2 * This file is part of the GROMACS molecular simulation package.
4 * Copyright (c) 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.
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 Implements PME-PP communication using CUDA
40 * \author Alan Gray <alang@nvidia.com>
42 * \ingroup module_ewald
46 #include "pme_force_sender_gpu_impl.h"
50 #include "gromacs/gpu_utils/cudautils.cuh"
51 #include "gromacs/gpu_utils/gpueventsynchronizer.cuh"
52 #include "gromacs/utility/gmxmpi.h"
57 /*! \brief Create PME-PP GPU communication object */
58 PmeForceSenderGpu::Impl::Impl(const DeviceStream& pmeStream, MPI_Comm comm, gmx::ArrayRef<PpRanks> ppRanks) :
59 pmeStream_(pmeStream),
65 "PME-PP GPU Communication is currently only supported with thread-MPI enabled");
68 PmeForceSenderGpu::Impl::~Impl() = default;
70 /*! \brief sends force buffer address to PP ranks */
71 void PmeForceSenderGpu::Impl::sendForceBufferAddressToPpRanks(rvec* d_f)
75 for (const auto& receiver : ppRanks_)
78 ind_end = ind_start + receiver.numAtoms;
80 // Data will be transferred directly from GPU.
81 void* sendBuf = reinterpret_cast<void*>(&d_f[ind_start]);
84 MPI_Send(&sendBuf, sizeof(void**), MPI_BYTE, receiver.rankId, 0, comm_);
86 GMX_UNUSED_VALUE(sendBuf);
91 /*! \brief Send PME data directly using CUDA memory copy */
92 void PmeForceSenderGpu::Impl::sendFToPpCudaDirect(int ppRank)
94 // Data will be pulled directly from PP task
96 // Record and send event to ensure PME force calcs are completed before PP task pulls data
97 pmeSync_.markEvent(pmeStream_);
98 GpuEventSynchronizer* pmeSyncPtr = &pmeSync_;
100 // TODO Using MPI_Isend would be more efficient, particularly when
101 // sending to multiple PP ranks
102 MPI_Send(&pmeSyncPtr, sizeof(GpuEventSynchronizer*), MPI_BYTE, ppRank, 0, comm_);
104 GMX_UNUSED_VALUE(pmeSyncPtr);
105 GMX_UNUSED_VALUE(ppRank);
109 PmeForceSenderGpu::PmeForceSenderGpu(const DeviceStream& pmeStream,
111 gmx::ArrayRef<PpRanks> ppRanks) :
112 impl_(new Impl(pmeStream, comm, ppRanks))
116 PmeForceSenderGpu::~PmeForceSenderGpu() = default;
118 void PmeForceSenderGpu::sendForceBufferAddressToPpRanks(rvec* d_f)
120 impl_->sendForceBufferAddressToPpRanks(d_f);
123 void PmeForceSenderGpu::sendFToPpCudaDirect(int ppRank)
125 impl_->sendFToPpCudaDirect(ppRank);