1) {
54 for (int64_t ctr_1 = 1; ctr_1 < _size_f_1 - 1; ctr_1 += 1) {
55 for (int64_t ctr_0 = 1; ctr_0 < _size_f_0 - 1; ctr_0 += 1) {
56 _data_f[_stride_f_0 * ctr_0 + _stride_f_1 * ctr_1 + _stride_f_2 * ctr_2] = kT * (-_data_j[_stride_j_0 * ctr_0 + _stride_j_0 + _stride_j_1 * ctr_1 + _stride_j_1 + _stride_j_2 * ctr_2 + 3 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_0 + _stride_j_1 * ctr_1 + _stride_j_1 + _stride_j_2 * ctr_2 + _stride_j_2 + 9 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_0 + _stride_j_1 * ctr_1 + _stride_j_1 + _stride_j_2 * ctr_2 - _stride_j_2 + 10 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + _stride_j_2 + 5 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 - _stride_j_2 + 6 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2] - _data_j[_stride_j_0 * ctr_0 + _stride_j_0 + _stride_j_1 * ctr_1 - _stride_j_1 + _stride_j_2 * ctr_2 + 4 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_0 + _stride_j_1 * ctr_1 - _stride_j_1 + _stride_j_2 * ctr_2 + _stride_j_2 + 11 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_0 + _stride_j_1 * ctr_1 - _stride_j_1 + _stride_j_2 * ctr_2 - _stride_j_2 + 12 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 10 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 11 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 12 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 3 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 4 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 5 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 6 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 9 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2]) * 0.5f * ((1.0f) / (D)) * ((1.0f) / (rho_lb)) + _data_f[_stride_f_0 * ctr_0 + _stride_f_1 * ctr_1 + _stride_f_2 * ctr_2];
57 _data_f[_stride_f_0 * ctr_0 + _stride_f_1 * ctr_1 + _stride_f_2 * ctr_2 + _stride_f_3] = kT * (-_data_j[_stride_j_0 * ctr_0 + _stride_j_0 + _stride_j_1 * ctr_1 + _stride_j_1 + _stride_j_2 * ctr_2 + 3 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_0 + _stride_j_1 * ctr_1 + _stride_j_1 + _stride_j_2 * ctr_2 + _stride_j_2 + 9 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_0 + _stride_j_1 * ctr_1 + _stride_j_1 + _stride_j_2 * ctr_2 - _stride_j_2 + 10 * _stride_j_3] + _data_j[_stride_j_0 * ctr_0 + _stride_j_0 + _stride_j_1 * ctr_1 - _stride_j_1 + _stride_j_2 * ctr_2 + 4 * _stride_j_3] + _data_j[_stride_j_0 * ctr_0 + _stride_j_0 + _stride_j_1 * ctr_1 - _stride_j_1 + _stride_j_2 * ctr_2 + _stride_j_2 + 11 * _stride_j_3] + _data_j[_stride_j_0 * ctr_0 + _stride_j_0 + _stride_j_1 * ctr_1 - _stride_j_1 + _stride_j_2 * ctr_2 - _stride_j_2 + 12 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_1 + _stride_j_2 * ctr_2 + _stride_j_2 + 7 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_1 + _stride_j_2 * ctr_2 + _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_1 + _stride_j_2 * ctr_2 - _stride_j_2 + 8 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 10 * _stride_j_3] + _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 11 * _stride_j_3] + _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 12 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 3 * _stride_j_3] + _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 4 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 7 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 8 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 9 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + _stride_j_3]) * 0.5f * ((1.0f) / (D)) * ((1.0f) / (rho_lb)) + _data_f[_stride_f_0 * ctr_0 + _stride_f_1 * ctr_1 + _stride_f_2 * ctr_2 + _stride_f_3];
