2 * This file is part of the GROMACS molecular simulation package.
4 * Copyright (c) 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.
38 * Common code for GPU buffer operations, namely the coordinate layout conversion
40 * \ingroup module_nbnxm
46 #include "gromacs/gpu_utils/device_stream.h"
48 # include "gromacs/gpu_utils/gpueventsynchronizer.cuh"
50 # include "gromacs/gpu_utils/gpueventsynchronizer_sycl.h"
52 #include "gromacs/mdtypes/locality.h"
53 #include "gromacs/nbnxm/gridset.h"
54 #include "gromacs/nbnxm/nbnxm_gpu.h"
55 #include "gromacs/nbnxm/nbnxm_gpu_buffer_ops_internal.h"
57 # include "gromacs/nbnxm/cuda/nbnxm_cuda_types.h"
59 # include "gromacs/nbnxm/sycl/nbnxm_sycl_types.h"
61 #include "gromacs/utility/exceptions.h"
66 void nbnxn_gpu_x_to_nbat_x(const Nbnxm::Grid& grid,
68 DeviceBuffer<gmx::RVec> d_x,
69 GpuEventSynchronizer* xReadyOnDevice,
70 const gmx::AtomLocality locality,
73 bool mustInsertNonLocalDependency)
75 static_assert((bool)GMX_GPU_CUDA || (bool)GMX_GPU_SYCL,
76 "nbnxn_gpu_x_to_nbat_x only supported with CUDA and SYCL");
77 GMX_ASSERT(nb, "Need a valid nbnxn_gpu object");
78 gmx::InteractionLocality interactionLoc = gmx::atomToInteractionLocality(locality);
80 const DeviceStream& deviceStream = *nb->deviceStreams[interactionLoc];
82 const int numAtoms = grid.srcAtomEnd() - grid.srcAtomBegin();
84 // Only insert wait on the first iteration of the loop.
85 if (xReadyOnDevice != nullptr)
87 xReadyOnDevice->enqueueWaitEvent(deviceStream);
90 // avoid empty kernel launch, skip to inserting stream dependency
93 GMX_ASSERT(d_x, "Need a valid device pointer");
94 launchNbnxmKernelTransformXToXq(grid, nb, d_x, deviceStream, numColumnsMax, gridId);
97 if (mustInsertNonLocalDependency)
99 Nbnxm::nbnxnInsertNonlocalGpuDependency(nb, interactionLoc);
103 DeviceBuffer<Float3> getGpuForces(NbnxmGpu* nb)