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.
37 * \brief Declares vendor-specific function to launch force reduction kernel
39 * \author Andrey Alekseenko <al42and@gmail.com>
41 * \ingroup module_mdlib
44 #include "gromacs/gpu_utils/devicebuffer_datatype.h"
45 #include "gromacs/gpu_utils/gputraits.h"
52 /*! \brief Backend-specific function to launch GPU Force Reduction kernel.
57 * for (int i = 0; i < numAtoms; i++) {
58 * totalForce = d_nbnxmForceToAdd[d_cell[i]]
60 * totalForce += d_baseForce[atomStart + i]
62 * totalForce += d_rvecForceToAdd[atomStart + i]
63 * d_baseForce[atomStart + i] = totalForce[i]
67 * \param numAtoms Number of atoms subject to reduction.
68 * \param atomStart First atom index (for \p d_rvecForceToAdd and \p d_baseForce).
69 * \param addRvecForce When \c false, \p d_rvecForceToAdd is ignored.
70 * \param accumulate When \c false, the previous values of \p d_baseForce are discarded.
71 * \param d_nbnxmForceToAdd Buffer containing Nbnxm forces in Nbnxm layout.
72 * \param d_rvecForceToAdd Optional buffer containing arbitrary forces in linear layout.
73 * \param d_baseForce Destination buffer for forces in linear layout.
74 * \param d_cell Atom index to Nbnxm cell index.
75 * \param deviceStream Device stream for kernel submission.
77 void launchForceReductionKernel(int numAtoms,
81 DeviceBuffer<Float3> d_nbnxmForceToAdd,
82 DeviceBuffer<Float3> d_rvecForceToAdd,
83 DeviceBuffer<Float3> d_baseForce,
84 DeviceBuffer<int> d_cell,
85 const DeviceStream& deviceStream);