2 * This file is part of the GROMACS molecular simulation package.
4 * Copyright (c) 2016,2017,2018,2019,2021, by the GROMACS development team, led by
5 * Mark Abraham, David van der Spoel, Berk Hess, and Erik Lindahl,
6 * and including many others, as listed in the AUTHORS file in the
7 * top-level source directory and at http://www.gromacs.org.
9 * GROMACS is free software; you can redistribute it and/or
10 * modify it under the terms of the GNU Lesser General Public License
11 * as published by the Free Software Foundation; either version 2.1
12 * of the License, or (at your option) any later version.
14 * GROMACS is distributed in the hope that it will be useful,
15 * but WITHOUT ANY WARRANTY; without even the implied warranty of
16 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
17 * Lesser General Public License for more details.
19 * You should have received a copy of the GNU Lesser General Public
20 * License along with GROMACS; if not, see
21 * http://www.gnu.org/licenses, or write to the Free Software Foundation,
22 * Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
24 * If you want to redistribute modifications to GROMACS, please
25 * consider that scientific software is very special. Version
26 * control is crucial - bugs must be traceable. We will be happy to
27 * consider code for inclusion in the official distribution, but
28 * derived work must not be called official GROMACS. Details are found
29 * in the README & COPYING files - if they are missing, get the
30 * official version at http://www.gromacs.org.
32 * To help us fund GROMACS development, we humbly ask that you cite
33 * the research papers on the package. Check out http://www.gromacs.org.
37 * \brief Declares the GPU 3D FFT routines.
39 * \author Aleksei Iupinov <a.yupinov@gmail.com>
40 * \author Mark Abraham <mark.j.abraham@gmail.com>
41 * \author Gaurav Garg <gaugarg@nvidia.com>
45 #ifndef GMX_FFT_GPU_3DFFT_H
46 #define GMX_FFT_GPU_3DFFT_H
50 #include "gromacs/fft/fft.h"
51 #include "gromacs/gpu_utils/devicebuffer_datatype.h"
52 #include "gromacs/gpu_utils/gputraits.h"
53 #include "gromacs/utility/gmxmpi.h"
65 * Enum specifying all GPU FFT backends supported by GROMACS
66 * Some of the backends support only single GPU, some only multi-node, multi-GPU
70 Cufft, // supports only single-GPU
71 Ocl, // supports only single-GPU
73 SyclMkl, // supports only single-GPU
74 SyclRocfft, // supports only single-GPU
75 Sycl, // stubs for not supported configurations
80 * A 3D FFT class for performing R2C/C2R transforms
86 * Construct 3D FFT object for given backend
88 * \param[in] backend FFT backend to be instantiated
89 * \param[in] allocateGrids True if fft grids are to be allocated, false if pre-allocated
90 * \param[in] comm MPI communicator, used with distributed-FFT backends
91 * \param[in] gridSizesInXForEachRank Number of grid points used with each rank in X-dimension
92 * \param[in] gridSizesInYForEachRank Number of grid points used with each rank in Y-dimension
93 * \param[in] nz Grid dimension in Z
94 * \param[in] performOutOfPlaceFFT Whether the FFT will be performed out-of-place
95 * \param[in] context GPU context.
96 * \param[in] pmeStream GPU stream for PME.
97 * \param[in,out] realGridSize Dimensions of the local real grid, out if allocateGrids=true
98 * \param[in,out] realGridSizePadded Dimensions of the local real grid with padding, out if allocateGrids=true
99 * \param[in,out] complexGridSizePadded Dimensions of the local complex grid with padding, out if allocateGrids=true
100 * \param[in,out] realGrid Device buffer of floats for the local real grid, out if allocateGrids=true
101 * \param[in,out] complexGrid Device buffer of complex floats for the local complex grid, out if allocateGrids=true
103 Gpu3dFft(FftBackend backend,
106 ArrayRef<const int> gridSizesInXForEachRank,
107 ArrayRef<const int> gridSizesInYForEachRank,
109 bool performOutOfPlaceFFT,
110 const DeviceContext& context,
111 const DeviceStream& pmeStream,
113 ivec realGridSizePadded,
114 ivec complexGridSizePadded,
115 DeviceBuffer<float>* realGrid,
116 DeviceBuffer<float>* complexGrid);
118 /*! \brief Destroys the FFT plans. */
120 /*! \brief Performs the FFT transform in given direction
122 * \param[in] dir FFT transform direction specifier
123 * \param[out] timingEvent pointer to the timing event where timing data is recorded
125 void perform3dFft(gmx_fft_direction dir, CommandEvent* timingEvent);
132 class ImplSyclRocfft;
135 template<typename backend_tag>
138 std::unique_ptr<Impl> impl_;