rocsparse_sprune_dense2csr Interface Reference

rocsparse_sprune_dense2csr Interface Reference#

hipFORT API Reference: hipfort_rocsparse::rocsparse_sprune_dense2csr Interface Reference

Convert and prune dense matrix \(A\) into a sparse CSR matrix \(C\). More...

Public Member Functions
integer(c_int) function	rocsparse_sprune_dense2csr_ (handle, m, n, a, lda, threshold, descr, csr_val, csr_row_ptr, csr_col_ind, temp_buffer)

integer(kind(rocsparse_status_success)) function	rocsparse_sprune_dense2csr_typed (handle, m, n, a, lda, threshold, descr, csr_val, csr_row_ptr, csr_col_ind, temp_buffer)

integer(kind(rocsparse_status_success)) function	rocsparse_sprune_dense2csr_rank_0 (handle, m, n, a, lda, threshold, descr, csr_val, csr_row_ptr, csr_col_ind, temp_buffer)

integer(kind(rocsparse_status_success)) function	rocsparse_sprune_dense2csr_rank_1 (handle, m, n, a, lda, threshold, descr, csr_val, csr_row_ptr, csr_col_ind, temp_buffer)

integer(kind(rocsparse_status_success)) function	rocsparse_sprune_dense2csr_full_rank (handle, m, n, a, lda, threshold, descr, csr_val, csr_row_ptr, csr_col_ind, temp_buffer)

Detailed Description

Convert and prune dense matrix \(A\) into a sparse CSR matrix \(C\).

This function converts the dense matrix \(A\) into a sparse CSR matrix \(C\) by pruning values in \(A\) that are less than a threshold.

The conversion involves three steps. First, call rocsparse_Xprune_dense2csr_buffer_size() to determine the size of the temporary storage buffer. Allocate this buffer as well as the array csr_row_ptr to have m+1 elements. Then call rocsparse_Xprune_dense2csr_nnz(), which fills in the csr_row_ptr array and stores the number of elements that are larger than the pruning threshold in nnz_total_dev_host_ptr. Now that the number of non-zeros larger than the pruning threshold is known, use this information to allocate the csr_col_ind and csr_val arrays and then call rocsparse_prune_dense2csr to complete the conversion. After the conversion is complete, the temporary storage buffer can be freed.

Note: This function is blocking with respect to the host.; This routine does not support execution in a hipGraph context.

Parameters

[in]	handle	- handle to the rocSPARSE library context queue.
[in]	m	- number of rows of the dense matrix `A`.
[in]	n	- number of columns of the dense matrix `A`.
[in]	A	- array of dimensions (`lda`, `n`).
[in]	lda	- leading dimension of dense array `A`.
[in]	threshold	- pointer to the non-negative pruning threshold, which can exist in either host or device memory.
[in]	descr	- the descriptor of the dense matrix `A`. The supported matrix type is `rocsparse_matrix_type_general` and also any valid value of the `rocsparse_index_base`.
[out]	csr_val	- array of nnz ( = `csr_row_ptr`[m] - `csr_row_ptr`[0] ) non-zero elements of matrix `A`.
[in]	csr_row_ptr	- integer array of `m+1` elements that contains the start of every row and the end of the last row plus one.
[out]	csr_col_ind	- integer array of nnz ( = `csr_row_ptr`[m] - `csr_row_ptr`[0] ) column indices of the non-zero elements of matrix `A`.
[in]	temp_buffer	- temporary storage buffer allocated by the user. The size is returned by rocsparse_Xprune_dense2csr_buffer_size().

Return values

rocsparse_status_success	the operation completed successfully.
rocsparse_status_invalid_handle	the library context was not initialized.
rocsparse_status_invalid_size	`m`, `n`, or `lda` is invalid.
rocsparse_status_invalid_pointer	`A`, `descr`, `threshold`, `csr_val`, `csr_row_ptr`, `csr_col_ind`, or `temp_buffer` pointer is invalid.

Example

Member Function/Subroutine Documentation