ESPResSo
Extensible Simulation Package for Research on Soft Matter Systems
Loading...
Searching...
No Matches
AdvectiveFluxKernel_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 AdvectiveFluxKernel_double_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 rhoID_,
61 BlockDataID uID_)
62 : jID(jID_), rhoID(rhoID_), uID(uID_) {}
63
64 void run(IBlock *block, gpuStream_t stream = nullptr);
65
66 void runOnCellInterval(const shared_ptr<StructuredBlockStorage> &blocks,
67 const CellInterval &globalCellInterval,
68 cell_idx_t ghostLayers, IBlock *block,
69 gpuStream_t stream = nullptr);
70
71 void operator()(IBlock *block, gpuStream_t stream = nullptr) {
73 }
74
75 static std::function<void(IBlock *)> getSweep(
76 const shared_ptr<AdvectiveFluxKernel_double_precision_CUDA> &kernel) {
77 return [kernel](IBlock *b) { kernel->run(b); };
78 }
79
80 static std::function<void(IBlock *, gpuStream_t)> getSweepOnCellInterval(
81 const shared_ptr<AdvectiveFluxKernel_double_precision_CUDA> &kernel,
82 const shared_ptr<StructuredBlockStorage> &blocks,
83 const CellInterval &globalCellInterval, cell_idx_t ghostLayers = 1) {
84 return [kernel, blocks, globalCellInterval,
85 ghostLayers](IBlock *b, gpuStream_t stream = nullptr) {
86 kernel->runOnCellInterval(blocks, globalCellInterval, ghostLayers, b,
87 stream);
88 };
89 }
90
91 std::function<void(IBlock *)> getSweep(gpuStream_t stream = nullptr) {
92 return [this, stream](IBlock *b) { this->run(b, stream); };
93 }
94
95 std::function<void(IBlock *)>
96 getSweepOnCellInterval(const shared_ptr<StructuredBlockStorage> &blocks,
97 const CellInterval &globalCellInterval,
98 cell_idx_t ghostLayers = 1,
99 gpuStream_t stream = nullptr) {
100 return [this, blocks, globalCellInterval, ghostLayers, stream](IBlock *b) {
101 this->runOnCellInterval(blocks, globalCellInterval, ghostLayers, b,
102 stream);
103 };
104 }
105
106 void configure(const shared_ptr<StructuredBlockStorage> & /*blocks*/,
107 IBlock * /*block*/) {}
108
109private:
110 BlockDataID jID;
111 BlockDataID rhoID;
112 BlockDataID uID;
113};
114
115} // namespace pystencils
116} // namespace walberla
117
118#if (defined WALBERLA_CXX_COMPILER_IS_GNU) || \
119 (defined WALBERLA_CXX_COMPILER_IS_CLANG)
120#pragma GCC diagnostic pop
121#endif
void configure(const shared_ptr< StructuredBlockStorage > &, IBlock *)
std::function< void(IBlock *)> getSweepOnCellInterval(const shared_ptr< StructuredBlockStorage > &blocks, const CellInterval &globalCellInterval, cell_idx_t ghostLayers=1, gpuStream_t stream=nullptr)
void runOnCellInterval(const shared_ptr< StructuredBlockStorage > &blocks, const CellInterval &globalCellInterval, cell_idx_t ghostLayers, IBlock *block, gpuStream_t stream=nullptr)
static std::function< void(IBlock *, gpuStream_t)> getSweepOnCellInterval(const shared_ptr< AdvectiveFluxKernel_double_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< AdvectiveFluxKernel_double_precision_CUDA > &kernel)
AdvectiveFluxKernel_double_precision_CUDA(BlockDataID jID_, BlockDataID rhoID_, BlockDataID uID_)
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