hipsparsesbsrmm Interface Reference

hipsparsesbsrmm Interface Reference#

HIPFORT API Reference: hipfort_hipsparse::hipsparsesbsrmm Interface Reference
Public Member Functions | List of all members
hipfort_hipsparse::hipsparsesbsrmm Interface Reference

Sparse matrix dense matrix multiplication using the BSR storage format. More...

Public Member Functions

integer(kind(hipsparse_status_success)) function hipsparsesbsrmm_ (handle, dira, transa, transb, mb, n, kb, nnzb, alpha, descra, bsrvala, bsrrowptra, bsrcolinda, blockdim, b, ldb, beta, c, ldc)
 
integer(kind(hipsparse_status_success)) function hipsparsesbsrmm_rank_0 (handle, dira, transa, transb, mb, n, kb, nnzb, alpha, descra, bsrvala, bsrrowptra, bsrcolinda, blockdim, b, ldb, beta, c, ldc)
 
integer(kind(hipsparse_status_success)) function hipsparsesbsrmm_rank_1 (handle, dira, transa, transb, mb, n, kb, nnzb, alpha, descra, bsrvala, bsrrowptra, bsrcolinda, blockdim, b, ldb, beta, c, ldc)
 
integer(kind(hipsparse_status_success)) function hipsparsesbsrmm_full_rank (handle, dira, transa, transb, mb, n, kb, nnzb, alpha, descra, bsrvala, bsrrowptra, bsrcolinda, blockdim, b, ldb, beta, c, ldc)
 

Detailed Description

Sparse matrix dense matrix multiplication using the BSR storage format.

hipsparseXbsrmm multiplies the scalar \(\alpha\) with a sparse \(m \times k\) matrix \(A\), defined in BSR storage format, and the column-oriented dense \(k \times n\) matrix \(B\) and adds the result to the column-oriented dense \(m \times n\) matrix \(C\) that is multiplied by the scalar \(\beta\), such that

\[ C := \alpha \cdot op(A) \cdot op(B) + \beta \cdot C, \]

with

\[ op(A) = \left\{ \begin{array}{ll} A, & \text{if transA == HIPSPARSE_OPERATION_NON_TRANSPOSE} \\% \end{array} \right. \]

and

\[ op(B) = \left\{ \begin{array}{ll} B, & \text{if transB == HIPSPARSE_OPERATION_NON_TRANSPOSE} \\% B^T, & \text{if transB == HIPSPARSE_OPERATION_TRANSPOSE} \\% \end{array} \right. \]

and where \(k = blockDim \times kb\) and \(m = blockDim \times mb\).

Note
This function is non-blocking and executed asynchronously with respect to the host. It can return before the actual computation has finished.
Currently, only transA == HIPSPARSE_OPERATION_NON_TRANSPOSE is supported.
Parameters
[in]handle- handle to the hipSPARSE library context queue.
[in]dirA- the storage format of the blocks. Can be HIPSPARSE_DIRECTION_ROW or HIPSPARSE_DIRECTION_COLUMN.
[in]transA- matrix \(A\) operation type. Currently, only HIPSPARSE_OPERATION_NON_TRANSPOSE is supported.
[in]transB- matrix \(B\) operation type. Currently, only HIPSPARSE_OPERATION_NON_TRANSPOSE and HIPSPARSE_OPERATION_TRANSPOSE are supported.
[in]mb- number of block rows of the sparse BSR matrix \(A\). Must be non-negative.
[in]n- number of columns of the dense matrix \(op(B)\) and \(C\). Must be non-negative.
[in]kb- number of block columns of the sparse BSR matrix \(A\). Must be non-negative.
[in]nnzb- number of non-zero blocks of the sparse BSR matrix \(A\). Must be non-negative.
[in]alpha- scalar \(\alpha\).
[in]descrA- descriptor of the sparse BSR matrix \(A\). Currently, only HIPSPARSE_MATRIX_TYPE_GENERAL is supported.
[in]bsrValA- array of nnzb*blockDim*blockDim elements of the sparse BSR matrix \(A\).
[in]bsrRowPtrA- array of mb+1 elements that point to the start of every block row of the sparse BSR matrix \(A\).
[in]bsrColIndA- array of nnzb elements containing the block column indices of the sparse BSR matrix \(A\).
[in]blockDim- size of the blocks in the sparse BSR matrix. Must be positive.
[in]B- array of dimension ldb*n ( \(op(B) == B\)), ldb*k otherwise.
[in]ldb- leading dimension of \(B\), must be at least \(\max{(1, k)}\) ( \( op(B) == B\)) where k=blockDim*kb, \(\max{(1, n)}\) otherwise.
[in]beta- scalar \(\beta\).
[in,out]C- array of dimension ldc*n.
[in]ldc- leading dimension of \(C\), must be at least \(\max{(1, m)}\) ( \( op(A) == A\)) where m=blockDim*mb, \(\max{(1, k)}\) where k=blockDim*kb otherwise.
Return values
HIPSPARSE_STATUS_SUCCESSthe operation completed successfully.
HIPSPARSE_STATUS_NOT_INITIALIZEDhandle is not initialized.
HIPSPARSE_STATUS_INVALID_VALUEhandle, descrA, alpha, or beta is nullptr, mb, n, kb, or nnzb is negative, ldb or ldc is invalid, blockDim is less than or equal to zero, or bsrValA, bsrRowPtrA, bsrColIndA, B, or C is nullptr.
HIPSPARSE_STATUS_ARCH_MISMATCHthe device is not supported.
HIPSPARSE_STATUS_NOT_SUPPORTEDtransA is not HIPSPARSE_OPERATION_NON_TRANSPOSE, transB is HIPSPARSE_OPERATION_CONJUGATE_TRANSPOSE, or hipsparseMatrixType_t is not HIPSPARSE_MATRIX_TYPE_GENERAL.

