rocsparse_cscsort Interface Reference

• hipfort_rocsparse
• rocsparse_cscsort

Public Member Functions | List of all members

hipfort_rocsparse::rocsparse_cscsort Interface Reference

Sort a sparse CSC matrix. More...

Public Member Functions
integer(kind(rocsparse_status_success)) function	rocsparse_cscsort_ (handle, m, n, nnz, descr, csc_col_ptr, csc_row_ind, perm, temp_buffer)
integer(kind(rocsparse_status_success)) function	rocsparse_cscsort_rank_0 (handle, m, n, nnz, descr, csc_col_ptr, csc_row_ind, perm, temp_buffer)
integer(kind(rocsparse_status_success)) function	rocsparse_cscsort_rank_1 (handle, m, n, nnz, descr, csc_col_ptr, csc_row_ind, perm, temp_buffer)

Detailed Description

Sort a sparse CSC matrix.

rocsparse_cscsort sorts a matrix in CSC format. The sorted permutation vector perm can be used to obtain the sorted csc_val array. In this case, perm must be initialized as the identity permutation. For more information, see rocsparse_create_identity_permutation ().

rocsparse_cscsort requires an extra temporary storage buffer that has to be allocated by the user. The storage buffer size can be determined by rocsparse_cscsort_buffer_size().

Note

perm can be NULL if a sorted permutation vector is not required.

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

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 sparse CSC matrix.
[in]	n	- number of columns of the sparse CSC matrix.
[in]	nnz	- number of non-zero entries of the sparse CSC matrix.
[in]	descr	- descriptor of the sparse CSC matrix. Currently, only rocsparse_matrix_type_general is supported.
[in]	csc_col_ptr	- array of n+1 elements that point to the start of every column of the sparse CSC matrix.
[in,out]	csc_row_ind	- array of nnz elements containing the row indices of the sparse CSC matrix.
[in,out]	perm	- array of nnz integers containing the unsorted map indices, which can be NULL.
[in]	temp_buffer	- temporary storage buffer allocated by the user. The size is returned by rocsparse_cscsort_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 is invalid.
rocsparse_status_invalid_pointer	descr, csc_col_ptr, csc_row_ind, or temp_buffer pointer is invalid.
rocsparse_status_internal_error	an internal error occurred.
rocsparse_status_not_implemented	rocsparse_matrix_type != rocsparse_matrix_type_general.

Example

The following example sorts a \(3 \times 3\) CSC matrix.

Member Function/Subroutine Documentation

◆ rocsparse_cscsort_()

integer(kind(rocsparse_status_success)) function hipfort_rocsparse::rocsparse_cscsort::rocsparse_cscsort_	(	type(c_ptr), value	handle,
		integer(c_int), value	m,
		integer(c_int), value	n,
		integer(c_int), value	nnz,
		type(c_ptr), value	descr,
		type(c_ptr), value	csc_col_ptr,
		type(c_ptr), value	csc_row_ind,
		type(c_ptr), value	perm,
		type(c_ptr), value	temp_buffer
	)

◆ rocsparse_cscsort_rank_0()

integer(kind(rocsparse_status_success)) function hipfort_rocsparse::rocsparse_cscsort::rocsparse_cscsort_rank_0	(	type(c_ptr)	handle,
		integer(c_int)	m,
		integer(c_int)	n,
		integer(c_int)	nnz,
		type(c_ptr)	descr,
		integer(c_int), target	csc_col_ptr,
		integer(c_int), target	csc_row_ind,
		integer(c_int), target	perm,
		type(c_ptr)	temp_buffer
	)

◆ rocsparse_cscsort_rank_1()

integer(kind(rocsparse_status_success)) function hipfort_rocsparse::rocsparse_cscsort::rocsparse_cscsort_rank_1	(	type(c_ptr)	handle,
		integer(c_int)	m,
		integer(c_int)	n,
		integer(c_int)	nnz,
		type(c_ptr)	descr,
		integer(c_int), dimension(:), target	csc_col_ptr,
		integer(c_int), dimension(:), target	csc_row_ind,
		integer(c_int), dimension(:), target	perm,
		type(c_ptr)	temp_buffer
	)

---

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

• hipfort_rocsparse.F90