rocsparse_sbsrxmv Interface Reference

• hipfort_rocsparse
• rocsparse_sbsrxmv

Public Member Functions | List of all members

hipfort_rocsparse::rocsparse_sbsrxmv Interface Reference

Sparse matrix vector multiplication with mask operation using the BSR storage format. More...

Public Member Functions
integer(kind(rocsparse_status_success)) function	rocsparse_sbsrxmv_ (handle, dir, trans, size_of_mask, mb, nb, nnzb, alpha, descr, bsr_val, bsr_mask_ptr, bsr_row_ptr, bsr_end_ptr, bsr_col_ind, block_dim, x, beta, y)
integer(kind(rocsparse_status_success)) function	rocsparse_sbsrxmv_rank_0 (handle, dir, trans, size_of_mask, mb, nb, nnzb, alpha, descr, bsr_val, bsr_mask_ptr, bsr_row_ptr, bsr_end_ptr, bsr_col_ind, block_dim, x, beta, y)
integer(kind(rocsparse_status_success)) function	rocsparse_sbsrxmv_rank_1 (handle, dir, trans, size_of_mask, mb, nb, nnzb, alpha, descr, bsr_val, bsr_mask_ptr, bsr_row_ptr, bsr_end_ptr, bsr_col_ind, block_dim, x, beta, y)

Detailed Description

Sparse matrix vector multiplication with mask operation using the BSR storage format.

rocsparse_bsrxmv multiplies the scalar \(\alpha\) with a sparse \(m \times n\) modified matrix, defined in BSR storage format, and the dense vector \(x\) and adds the result to the dense vector \(y\) that is multiplied by the scalar \(\beta\), such that

\[ y := \left( \alpha \cdot op(A) \cdot x + \beta \cdot y \right)\left( \text{mask} \right), \]

with

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

and where \(m = mb \times block\_dim\) and \(n = nb \times block\_dim\).

The \(\text{mask}\) is defined as an array of block row indices. The input sparse matrix is defined with a modified BSR storage format where the beginning and the end of each row is defined with two arrays, bsr_row_ptr and bsr_end_ptr (both of size mb), rather the usual bsr_row_ptr of size mb+1.

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 trans == rocsparse_operation_none is supported. Currently, block_dim==1 is not supported.

This routine supports execution in a hipGraph context.

Parameters

[in]	handle	- handle to the rocSPARSE library context queue.
[in]	dir	- matrix storage of BSR blocks.
[in]	trans	- matrix operation type.
[in]	size_of_mask	- number of updated block rows of the array y.
[in]	mb	- number of block rows of the sparse BSR matrix.
[in]	nb	- number of block columns of the sparse BSR matrix.
[in]	nnzb	- number of non-zero blocks of the sparse BSR matrix.
[in]	alpha	- scalar \(\alpha\).
[in]	descr	- descriptor of the sparse BSR matrix. Currently, only rocsparse_matrix_type_general is supported.
[in]	bsr_val	- array of nnzb blocks of the sparse BSR matrix.
[in]	bsr_mask_ptr	- array of size_of_mask elements that give the indices of the updated block rows.
[in]	bsr_row_ptr	- array of mb elements that point to the start of every block row of the sparse BSR matrix.
[in]	bsr_end_ptr	- array of mb elements that point to the end of every block row of the sparse BSR matrix.
[in]	bsr_col_ind	- array of nnzb elements containing the block column indices of the sparse BSR matrix.
[in]	block_dim	- block dimension of the sparse BSR matrix.
[in]	x	- array of nb*block_dim elements ( \(op(A) = A\)) or mb*block_dim elements ( \(op(A) = A^T\) or \(op(A) = A^H\)).
[in]	beta	- scalar \(\beta\).
[in,out]	y	- array of mb*block_dim elements ( \(op(A) = A\)) or nb*block_dim elements ( \(op(A) = A^T\) or \(op(A) = A^H\)).

Return values

rocsparse_status_success	the operation completed successfully.
rocsparse_status_invalid_handle	the library context was not initialized.
rocsparse_status_invalid_size	mb, nb, nnzb, block_dim, or size_of_mask is invalid.
rocsparse_status_invalid_value	size_of_mask is greater than mb.
rocsparse_status_invalid_pointer	descr, alpha, bsr_val, bsr_row_ind, bsr_col_ind, x, beta, or y pointer is invalid.
rocsparse_status_arch_mismatch	the device is not supported.
rocsparse_status_not_implemented	block_dim==1, trans != rocsparse_operation_none or rocsparse_matrix_type != rocsparse_matrix_type_general.

Member Function/Subroutine Documentation

◆ rocsparse_sbsrxmv_()

integer(kind(rocsparse_status_success)) function hipfort_rocsparse::rocsparse_sbsrxmv::rocsparse_sbsrxmv_	(	type(c_ptr), value	handle,
		integer(kind(rocsparse_direction_row)), value	dir,
		integer(kind(rocsparse_operation_none)), value	trans,
		integer(c_int), value	size_of_mask,
		integer(c_int), value	mb,
		integer(c_int), value	nb,
		integer(c_int), value	nnzb,
		real(c_float)	alpha,
		type(c_ptr), value	descr,
		type(c_ptr), value	bsr_val,
		type(c_ptr), value	bsr_mask_ptr,
		type(c_ptr), value	bsr_row_ptr,
		type(c_ptr), value	bsr_end_ptr,
		type(c_ptr), value	bsr_col_ind,
		integer(c_int), value	block_dim,
		type(c_ptr), value	x,
		real(c_float)	beta,
		type(c_ptr), value	y
	)

◆ rocsparse_sbsrxmv_rank_0()

integer(kind(rocsparse_status_success)) function hipfort_rocsparse::rocsparse_sbsrxmv::rocsparse_sbsrxmv_rank_0	(	type(c_ptr)	handle,
		integer(kind(rocsparse_direction_row))	dir,
		integer(kind(rocsparse_operation_none))	trans,
		integer(c_int)	size_of_mask,
		integer(c_int)	mb,
		integer(c_int)	nb,
		integer(c_int)	nnzb,
		real(c_float)	alpha,
		type(c_ptr)	descr,
		real(c_float), target	bsr_val,
		integer(c_int), target	bsr_mask_ptr,
		integer(c_int), target	bsr_row_ptr,
		integer(c_int), target	bsr_end_ptr,
		integer(c_int), target	bsr_col_ind,
		integer(c_int)	block_dim,
		real(c_float), target	x,
		real(c_float)	beta,
		real(c_float), target	y
	)

◆ rocsparse_sbsrxmv_rank_1()

integer(kind(rocsparse_status_success)) function hipfort_rocsparse::rocsparse_sbsrxmv::rocsparse_sbsrxmv_rank_1	(	type(c_ptr)	handle,
		integer(kind(rocsparse_direction_row))	dir,
		integer(kind(rocsparse_operation_none))	trans,
		integer(c_int)	size_of_mask,
		integer(c_int)	mb,
		integer(c_int)	nb,
		integer(c_int)	nnzb,
		real(c_float)	alpha,
		type(c_ptr)	descr,
		real(c_float), dimension(:), target	bsr_val,
		integer(c_int), dimension(:), target	bsr_mask_ptr,
		integer(c_int), dimension(:), target	bsr_row_ptr,
		integer(c_int), dimension(:), target	bsr_end_ptr,
		integer(c_int), dimension(:), target	bsr_col_ind,
		integer(c_int)	block_dim,
		real(c_float), dimension(:), target	x,
		real(c_float)	beta,
		real(c_float), dimension(:), target	y
	)

---

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

• hipfort_rocsparse.F90