2 * This file is part of the GROMACS molecular simulation package.
4 * Copyright (c) 2018,2019,2020,2021, 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.
36 * \brief Defines the runner for CUDA version of SETTLE.
38 * \author Artem Zhmurov <zhmurov@gmail.com>
39 * \ingroup module_mdlib
43 #include "settletestrunners.h"
54 #include "gromacs/gpu_utils/devicebuffer.cuh"
55 #include "gromacs/gpu_utils/gputraits.h"
56 #include "gromacs/hardware/device_information.h"
57 #include "gromacs/mdlib/settle_gpu.h"
58 #include "gromacs/utility/unique_cptr.h"
60 #include "testutils/test_device.h"
67 void SettleDeviceTestRunner::applySettle(SettleTestData* testData,
69 const bool updateVelocities,
70 const bool calcVirial,
71 const std::string& /* testDescription */)
73 // These should never fail since this function should only be called if CUDA is enabled and
74 // there is a CUDA-capable device available.
75 GMX_RELEASE_ASSERT(GMX_GPU_CUDA, "CUDA version of SETTLE was called from non-CUDA build.");
77 const DeviceContext& deviceContext = testDevice_.deviceContext();
78 const DeviceStream& deviceStream = testDevice_.deviceStream();
79 setActiveDevice(testDevice_.deviceInfo());
81 auto settleGpu = std::make_unique<SettleGpu>(testData->mtop_, deviceContext, deviceStream);
83 settleGpu->set(*testData->idef_);
85 setPbcAiuc(pbc.ndim_ePBC, pbc.box, &pbcAiuc);
87 int numAtoms = testData->numAtoms_;
89 DeviceBuffer<Float3> d_x, d_xp, d_v;
91 Float3* h_x = gmx::asGenericFloat3Pointer(testData->x_);
92 Float3* h_xp = gmx::asGenericFloat3Pointer(testData->xPrime_);
93 Float3* h_v = gmx::asGenericFloat3Pointer(testData->v_);
95 allocateDeviceBuffer(&d_x, numAtoms, deviceContext);
96 allocateDeviceBuffer(&d_xp, numAtoms, deviceContext);
97 allocateDeviceBuffer(&d_v, numAtoms, deviceContext);
99 copyToDeviceBuffer(&d_x, h_x, 0, numAtoms, deviceStream, GpuApiCallBehavior::Sync, nullptr);
100 copyToDeviceBuffer(&d_xp, h_xp, 0, numAtoms, deviceStream, GpuApiCallBehavior::Sync, nullptr);
101 if (updateVelocities)
103 copyToDeviceBuffer(&d_v, h_v, 0, numAtoms, deviceStream, GpuApiCallBehavior::Sync, nullptr);
106 d_x, d_xp, updateVelocities, d_v, testData->reciprocalTimeStep_, calcVirial, testData->virial_, pbcAiuc);
108 copyFromDeviceBuffer(h_xp, &d_xp, 0, numAtoms, deviceStream, GpuApiCallBehavior::Sync, nullptr);
109 if (updateVelocities)
111 copyFromDeviceBuffer(h_v, &d_v, 0, numAtoms, deviceStream, GpuApiCallBehavior::Sync, nullptr);
114 freeDeviceBuffer(&d_x);
115 freeDeviceBuffer(&d_xp);
116 freeDeviceBuffer(&d_v);