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 Gaurav Garg <gaugarg@nvidia.com>
43 #ifndef GMX_FFT_GPU_3DFFT_IMPL_H
44 #define GMX_FFT_GPU_3DFFT_IMPL_H
46 #include "gromacs/fft/fft.h"
47 #include "gromacs/fft/gpu_3dfft.h"
48 #include "gromacs/gpu_utils/devicebuffer_datatype.h"
49 #include "gromacs/gpu_utils/gputraits.h"
55 * Impl base class for all FFT backends
60 //! Default constructor
64 * Constructs GPU FFT plans for performing 3D FFT on a PME grid.
66 * \param[in] allocateGrids True if fft grids are to be allocated, false if pre-allocated
67 * \param[in] comm MPI communicator, used with distributed-FFT backends
68 * \param[in] gridSizesInXForEachRank Number of grid points used with each rank in X-dimension
69 * \param[in] gridSizesInYForEachRank Number of grid points used with each rank in Y-dimension
70 * \param[in] nz Grid dimension in Z
71 * \param[in] performOutOfPlaceFFT Whether the FFT will be performed out-of-place
72 * \param[in] context GPU context.
73 * \param[in] pmeStream GPU stream for PME.
74 * \param[in,out] realGridSize Dimensions of the local real grid, out if allocateGrids=true
75 * \param[in,out] realGridSizePadded Dimensions of the local real grid with padding, out if allocateGrids=true
76 * \param[in,out] complexGridSizePadded Dimensions of the local complex grid with padding, out if allocateGrids=true
77 * \param[in,out] realGrid Device buffer of floats for the local real grid, out if allocateGrids=true
78 * \param[in,out] complexGrid Device buffer of complex floats for the local complex grid, out if allocateGrids=true
80 Impl(bool allocateGrids,
82 ArrayRef<const int> gridSizesInXForEachRank,
83 ArrayRef<const int> gridSizesInYForEachRank,
85 bool performOutOfPlaceFFT,
86 const DeviceContext& context,
87 const DeviceStream& pmeStream,
89 ivec realGridSizePadded,
90 ivec complexGridSizePadded,
91 DeviceBuffer<float>* realGrid,
92 DeviceBuffer<float>* complexGrid);
94 /*! \brief Default destructor */
95 virtual ~Impl() = default;
97 //! \copydoc Gpu3dFft::perform3dFft
98 virtual void perform3dFft(gmx_fft_direction dir, CommandEvent* timingEvent) = 0;