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.
36 * \brief Runner for CUDA version of the integrator
38 * Handles GPU data management and actual numerical integration.
40 * \author Artem Zhmurov <zhmurov@gmail.com>
41 * \ingroup module_mdlib
45 #include "leapfrogtestrunners.h"
52 #include <unordered_map>
55 #include "gromacs/gpu_utils/devicebuffer.cuh"
56 #include "gromacs/gpu_utils/gpu_utils.h"
57 #include "gromacs/math/vec.h"
58 #include "gromacs/mdlib/leapfrog_gpu.cuh"
59 #include "gromacs/mdlib/stat.h"
60 #include "gromacs/mdtypes/group.h"
67 void integrateLeapFrogGpu(LeapFrogTestData* testData, int numSteps)
69 DeviceInformation deviceInfo;
70 const DeviceContext deviceContext(deviceInfo);
72 int numAtoms = testData->numAtoms_;
74 float3* h_x = reinterpret_cast<float3*>(testData->x_.data());
75 float3* h_xp = reinterpret_cast<float3*>(testData->xPrime_.data());
76 float3* h_v = reinterpret_cast<float3*>(testData->v_.data());
77 float3* h_f = reinterpret_cast<float3*>(testData->f_.data());
79 float3 *d_x, *d_xp, *d_v, *d_f;
81 allocateDeviceBuffer(&d_x, numAtoms, deviceContext);
82 allocateDeviceBuffer(&d_xp, numAtoms, deviceContext);
83 allocateDeviceBuffer(&d_v, numAtoms, deviceContext);
84 allocateDeviceBuffer(&d_f, numAtoms, deviceContext);
86 copyToDeviceBuffer(&d_x, h_x, 0, numAtoms, nullptr, GpuApiCallBehavior::Sync, nullptr);
87 copyToDeviceBuffer(&d_xp, h_xp, 0, numAtoms, nullptr, GpuApiCallBehavior::Sync, nullptr);
88 copyToDeviceBuffer(&d_v, h_v, 0, numAtoms, nullptr, GpuApiCallBehavior::Sync, nullptr);
89 copyToDeviceBuffer(&d_f, h_f, 0, numAtoms, nullptr, GpuApiCallBehavior::Sync, nullptr);
91 auto integrator = std::make_unique<LeapFrogGpu>(deviceContext, nullptr);
93 integrator->set(testData->mdAtoms_, testData->numTCoupleGroups_, testData->mdAtoms_.cTC);
95 bool doTempCouple = testData->numTCoupleGroups_ > 0;
96 for (int step = 0; step < numSteps; step++)
98 // This follows the logic of the CPU-based implementation
99 bool doPressureCouple = testData->doPressureCouple_
100 && do_per_step(step + testData->inputRecord_.nstpcouple - 1,
101 testData->inputRecord_.nstpcouple);
102 integrator->integrate(d_x, d_xp, d_v, d_f, testData->timestep_, doTempCouple,
103 testData->kineticEnergyData_.tcstat, doPressureCouple,
104 testData->dtPressureCouple_, testData->velocityScalingMatrix_);
107 copyFromDeviceBuffer(h_xp, &d_x, 0, numAtoms, nullptr, GpuApiCallBehavior::Sync, nullptr);
108 copyFromDeviceBuffer(h_v, &d_v, 0, numAtoms, nullptr, GpuApiCallBehavior::Sync, nullptr);
110 freeDeviceBuffer(&d_x);
111 freeDeviceBuffer(&d_xp);
112 freeDeviceBuffer(&d_v);
113 freeDeviceBuffer(&d_f);