ESPResSo
Extensible Simulation Package for Research on Soft Matter Systems
Loading...
Searching...
No Matches
AdvectiveFluxKernel_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 AdvectiveFluxKernel_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 "AdvectiveFluxKernel_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_47df4b171f276b8c3a55fc08d45e245e {
49static FUNC_PREFIX void advectivefluxkernel_single_precision_advectivefluxkernel_single_precision(float *RESTRICT const _data_j, float *RESTRICT const _data_rho, float *RESTRICT const _data_u, 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, int64_t const _stride_u_0, int64_t const _stride_u_1, int64_t const _stride_u_2, int64_t const _stride_u_3) {
50#pragma omp parallel
51 {
52#pragma omp for schedule(static)
53 for (int64_t ctr_2 = 0; ctr_2 < _size_j_2; ctr_2 += 1) {
54 for (int64_t ctr_1 = 0; ctr_1 < _size_j_1; ctr_1 += 1) {
55 for (int64_t ctr_0 = 1; ctr_0 < _size_j_0; ctr_0 += 1) {
56 if (ctr_1 > 0 && ctr_2 > 0 && ctr_1 < _size_j_1 - 1 && ctr_2 < _size_j_2 - 1) {
57 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2] = -(1.0f - fabs(_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3])) * (1.0f - fabs(_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_3])) * ((_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2] < 0.0f) ? (1.0f) : (0.0f)) * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2] - (1.0f - fabs(_data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3])) * (1.0f - fabs(_data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_3])) * ((_data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2] > 0.0f) ? (1.0f) : (0.0f)) * _data_rho[_stride_rho_0 * ctr_0 - _stride_rho_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] * _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2] + _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2];
58 }
59 if (ctr_1 > 0 && ctr_2 > 0 && ctr_0 < _size_j_0 - 1 && ctr_2 < _size_j_2 - 1) {
60 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + _stride_j_3] = -(1.0f - fabs(_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3])) * (1.0f - fabs(_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2])) * ((_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_3] < 0.0f) ? (1.0f) : (0.0f)) * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_3] - (1.0f - fabs(_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3])) * (1.0f - fabs(_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2])) * ((_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 + _stride_u_3] > 0.0f) ? (1.0f) : (0.0f)) * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 - _stride_rho_1 + _stride_rho_2 * ctr_2] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 + _stride_u_3] + _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + _stride_j_3];
61 }
62 if (ctr_1 > 0 && ctr_2 > 0 && ctr_0 < _size_j_0 - 1 && ctr_1 < _size_j_1 - 1) {
63 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 2 * _stride_j_3] = -(1.0f - fabs(_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_3])) * (1.0f - fabs(_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2])) * ((_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3] < 0.0f) ? (1.0f) : (0.0f)) * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3] - (1.0f - fabs(_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 - _stride_u_2 + _stride_u_3])) * (1.0f - fabs(_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 - _stride_u_2])) * ((_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 - _stride_u_2 + 2 * _stride_u_3] > 0.0f) ? (1.0f) : (0.0f)) * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2 - _stride_rho_2] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 - _stride_u_2 + 2 * _stride_u_3] + _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 2 * _stride_j_3];
64 }
65 if (ctr_1 > 0 && ctr_2 > 0 && ctr_2 < _size_j_2 - 1) {
66 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 3 * _stride_j_3] = (1.0f - fabs(_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3])) * ((_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_3] < 0.0f && _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2] < 0.0f) ? (1.0f) : (0.0f)) * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_3] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2] - (1.0f - fabs(_data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3])) * ((_data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 + _stride_u_3] > 0.0f && _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2] > 0.0f) ? (1.0f) : (0.0f)) * _data_rho[_stride_rho_0 * ctr_0 - _stride_rho_0 + _stride_rho_1 * ctr_1 - _stride_rho_1 + _stride_rho_2 * ctr_2] * _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 + _stride_u_3] * _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2] + _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 3 * _stride_j_3];
67 }
68 if (ctr_2 > 0 && ctr_1 < _size_j_1 - 1 && ctr_2 < _size_j_2 - 1) {
69 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 4 * _stride_j_3] = -(1.0f - fabs(_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3])) * ((_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_3] > 0.0f && _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2] < 0.0f) ? (1.0f) : (0.0f)) * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_3] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2] + (1.0f - fabs(_data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3])) * ((_data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_1 + _stride_u_2 * ctr_2] > 0.0f && _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_1 + _stride_u_2 * ctr_2 + _stride_u_3] < 0.0f) ? (1.0f) : (0.0f)) * _data_rho[_stride_rho_0 * ctr_0 - _stride_rho_0 + _stride_rho_1 * ctr_1 + _stride_rho_1 + _stride_rho_2 * ctr_2] * _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_1 + _stride_u_2 * ctr_2 + _stride_u_3] * _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_1 + _stride_u_2 * ctr_2] + _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 4 * _stride_j_3];
70 }
71 if (ctr_1 > 0 && ctr_2 > 0 && ctr_1 < _size_j_1 - 1) {
72 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 5 * _stride_j_3] = (1.0f - fabs(_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_3])) * ((_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3] < 0.0f && _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2] < 0.0f) ? (1.0f) : (0.0f)) * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2] - (1.0f - fabs(_data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 - _stride_u_2 + _stride_u_3])) * ((_data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 - _stride_u_2 + 2 * _stride_u_3] > 0.0f && _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 - _stride_u_2] > 0.0f) ? (1.0f) : (0.0f)) * _data_rho[_stride_rho_0 * ctr_0 - _stride_rho_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2 - _stride_rho_2] * _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 - _stride_u_2 + 2 * _stride_u_3] * _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 - _stride_u_2] + _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 5 * _stride_j_3];
73 }
74 if (ctr_1 > 0 && ctr_1 < _size_j_1 - 1 && ctr_2 < _size_j_2 - 1) {
75 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 6 * _stride_j_3] = -(1.0f - fabs(_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_3])) * ((_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3] > 0.0f && _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2] < 0.0f) ? (1.0f) : (0.0f)) * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2] + (1.0f - fabs(_data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_2 + _stride_u_3])) * ((_data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_2] > 0.0f && _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_2 + 2 * _stride_u_3] < 0.0f) ? (1.0f) : (0.0f)) * _data_rho[_stride_rho_0 * ctr_0 - _stride_rho_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2 + _stride_rho_2] * _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_2 + 2 * _stride_u_3] * _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_2] + _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 6 * _stride_j_3];
76 }
77 if (ctr_1 > 0 && ctr_2 > 0 && ctr_0 < _size_j_0 - 1) {
78 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 7 * _stride_j_3] = (1.0f - fabs(_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2])) * ((_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3] < 0.0f && _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_3] < 0.0f) ? (1.0f) : (0.0f)) * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_3] - (1.0f - fabs(_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 - _stride_u_2])) * ((_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 - _stride_u_2 + 2 * _stride_u_3] > 0.0f && _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 - _stride_u_2 + _stride_u_3] > 0.0f) ? (1.0f) : (0.0f)) * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 - _stride_rho_1 + _stride_rho_2 * ctr_2 - _stride_rho_2] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 - _stride_u_2 + 2 * _stride_u_3] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 - _stride_u_2 + _stride_u_3] + _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 7 * _stride_j_3];
