rocsolver_sgetf2_batched Interface Reference

• hipfort_rocsolver
• rocsolver_sgetf2_batched

Public Member Functions | List of all members

hipfort_rocsolver::rocsolver_sgetf2_batched Interface Reference

! More...

Public Member Functions
integer(kind(rocblas_status_success)) function	rocsolver_sgetf2_batched_full_rank (handle, m, n, A, lda, ipiv, strideP, myInfo, batch_count)
integer(kind(rocblas_status_success)) function	rocsolver_sgetf2_batched_orig (handle, m, n, A, lda, ipiv, strideP, myInfo, batch_count)
integer(kind(rocblas_status_success)) function	rocsolver_sgetf2_batched_rank_0 (handle, m, n, A, lda, ipiv, strideP, myInfo, batch_count)
integer(kind(rocblas_status_success)) function	rocsolver_sgetf2_batched_rank_1 (handle, m, n, A, lda, ipiv, strideP, myInfo, batch_count)

Detailed Description

!

GETF2_BATCHED computes the LU factorization of a batch of general m-by-n matrices using partial pivoting with row interchanges.

(This is the unblocked Level-2-BLAS version of the algorithm. An optimized internal implementation without rocBLAS calls could be executed with small and mid-size matrices if optimizations are enabled (default option). For more details see the section "tuning rocSOLVER performance" on the User's guide).

The factorization of matrix A_i in the batch has the form

    A_i = P_i  L_i  U_i

where P_i is a permutation matrix, 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).

@param[in]
handle    rocblas_handle.
@param[in]
m         rocblas_int. m >= 0.\n
          The number of rows of all matrices A_i in the batch.
@param[in]
n         rocblas_int. n >= 0.\n
          The number of columns of all matrices A_i in the batch.
@param[inout]
A         array of pointers to type. Each pointer points to an array on the GPU of dimension ldan.\n
          On entry, the m-by-n matrices A_i to be factored.
          On exit, the factors L_i and U_i from the factorizations.
          The unit diagonal elements of L_i are not stored.
@param[in]
lda       rocblas_int. lda >= m.\n
          Specifies the leading dimension of matrices A_i.
@param[out]
ipiv      pointer to rocblas_int. Array on the GPU (the size depends on the value of strideP).\n
          Contains the vectors of pivot indices ipiv_i (corresponding to A_i).
          Dimension of ipiv_i is min(m,n).
          Elements of ipiv_i are 1-based indices.
          For each instance A_i in the batch and for 1 <= j <= min(m,n), the row j of the
          matrix A_i was interchanged with row ipiv_i[j].
          Matrix P_i of the factorization can be derived from ipiv_i.
@param[in]
strideP   rocblas_stride.\n
          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 >= min(m,n).
@param[out]
info      pointer to rocblas_int. Array of batch_count integers on the GPU.\n
          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 pivot.
@param[in]
batch_count rocblas_int. batch_count >= 0.\n
            Number of matrices in the batch.

Member Function/Subroutine Documentation

◆ rocsolver_sgetf2_batched_full_rank()

integer(kind(rocblas_status_success)) function hipfort_rocsolver::rocsolver_sgetf2_batched::rocsolver_sgetf2_batched_full_rank	(	type(c_ptr), value	handle,
		integer(c_int), value	m,
		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
	)

◆ rocsolver_sgetf2_batched_orig()

integer(kind(rocblas_status_success)) function hipfort_rocsolver::rocsolver_sgetf2_batched::rocsolver_sgetf2_batched_orig	(	type(c_ptr), value	handle,
		integer(c_int), value	m,
		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
	)

◆ rocsolver_sgetf2_batched_rank_0()

integer(kind(rocblas_status_success)) function hipfort_rocsolver::rocsolver_sgetf2_batched::rocsolver_sgetf2_batched_rank_0	(	type(c_ptr), value	handle,
		integer(c_int), value	m,
		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
	)

◆ rocsolver_sgetf2_batched_rank_1()

integer(kind(rocblas_status_success)) function hipfort_rocsolver::rocsolver_sgetf2_batched::rocsolver_sgetf2_batched_rank_1	(	type(c_ptr), value	handle,
		integer(c_int), value	m,
		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:

• hipfort_rocsolver.f