58 _data_f[_stride_f_0 * ctr_0 + _stride_f_1 * ctr_1 + _stride_f_2 * ctr_2 + 2 * _stride_f_3] = kT * (-_data_j[_stride_j_0 * ctr_0 + _stride_j_0 + _stride_j_1 * ctr_1 + _stride_j_1 + _stride_j_2 * ctr_2 + _stride_j_2 + 9 * _stride_j_3] + _data_j[_stride_j_0 * ctr_0 + _stride_j_0 + _stride_j_1 * ctr_1 + _stride_j_1 + _stride_j_2 * ctr_2 - _stride_j_2 + 10 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + _stride_j_2 + 5 * _stride_j_3] + _data_j[_stride_j_0 * ctr_0 + _stride_j_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 - _stride_j_2 + 6 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_0 + _stride_j_1 * ctr_1 - _stride_j_1 + _stride_j_2 * ctr_2 + _stride_j_2 + 11 * _stride_j_3] + _data_j[_stride_j_0 * ctr_0 + _stride_j_0 + _stride_j_1 * ctr_1 - _stride_j_1 + _stride_j_2 * ctr_2 - _stride_j_2 + 12 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_1 + _stride_j_2 * ctr_2 + _stride_j_2 + 7 * _stride_j_3] + _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_1 + _stride_j_2 * ctr_2 - _stride_j_2 + 8 * _stride_j_3] + _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 10 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 11 * _stride_j_3] + _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 12 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 2 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 5 * _stride_j_3] + _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 6 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 7 * _stride_j_3] + _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 8 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 9 * _stride_j_3] - _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + _stride_j_2 + 2 * _stride_j_3]) * 0.5f * ((1.0f) / (D)) * ((1.0f) / (rho_lb)) + _data_f[_stride_f_0 * ctr_0 + _stride_f_1 * ctr_1 + _stride_f_2 * ctr_2 + 2 * _stride_f_3];
59 }
60 }
61 }
62 }
63}
64} // namespace internal_910e9429dc8b77dbed969a16d3f227fb
65
66void FrictionCouplingKernel_single_precision::run(IBlock *block) {
67
68 auto f = block->getData<field::GhostLayerField<float, 3>>(fID);
69 auto j = block->getData<field::GhostLayerField<float, 13>>(jID);
70
71 auto &kT = this->kT_;
72 auto &D = this->D_;
73 auto &rho_lb = this->rho_lb_;
74 WALBERLA_ASSERT_GREATER_EQUAL(-1, -int_c(f->nrOfGhostLayers()))
75 float *RESTRICT _data_f = f->dataAt(-1, -1, -1, 0);
76 WALBERLA_ASSERT_GREATER_EQUAL(-1, -int_c(j->nrOfGhostLayers()))
77 float *RESTRICT const _data_j = j->dataAt(-1, -1, -1, 0);
78 WALBERLA_ASSERT_GREATER_EQUAL(f->xSizeWithGhostLayer(), int64_t(int64_c(f->xSize()) + 2))
79 const int64_t _size_f_0 = int64_t(int64_c(f->xSize()) + 2);
80 WALBERLA_ASSERT_GREATER_EQUAL(f->ySizeWithGhostLayer(), int64_t(int64_c(f->ySize()) + 2))
81 const int64_t _size_f_1 = int64_t(int64_c(f->ySize()) + 2);
82 WALBERLA_ASSERT_GREATER_EQUAL(f->zSizeWithGhostLayer(), int64_t(int64_c(f->zSize()) + 2))
83 const int64_t _size_f_2 = int64_t(int64_c(f->zSize()) + 2);
84 const int64_t _stride_f_0 = int64_t(f->xStride());
85 const int64_t _stride_f_1 = int64_t(f->yStride());
86 const int64_t _stride_f_2 = int64_t(f->zStride());
87 const int64_t _stride_f_3 = int64_t(1 * int64_t(f->fStride()));
88 const int64_t _stride_j_0 = int64_t(j->xStride());
89 const int64_t _stride_j_1 = int64_t(j->yStride());
90 const int64_t _stride_j_2 = int64_t(j->zStride());
91 const int64_t _stride_j_3 = int64_t(1 * int64_t(j->fStride()));
92 internal_910e9429dc8b77dbed969a16d3f227fb::frictioncouplingkernel_single_precision_frictioncouplingkernel_single_precision(D, _data_f, _data_j, _size_f_0, _size_f_1, _size_f_2, _stride_f_0, _stride_f_1, _stride_f_2, _stride_f_3, _stride_j_0, _stride_j_1, _stride_j_2, _stride_j_3, kT, rho_lb);
93}
94
95void FrictionCouplingKernel_single_precision::runOnCellInterval(const shared_ptr<StructuredBlockStorage> &blocks, const CellInterval &globalCellInterval, cell_idx_t ghostLayers, IBlock *block) {
96
97 CellInterval ci = globalCellInterval;
98 CellInterval blockBB = blocks->getBlockCellBB(*block);
99 blockBB.expand(ghostLayers);
100 ci.intersect(blockBB);
101 blocks->transformGlobalToBlockLocalCellInterval(ci, *block);
