ESPResSo
Extensible Simulation Package for Research on Soft Matter Systems
Loading...
Searching...
No Matches
DiffusiveFluxKernelWithElectrostatic_single_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 DiffusiveFluxKernelWithElectrostatic_single_precision_CUDA.h
17//! \\author pystencils
18//======================================================================================================================
19
20// kernel generated with pystencils v1.3.7+13.gdfd203a, lbmpy
21// v1.3.7+10.gd3f6236, sympy v1.12.1, lbmpy_walberla/pystencils_walberla from
22// waLBerla commit c69cb11d6a95d32b2280544d3d9abde1fe5fdbb5
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#elif _MSC_VER
42#define RESTRICT __restrict
43#else
44#define RESTRICT
45#endif
46
47#if (defined WALBERLA_CXX_COMPILER_IS_GNU) || \
48 (defined WALBERLA_CXX_COMPILER_IS_CLANG)
49#pragma GCC diagnostic push
50#pragma GCC diagnostic ignored "-Wunused-parameter"
51#pragma GCC diagnostic ignored "-Wreorder"
52#endif
53
54namespace walberla {
55namespace pystencils {
56
58public:
60 BlockDataID jID_, BlockDataID phiID_, BlockDataID rhoID_, float D,
61 float f_ext_0, float f_ext_1, float f_ext_2, float kT, float z)
62 : jID(jID_), phiID(phiID_), rhoID(rhoID_), D_(D), f_ext_0_(f_ext_0),
63 f_ext_1_(f_ext_1), f_ext_2_(f_ext_2), kT_(kT), z_(z) {}
64
65 void run(IBlock *block, gpuStream_t stream = nullptr);
66
67 void runOnCellInterval(const shared_ptr<StructuredBlockStorage> &blocks,
68 const CellInterval &globalCellInterval,
69 cell_idx_t ghostLayers, IBlock *block,
70 gpuStream_t stream = nullptr);
71
72 void operator()(IBlock *block, gpuStream_t stream = nullptr) {
74 }
75
76 static std::function<void(IBlock *)> getSweep(
77 const shared_ptr<
79 return [kernel](IBlock *b) { kernel->run(b); };
80 }
81
82 static std::function<void(IBlock *, gpuStream_t)> getSweepOnCellInterval(
83 const shared_ptr<
85 const shared_ptr<StructuredBlockStorage> &blocks,
86 const CellInterval &globalCellInterval, cell_idx_t ghostLayers = 1) {
87 return [kernel, blocks, globalCellInterval,
88 ghostLayers](IBlock *b, gpuStream_t stream = nullptr) {
89 kernel->runOnCellInterval(blocks, globalCellInterval, ghostLayers, b,
90 stream);
91 };
92 }
93
94 std::function<void(IBlock *)> getSweep(gpuStream_t stream = nullptr) {
95 return [this, stream](IBlock *b) { this->run(b, stream); };
96 }
97
98 std::function<void(IBlock *)>
99 getSweepOnCellInterval(const shared_ptr<StructuredBlockStorage> &blocks,
100 const CellInterval &globalCellInterval,
101 cell_idx_t ghostLayers = 1,
102 gpuStream_t stream = nullptr) {
103 return [this, blocks, globalCellInterval, ghostLayers, stream](IBlock *b) {
104 this->runOnCellInterval(blocks, globalCellInterval, ghostLayers, b,
105 stream);
106 };
107 }
108
109 void configure(const shared_ptr<StructuredBlockStorage> & /*blocks*/,
110 IBlock * /*block*/) {}
111
112 inline float getD() const { return D_; }
113 inline float getF_ext_0() const { return f_ext_0_; }
114 inline float getF_ext_1() const { return f_ext_1_; }
115 inline float getF_ext_2() const { return f_ext_2_; }
116 inline float getKt() const { return kT_; }
117 inline float getZ() const { return z_; }
118 inline void setD(const float value) { D_ = value; }
119 inline void setF_ext_0(const float value) { f_ext_0_ = value; }
120 inline void setF_ext_1(const float value) { f_ext_1_ = value; }
121 inline void setF_ext_2(const float value) { f_ext_2_ = value; }
122 inline void setKt(const float value) { kT_ = value; }
123 inline void setZ(const float value) { z_ = value; }
124
125private:
126 BlockDataID jID;
127 BlockDataID phiID;
128
129public:
130 inline void setPhiID(BlockDataID phiID_) { phiID = phiID_; }
131
132private:
133 BlockDataID rhoID;
134 float D_;
135 float f_ext_0_;
136 float f_ext_1_;
137 float f_ext_2_;
138 float kT_;
139 float z_;
140};
141
142} // namespace pystencils
143} // namespace walberla
144
145#if (defined WALBERLA_CXX_COMPILER_IS_GNU) || \
146 (defined WALBERLA_CXX_COMPILER_IS_CLANG)
147#pragma GCC diagnostic pop
148#endif
void runOnCellInterval(const shared_ptr< StructuredBlockStorage > &blocks, const CellInterval &globalCellInterval, cell_idx_t ghostLayers, IBlock *block, gpuStream_t stream=nullptr)
DiffusiveFluxKernelWithElectrostatic_single_precision_CUDA(BlockDataID jID_, BlockDataID phiID_, BlockDataID rhoID_, float D, float f_ext_0, float f_ext_1, float f_ext_2, float kT, float z)
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 *, gpuStream_t)> getSweepOnCellInterval(const shared_ptr< DiffusiveFluxKernelWithElectrostatic_single_precision_CUDA > &kernel, const shared_ptr< StructuredBlockStorage > &blocks, const CellInterval &globalCellInterval, cell_idx_t ghostLayers=1)
static std::function< void(IBlock *)> getSweep(const shared_ptr< DiffusiveFluxKernelWithElectrostatic_single_precision_CUDA > &kernel)
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