src/gromacs/ewald/pme_gpu_calculate_splines.h

   1 /*
   2  * This file is part of the GROMACS molecular simulation package.
   3  *
   4  * Copyright (c) 2018,2019,2020, 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.
   8  *
   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.
  13  *
  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.
  18  *
  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.
  23  *
  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.
  31  *
  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.
  34  */
  35 #ifndef GMX_EWALD_PME_GPU_UTILS_H
  36 #define GMX_EWALD_PME_GPU_UTILS_H
  37
  38 /*! \internal \file
  39  * \brief This file defines small PME GPU inline host/device functions.
  40  * Note that OpenCL device-side functions can't use C++ features, so they are
  41  * located in a similar file pme_gpu_utils.clh.
  42  * Be sure to keep the logic in sync in both files when changing it!
  43  *
  44  * \author Aleksei Iupinov <a.yupinov@gmail.com>
  45  * \ingroup module_ewald
  46  */
  47
  48 #include <cassert>
  49
  50 #include "gromacs/math/vectypes.h"
  51
  52 struct PmeGpu;
  53
  54 /*! \internal \brief
  55  * Gets a base of the unique index to an element in a spline parameter buffer (theta/dtheta),
  56  * which is laid out for GPU spread/gather kernels. The base only corresponds to the atom index within the execution block.
  57  * Feed the result into getSplineParamIndex() to get a full index.
  58  * TODO: it's likely that both parameters can be just replaced with a single atom index, as they are derived from it.
  59  * Do that, verifying that the generated code is not bloated, and/or revise the spline indexing scheme.
  60  * Removing warp dependency would also be nice (and would probably coincide with removing c_pmeSpreadGatherAtomsPerWarp).
  61  *
  62  * \tparam order               PME order
  63  * \tparam atomsPerWarp        Number of atoms processed by a warp
  64  * \param[in] warpIndex        Warp index wrt the block.
  65  * \param[in] atomWarpIndex    Atom index wrt the warp (from 0 to atomsPerWarp - 1).
  66  *
  67  * \returns Index into theta or dtheta array using GPU layout.
  68  */
  69 template<int order, int atomsPerWarp>
  70 int inline getSplineParamIndexBase(int warpIndex, int atomWarpIndex)
  71 {
  72     assert((atomWarpIndex >= 0) && (atomWarpIndex < atomsPerWarp));
  73     const int dimIndex    = 0;
  74     const int splineIndex = 0;
  75     // The zeroes are here to preserve the full index formula for reference
  76     return (((splineIndex + order * warpIndex) * DIM + dimIndex) * atomsPerWarp + atomWarpIndex);
  77 }
  78
  79 /*! \internal \brief
  80  * Gets a unique index to an element in a spline parameter buffer (theta/dtheta),
  81  * which is laid out for GPU spread/gather kernels. The index is wrt to the execution block,
  82  * in range(0, atomsPerBlock * order * DIM).
  83  * This function consumes result of getSplineParamIndexBase() and adjusts it for \p dimIndex and \p splineIndex.
  84  *
  85  * \tparam order               PME order
  86  * \tparam atomsPerWarp        Number of atoms processed by a warp
  87  * \param[in] paramIndexBase   Must be result of getSplineParamIndexBase().
  88  * \param[in] dimIndex         Dimension index (from 0 to 2)
  89  * \param[in] splineIndex      Spline contribution index (from 0 to \p order - 1)
  90  *
  91  * \returns Index into theta or dtheta array using GPU layout.
  92  */
  93 template<int order, int atomsPerWarp>
  94 int inline getSplineParamIndex(int paramIndexBase, int dimIndex, int splineIndex)
  95 {
  96     assert((dimIndex >= XX) && (dimIndex < DIM));
  97     assert((splineIndex >= 0) && (splineIndex < order));
  98     return (paramIndexBase + (splineIndex * DIM + dimIndex) * atomsPerWarp);
  99 }
 100
 101 #endif