102 if (ci.empty())
103 return;
104
105 auto f = block->getData<field::GhostLayerField<float, 3>>(fID);
106 auto j = block->getData<field::GhostLayerField<float, 13>>(jID);
107
108 auto &kT = this->kT_;
109 auto &D = this->D_;
110 auto &rho_lb = this->rho_lb_;
111 WALBERLA_ASSERT_GREATER_EQUAL(ci.xMin() - 1, -int_c(f->nrOfGhostLayers()))
112 WALBERLA_ASSERT_GREATER_EQUAL(ci.yMin() - 1, -int_c(f->nrOfGhostLayers()))
113 WALBERLA_ASSERT_GREATER_EQUAL(ci.zMin() - 1, -int_c(f->nrOfGhostLayers()))
114 float *RESTRICT _data_f = f->dataAt(ci.xMin() - 1, ci.yMin() - 1, ci.zMin() - 1, 0);
115 WALBERLA_ASSERT_GREATER_EQUAL(ci.xMin() - 1, -int_c(j->nrOfGhostLayers()))
116 WALBERLA_ASSERT_GREATER_EQUAL(ci.yMin() - 1, -int_c(j->nrOfGhostLayers()))
117 WALBERLA_ASSERT_GREATER_EQUAL(ci.zMin() - 1, -int_c(j->nrOfGhostLayers()))
118 float *RESTRICT const _data_j = j->dataAt(ci.xMin() - 1, ci.yMin() - 1, ci.zMin() - 1, 0);
119 WALBERLA_ASSERT_GREATER_EQUAL(f->xSizeWithGhostLayer(), int64_t(int64_c(ci.xSize()) + 2))
120 const int64_t _size_f_0 = int64_t(int64_c(ci.xSize()) + 2);
121 WALBERLA_ASSERT_GREATER_EQUAL(f->ySizeWithGhostLayer(), int64_t(int64_c(ci.ySize()) + 2))
122 const int64_t _size_f_1 = int64_t(int64_c(ci.ySize()) + 2);
123 WALBERLA_ASSERT_GREATER_EQUAL(f->zSizeWithGhostLayer(), int64_t(int64_c(ci.zSize()) + 2))
124 const int64_t _size_f_2 = int64_t(int64_c(ci.zSize()) + 2);
125 const int64_t _stride_f_0 = int64_t(f->xStride());
126 const int64_t _stride_f_1 = int64_t(f->yStride());
127 const int64_t _stride_f_2 = int64_t(f->zStride());
128 const int64_t _stride_f_3 = int64_t(1 * int64_t(f->fStride()));
129 const int64_t _stride_j_0 = int64_t(j->xStride());
130 const int64_t _stride_j_1 = int64_t(j->yStride());
131 const int64_t _stride_j_2 = int64_t(j->zStride());
132 const int64_t _stride_j_3 = int64_t(1 * int64_t(j->fStride()));
133 internal_910e9429dc8b77dbed969a16d3f227fb::frictioncouplingkernel_single_precision_frictioncouplingkernel_single_precision(D, _data_f, _data_j, _size_f_0, _size_f_1, _size_f_2, _stride_f_0, _stride_f_1, _stride_f_2, _stride_f_3, _stride_j_0, _stride_j_1, _stride_j_2, _stride_j_3, kT, rho_lb);
134}
135
136} // namespace pystencils
137} // namespace walberla
138
139#if (defined WALBERLA_CXX_COMPILER_IS_GNU) || (defined WALBERLA_CXX_COMPILER_IS_CLANG)
140#pragma GCC diagnostic pop
141#endif
142
143#if (defined WALBERLA_CXX_COMPILER_IS_INTEL)
144#pragma warning pop
145#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
FrictionCouplingKernel_single_precision.h
walberla::pystencils::FrictionCouplingKernel_single_precision::runOnCellInterval
void runOnCellInterval(const shared_ptr< StructuredBlockStorage > &blocks, const CellInterval &globalCellInterval, cell_idx_t ghostLayers, IBlock *block)
Definition FrictionCouplingKernel_single_precision.cpp:95
walberla::pystencils::FrictionCouplingKernel_single_precision::run
void run(IBlock *block)
Definition FrictionCouplingKernel_single_precision.cpp:66
block
static double * block(double *p, std::size_t index, std::size_t size)
Definition elc.cpp:175
std
STL namespace.
walberla::pystencils::internal_910e9429dc8b77dbed969a16d3f227fb::frictioncouplingkernel_single_precision_frictioncouplingkernel_single_precision
static FUNC_PREFIX void frictioncouplingkernel_single_precision_frictioncouplingkernel_single_precision(float D, float *RESTRICT _data_f, float *RESTRICT const _data_j, int64_t const _size_f_0, int64_t const _size_f_1, int64_t const _size_f_2, int64_t const _stride_f_0, int64_t const _stride_f_1, int64_t const _stride_f_2, int64_t const _stride_f_3, int64_t const _stride_j_0, int64_t const _stride_j_1, int64_t const _stride_j_2, int64_t const _stride_j_3, float kT, float rho_lb)
Definition FrictionCouplingKernel_single_precision.cpp:49
walberla
\file PackInfoPdfDoublePrecision.cpp \author pystencils
Definition EKWalberla.hpp:38