rocsolver_sgetri_batched Interface Reference

rocsolver_sgetri_batched Interface Reference#

HIPFORT API Reference: hipfort_rocsolver::rocsolver_sgetri_batched Interface Reference

Public Member Functions
integer(kind(rocblas_status_success)) function	rocsolver_sgetri_batched_full_rank (handle, n, A, lda, ipiv, strideP, myInfo, batch_count)


integer(kind(rocblas_status_success)) function	rocsolver_sgetri_batched_orig (handle, n, A, lda, ipiv, strideP, myInfo, batch_count)

integer(kind(rocblas_status_success)) function	rocsolver_sgetri_batched_rank_0 (handle, n, A, lda, ipiv, strideP, myInfo, batch_count)

integer(kind(rocblas_status_success)) function	rocsolver_sgetri_batched_rank_1 (handle, n, A, lda, ipiv, strideP, myInfo, batch_count)

!

GETRI_BATCHED inverts a batch of general n-by-n matrices using the LU factorization computed by GETRF_BATCHED.

The inverse is computed by solving the linear system

inv(A_j)  L_j = inv(U_j)

where L_j is the lower triangular factor of A_j with unit diagonal elements, and U_j is the upper triangular factor.

Parameters

[in]	handle	rocblas_handle.
[in]	n	rocblas_int. n >= 0. The number of rows and columns of all matrices A_j in the batch.
[in,out]	A	array of pointers to type. Each pointer points to an array on the GPU of dimension ldan. On entry, the factors L_j and U_j of the factorization A = P_jL_jU_j returned by GETRF_BATCHED. On exit, the inverses of A_j if info_j = 0; otherwise undefined.
[in]	lda	rocblas_int. lda >= n. Specifies the leading dimension of matrices A_j.
[in]	ipiv	pointer to rocblas_int. Array on the GPU (the size depends on the value of strideP). The pivot indices returned by GETRF_BATCHED.
[in]	strideP	rocblas_stride. Stride from the start of one vector ipiv_j to the next one ipiv_(i+j). There is no restriction for the value of strideP. Normal use case is strideP >= n.
[out]	info	pointer to rocblas_int. Array of batch_count integers on the GPU. If info_j = 0, successful exit for inversion of A_j. If info_j = i > 0, U_j is singular. U_j(i,i) is the first zero pivot.
[in]	batch_count	rocblas_int. batch_count >= 0. Number of matrices in the batch.

integer(kind(rocblas_status_success)) function hipfort_rocsolver::rocsolver_sgetri_batched::rocsolver_sgetri_batched_full_rank	(	type(c_ptr), value	handle,
		integer(c_int), value	n,
		real(c_float), dimension(:,:,:), target	A,
		integer(c_int), value	lda,
		integer(c_int), dimension(:), target	ipiv,
		integer(c_int64_t), value	strideP,
		type(c_ptr), value	myInfo,
		integer(c_int), value	batch_count
	)

integer(kind(rocblas_status_success)) function hipfort_rocsolver::rocsolver_sgetri_batched::rocsolver_sgetri_batched_orig	(	type(c_ptr), value	handle,
		integer(c_int), value	n,
		type(c_ptr)	A,
		integer(c_int), value	lda,
		type(c_ptr), value	ipiv,
		integer(c_int64_t), value	strideP,
		type(c_ptr), value	myInfo,
		integer(c_int), value	batch_count
	)

integer(kind(rocblas_status_success)) function hipfort_rocsolver::rocsolver_sgetri_batched::rocsolver_sgetri_batched_rank_0	(	type(c_ptr), value	handle,
		integer(c_int), value	n,
		real(c_float), target	A,
		integer(c_int), value	lda,
		integer(c_int), target	ipiv,
		integer(c_int64_t), value	strideP,
		type(c_ptr), value	myInfo,
		integer(c_int), value	batch_count
	)

integer(kind(rocblas_status_success)) function hipfort_rocsolver::rocsolver_sgetri_batched::rocsolver_sgetri_batched_rank_1	(	type(c_ptr), value	handle,
		integer(c_int), value	n,
		real(c_float), dimension(:), target	A,
		integer(c_int), value	lda,
		integer(c_int), dimension(:), target	ipiv,
		integer(c_int64_t), value	strideP,
		type(c_ptr), value	myInfo,
		integer(c_int), value	batch_count
	)

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