rocsparse_sprune_csr2csr Interface Reference

rocsparse_sprune_csr2csr Interface Reference#

HIPFORT API Reference: hipfort_rocsparse::rocsparse_sprune_csr2csr Interface Reference

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

Public Member Functions
integer(kind(rocsparse_status_success)) function	rocsparse_sprune_csr2csr_ (handle, m, n, nnz_a, csr_descr_a, csr_val_a, csr_row_ptr_a, csr_col_ind_a, threshold, csr_descr_c, csr_val_c, csr_row_ptr_c, csr_col_ind_c, temp_buffer)

integer(kind(rocsparse_status_success)) function	rocsparse_sprune_csr2csr_rank_0 (handle, m, n, nnz_a, csr_descr_a, csr_val_a, csr_row_ptr_a, csr_col_ind_a, threshold, csr_descr_c, csr_val_c, csr_row_ptr_c, csr_col_ind_c, temp_buffer)

integer(kind(rocsparse_status_success)) function	rocsparse_sprune_csr2csr_rank_1 (handle, m, n, nnz_a, csr_descr_a, csr_val_a, csr_row_ptr_a, csr_col_ind_a, threshold, csr_descr_c, csr_val_c, csr_row_ptr_c, csr_col_ind_c, temp_buffer)

Detailed Description

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

This function converts the sparse CSR 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_csr2csr_buffer_size() to determine the size of the temporary storage buffer. Allocate this buffer as well as the array csr_row_ptr_C to have m+1 elements. Then call rocsparse_Xprune_csr2csr_nnz(), which fills in the csr_row_ptr_C 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_C and csr_val_C arrays and then call rocsparse_prune_csr2csr 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 in the sparse CSR matrix.
[in]	n	- number of columns in the sparse CSR matrix.
[in]	nnz_A	- number of non-zeros in the sparse CSR matrix \(A\).
[in]	csr_descr_A	- descriptor of the sparse CSR matrix \(A\). Currently, only `rocsparse_matrix_type_general` is supported.
[in]	csr_val_A	- array of `nnz_A` elements containing the values of the sparse CSR matrix \(A\).
[in]	csr_row_ptr_A	- array of `m+1` elements that point to the start of every row of the sparse CSR matrix \(A\).
[in]	csr_col_ind_A	- array of `nnz_A` elements containing the column indices of the sparse CSR matrix \(A\).
[in]	threshold	- pointer to the non-negative pruning threshold, which can exist in either host or device memory.
[in]	csr_descr_C	- descriptor of the sparse CSR matrix \(C\). Currently, only `rocsparse_matrix_type_general` is supported.
[out]	csr_val_C	- array of `nnz_C` elements containing the values of the sparse CSR matrix \(C\).
[in]	csr_row_ptr_C	- array of `m+1` elements that point to the start of every row of the sparse CSR matrix \(C\).
[out]	csr_col_ind_C	- array of `nnz_C` elements containing the column indices of the sparse CSR matrix \(C\).
[in]	temp_buffer	- buffer allocated by the user. Its size is determined by calling rocsparse_Xprune_csr2csr_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 `nnz_A` is invalid.
rocsparse_status_invalid_pointer	`threshold`, `csr_descr_A`, `csr_descr_C`, `csr_val_A`, `csr_row_ptr_A`, `csr_col_ind_A`, `csr_val_C`, `csr_row_ptr_C`, `csr_col_ind_C`, or `temp_buffer` pointer is invalid.

Example

Member Function/Subroutine Documentation