rocsolver_sgetrf_npvt_strided_batched Interface Reference

• hipfort_rocsolver
• rocsolver_sgetrf_npvt_strided_batched

Public Member Functions | List of all members

hipfort_rocsolver::rocsolver_sgetrf_npvt_strided_batched Interface Reference

GETRF_NPVT_STRIDED_BATCHED computes the LU factorization of a batch of general m-by-n matrices without partial pivoting. More...

Public Member Functions
integer(kind(rocblas_status_success)) function	rocsolver_sgetrf_npvt_strided_batched_ (handle, m, n, A, lda, strideA, myInfo, batch_count)
integer(kind(rocblas_status_success)) function	rocsolver_sgetrf_npvt_strided_batched_full_rank (handle, m, n, A, lda, strideA, myInfo, batch_count)
integer(kind(rocblas_status_success)) function	rocsolver_sgetrf_npvt_strided_batched_rank_0 (handle, m, n, A, lda, strideA, myInfo, batch_count)
integer(kind(rocblas_status_success)) function	rocsolver_sgetrf_npvt_strided_batched_rank_1 (handle, m, n, A, lda, strideA, myInfo, batch_count)

Detailed Description

GETRF_NPVT_STRIDED_BATCHED computes the LU factorization of a batch of general m-by-n matrices without partial pivoting.

(This is the blocked Level-3-BLAS version of the algorithm. An optimized internal implementation without rocBLAS calls could be executed with mid-size matrices if optimizations are enabled (default option). For more details, see the "Tuning rocSOLVER performance" section of the Library Design Guide).

The factorization of matrix \(A_i\) in the batch has the form

\[ A_i = L_iU_i \]

where \(L_i\) is lower triangular with unit diagonal elements (lower trapezoidal if m > n), and \(U_i\) is upper triangular (upper trapezoidal if m < n).

Note: Although this routine can offer better performance, Gaussian elimination without pivoting is not backward stable. If numerical accuracy is compromised, use the legacy-LAPACK-like API GETRF_STRIDED_BATCHED routines instead.

Parameters

[in]	handle	rocblas_handle.
[in]	m	rocblas_int. m >= 0. The number of rows of all matrices A_i in the batch.
[in]	n	rocblas_int. n >= 0. The number of columns of all matrices A_i in the batch.
[in,out]	A	pointer to type. Array on the GPU (the size depends on the value of strideA). On entry, the m-by-n matrices A_i to be factored. On exit, the factors L_i and U_i from the factorization. The unit diagonal elements of L_i are not stored.
[in]	lda	rocblas_int. lda >= m. Specifies the leading dimension of matrices A_i.
[in]	strideA	rocblas_stride. 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
[out]	info	pointer to rocblas_int. Array of batch_count integers on the GPU. If info[i] = 0, successful exit for factorization of A_i. If info[i] = j > 0, U_i is singular. U_i[j,j] is the first zero element in the diagonal. The factorization from this point might be incomplete.
[in]	batch_count	rocblas_int. batch_count >= 0. Number of matrices in the batch.

Member Function/Subroutine Documentation

◆ rocsolver_sgetrf_npvt_strided_batched_()

integer(kind(rocblas_status_success)) function hipfort_rocsolver::rocsolver_sgetrf_npvt_strided_batched::rocsolver_sgetrf_npvt_strided_batched_	(	type(c_ptr), value	handle,
		integer(c_int), value	m,
		integer(c_int), value	n,
		type(c_ptr), value	A,
		integer(c_int), value	lda,
		integer(c_int64_t), value	strideA,
		integer(c_int)	myInfo,
		integer(c_int), value	batch_count
	)

◆ rocsolver_sgetrf_npvt_strided_batched_full_rank()

integer(kind(rocblas_status_success)) function hipfort_rocsolver::rocsolver_sgetrf_npvt_strided_batched::rocsolver_sgetrf_npvt_strided_batched_full_rank	(	type(c_ptr)	handle,
		integer(c_int)	m,
		integer(c_int)	n,
		real(c_float), dimension(:,:), target	A,
		integer(c_int)	lda,
		integer(c_int64_t)	strideA,
		integer(c_int)	myInfo,
		integer(c_int)	batch_count
	)

◆ rocsolver_sgetrf_npvt_strided_batched_rank_0()

integer(kind(rocblas_status_success)) function hipfort_rocsolver::rocsolver_sgetrf_npvt_strided_batched::rocsolver_sgetrf_npvt_strided_batched_rank_0	(	type(c_ptr)	handle,
		integer(c_int)	m,
		integer(c_int)	n,
		real(c_float), target	A,
		integer(c_int)	lda,
		integer(c_int64_t)	strideA,
		integer(c_int)	myInfo,
		integer(c_int)	batch_count
	)

◆ rocsolver_sgetrf_npvt_strided_batched_rank_1()

integer(kind(rocblas_status_success)) function hipfort_rocsolver::rocsolver_sgetrf_npvt_strided_batched::rocsolver_sgetrf_npvt_strided_batched_rank_1	(	type(c_ptr)	handle,
		integer(c_int)	m,
		integer(c_int)	n,
		real(c_float), dimension(:), target	A,
		integer(c_int)	lda,
		integer(c_int64_t)	strideA,
		integer(c_int)	myInfo,
		integer(c_int)	batch_count
	)

---

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

• hipfort_rocsolver.f