ILU0Kernels.hpp

/*
  Copyright 2024 SINTEF AS
 
  This file is part of the Open Porous Media project (OPM).
 
  OPM is free software: you can redistribute it and/or modify
  it under the terms of the GNU General Public License as published by
  the Free Software Foundation, either version 3 of the License, or
  (at your option) any later version.
 
  OPM is distributed in the hope that it will be useful,
  but WITHOUT ANY WARRANTY; without even the implied warranty of
  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  GNU General Public License for more details.
 
  You should have received a copy of the GNU General Public License
  along with OPM.  If not, see <http://www.gnu.org/licenses/>.
*/
#ifndef OPM_ILU0_KERNELS_HPP
#define OPM_ILU0_KERNELS_HPP
#include <cstddef>
#include <vector>
#include <opm/simulators/linalg/gpuistl/detail/kernel_enums.hpp>
namespace Opm::gpuistl::detail::ILU0
{

template <class T, int blocksize>
void solveUpperLevelSet(T* reorderedMat,
                        int* rowIndices,
                        int* colIndices,
                        int* indexConversion,
                        int startIdx,
                        int rowsInLevelSet,
                        T* v,
                        int threadBlockSize,
                        cudaStream_t stream);

template <class T, int blocksize>
void solveLowerLevelSet(T* reorderedMat,
                        int* rowIndices,
                        int* colIndices,
                        int* indexConversion,
                        int startIdx,
                        int rowsInLevelSet,
                        const T* d,
                        T* v,
                        int threadBlockSize,
                        cudaStream_t stream);

template <int blocksize, class LinearSolverScalar, class MatrixScalar, class DiagonalScalar>
void solveUpperLevelSetSplit(MatrixScalar* reorderedMat,
                             int* rowIndices,
                             int* colIndices,
                             int* indexConversion,
                             int startIdx,
                             int rowsInLevelSet,
                             const DiagonalScalar* dInv,
                             LinearSolverScalar* v,
                             int threadBlockSize,
                             cudaStream_t stream);

template <int blocksize, class LinearSolverScalar, class MatrixScalar>
void solveLowerLevelSetSplit(MatrixScalar* reorderedLowerMat,
                             int* rowIndices,
                             int* colIndices,
                             int* indexConversion,
                             int startIdx,
                             int rowsInLevelSet,
                             const LinearSolverScalar* d,
                             LinearSolverScalar* v,
                             int threadBlockSize,
                             cudaStream_t stream);

template <class T, int blocksize>
void LUFactorization(T* reorderedMat,
                     int* rowIndices,
                     int* columnIndices,
                     int* naturalToReordered,
                     int* reorderedToNatual,
                     size_t rowsInLevelSet,
                     int startIdx,
                     int threadBlockSize);

template <int blocksize, class InputScalar, class OutputScalar, MatrixStorageMPScheme mixedPrecisionScheme>
void LUFactorizationSplit(InputScalar* srcReorderedLowerMat,
                          int* lowerRowIndices,
                          int* lowerColIndices,
                          InputScalar* srcReorderedUpperMat,
                          int* upperRowIndices,
                          int* upperColIndices,
                          InputScalar* srcDiagonal,
                          OutputScalar* dstReorderedLowerMat,
                          OutputScalar* dstReorderedUpperMat,
                          OutputScalar* dstDiagonal,
                          int* reorderedToNatural,
                          int* naturalToReordered,
                          int startIdx,
                          int rowsInLevelSet,
                          int threadBlockSize);
 
} // namespace Opm::gpuistl::detail::ILU0
#endif