2 * This file is part of the GROMACS molecular simulation package.
4 * Copyright (c) 2018, 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 * Declares PmeGpuProgramImpl, which stores PME GPU (compiled) kernel handles.
39 * \author Aleksei Iupinov <a.yupinov@gmail.com>
40 * \ingroup module_ewald
42 #ifndef GMX_EWALD_PME_PME_GPU_PROGRAM_IMPL_H
43 #define GMX_EWALD_PME_PME_GPU_PROGRAM_IMPL_H
47 #include "gromacs/utility/classhelpers.h"
49 #if GMX_GPU == GMX_GPU_CUDA
50 // TODO uncomment when we learn to compile .cpp with CUDA compiler
51 //! include "gromacs/gpu_utils/gputraits.cuh"
52 using Context = void *;
53 #elif GMX_GPU == GMX_GPU_OPENCL
54 #include "gromacs/gpu_utils/gputraits_ocl.h"
55 #elif GMX_GPU == GMX_GPU_NONE
56 // TODO place in gputraits_stub.h
57 using Context = void *;
60 struct gmx_device_info_t;
64 * PME GPU persistent host program/kernel data, which should be initialized once for the whole execution.
66 * Primary purpose of this is to not recompile GPU kernels for each OpenCL unit test,
67 * while the relevant GPU context (e.g. cl_context) instance persists.
68 * In CUDA, this just assigns the kernel function pointers.
69 * This also implicitly relies on the fact that reasonable share of the kernels are always used.
70 * If there were more template parameters, even smaller share of all possible kernels would be used.
72 * \todo In future if we would need to react to either user input or
73 * auto-tuning to compile different kernels, then we might wish to
74 * revisit the number of kernels we pre-compile, and/or the management
77 * This also doesn't manage cuFFT/clFFT kernels, which depend on the PME grid dimensions.
79 * TODO: pass cl_context to the constructor and not create it inside.
80 * See also Redmine #2522.
82 struct PmeGpuProgramImpl
85 * This is a handle to the GPU context, which is just a dummy in CUDA,
86 * but is created/destroyed by this class in OpenCL.
87 * TODO: Later we want to be able to own the context at a higher level and not here,
88 * but this class would still need the non-owning context handle to build the kernels.
92 //! Conveniently all the PME kernels use the same single argument type
93 #if GMX_GPU == GMX_GPU_CUDA
94 using PmeKernelHandle = void(*)(const struct PmeGpuCudaKernelParams);
95 #elif GMX_GPU == GMX_GPU_OPENCL
96 using PmeKernelHandle = cl_kernel;
98 using PmeKernelHandle = void *;
103 * Spread/spline kernels are compiled only for order of 4.
104 * Spreading kernels also have hardcoded X/Y indices wrapping parameters,
105 * as a placeholder for implementing 1/2D decomposition.
107 PmeKernelHandle splineKernel;
108 PmeKernelHandle spreadKernel;
109 PmeKernelHandle splineAndSpreadKernel;
113 /** Same for gather: hardcoded X/Y unwrap parameters, order of 4, plus
114 * it can either reduce with previous forces in the host buffer, or ignore them.
116 PmeKernelHandle gatherReduceWithInputKernel;
117 PmeKernelHandle gatherKernel;
121 /** Solve kernel doesn't care about the interpolation order, but can optionally
122 * compute energy and virial, and supports XYZ and YZX grid orderings.
124 PmeKernelHandle solveYZXKernel;
125 PmeKernelHandle solveXYZKernel;
126 PmeKernelHandle solveYZXEnergyKernel;
127 PmeKernelHandle solveXYZEnergyKernel;
130 PmeGpuProgramImpl() = delete;
131 //! Constructor for the given device
132 explicit PmeGpuProgramImpl(const gmx_device_info_t *deviceInfo);
133 ~PmeGpuProgramImpl();
134 GMX_DISALLOW_COPY_AND_ASSIGN(PmeGpuProgramImpl);