hipsparsesgemmi Interface Reference

• hipfort_hipsparse
• hipsparsesgemmi

Public Member Functions | List of all members

hipfort_hipsparse::hipsparsesgemmi Interface Reference

Dense matrix sparse matrix multiplication using the CSC storage format. More...

Public Member Functions
integer(kind(hipsparse_status_success)) function	hipsparsesgemmi_ (handle, m, n, k, nnz, alpha, a, lda, cscvalb, csccolptrb, cscrowindb, beta, c, ldc)
integer(kind(hipsparse_status_success)) function	hipsparsesgemmi_rank_0 (handle, m, n, k, nnz, alpha, a, lda, cscvalb, csccolptrb, cscrowindb, beta, c, ldc)
integer(kind(hipsparse_status_success)) function	hipsparsesgemmi_rank_1 (handle, m, n, k, nnz, alpha, a, lda, cscvalb, csccolptrb, cscrowindb, beta, c, ldc)
integer(kind(hipsparse_status_success)) function	hipsparsesgemmi_full_rank (handle, m, n, k, nnz, alpha, a, lda, cscvalb, csccolptrb, cscrowindb, beta, c, ldc)

Detailed Description

Dense matrix sparse matrix multiplication using the CSC storage format.

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

\[ C := \alpha \cdot A \cdot B + \beta \cdot C \]

Note

This function is non-blocking and executed asynchronously with respect to the host. It can return before the actual computation has finished.

Deprecated:

This function is deprecated when using the CUDA backend (CUDA 11.0+) and will be removed in CUDA 12.0. This deprecation does not apply to the ROCm backend.

Parameters

[in]	handle	- handle to the hipSPARSE library context queue.
[in]	m	- number of rows of the dense matrix \(A\). Must be non-negative.
[in]	n	- number of columns of the sparse CSC matrix \(op(B)\) and \(C\). Must be non-negative.
[in]	k	- number of columns of the dense matrix \(A\). Must be non-negative.
[in]	nnz	- number of non-zero entries of the sparse CSC matrix \(B\). Must be non-negative.
[in]	alpha	- scalar \(\alpha\).
[in]	A	- array of dimension \(lda \times k\) ( \(op(A) == A\)) or \(lda \times m\) ( \(op(A) == A^T\) or \(op(A) == A^H\)).
[in]	lda	- leading dimension of \(A\), must be at least \(m\) ( \(op(A) == A\)) or \(k\) ( \(op(A) == A^T\) or \(op(A) == A^H\)).
[in]	cscValB	- array of nnz elements of the sparse CSC matrix \(B\).
[in]	cscColPtrB	- array of n+1 elements that point to the start of every column of the sparse CSC matrix \(B\).
[in]	cscRowIndB	- array of nnz elements containing the column indices of the sparse CSC matrix \(B\).
[in]	beta	- scalar \(\beta\).
[in,out]	C	- array of dimension \(ldc \times n\) that holds the values of \(C\).
[in]	ldc	- leading dimension of \(C\), must be at least \(m\).

Return values

HIPSPARSE_STATUS_SUCCESS	the operation completed successfully.
HIPSPARSE_STATUS_NOT_INITIALIZED	handle is not initialized.
HIPSPARSE_STATUS_INVALID_VALUE	handle, alpha or beta is nullptr, m, n, k, or nnz is negative, lda or ldc is invalid, or A, cscValB, cscColPtrB, cscRowIndB, or C is nullptr.

Member Function/Subroutine Documentation

◆ hipsparsesgemmi_()

integer(kind(hipsparse_status_success)) function hipfort_hipsparse::hipsparsesgemmi::hipsparsesgemmi_	(	type(c_ptr), value	handle,
		integer(c_int), value	m,
		integer(c_int), value	n,
		integer(c_int), value	k,
		integer(c_int), value	nnz,
		real(c_float)	alpha,
		type(c_ptr), value	a,
		integer(c_int), value	lda,
		type(c_ptr), value	cscvalb,
		type(c_ptr), value	csccolptrb,
		type(c_ptr), value	cscrowindb,
		real(c_float)	beta,
		type(c_ptr), value	c,
		integer(c_int), value	ldc
	)

◆ hipsparsesgemmi_full_rank()

integer(kind(hipsparse_status_success)) function hipfort_hipsparse::hipsparsesgemmi::hipsparsesgemmi_full_rank	(	type(c_ptr)	handle,
		integer(c_int)	m,
		integer(c_int)	n,
		integer(c_int)	k,
		integer(c_int)	nnz,
		real(c_float)	alpha,
		real(c_float), dimension(:,:), target	a,
		integer(c_int)	lda,
		real(c_float), dimension(:), target	cscvalb,
		integer(c_int), dimension(:), target	csccolptrb,
		integer(c_int), dimension(:), target	cscrowindb,
		real(c_float)	beta,
		real(c_float), dimension(:,:), target	c,
		integer(c_int)	ldc
	)

◆ hipsparsesgemmi_rank_0()

integer(kind(hipsparse_status_success)) function hipfort_hipsparse::hipsparsesgemmi::hipsparsesgemmi_rank_0	(	type(c_ptr)	handle,
		integer(c_int)	m,
		integer(c_int)	n,
		integer(c_int)	k,
		integer(c_int)	nnz,
		real(c_float)	alpha,
		real(c_float), target	a,
		integer(c_int)	lda,
		real(c_float), target	cscvalb,
		integer(c_int), target	csccolptrb,
		integer(c_int), target	cscrowindb,
		real(c_float)	beta,
		real(c_float), target	c,
		integer(c_int)	ldc
	)

◆ hipsparsesgemmi_rank_1()

integer(kind(hipsparse_status_success)) function hipfort_hipsparse::hipsparsesgemmi::hipsparsesgemmi_rank_1	(	type(c_ptr)	handle,
		integer(c_int)	m,
		integer(c_int)	n,
		integer(c_int)	k,
		integer(c_int)	nnz,
		real(c_float)	alpha,
		real(c_float), dimension(:), target	a,
		integer(c_int)	lda,
		real(c_float), dimension(:), target	cscvalb,
		integer(c_int), dimension(:), target	csccolptrb,
		integer(c_int), dimension(:), target	cscrowindb,
		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:

• hipfort_hipsparse.F90