hipblassgetrsstridedbatched Interface Reference

• hipfort_hipblas
• hipblassgetrsstridedbatched

Public Member Functions | List of all members

hipfort_hipblas::hipblassgetrsstridedbatched Interface Reference

SOLVER API. More...

Public Member Functions
integer(kind(hipblas_status_success)) function	hipblassgetrsstridedbatched_ (handle, trans, n, nrhs, a, lda, stridea, ipiv, stridep, b, ldb, strideb, myinfo, batchcount)
integer(kind(hipblas_status_success)) function	hipblassgetrsstridedbatched_rank_0 (handle, trans, n, nrhs, a, lda, stridea, ipiv, stridep, b, ldb, strideb, myinfo, batchcount)
integer(kind(hipblas_status_success)) function	hipblassgetrsstridedbatched_rank_1 (handle, trans, n, nrhs, a, lda, stridea, ipiv, stridep, b, ldb, strideb, myinfo, batchcount)
integer(kind(hipblas_status_success)) function	hipblassgetrsstridedbatched_full_rank (handle, trans, n, nrhs, a, lda, stridea, ipiv, stridep, b, ldb, strideb, myinfo, batchcount)

Detailed Description

SOLVER API.

The getrsStridedBatched functions solve a batch of systems of n linear equations on n variables in its factorized forms.

For each instance i in the batch, they solve one of the following systems, depending on the value of trans:

\[ \begin{array}{cl} A_i X_i = B_i & \: \text{not transposed,}\\% A_i^T X_i = B_i & \: \text{transposed, or}\\% A_i^H X_i = B_i & \: \text{conjugate transposed.} \end{array} \]

Matrix \(A_i\) is defined by its triangular factors as returned by hipblasSgetrfStridedBatched "getrfStridedBatched".

• Supported precisions in rocSOLVER : s, d, c, and z.
• Supported precisions in cuBLAS : No support.

Parameters

[in]	handle	- hipblasHandle_t.
[in]	trans	- hipblasOperation_t. Specifies the form of the system of equations of each instance in the batch.
[in]	n	- int. n >= 0. The order of the system, that is, the number of columns and rows of all A_i matrices.
[in]	nrhs	- int. nrhs >= 0. The number of right hand sides, that is, the number of columns of all the matrices B_i.
[in]	A	- pointer to type. Array on the GPU (the size depends on the value of strideA). The factors L_i and U_i of the factorization A_i = P_i*L_i*U_i returned by hipblasSgetrfStridedBatched "getrfStridedBatched".
[in]	lda	- int. lda >= n. The leading dimension of matrices A_i.
[in]	strideA	- hipblasStride. Stride from the start of one matrix A_i to the next one A_(i+1). There is no restriction for the value of strideA. Normal use case is strideA >= lda*n.
[in]	ipiv	- pointer to int. Array on the GPU (the size depends on the value of strideP). Contains the vectors ipiv_i of pivot indices returned by hipblasSgetrfStridedBatched "getrfStridedBatched".
[in]	strideP	- hipblasStride. Stride from the start of one vector ipiv_i to the next one ipiv_(i+1). There is no restriction for the value of strideP. Normal use case is strideP >= n.
[in,out]	B	- pointer to type. Array on the GPU (size depends on the value of strideB). On entry, the right hand side matrices B_i. On exit, the solution matrix X_i of each system in the batch.
[in]	ldb	- int. ldb >= n. The leading dimension of matrices B_i.
[in]	strideB	- hipblasStride. Stride from the start of one matrix B_i to the next one B_(i+1). There is no restriction for the value of strideB. Normal use case is strideB >= ldb*nrhs.
[out]	myInfo	- pointer to a int on the host. If info = 0, successful exit. If info = j < 0, the argument at position -j is invalid.
[in]	batchCount	- int. batchCount >= 0. Number of instances (systems) in the batch.

Member Function/Subroutine Documentation

◆ hipblassgetrsstridedbatched_()

integer(kind(hipblas_status_success)) function hipfort_hipblas::hipblassgetrsstridedbatched::hipblassgetrsstridedbatched_	(	type(c_ptr), value	handle,
		integer(kind(hipblas_op_n)), value	trans,
		integer(c_int), value	n,
		integer(c_int), value	nrhs,
		type(c_ptr), value	a,
		integer(c_int), value	lda,
		integer(c_int64_t), value	stridea,
		type(c_ptr), value	ipiv,
		integer(c_int64_t), value	stridep,
		type(c_ptr), value	b,
		integer(c_int), value	ldb,
		integer(c_int64_t), value	strideb,
		type(c_ptr), value	myinfo,
		integer(c_int), value	batchcount
	)

◆ hipblassgetrsstridedbatched_full_rank()

integer(kind(hipblas_status_success)) function hipfort_hipblas::hipblassgetrsstridedbatched::hipblassgetrsstridedbatched_full_rank	(	type(c_ptr)	handle,
		integer(kind(hipblas_op_n))	trans,
		integer(c_int)	n,
		integer(c_int)	nrhs,
		real(c_float), dimension(:,:), target	a,
		integer(c_int)	lda,
		integer(c_int64_t)	stridea,
		integer(c_int), dimension(:), target	ipiv,
		integer(c_int64_t)	stridep,
		real(c_float), dimension(:,:), target	b,
		integer(c_int)	ldb,
		integer(c_int64_t)	strideb,
		type(c_ptr)	myinfo,
		integer(c_int)	batchcount
	)

◆ hipblassgetrsstridedbatched_rank_0()

integer(kind(hipblas_status_success)) function hipfort_hipblas::hipblassgetrsstridedbatched::hipblassgetrsstridedbatched_rank_0	(	type(c_ptr)	handle,
		integer(kind(hipblas_op_n))	trans,
		integer(c_int)	n,
		integer(c_int)	nrhs,
		real(c_float), target	a,
		integer(c_int)	lda,
		integer(c_int64_t)	stridea,
		integer(c_int), target	ipiv,
		integer(c_int64_t)	stridep,
		real(c_float), target	b,
		integer(c_int)	ldb,
		integer(c_int64_t)	strideb,
		type(c_ptr)	myinfo,
		integer(c_int)	batchcount
	)

◆ hipblassgetrsstridedbatched_rank_1()

integer(kind(hipblas_status_success)) function hipfort_hipblas::hipblassgetrsstridedbatched::hipblassgetrsstridedbatched_rank_1	(	type(c_ptr)	handle,
		integer(kind(hipblas_op_n))	trans,
		integer(c_int)	n,
		integer(c_int)	nrhs,
		real(c_float), dimension(:), target	a,
		integer(c_int)	lda,
		integer(c_int64_t)	stridea,
		integer(c_int), dimension(:), target	ipiv,
		integer(c_int64_t)	stridep,
		real(c_float), dimension(:), target	b,
		integer(c_int)	ldb,
		integer(c_int64_t)	strideb,
		type(c_ptr)	myinfo,
		integer(c_int)	batchcount
	)

---

The documentation for this interface was generated from the following file:

• hipfort_hipblas.F90