hipsparsesnnz_compress Interface Reference

• hipfort_hipsparse
• hipsparsesnnz_compress

Public Member Functions | List of all members

hipfort_hipsparse::hipsparsesnnz_compress Interface Reference

This function is used as the first step in converting a CSR matrix to a compressed CSR matrix. More...

Public Member Functions
integer(kind(hipsparse_status_success)) function	hipsparsesnnz_compress_ (handle, m, descra, csrvala, csrrowptra, nnzperrow, nnzc, tol)
integer(kind(hipsparse_status_success)) function	hipsparsesnnz_compress_rank_0 (handle, m, descra, csrvala, csrrowptra, nnzperrow, nnzc, tol)
integer(kind(hipsparse_status_success)) function	hipsparsesnnz_compress_rank_1 (handle, m, descra, csrvala, csrrowptra, nnzperrow, nnzc, tol)

Detailed Description

This function is used as the first step in converting a CSR matrix to a compressed CSR matrix.

Given a sparse CSR matrix and a non-negative tolerance, this function computes how many entries would be left in each row of the matrix if elements less than the tolerance were removed. It also computes the total number of remaining elements in the matrix.

Given an input sparse matrix \(A\) in CSR format, the resulting compressed sparse CSR matrix \(C\) is computed using:

\[ C(i,j) = A(i, j) \text{ if |A(i, j)| > tol} \]

The user first allocates nnzPerRow with size m elements, then calls hipsparseXnnz_compress. The function fills in the nnzPerRow array and sets the total number of non-zeros found in nnzC.

See hipsparseScsr2csr_compress() for a full code example.

Note

In the case of complex matrices, only the magnitude of the real part of tol is used.

Parameters

[in]	handle	- handle to the hipSPARSE library context queue.
[in]	m	- number of rows of the sparse CSR matrix.
[in]	descrA	- the descriptor of the sparse CSR matrix.
[in]	csrValA	- array of nnzA elements of the sparse CSR matrix.
[in]	csrRowPtrA	- array of m+1 elements that point to the start of every row of the uncompressed sparse CSR matrix.
[out]	nnzPerRow	- array of length m containing the number of entries that will be kept per row in the final compressed CSR matrix.
[out]	nnzC	- number of elements in the column indices and values arrays of the compressed sparse CSR matrix. Can be either host or device pointer.
[in]	tol	- the non-negative tolerance used for compression. If tol is complex, then only the magnitude of the real part is used. Entries in the input uncompressed CSR array that are below the tolerance are removed in output compressed CSR matrix.

Return values

HIPSPARSE_STATUS_SUCCESS	the operation completed successfully.
HIPSPARSE_STATUS_INVALID_VALUE	handle, m, n, tol, csrValA, csrRowPtrA, nnzPerRow, or nnzC pointer is invalid.

Member Function/Subroutine Documentation

◆ hipsparsesnnz_compress_()

integer(kind(hipsparse_status_success)) function hipfort_hipsparse::hipsparsesnnz_compress::hipsparsesnnz_compress_	(	type(c_ptr), value	handle,
		integer(c_int), value	m,
		type(c_ptr), value	descra,
		type(c_ptr), value	csrvala,
		type(c_ptr), value	csrrowptra,
		type(c_ptr), value	nnzperrow,
		type(c_ptr), value	nnzc,
		real(c_float), value	tol
	)

◆ hipsparsesnnz_compress_rank_0()

integer(kind(hipsparse_status_success)) function hipfort_hipsparse::hipsparsesnnz_compress::hipsparsesnnz_compress_rank_0	(	type(c_ptr)	handle,
		integer(c_int)	m,
		type(c_ptr)	descra,
		real(c_float), target	csrvala,
		integer(c_int), target	csrrowptra,
		integer(c_int), target	nnzperrow,
		integer(c_int), target	nnzc,
		real(c_float)	tol
	)

◆ hipsparsesnnz_compress_rank_1()

integer(kind(hipsparse_status_success)) function hipfort_hipsparse::hipsparsesnnz_compress::hipsparsesnnz_compress_rank_1	(	type(c_ptr)	handle,
		integer(c_int)	m,
		type(c_ptr)	descra,
		real(c_float), dimension(:), target	csrvala,
		integer(c_int), dimension(:), target	csrrowptra,
		integer(c_int), dimension(:), target	nnzperrow,
		integer(c_int), dimension(:), target	nnzc,
		real(c_float)	tol
	)

---

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

• hipfort_hipsparse.F90