src/gromacs/ewald/pme_gpu_3dfft.h

   1 /*
   2  * This file is part of the GROMACS molecular simulation package.
   3  *
   4  * Copyright (c) 2016,2017,2018,2019,2020, 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.
   8  *
   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.
  13  *
  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.
  18  *
  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.
  23  *
  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.
  31  *
  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.
  34  */
  35
  36 /*! \internal \file
  37  *  \brief Declares the 3D FFT class for PME.
  38  *
  39  *  \author Aleksei Iupinov <a.yupinov@gmail.com>
  40  *  \ingroup module_ewald
  41  */
  42
  43 #ifndef GMX_EWALD_PME_GPU_3DFFT_H
  44 #define GMX_EWALD_PME_GPU_3DFFT_H
  45
  46 #include "config.h"
  47
  48 #include <vector>
  49
  50 #if GMX_GPU == GMX_GPU_CUDA
  51 #    include <cufft.h>
  52
  53 #    include "gromacs/gpu_utils/gputraits.cuh"
  54 #elif GMX_GPU == GMX_GPU_OPENCL
  55 #    include <clFFT.h>
  56
  57 #    include "gromacs/gpu_utils/gmxopencl.h"
  58 #    include "gromacs/gpu_utils/gputraits_ocl.h"
  59 #endif
  60
  61 #include "gromacs/fft/fft.h" // for the enum gmx_fft_direction
  62
  63 struct PmeGpu;
  64
  65 /*! \internal \brief
  66  * A 3D FFT class for performing R2C/C2R transforms
  67  * \todo Make this class actually parallel over multiple GPUs
  68  */
  69 class GpuParallel3dFft
  70 {
  71 public:
  72     /*! \brief
  73      * Constructs CUDA/OpenCL FFT plans for performing 3D FFT on a PME grid.
  74      *
  75      * \param[in] pmeGpu                  The PME GPU structure.
  76      * \param[in] gridIndex               The index of the grid on which to perform the calculations.
  77      */
  78     GpuParallel3dFft(const PmeGpu* pmeGpu, const int gridIndex);
  79     /*! \brief Destroys the FFT plans. */
  80     ~GpuParallel3dFft();
  81     /*! \brief Performs the FFT transform in given direction
  82      *
  83      * \param[in]  dir           FFT transform direction specifier
  84      * \param[out] timingEvent   pointer to the timing event where timing data is recorded
  85      */
  86     void perform3dFft(gmx_fft_direction dir, CommandEvent* timingEvent);
  87
  88 private:
  89 #if GMX_GPU == GMX_GPU_CUDA
  90     cufftHandle   planR2C_;
  91     cufftHandle   planC2R_;
  92     cufftReal*    realGrid_;
  93     cufftComplex* complexGrid_;
  94 #elif GMX_GPU == GMX_GPU_OPENCL
  95     clfftPlanHandle               planR2C_;
  96     clfftPlanHandle               planC2R_;
  97     std::vector<cl_command_queue> deviceStreams_;
  98     cl_mem                        realGrid_;
  99     cl_mem                        complexGrid_;
 100 #endif
 101 };
 102
 103 #endif