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.
37 * \brief Implements backend-specific functions of the update-constraints in SYCL.
39 * \author Artem Zhmurov <zhmurov@gmail.com>
41 * \ingroup module_mdlib
45 #include "update_constrain_gpu_internal.h"
47 #include "gromacs/gpu_utils/devicebuffer_sycl.h"
48 #include "gromacs/gpu_utils/gmxsycl.h"
49 #include "gromacs/gpu_utils/gputraits_sycl.h"
50 #include "gromacs/utility/gmxassert.h"
52 //! \brief Class name for scaling kernel
58 //! \brief Function returning the scaling kernel lambda.
59 static auto scaleKernel(cl::sycl::handler& cgh,
60 DeviceAccessor<Float3, cl::sycl::access::mode::read_write> a_x,
61 const ScalingMatrix scalingMatrix)
65 return [=](cl::sycl::id<1> itemIdx) {
66 Float3 x = a_x[itemIdx];
67 x[0] = scalingMatrix.xx * x[0] + scalingMatrix.yx * x[1] + scalingMatrix.zx * x[2];
68 x[1] = scalingMatrix.yy * x[1] + scalingMatrix.zy * x[2];
69 x[2] = scalingMatrix.zz * x[2];
74 void launchScaleCoordinatesKernel(const int numAtoms,
75 DeviceBuffer<Float3> d_coordinates,
76 const ScalingMatrix& mu,
77 const DeviceStream& deviceStream)
79 const cl::sycl::range<1> rangeAllAtoms(numAtoms);
80 cl::sycl::queue queue = deviceStream.stream();
82 cl::sycl::event e = queue.submit([&](cl::sycl::handler& cgh) {
83 auto kernel = scaleKernel(cgh, d_coordinates, mu);
84 cgh.parallel_for<ScaleKernel>(rangeAllAtoms, kernel);
86 // TODO: Although this only happens on the pressure coupling steps, this synchronization
87 // can affect the performance if nstpcouple is small. See Issue #4018