ESPResSo
Extensible Simulation Package for Research on Soft Matter Systems
Loading...
Searching...
No Matches
CollideSweepDoublePrecisionThermalizedCUDA.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 CollideSweepDoublePrecisionThermalizedCUDA.h
17//! \\author pystencils
18//======================================================================================================================
19
20// kernel generated with pystencils v1.3.3, lbmpy v1.3.3,
21// lbmpy_walberla/pystencils_walberla from waLBerla commit
22// b0842e1a493ce19ef1bbb8d2cf382fc343970a7f
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#include <set>
36
37#ifdef __GNUC__
38#define RESTRICT __restrict__
39#elif _MSC_VER
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 forceID_, BlockDataID pdfsID_, double kT, double omega_bulk,
59 double omega_even, double omega_odd, double omega_shear, uint32_t seed,
60 uint32_t time_step)
61 : forceID(forceID_), pdfsID(pdfsID_), kT_(kT), omega_bulk_(omega_bulk),
62 omega_even_(omega_even), omega_odd_(omega_odd),
63 omega_shear_(omega_shear), seed_(seed), time_step_(time_step),
64 configured_(false){};
65
66 void run(IBlock *block, gpuStream_t stream = nullptr);
67
68 void runOnCellInterval(const shared_ptr<StructuredBlockStorage> &blocks,
69 const CellInterval &globalCellInterval,
70 cell_idx_t ghostLayers, IBlock *block,
71 gpuStream_t stream = nullptr);
72
73 void operator()(IBlock *block, gpuStream_t stream = nullptr) {
75 }
76
77 static std::function<void(IBlock *)> getSweep(
78 const shared_ptr<CollideSweepDoublePrecisionThermalizedCUDA> &kernel) {
79 return [kernel](IBlock *b) { kernel->run(b); };
80 }
81
82 static std::function<void(IBlock *, gpuStream_t)> getSweepOnCellInterval(
83 const shared_ptr<CollideSweepDoublePrecisionThermalizedCUDA> &kernel,
84 const shared_ptr<StructuredBlockStorage> &blocks,
85 const CellInterval &globalCellInterval, cell_idx_t ghostLayers = 1) {
86 return [kernel, blocks, globalCellInterval,
87 ghostLayers](IBlock *b, gpuStream_t stream = nullptr) {
88 kernel->runOnCellInterval(blocks, globalCellInterval, ghostLayers, b,
89 stream);
90 };
91 }
92
93 std::function<void(IBlock *)> getSweep(gpuStream_t stream = nullptr) {
94 return [this, stream](IBlock *b) { this->run(b, stream); };
95 }
96
97 std::function<void(IBlock *)>
98 getSweepOnCellInterval(const shared_ptr<StructuredBlockStorage> &blocks,
99 const CellInterval &globalCellInterval,
100 cell_idx_t ghostLayers = 1,
101 gpuStream_t stream = nullptr) {
102 return [this, blocks, globalCellInterval, ghostLayers, stream](IBlock *b) {
103 this->runOnCellInterval(blocks, globalCellInterval, ghostLayers, b,
104 stream);
105 };
106 }
107
108 void configure(const shared_ptr<StructuredBlockStorage> &blocks,
109 IBlock *block) {
110 Cell BlockCellBB = blocks->getBlockCellBB(*block).min();
111 block_offset_0_ = uint32_t(BlockCellBB[0]);
112 block_offset_1_ = uint32_t(BlockCellBB[1]);
113 block_offset_2_ = uint32_t(BlockCellBB[2]);
114 configured_ = true;
115 }
116
117 BlockDataID forceID;
118 BlockDataID pdfsID;
122 double kT_;
127 uint32_t seed_;
128 uint32_t time_step_;
130};
131
132} // namespace pystencils
133} // namespace walberla
134
135#if (defined WALBERLA_CXX_COMPILER_IS_GNU) || \
136 (defined WALBERLA_CXX_COMPILER_IS_CLANG)
137#pragma GCC diagnostic pop
138#endif
Definition Cell.hpp:97
static std::function< void(IBlock *)> getSweep(const shared_ptr< CollideSweepDoublePrecisionThermalizedCUDA > &kernel)
void runOnCellInterval(const shared_ptr< StructuredBlockStorage > &blocks, const CellInterval &globalCellInterval, cell_idx_t ghostLayers, IBlock *block, gpuStream_t stream=nullptr)
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< CollideSweepDoublePrecisionThermalizedCUDA > &kernel, const shared_ptr< StructuredBlockStorage > &blocks, const CellInterval &globalCellInterval, cell_idx_t ghostLayers=1)
void configure(const shared_ptr< StructuredBlockStorage > &blocks, IBlock *block)
CollideSweepDoublePrecisionThermalizedCUDA(BlockDataID forceID_, BlockDataID pdfsID_, double kT, double omega_bulk, double omega_even, double omega_odd, double omega_shear, uint32_t seed, uint32_t time_step)
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:172
\file PackInfoPdfDoublePrecision.cpp \author pystencils