ESPResSo
Extensible Simulation Package for Research on Soft Matter Systems
Loading...
Searching...
No Matches
ContinuityKernel_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 ContinuityKernel_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:
59 ContinuityKernel_single_precision_CUDA(BlockDataID jID_, BlockDataID rhoID_)
60 : jID(jID_), rhoID(rhoID_) {}
61
62 void run(IBlock *block, gpuStream_t stream = nullptr);
63
64 void runOnCellInterval(const shared_ptr<StructuredBlockStorage> &blocks,
65 const CellInterval &globalCellInterval,
66 cell_idx_t ghostLayers, IBlock *block,
67 gpuStream_t stream = nullptr);
68
69 void operator()(IBlock *block, gpuStream_t stream = nullptr) {
71 }
72
73 static std::function<void(IBlock *)>
74 getSweep(const shared_ptr<ContinuityKernel_single_precision_CUDA> &kernel) {
75 return [kernel](IBlock *b) { kernel->run(b); };
76 }
77
78 static std::function<void(IBlock *, gpuStream_t)> getSweepOnCellInterval(
79 const shared_ptr<ContinuityKernel_single_precision_CUDA> &kernel,
80 const shared_ptr<StructuredBlockStorage> &blocks,
81 const CellInterval &globalCellInterval, cell_idx_t ghostLayers = 1) {
82 return [kernel, blocks, globalCellInterval,
83 ghostLayers](IBlock *b, gpuStream_t stream = nullptr) {
84 kernel->runOnCellInterval(blocks, globalCellInterval, ghostLayers, b,
85 stream);
86 };
87 }
88
89 std::function<void(IBlock *)> getSweep(gpuStream_t stream = nullptr) {
90 return [this, stream](IBlock *b) { this->run(b, stream); };
91 }
92
93 std::function<void(IBlock *)>
94 getSweepOnCellInterval(const shared_ptr<StructuredBlockStorage> &blocks,
95 const CellInterval &globalCellInterval,
96 cell_idx_t ghostLayers = 1,
97 gpuStream_t stream = nullptr) {
98 return [this, blocks, globalCellInterval, ghostLayers, stream](IBlock *b) {
99 this->runOnCellInterval(blocks, globalCellInterval, ghostLayers, b,
100 stream);
101 };
102 }
103
104 void configure(const shared_ptr<StructuredBlockStorage> & /*blocks*/,
105 IBlock * /*block*/) {}
106
107private:
108 BlockDataID jID;
109 BlockDataID rhoID;
110};
111
112} // namespace pystencils
113} // namespace walberla
114
115#if (defined WALBERLA_CXX_COMPILER_IS_GNU) || \
116 (defined WALBERLA_CXX_COMPILER_IS_CLANG)
117#pragma GCC diagnostic pop
118#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< ContinuityKernel_single_precision_CUDA > &kernel)
void configure(const shared_ptr< StructuredBlockStorage > &, IBlock *)
std::function< void(IBlock *)> getSweep(gpuStream_t stream=nullptr)
static std::function< void(IBlock *, gpuStream_t)> getSweepOnCellInterval(const shared_ptr< ContinuityKernel_single_precision_CUDA > &kernel, const shared_ptr< StructuredBlockStorage > &blocks, const CellInterval &globalCellInterval, cell_idx_t ghostLayers=1)
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