Opm::HipKernels< Scalar > Class Template Reference

Static Public Member Functions
static void	init (int verbosity)
	Initialize verbosity level for the HIP kernels.
static void	full_to_pressure_restriction (const Scalar *fine_y, Scalar *weights, Scalar *coarse_y, int Nb, hipStream_t stream)
	Transform blocked vector to scalar vector using pressure-weights, where every workitem handles one blockrow.
static void	add_coarse_pressure_correction (Scalar *coarse_x, Scalar *fine_x, int pressure_idx, int Nb, hipStream_t stream)
	Add the coarse pressure solution back to the finer, complete solution; every workitem handles one blockrow.
static void	vmul (const Scalar alpha, Scalar *in1, Scalar *in2, Scalar *out, int N, hipStream_t stream)
	Function to multiply vector with another vector and a scalar, element-wise and add the result to a third vector (out = alpha * in1 + in2).
static void	prolongate_vector (const Scalar *in, Scalar *out, const int *cols, int N, hipStream_t stream)
	Function to prolongate vector during amg cycle, every workitem handles one row.
static void	residual (Scalar *vals, int *cols, int *rows, Scalar *x, const Scalar *rhs, Scalar *out, int Nb, unsigned int block_size, hipStream_t stream)
	Function to perform res = rhs - mat * x.
static void	spmv (Scalar *vals, int *cols, int *rows, Scalar *x, Scalar *y, int Nb, unsigned int block_size, hipStream_t stream)
	Function to perform sparse matrix vector multipliation.

Member Function Documentation

add_coarse_pressure_correction()

template<class Scalar>

void Opm::HipKernels< Scalar >::add_coarse_pressure_correction ( Scalar * coarse_x, Scalar * fine_x, int pressure_idx, int Nb, hipStream_t stream )

static

Add the coarse pressure solution back to the finer, complete solution; every workitem handles one blockrow.

Parameters

[in]	coarse_x	Input scalar x vector
[out]	fine_x	Output blocked x vector
[in]	pressure_idx	Pressure index
[in]	Nb	Number of blocks in the original matrix
[in]	stream	Hip stream to use for the computations

full_to_pressure_restriction()

template<class Scalar>

void Opm::HipKernels< Scalar >::full_to_pressure_restriction ( const Scalar * fine_y, Scalar * weights, Scalar * coarse_y, int Nb, hipStream_t stream )

static

Transform blocked vector to scalar vector using pressure-weights, where every workitem handles one blockrow.

Parameters

[in]	fine_y	Input y vector
[in]	weights	Weights used to combine cells
[out]	coarse_y	Output y vector
[in]	Nb	Number of blocks in the original matrix
[in]	stream	Hip stream to use for the computations

init()

template<class Scalar>

void Opm::HipKernels< Scalar >::init ( int verbosity )

static

Initialize verbosity level for the HIP kernels.

Parameters

[in]

verbosity

verbosity level

prolongate_vector()

template<class Scalar>

void Opm::HipKernels< Scalar >::prolongate_vector ( const Scalar * in, Scalar * out, const int * cols, int N, hipStream_t stream )

static

Function to prolongate vector during amg cycle, every workitem handles one row.

Parameters

[in]	in	Input fine-grained vector
[out]	out	Output course-graned vector
[in]	cols	Column indexes
[in]	N	Size of the vector
[in]	stream	Hip stream to use for the computations

residual()

template<class Scalar>

void Opm::HipKernels< Scalar >::residual ( Scalar * vals, int * cols, int * rows, Scalar * x, const Scalar * rhs, Scalar * out, int Nb, unsigned int block_size, hipStream_t stream )

static

Function to perform res = rhs - mat * x.

Parameters

[in]	vals	Matrix values
[in]	cols	Column indexes
[in]	rows	Row pointers
[in]	x	X vector
[in]	rhs	Rhs vector
[out]	out	Output res vector
[in]	Nb	Number of non-zero blocks in the original matrix
[in]	block_size	Block size
[in]	stream	Hip stream to use for the computations

spmv()

template<class Scalar>

void Opm::HipKernels< Scalar >::spmv ( Scalar * vals, int * cols, int * rows, Scalar * x, Scalar * y, int Nb, unsigned int block_size, hipStream_t stream )

static

Function to perform sparse matrix vector multipliation.

Parameters

[in]	vals	Matrix values
[in]	cols	Column indexes
[in]	rows	Row pointers
[in]	x	Input x vector
[out]	y	Output y vector
[in]	Nb	Number of non-zero blocks in the original matrix
[in]	block_size	Block size
[in]	stream	Hip stream to use for the computations

vmul()

template<class Scalar>

void Opm::HipKernels< Scalar >::vmul ( const Scalar alpha, Scalar * in1, Scalar * in2, Scalar * out, int N, hipStream_t stream )

static

Function to multiply vector with another vector and a scalar, element-wise and add the result to a third vector (out = alpha * in1 + in2).

Parameters

[in]	alpha	Input scalar
[in]	in1	First input vector
[in]	in2	Second input vector
[out]	out	Output vector
[in]	N	Size of the vector
[in]	stream	Hip stream to use for the computations

---

The documentation for this class was generated from the following files:

• opm/simulators/linalg/gpubridge/rocm/hipKernels.hpp
• opm/simulators/linalg/gpubridge/rocm/hipKernels.cpp