hipsparsescsr2dense Interface Reference

hipsparsescsr2dense Interface Reference#

HIPFORT API Reference: hipfort_hipsparse::hipsparsescsr2dense Interface Reference

hipsparseXcsr2dense functions convert the sparse matrix in CSR format into a dense matrix. More...

Public Member Functions
integer(kind(hipsparse_status_success)) function	hipsparsescsr2dense_ (handle, m, n, descr, csrval, csrrowptr, csrcolind, a, ld)

integer(kind(hipsparse_status_success)) function	hipsparsescsr2dense_rank_0 (handle, m, n, descr, csrval, csrrowptr, csrcolind, a, ld)

integer(kind(hipsparse_status_success)) function	hipsparsescsr2dense_rank_1 (handle, m, n, descr, csrval, csrrowptr, csrcolind, a, ld)

integer(kind(hipsparse_status_success)) function	hipsparsescsr2dense_full_rank (handle, m, n, descr, csrval, csrrowptr, csrcolind, a, ld)

Detailed Description

hipsparseXcsr2dense functions convert the sparse matrix in CSR format into a dense matrix.

Given the input CSR matrix of size mxn, the routine writes the matrix to the dense array A such that A has leading dimension ld and is column ordered. This means that A has size ldxn where ld>=m. All the parameters are assumed to have been preallocated by the user. If the input CSR matrix has index base of one, it must be set in the hipsparseMatDescr_t. See hipsparseSetMatIndexBase () prior to calling hipsparseXcsr2dense.

For example, consider the sparse CSR matrix:

\[ \begin{align} \text{csrRowPtr} &= \begin{bmatrix} 0 & 2 & 4 & 7 \end{bmatrix} \\% \text{csrColInd} &= \begin{bmatrix} 0 & 3 & 0 & 1 & 0 & 2 & 3 \end{bmatrix} \\% \text{csrVal} &= \begin{bmatrix} 1 & 2 & 3 & 4 & 5 & 6 & 7 \end{bmatrix} \\% \end{align} \]

hipsparseXcsr2dense is used to convert to the dense matrix:

\[ \begin{bmatrix} 1 & 0 & 0 & 2 \\% 3 & 4 & 0 & 0 \\% 5 & 0 & 6 & 7 \end{bmatrix} \]

where the values in the A array are column ordered:

\[ \text{A} &= \begin{bmatrix} 1 & 3 & 5 & 0 & 4 & 0 & 0 & 0 & 6 & 2 & 0 & 7 \end{bmatrix} \\% \]

Note: This function is executed asynchronously with respect to the host and can return control to the application on the host before the entire result is ready.

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 dense matrix `A`. Must be non-negative.
[in]	descr	- the descriptor of the dense matrix `A`, the supported matrix type is `HIPSPARSE_MATRIX_TYPE_GENERAL` and any valid value of the `hipsparseIndexBase_t`.
[in]	csrVal	- array of nnz ( = `csrRowPtr`[m] - `csrRowPtr`[0] ) non-zero elements of matrix `A`.
[in]	csrRowPtr	- integer array of `m+1` elements that contains the start of every row and the end of the last row plus one.
[in]	csrColInd	- integer array of nnz ( = `csrRowPtr`[m] - `csrRowPtr`[0] ) column indices of the non-zero elements of matrix `A`.
[out]	A	- array of dimensions (`ld`, `n`).
[in]	ld	- leading dimension of dense array `A`. 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`, `descr`, `csrVal`, `csrRowPtr`, `csrColInd`, or `A` is nullptr, `m` or `n` is negative, or `ld` is invalid.

Member Function/Subroutine Documentation