This page contains proposed changes for a future release of ROCm. Read the latest Linux release of ROCm documentation for your production environments.

rocsolver_spotrs_batched Interface Reference

rocsolver_spotrs_batched Interface Reference#

HIPFORT API Reference: hipfort_rocsolver::rocsolver_spotrs_batched Interface Reference
hipfort_rocsolver::rocsolver_spotrs_batched Interface Reference

POTRS_BATCHED solves a batch of symmetric/hermitian systems of n linear equations on n variables in its factorized forms. More...

Public Member Functions

integer(kind(rocblas_status_success)) function rocsolver_spotrs_batched_ (handle, uplo, n, nrhs, A, lda, B, ldb, batch_count)
 
integer(kind(rocblas_status_success)) function rocsolver_spotrs_batched_full_rank (handle, uplo, n, nrhs, A, lda, B, ldb, batch_count)
 
integer(kind(rocblas_status_success)) function rocsolver_spotrs_batched_rank_0 (handle, uplo, n, nrhs, A, lda, B, ldb, batch_count)
 
integer(kind(rocblas_status_success)) function rocsolver_spotrs_batched_rank_1 (handle, uplo, n, nrhs, A, lda, B, ldb, batch_count)
 

Detailed Description

POTRS_BATCHED solves a batch of symmetric/hermitian systems of n linear equations on n variables in its factorized forms.

For each instance j in the batch, it solves the system

\[ A_j X_j = B_j \]

where \(A_j\) is a real symmetric (complex hermitian) positive definite matrix defined by its triangular factor

\[ \begin{array}{cl} A_j = U_j'U_j & \: \text{if uplo is upper, or}\newline A_j = L_jL_j' & \: \text{if uplo is lower.} \end{array} \]

as returned by POTRF_BATCHED.

Parameters
[in]handlerocblas_handle.
[in]uplorocblas_fill.
Specifies whether the factorization is upper or lower triangular. If uplo indicates lower (or upper), then the upper (or lower) part of A is not used.
[in]nrocblas_int. n >= 0.
The order of the system, i.e. the number of columns and rows of all A_j matrices.
[in]nrhsrocblas_int. nrhs >= 0.
The number of right hand sides, i.e., the number of columns of all the matrices B_j.
[in]AArray of pointers to type. Each pointer points to an array on the GPU of dimension lda*n.
The factor L_j or U_j of the Cholesky factorization of A_j returned by POTRF_BATCHED.
[in]ldarocblas_int. lda >= n.
The leading dimension of matrices A_j.
[in,out]BArray of pointers to type. Each pointer points to an array on the GPU of dimension ldb*nrhs.
On entry, the right hand side matrices B_j. On exit, the solution matrix X_j of each system in the batch.
[in]ldbrocblas_int. ldb >= n.
The leading dimension of matrices B_j.
[in]batch_countrocblas_int. batch_count >= 0.
Number of instances (systems) in the batch.

Member Function/Subroutine Documentation

◆ rocsolver_spotrs_batched_()

integer(kind(rocblas_status_success)) function hipfort_rocsolver::rocsolver_spotrs_batched::rocsolver_spotrs_batched_ ( type(c_ptr), value  handle,
integer(kind(rocblas_fill_upper)), value  uplo,
integer(c_int), value  n,
integer(c_int), value  nrhs,
type(c_ptr)  A,
integer(c_int), value  lda,
type(c_ptr)  B,
integer(c_int), value  ldb,
integer(c_int), value  batch_count 
)

◆ rocsolver_spotrs_batched_full_rank()

integer(kind(rocblas_status_success)) function hipfort_rocsolver::rocsolver_spotrs_batched::rocsolver_spotrs_batched_full_rank ( type(c_ptr)  handle,
integer(kind(rocblas_fill_upper))  uplo,
integer(c_int)  n,
integer(c_int)  nrhs,
real(c_float), dimension(:,:,:), target  A,
integer(c_int)  lda,
real(c_float), dimension(:,:,:), target  B,
integer(c_int)  ldb,
integer(c_int)  batch_count 
)

◆ rocsolver_spotrs_batched_rank_0()

integer(kind(rocblas_status_success)) function hipfort_rocsolver::rocsolver_spotrs_batched::rocsolver_spotrs_batched_rank_0 ( type(c_ptr)  handle,
integer(kind(rocblas_fill_upper))  uplo,
integer(c_int)  n,
integer(c_int)  nrhs,
real(c_float), target  A,
integer(c_int)  lda,
real(c_float), target  B,
integer(c_int)  ldb,
integer(c_int)  batch_count 
)

◆ rocsolver_spotrs_batched_rank_1()

integer(kind(rocblas_status_success)) function hipfort_rocsolver::rocsolver_spotrs_batched::rocsolver_spotrs_batched_rank_1 ( type(c_ptr)  handle,
integer(kind(rocblas_fill_upper))  uplo,
integer(c_int)  n,
integer(c_int)  nrhs,
real(c_float), dimension(:), target  A,
integer(c_int)  lda,
real(c_float), dimension(:), target  B,
integer(c_int)  ldb,
integer(c_int)  batch_count 
)

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