Member Function/Subroutine Documentation

◆ hipsparsesbsrmm_()

integer(kind(hipsparse_status_success)) function hipfort_hipsparse::hipsparsesbsrmm::hipsparsesbsrmm_ ( type(c_ptr), value  handle,
integer(kind(hipsparse_direction_row)), value  dira,
integer(kind(hipsparse_operation_non_transpose)), value  transa,
integer(kind(hipsparse_operation_non_transpose)), value  transb,
integer(c_int), value  mb,
integer(c_int), value  n,
integer(c_int), value  kb,
integer(c_int), value  nnzb,
real(c_float)  alpha,
type(c_ptr), value  descra,
type(c_ptr), value  bsrvala,
type(c_ptr), value  bsrrowptra,
type(c_ptr), value  bsrcolinda,
integer(c_int), value  blockdim,
type(c_ptr), value  b,
integer(c_int), value  ldb,
real(c_float)  beta,
type(c_ptr), value  c,
integer(c_int), value  ldc 
)

◆ hipsparsesbsrmm_full_rank()

integer(kind(hipsparse_status_success)) function hipfort_hipsparse::hipsparsesbsrmm::hipsparsesbsrmm_full_rank ( type(c_ptr)  handle,
integer(kind(hipsparse_direction_row))  dira,
integer(kind(hipsparse_operation_non_transpose))  transa,
integer(kind(hipsparse_operation_non_transpose))  transb,
integer(c_int)  mb,
integer(c_int)  n,
integer(c_int)  kb,
integer(c_int)  nnzb,
real(c_float)  alpha,
type(c_ptr)  descra,
real(c_float), dimension(:), target  bsrvala,
integer(c_int), dimension(:), target  bsrrowptra,
integer(c_int), dimension(:), target  bsrcolinda,
integer(c_int)  blockdim,
real(c_float), dimension(:,:), target  b,
integer(c_int)  ldb,
real(c_float)  beta,
real(c_float), dimension(:,:), target  c,
integer(c_int)  ldc 
)

◆ hipsparsesbsrmm_rank_0()

integer(kind(hipsparse_status_success)) function hipfort_hipsparse::hipsparsesbsrmm::hipsparsesbsrmm_rank_0 ( type(c_ptr)  handle,
integer(kind(hipsparse_direction_row))  dira,
integer(kind(hipsparse_operation_non_transpose))  transa,
integer(kind(hipsparse_operation_non_transpose))  transb,
integer(c_int)  mb,
integer(c_int)  n,
integer(c_int)  kb,
integer(c_int)  nnzb,
real(c_float)  alpha,
type(c_ptr)  descra,
real(c_float), target  bsrvala,
integer(c_int), target  bsrrowptra,
integer(c_int), target  bsrcolinda,
integer(c_int)  blockdim,
real(c_float), target  b,
integer(c_int)  ldb,
real(c_float)  beta,
real(c_float), target  c,
integer(c_int)  ldc 
)

◆ hipsparsesbsrmm_rank_1()

integer(kind(hipsparse_status_success)) function hipfort_hipsparse::hipsparsesbsrmm::hipsparsesbsrmm_rank_1 ( type(c_ptr)  handle,
integer(kind(hipsparse_direction_row))  dira,
integer(kind(hipsparse_operation_non_transpose))  transa,
integer(kind(hipsparse_operation_non_transpose))  transb,
integer(c_int)  mb,
integer(c_int)  n,
integer(c_int)  kb,
integer(c_int)  nnzb,
real(c_float)  alpha,
type(c_ptr)  descra,
real(c_float), dimension(:), target  bsrvala,
integer(c_int), dimension(:), target  bsrrowptra,
integer(c_int), dimension(:), target  bsrcolinda,
integer(c_int)  blockdim,
real(c_float), dimension(:), target  b,
integer(c_int)  ldb,
real(c_float)  beta,
real(c_float), dimension(:), target  c,
integer(c_int)  ldc 
)
The documentation for this interface was generated from the following file: