rocsparse_sprune_csr2csr Interface Reference

rocsparse_sprune_csr2csr Interface Reference#

hipFORT API Reference: hipfort_rocsparse::rocsparse_sprune_csr2csr Interface Reference
Public Member Functions | List of all members
hipfort_rocsparse::rocsparse_sprune_csr2csr Interface Reference
Sparse Conversion Functions

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

Public Member Functions

integer(c_int) 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_typed (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_0_devptr (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)
 
integer(kind(rocsparse_status_success)) function rocsparse_sprune_csr2csr_rank_1_devptr (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_successthe operation completed successfully.
rocsparse_status_invalid_handlethe library context was not initialized.
rocsparse_status_invalid_sizem, n, or nnz_A is invalid.
rocsparse_status_invalid_pointerthreshold, 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

◆ rocsparse_sprune_csr2csr_()

integer(c_int) function hipfort_rocsparse::rocsparse_sprune_csr2csr::rocsparse_sprune_csr2csr_ ( type(c_ptr), value  handle,
integer(c_int), value  m,
integer(c_int), value  n,
integer(c_int), value  nnz_a,
type(c_ptr), value  csr_descr_a,
type(c_ptr), value  csr_val_a,
type(c_ptr), value  csr_row_ptr_a,
type(c_ptr), value  csr_col_ind_a,
type(c_ptr), value  threshold,
type(c_ptr), value  csr_descr_c,
type(c_ptr), value  csr_val_c,
type(c_ptr), value  csr_row_ptr_c,
type(c_ptr), value  csr_col_ind_c,
type(c_ptr), value  temp_buffer 
)

◆ rocsparse_sprune_csr2csr_rank_0()

integer(kind(rocsparse_status_success)) function hipfort_rocsparse::rocsparse_sprune_csr2csr::rocsparse_sprune_csr2csr_rank_0 ( type(c_ptr), value  handle,
integer(c_int)  m,
integer(c_int)  n,
integer(c_int)  nnz_a,
type(c_ptr), value  csr_descr_a,
real(c_float), target  csr_val_a,
integer(c_int), target  csr_row_ptr_a,
integer(c_int), target  csr_col_ind_a,
real(c_float), target  threshold,
type(c_ptr), value  csr_descr_c,
real(c_float), target  csr_val_c,
integer(c_int), target  csr_row_ptr_c,
integer(c_int), target  csr_col_ind_c,
type(c_ptr), value  temp_buffer 
)

◆ rocsparse_sprune_csr2csr_rank_0_devptr()

integer(kind(rocsparse_status_success)) function hipfort_rocsparse::rocsparse_sprune_csr2csr::rocsparse_sprune_csr2csr_rank_0_devptr ( type(c_ptr), value  handle,
integer(c_int)  m,
integer(c_int)  n,
integer(c_int)  nnz_a,
type(c_ptr), value  csr_descr_a,
real(c_float), target  csr_val_a,
integer(c_int), target  csr_row_ptr_a,
integer(c_int), target  csr_col_ind_a,
type(c_ptr), value  threshold,
type(c_ptr), value  csr_descr_c,
real(c_float), target  csr_val_c,
integer(c_int), target  csr_row_ptr_c,
integer(c_int), target  csr_col_ind_c,
type(c_ptr), value  temp_buffer 
)

◆ rocsparse_sprune_csr2csr_rank_1()

integer(kind(rocsparse_status_success)) function hipfort_rocsparse::rocsparse_sprune_csr2csr::rocsparse_sprune_csr2csr_rank_1 ( type(c_ptr), value  handle,
integer(c_int)  m,
integer(c_int)  n,
integer(c_int)  nnz_a,
type(c_ptr), value  csr_descr_a,
real(c_float), dimension(:), target  csr_val_a,
integer(c_int), dimension(:), target  csr_row_ptr_a,
integer(c_int), dimension(:), target  csr_col_ind_a,
real(c_float), target  threshold,
type(c_ptr), value  csr_descr_c,
real(c_float), dimension(:), target  csr_val_c,
integer(c_int), dimension(:), target  csr_row_ptr_c,
integer(c_int), dimension(:), target  csr_col_ind_c,
type(c_ptr), value  temp_buffer 
)

◆ rocsparse_sprune_csr2csr_rank_1_devptr()

integer(kind(rocsparse_status_success)) function hipfort_rocsparse::rocsparse_sprune_csr2csr::rocsparse_sprune_csr2csr_rank_1_devptr ( type(c_ptr), value  handle,
integer(c_int)  m,
integer(c_int)  n,
integer(c_int)  nnz_a,
type(c_ptr), value  csr_descr_a,
real(c_float), dimension(:), target  csr_val_a,
integer(c_int), dimension(:), target  csr_row_ptr_a,
integer(c_int), dimension(:), target  csr_col_ind_a,
type(c_ptr), value  threshold,
type(c_ptr), value  csr_descr_c,
real(c_float), dimension(:), target  csr_val_c,
integer(c_int), dimension(:), target  csr_row_ptr_c,
integer(c_int), dimension(:), target  csr_col_ind_c,
type(c_ptr), value  temp_buffer 
)

◆ rocsparse_sprune_csr2csr_typed()

integer(kind(rocsparse_status_success)) function hipfort_rocsparse::rocsparse_sprune_csr2csr::rocsparse_sprune_csr2csr_typed ( type(c_ptr), value  handle,
integer(c_int)  m,
integer(c_int)  n,
integer(c_int)  nnz_a,
type(c_ptr), value  csr_descr_a,
type(c_ptr)  csr_val_a,
type(c_ptr)  csr_row_ptr_a,
type(c_ptr)  csr_col_ind_a,
real(c_float), target  threshold,
type(c_ptr), value  csr_descr_c,
type(c_ptr)  csr_val_c,
type(c_ptr)  csr_row_ptr_c,
type(c_ptr)  csr_col_ind_c,
type(c_ptr), value  temp_buffer 
)
The documentation for this interface was generated from the following file: