ESPResSo
Extensible Simulation Package for Research on Soft Matter Systems
Loading...
Searching...
No Matches
ReactionKernelBulk_5_double_precision_CUDA.h
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 ReactionKernelBulk_5_double_precision_CUDA.h
17//! \\author pystencils
18//======================================================================================================================
19
20// kernel generated with pystencils v1.4+1.ge851f4e, lbmpy v1.4+1.ge9efe34,
21// sympy v1.12.1, lbmpy_walberla/pystencils_walberla from waLBerla commit
22// 007e77e077ad9d22b5eed6f3d3118240993e553c
23
24#pragma once
25#include "core/DataTypes.h"
26#include "core/logging/Logging.h"
27
28#include "gpu/GPUField.h"
29#include "gpu/GPUWrapper.h"
30
31#include "domain_decomposition/BlockDataID.h"
32#include "domain_decomposition/IBlock.h"
33#include "domain_decomposition/StructuredBlockStorage.h"
34#include "field/SwapableCompare.h"
35
36#include <functional>
37#include <unordered_map>
38
39#ifdef __GNUC__
40#define RESTRICT __restrict__
41#else
42#define RESTRICT
43#endif
44
45#if (defined WALBERLA_CXX_COMPILER_IS_GNU) || \
46 (defined WALBERLA_CXX_COMPILER_IS_CLANG)
47#pragma GCC diagnostic push
48#pragma GCC diagnostic ignored "-Wunused-parameter"
49#pragma GCC diagnostic ignored "-Wreorder"
50#endif
51
52namespace walberla {
53namespace pystencils {
54
56public:
58 BlockDataID rho_0ID_, BlockDataID rho_1ID_, BlockDataID rho_2ID_,
59 BlockDataID rho_3ID_, BlockDataID rho_4ID_, double order_0,
60 double order_1, double order_2, double order_3, double order_4,
61 double rate_coefficient, double stoech_0, double stoech_1,
62 double stoech_2, double stoech_3, double stoech_4)
63 : rho_0ID(rho_0ID_), rho_1ID(rho_1ID_), rho_2ID(rho_2ID_),
64 rho_3ID(rho_3ID_), rho_4ID(rho_4ID_), order_0_(order_0),
65 order_1_(order_1), order_2_(order_2), order_3_(order_3),
66 order_4_(order_4), rate_coefficient_(rate_coefficient),
67 stoech_0_(stoech_0), stoech_1_(stoech_1), stoech_2_(stoech_2),
68 stoech_3_(stoech_3), stoech_4_(stoech_4) {}
69
70 void run(IBlock *block, gpuStream_t stream = nullptr);
71
72 void runOnCellInterval(const shared_ptr<StructuredBlockStorage> &blocks,
73 const CellInterval &globalCellInterval,
74 cell_idx_t ghostLayers, IBlock *block,
75 gpuStream_t stream = nullptr);
76
77 void operator()(IBlock *block, gpuStream_t stream = nullptr) {
79 }
80
81 static std::function<void(IBlock *)> getSweep(
82 const shared_ptr<ReactionKernelBulk_5_double_precision_CUDA> &kernel) {
83 return [kernel](IBlock *b) { kernel->run(b); };
84 }
85
86 static std::function<void(IBlock *, gpuStream_t)> getSweepOnCellInterval(
87 const shared_ptr<ReactionKernelBulk_5_double_precision_CUDA> &kernel,
88 const shared_ptr<StructuredBlockStorage> &blocks,
89 const CellInterval &globalCellInterval, cell_idx_t ghostLayers = 1) {
90 return [kernel, blocks, globalCellInterval,
91 ghostLayers](IBlock *b, gpuStream_t stream = nullptr) {
92 kernel->runOnCellInterval(blocks, globalCellInterval, ghostLayers, b,
93 stream);
94 };
95 }
96
97 std::function<void(IBlock *)> getSweep(gpuStream_t stream = nullptr) {
98 return [this, stream](IBlock *b) { this->run(b, stream); };
99 }
100
101 std::function<void(IBlock *)>
102 getSweepOnCellInterval(const shared_ptr<StructuredBlockStorage> &blocks,
103 const CellInterval &globalCellInterval,
104 cell_idx_t ghostLayers = 1,
105 gpuStream_t stream = nullptr) {
106 return [this, blocks, globalCellInterval, ghostLayers, stream](IBlock *b) {
107 this->runOnCellInterval(blocks, globalCellInterval, ghostLayers, b,
108 stream);
109 };
110 }
111
112 void configure(const shared_ptr<StructuredBlockStorage> & /*blocks*/,
113 IBlock * /*block*/) {}
114
115 inline double getOrder_0() const { return order_0_; }
116 inline double getOrder_1() const { return order_1_; }
117 inline double getOrder_2() const { return order_2_; }
118 inline double getOrder_3() const { return order_3_; }
119 inline double getOrder_4() const { return order_4_; }
120 inline double getRate_coefficient() const { return rate_coefficient_; }
121 inline double getStoech_0() const { return stoech_0_; }
122 inline double getStoech_1() const { return stoech_1_; }
123 inline double getStoech_2() const { return stoech_2_; }
124 inline double getStoech_3() const { return stoech_3_; }
125 inline double getStoech_4() const { return stoech_4_; }
126 inline void setOrder_0(const double value) { order_0_ = value; }
127 inline void setOrder_1(const double value) { order_1_ = value; }
128 inline void setOrder_2(const double value) { order_2_ = value; }
129 inline void setOrder_3(const double value) { order_3_ = value; }
130 inline void setOrder_4(const double value) { order_4_ = value; }
131 inline void setRate_coefficient(const double value) {
132 rate_coefficient_ = value;
133 }
134 inline void setStoech_0(const double value) { stoech_0_ = value; }
135 inline void setStoech_1(const double value) { stoech_1_ = value; }
136 inline void setStoech_2(const double value) { stoech_2_ = value; }
137 inline void setStoech_3(const double value) { stoech_3_ = value; }
138 inline void setStoech_4(const double value) { stoech_4_ = value; }
139
140private:
141 BlockDataID rho_0ID;
142 BlockDataID rho_1ID;
143 BlockDataID rho_2ID;
144 BlockDataID rho_3ID;
145 BlockDataID rho_4ID;
146 double order_0_;
147 double order_1_;
148 double order_2_;
149 double order_3_;
150 double order_4_;
151 double rate_coefficient_;
152 double stoech_0_;
153 double stoech_1_;
154 double stoech_2_;
155 double stoech_3_;
156 double stoech_4_;
157};
158
159} // namespace pystencils
160} // namespace walberla
161
162#if (defined WALBERLA_CXX_COMPILER_IS_GNU) || \
163 (defined WALBERLA_CXX_COMPILER_IS_CLANG)
164#pragma GCC diagnostic pop
165#endif
std::function< void(IBlock *)> getSweepOnCellInterval(const shared_ptr< StructuredBlockStorage > &blocks, const CellInterval &globalCellInterval, cell_idx_t ghostLayers=1, gpuStream_t stream=nullptr)
static std::function< void(IBlock *)> getSweep(const shared_ptr< ReactionKernelBulk_5_double_precision_CUDA > &kernel)
static std::function< void(IBlock *, gpuStream_t)> getSweepOnCellInterval(const shared_ptr< ReactionKernelBulk_5_double_precision_CUDA > &kernel, const shared_ptr< StructuredBlockStorage > &blocks, const CellInterval &globalCellInterval, cell_idx_t ghostLayers=1)
ReactionKernelBulk_5_double_precision_CUDA(BlockDataID rho_0ID_, BlockDataID rho_1ID_, BlockDataID rho_2ID_, BlockDataID rho_3ID_, BlockDataID rho_4ID_, double order_0, double order_1, double order_2, double order_3, double order_4, double rate_coefficient, double stoech_0, double stoech_1, double stoech_2, double stoech_3, double stoech_4)
void runOnCellInterval(const shared_ptr< StructuredBlockStorage > &blocks, const CellInterval &globalCellInterval, cell_idx_t ghostLayers, IBlock *block, gpuStream_t stream=nullptr)
cudaStream_t stream[1]
CUDA streams for parallel computing on CPU and GPU.
static double * block(double *p, std::size_t index, std::size_t size)
Definition elc.cpp:176
\file PackInfoPdfDoublePrecision.cpp \author pystencils