79 }
80 if (ctr_1 > 0 && ctr_0 < _size_j_0 - 1 && ctr_2 < _size_j_2 - 1) {
81 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 8 * _stride_j_3] = -(1.0f - fabs(_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2])) * ((_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3] > 0.0f && _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_3] < 0.0f) ? (1.0f) : (0.0f)) * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_3] + (1.0f - fabs(_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 + _stride_u_2])) * ((_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 + _stride_u_2 + _stride_u_3] > 0.0f && _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 + _stride_u_2 + 2 * _stride_u_3] < 0.0f) ? (1.0f) : (0.0f)) * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 - _stride_rho_1 + _stride_rho_2 * ctr_2 + _stride_rho_2] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 + _stride_u_2 + 2 * _stride_u_3] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 + _stride_u_2 + _stride_u_3] + _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 8 * _stride_j_3];
82 }
83 if (ctr_1 > 0 && ctr_2 > 0) {
84 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 9 * _stride_j_3] = -((_data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 - _stride_u_2 + 2 * _stride_u_3] > 0.0f && _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 - _stride_u_2 + _stride_u_3] > 0.0f && _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 - _stride_u_2] > 0.0f) ? (1.0f) : (0.0f)) * _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] * _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 - _stride_u_2 + 2 * _stride_u_3] * _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 - _stride_u_2 + _stride_u_3] * _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 - _stride_u_2] - ((_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3] < 0.0f && _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_3] < 0.0f && _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2] < 0.0f) ? (1.0f) : (0.0f)) * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_3] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2] + _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 9 * _stride_j_3];
85 }
86 if (ctr_1 > 0 && ctr_2 < _size_j_2 - 1) {
87 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 10 * _stride_j_3] = ((_data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 + _stride_u_2 + _stride_u_3] > 0.0f && _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 + _stride_u_2] > 0.0f && _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 + _stride_u_2 + 2 * _stride_u_3] < 0.0f) ? (1.0f) : (0.0f)) * _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] * _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 + _stride_u_2 + 2 * _stride_u_3] * _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 + _stride_u_2 + _stride_u_3] * _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 - _stride_u_1 + _stride_u_2 * ctr_2 + _stride_u_2] + ((_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3] > 0.0f && _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_3] < 0.0f && _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2] < 0.0f) ? (1.0f) : (0.0f)) * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_3] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2] + _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 10 * _stride_j_3];
88 }
89 if (ctr_2 > 0 && ctr_1 < _size_j_1 - 1) {
90 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 11 * _stride_j_3] = ((_data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_1 + _stride_u_2 * ctr_2 - _stride_u_2 + 2 * _stride_u_3] > 0.0f && _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_1 + _stride_u_2 * ctr_2 - _stride_u_2] > 0.0f && _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_1 + _stride_u_2 * ctr_2 - _stride_u_2 + _stride_u_3] < 0.0f) ? (1.0f) : (0.0f)) * _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] * _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_1 + _stride_u_2 * ctr_2 - _stride_u_2 + 2 * _stride_u_3] * _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_1 + _stride_u_2 * ctr_2 - _stride_u_2 + _stride_u_3] * _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_1 + _stride_u_2 * ctr_2 - _stride_u_2] + ((_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_3] > 0.0f && _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3] < 0.0f && _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2] < 0.0f) ? (1.0f) : (0.0f)) * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_3] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2] + _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 11 * _stride_j_3];
