2 * This file is part of the GROMACS molecular simulation package.
4 * Copyright (c) 2019,2020,2021, 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.
35 /*! \libinternal \file
36 * \brief Declaration of GPU PME-PP Communication.
38 * \author Alan Gray <alang@nvidia.com>
40 * \ingroup module_ewald
42 #ifndef GMX_PME_PP_COMM_GPU_H
43 #define GMX_PME_PP_COMM_GPU_H
48 #include "gromacs/gpu_utils/devicebuffer_datatype.h"
49 #include "gromacs/math/vectypes.h"
50 #include "gromacs/utility/gmxmpi.h"
54 class GpuEventSynchronizer;
59 class DeviceStreamManager;
63 * \brief Manages communication related to GPU buffers between this
64 * PME rank and its PP rank. */
69 /*! \brief Creates PME-PP GPU communication object
70 * \param[in] comm Communicator used for simulation
71 * \param[in] pmeRank Rank of PME task
72 * \param[in] pmeCpuForceBuffer Buffer for PME force in CPU memory
73 * \param[in] deviceContext GPU context.
74 * \param[in] deviceStream GPU stream.
76 PmePpCommGpu(MPI_Comm comm,
78 std::vector<gmx::RVec>& pmeCpuForceBuffer,
79 const DeviceContext& deviceContext,
80 const DeviceStream& deviceStream);
83 /*! \brief Perform steps required when buffer size changes
84 * \param[in] size Number of elements in buffer
86 void reinit(int size);
89 * Pull data from PME GPU directly using CUDA Memory copy.
90 * \param[out] recvPtr Buffer to receive PME force data
91 * \param[in] recvSize Number of elements to receive
92 * \param[in] recvPmeForceToGpu Whether receive is to GPU, otherwise CPU
94 void receiveForceFromPme(RVec* recvPtr, int recvSize, bool recvPmeForceToGpu);
96 /*! \brief Push coordinates buffer directly to GPU memory on PME task
97 * \param[in] sendPtr Buffer with coordinate data
98 * \param[in] sendSize Number of elements to send
99 * \param[in] coordinatesReadyOnDeviceEvent Event recorded when coordinates are available on device
101 void sendCoordinatesToPmeFromGpu(DeviceBuffer<RVec> sendPtr,
103 GpuEventSynchronizer* coordinatesReadyOnDeviceEvent);
105 /*! \brief Push coordinates buffer from host memory directly to GPU memory on PME task
106 * \param[in] sendPtr Buffer with coordinate data
107 * \param[in] sendSize Number of elements to send
108 * \param[in] coordinatesReadyOnDeviceEvent Event recorded when coordinates are available on device
110 void sendCoordinatesToPmeFromCpu(RVec* sendPtr,
112 GpuEventSynchronizer* coordinatesReadyOnDeviceEvent);
115 * Return pointer to buffer used for staging PME force on GPU
117 DeviceBuffer<gmx::RVec> getGpuForceStagingPtr();
120 * Return pointer to event recorded when forces are ready
122 GpuEventSynchronizer* getForcesReadySynchronizer();
126 std::unique_ptr<Impl> impl_;