91 }
92 if (ctr_1 < _size_j_1 - 1 && ctr_2 < _size_j_2 - 1) {
93 _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 12 * _stride_j_3] = -((_data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_1 + _stride_u_2 * ctr_2 + _stride_u_2] > 0.0f && _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_1 + _stride_u_2 * ctr_2 + _stride_u_2 + 2 * _stride_u_3] < 0.0f && _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_1 + _stride_u_2 * ctr_2 + _stride_u_2 + _stride_u_3] < 0.0f) ? (1.0f) : (0.0f)) * _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] * _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_1 + _stride_u_2 * ctr_2 + _stride_u_2 + 2 * _stride_u_3] * _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_1 + _stride_u_2 * ctr_2 + _stride_u_2 + _stride_u_3] * _data_u[_stride_u_0 * ctr_0 - _stride_u_0 + _stride_u_1 * ctr_1 + _stride_u_1 + _stride_u_2 * ctr_2 + _stride_u_2] - ((_data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3] > 0.0f && _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_3] > 0.0f && _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2] < 0.0f) ? (1.0f) : (0.0f)) * _data_rho[_stride_rho_0 * ctr_0 + _stride_rho_1 * ctr_1 + _stride_rho_2 * ctr_2] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + 2 * _stride_u_3] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2 + _stride_u_3] * _data_u[_stride_u_0 * ctr_0 + _stride_u_1 * ctr_1 + _stride_u_2 * ctr_2] + _data_j[_stride_j_0 * ctr_0 + _stride_j_1 * ctr_1 + _stride_j_2 * ctr_2 + 12 * _stride_j_3];
94 }
95 }
96 }
97 }
98 }
99}
100} // namespace internal_47df4b171f276b8c3a55fc08d45e245e
101
102void AdvectiveFluxKernel_single_precision::run(IBlock *block) {
103
104 auto j = block->getData<field::GhostLayerField<float, 13>>(jID);
105 auto rho = block->getData<field::GhostLayerField<float, 1>>(rhoID);
106 auto u = block->getData<field::GhostLayerField<float, 3>>(uID);
107
108 WALBERLA_ASSERT_GREATER_EQUAL(-1, -int_c(j->nrOfGhostLayers()))
109 float *RESTRICT const _data_j = j->dataAt(-1, -1, -1, 0);
110 WALBERLA_ASSERT_GREATER_EQUAL(-1, -int_c(rho->nrOfGhostLayers()))
111 float *RESTRICT const _data_rho = rho->dataAt(-1, -1, -1, 0);
112 WALBERLA_ASSERT_GREATER_EQUAL(-1, -int_c(u->nrOfGhostLayers()))
113 float *RESTRICT const _data_u = u->dataAt(-1, -1, -1, 0);
114 WALBERLA_ASSERT_GREATER_EQUAL(j->xSizeWithGhostLayer(), int64_t(int64_c(j->xSize()) + 2))
115 const int64_t _size_j_0 = int64_t(int64_c(j->xSize()) + 2);
116 WALBERLA_ASSERT_GREATER_EQUAL(j->ySizeWithGhostLayer(), int64_t(int64_c(j->ySize()) + 2))
117 const int64_t _size_j_1 = int64_t(int64_c(j->ySize()) + 2);
118 WALBERLA_ASSERT_GREATER_EQUAL(j->zSizeWithGhostLayer(), int64_t(int64_c(j->zSize()) + 2))
119 const int64_t _size_j_2 = int64_t(int64_c(j->zSize()) + 2);
120 const int64_t _stride_j_0 = int64_t(j->xStride());
121 const int64_t _stride_j_1 = int64_t(j->yStride());
122 const int64_t _stride_j_2 = int64_t(j->zStride());
123 const int64_t _stride_j_3 = int64_t(1 * int64_t(j->fStride()));
124 const int64_t _stride_rho_0 = int64_t(rho->xStride());
125 const int64_t _stride_rho_1 = int64_t(rho->yStride());
126 const int64_t _stride_rho_2 = int64_t(rho->zStride());
127 const int64_t _stride_u_0 = int64_t(u->xStride());
128 const int64_t _stride_u_1 = int64_t(u->yStride());
129 const int64_t _stride_u_2 = int64_t(u->zStride());
130 const int64_t _stride_u_3 = int64_t(1 * int64_t(u->fStride()));
131 internal_47df4b171f276b8c3a55fc08d45e245e::advectivefluxkernel_single_precision_advectivefluxkernel_single_precision(_data_j, _data_rho, _data_u, _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, _stride_u_0, _stride_u_1, _stride_u_2, _stride_u_3);
132}
133
134void AdvectiveFluxKernel_single_precision::runOnCellInterval(const shared_ptr<StructuredBlockStorage> &blocks, const CellInterval &globalCellInterval, cell_idx_t ghostLayers, IBlock *block) {
135
136 CellInterval ci = globalCellInterval;
137 CellInterval blockBB = blocks->getBlockCellBB(*block);
138 blockBB.expand(ghostLayers);
139 ci.intersect(blockBB);
140 blocks->transformGlobalToBlockLocalCellInterval(ci, *block);
141 if (ci.empty())
142 return;
143
144 auto j = block->getData<field::GhostLayerField<float, 13>>(jID);
145 auto rho = block->getData<field::GhostLayerField<float, 1>>(rhoID);
146 auto u = block->getData<field::GhostLayerField<float, 3>>(uID);
147
148 WALBERLA_ASSERT_GREATER_EQUAL(ci.xMin() - 1, -int_c(j->nrOfGhostLayers()))
149 WALBERLA_ASSERT_GREATER_EQUAL(ci.yMin() - 1, -int_c(j->nrOfGhostLayers()))
150 WALBERLA_ASSERT_GREATER_EQUAL(ci.zMin() - 1, -int_c(j->nrOfGhostLayers()))
151 float *RESTRICT const _data_j = j->dataAt(ci.xMin() - 1, ci.yMin() - 1, ci.zMin() - 1, 0);
152 WALBERLA_ASSERT_GREATER_EQUAL(ci.xMin() - 1, -int_c(rho->nrOfGhostLayers()))
153 WALBERLA_ASSERT_GREATER_EQUAL(ci.yMin() - 1, -int_c(rho->nrOfGhostLayers()))
154 WALBERLA_ASSERT_GREATER_EQUAL(ci.zMin() - 1, -int_c(rho->nrOfGhostLayers()))
155 float *RESTRICT const _data_rho = rho->dataAt(ci.xMin() - 1, ci.yMin() - 1, ci.zMin() - 1, 0);
156 WALBERLA_ASSERT_GREATER_EQUAL(ci.xMin() - 1, -int_c(u->nrOfGhostLayers()))
157 WALBERLA_ASSERT_GREATER_EQUAL(ci.yMin() - 1, -int_c(u->nrOfGhostLayers()))
158 WALBERLA_ASSERT_GREATER_EQUAL(ci.zMin() - 1, -int_c(u->nrOfGhostLayers()))
159 float *RESTRICT const _data_u = u->dataAt(ci.xMin() - 1, ci.yMin() - 1, ci.zMin() - 1, 0);
160 WALBERLA_ASSERT_GREATER_EQUAL(j->xSizeWithGhostLayer(), int64_t(int64_c(ci.xSize()) + 2))
161 const int64_t _size_j_0 = int64_t(int64_c(ci.xSize()) + 2);
162 WALBERLA_ASSERT_GREATER_EQUAL(j->ySizeWithGhostLayer(), int64_t(int64_c(ci.ySize()) + 2))
163 const int64_t _size_j_1 = int64_t(int64_c(ci.ySize()) + 2);
164 WALBERLA_ASSERT_GREATER_EQUAL(j->zSizeWithGhostLayer(), int64_t(int64_c(ci.zSize()) + 2))
165 const int64_t _size_j_2 = int64_t(int64_c(ci.zSize()) + 2);
166 const int64_t _stride_j_0 = int64_t(j->xStride());
167 const int64_t _stride_j_1 = int64_t(j->yStride());
168 const int64_t _stride_j_2 = int64_t(j->zStride());
169 const int64_t _stride_j_3 = int64_t(1 * int64_t(j->fStride()));
170 const int64_t _stride_rho_0 = int64_t(rho->xStride());
171 const int64_t _stride_rho_1 = int64_t(rho->yStride());
172 const int64_t _stride_rho_2 = int64_t(rho->zStride());
173 const int64_t _stride_u_0 = int64_t(u->xStride());
174 const int64_t _stride_u_1 = int64_t(u->yStride());
175 const int64_t _stride_u_2 = int64_t(u->zStride());
176 const int64_t _stride_u_3 = int64_t(1 * int64_t(u->fStride()));
177 internal_47df4b171f276b8c3a55fc08d45e245e::advectivefluxkernel_single_precision_advectivefluxkernel_single_precision(_data_j, _data_rho, _data_u, _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, _stride_u_0, _stride_u_1, _stride_u_2, _stride_u_3);
178}
179
180} // namespace pystencils
181} // namespace walberla
182
183#if (defined WALBERLA_CXX_COMPILER_IS_GNU) || (defined WALBERLA_CXX_COMPILER_IS_CLANG)
184#pragma GCC diagnostic pop
185#endif
186
187#if (defined WALBERLA_CXX_COMPILER_IS_INTEL)
188#pragma warning pop
189#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
AdvectiveFluxKernel_single_precision.h
walberla::pystencils::AdvectiveFluxKernel_single_precision::run
void run(IBlock *block)
Definition AdvectiveFluxKernel_single_precision.cpp:102
walberla::pystencils::AdvectiveFluxKernel_single_precision::runOnCellInterval
void runOnCellInterval(const shared_ptr< StructuredBlockStorage > &blocks, const CellInterval &globalCellInterval, cell_idx_t ghostLayers, IBlock *block)
Definition AdvectiveFluxKernel_single_precision.cpp:134
block
static double * block(double *p, std::size_t index, std::size_t size)
Definition elc.cpp:175
std
STL namespace.
walberla::pystencils::internal_47df4b171f276b8c3a55fc08d45e245e::advectivefluxkernel_single_precision_advectivefluxkernel_single_precision
static FUNC_PREFIX void advectivefluxkernel_single_precision_advectivefluxkernel_single_precision(float *RESTRICT const _data_j, float *RESTRICT const _data_rho, float *RESTRICT const _data_u, 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, int64_t const _stride_u_0, int64_t const _stride_u_1, int64_t const _stride_u_2, int64_t const _stride_u_3)
Definition AdvectiveFluxKernel_single_precision.cpp:49
walberla
\file PackInfoPdfDoublePrecision.cpp \author pystencils
Definition EKWalberla.hpp:38