rocsparse_scsrgemm Interface Reference

rocsparse_scsrgemm Interface Reference#

HIPFORT API Reference: hipfort_rocsparse::rocsparse_scsrgemm Interface Reference

Sparse matrix sparse matrix multiplication using the CSR storage format. More...

Public Member Functions
integer(kind(rocsparse_status_success)) function	rocsparse_scsrgemm_ (handle, trans_a, trans_b, m, n, k, alpha, descr_a, nnz_a, csr_val_a, csr_row_ptr_a, csr_col_ind_a, descr_b, nnz_b, csr_val_b, csr_row_ptr_b, csr_col_ind_b, beta, descr_d, nnz_d, csr_val_d, csr_row_ptr_d, csr_col_ind_d, descr_c, csr_val_c, csr_row_ptr_c, csr_col_ind_c, info_c, temp_buffer)

integer(kind(rocsparse_status_success)) function	rocsparse_scsrgemm_rank_0 (handle, trans_a, trans_b, m, n, k, alpha, descr_a, nnz_a, csr_val_a, csr_row_ptr_a, csr_col_ind_a, descr_b, nnz_b, csr_val_b, csr_row_ptr_b, csr_col_ind_b, beta, descr_d, nnz_d, csr_val_d, csr_row_ptr_d, csr_col_ind_d, descr_c, csr_val_c, csr_row_ptr_c, csr_col_ind_c, info_c, temp_buffer)

integer(kind(rocsparse_status_success)) function	rocsparse_scsrgemm_rank_1 (handle, trans_a, trans_b, m, n, k, alpha, descr_a, nnz_a, csr_val_a, csr_row_ptr_a, csr_col_ind_a, descr_b, nnz_b, csr_val_b, csr_row_ptr_b, csr_col_ind_b, beta, descr_d, nnz_d, csr_val_d, csr_row_ptr_d, csr_col_ind_d, descr_c, csr_val_c, csr_row_ptr_c, csr_col_ind_c, info_c, temp_buffer)

Detailed Description

Sparse matrix sparse matrix multiplication using the CSR storage format.

rocsparse_csrgemm multiplies the scalar \(\alpha\) with the sparse \(m \times k\) matrix \(A\), defined in CSR storage format, and the sparse \(k \times n\) matrix \(B\), defined in CSR storage format, and adds the result to the sparse \(m \times n\) matrix \(D\) that is multiplied by \(\beta\). The final result is stored in the sparse \(m \times n\) matrix \(C\), defined in CSR storage format, such that

\[ C := \alpha \cdot op(A) \cdot op(B) + \beta \cdot D, \]

with

\[ op(A) = \left\{ \begin{array}{ll} A, & \text{if trans_A == rocsparse_operation_none} \\% A^T, & \text{if trans_A == rocsparse_operation_transpose} \\% A^H, & \text{if trans_A == rocsparse_operation_conjugate_transpose} \end{array} \right. \]

and

\[ op(B) = \left\{ \begin{array}{ll} B, & \text{if trans_B == rocsparse_operation_none} \\% B^T, & \text{if trans_B == rocsparse_operation_transpose} \\% B^H, & \text{if trans_B == rocsparse_operation_conjugate_transpose} \end{array} \right. \]

Note: This function does not produce deterministic results.

It is assumed that csr_row_ptr_C has already been filled and that csr_val_C and csr_col_ind_C are allocated by the user. csr_row_ptr_C and the allocation size of csr_col_ind_C and csr_val_C are defined by the number of non-zero elements of the sparse CSR matrix C. Both can be obtained by using rocsparse_csrgemm_nnz(). The required buffer size for the computation can be obtained by rocsparse_scsrgemm_buffer_size(), rocsparse_dcsrgemm_buffer_size(), rocsparse_ccsrgemm_buffer_size(), and rocsparse_zcsrgemm_buffer_size(), respectively.

Note: If \(\alpha == 0\), then \(C = \beta \cdot D\) will be computed.; If \(\beta == 0\), then \(C = \alpha \cdot op(A) \cdot op(B)\) will be computed.; \(\alpha == beta == 0\) is invalid.; Currently, only trans_A == rocsparse_operation_none is supported.; Currently, only trans_B == rocsparse_operation_none is supported.; Currently, only rocsparse_matrix_type_general is supported.; Note that for matrix products with more than 4096 non-zero entries per row, an additional temporary storage buffer is allocated by the algorithm.; This function supports unsorted CSR matrices as input, while output will be sorted. Note that matrices B and D can only be unsorted up to 4096 non-zero entries per row. If this number is exceeded, rocsparse_status_requires_sorted_storage will be returned.; 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]	trans_A	- matrix \(A\) operation type.
[in]	trans_B	- matrix \(B\) operation type.
[in]	m	- number of rows of the sparse CSR matrix \(op(A)\) and \(C\).
[in]	n	- number of columns of the sparse CSR matrix \(op(B)\) and \(C\).
[in]	k	- number of columns of the sparse CSR matrix \(op(A)\) and number of rows of the sparse CSR matrix \(op(B)\).
[in]	alpha	- scalar \(\alpha\).
[in]	descr_A	- descriptor of the sparse CSR matrix \(A\). Currently, only `rocsparse_matrix_type_general` is supported.
[in]	nnz_A	- number of non-zero entries of the sparse CSR matrix \(A\).
[in]	csr_val_A	- array of `nnz_A` elements of the sparse CSR matrix \(A\).
[in]	csr_row_ptr_A	- array of `m+1` elements ( \(op(A) == A\), `k+1` otherwise) that point to the start of every row of the sparse CSR matrix \(op(A)\).
[in]	csr_col_ind_A	- array of `nnz_A` elements containing the column indices of the sparse CSR matrix \(A\).
[in]	descr_B	- descriptor of the sparse CSR matrix \(B\). Currently, only `rocsparse_matrix_type_general` is supported.
[in]	nnz_B	- number of non-zero entries of the sparse CSR matrix \(B\).
[in]	csr_val_B	- array of `nnz_B` elements of the sparse CSR matrix \(B\).
[in]	csr_row_ptr_B	- array of `k+1` elements ( \(op(B) == B\), `m+1` otherwise) that point to the start of every row of the sparse CSR matrix \(op(B)\).
[in]	csr_col_ind_B	- array of `nnz_B` elements containing the column indices of the sparse CSR matrix \(B\).
[in]	beta	- scalar \(\beta\).
[in]	descr_D	- descriptor of the sparse CSR matrix \(D\). Currently, only `rocsparse_matrix_type_general` is supported.
[in]	nnz_D	- number of non-zero entries of the sparse CSR matrix \(D\).
[in]	csr_val_D	- array of `nnz_D` elements of the sparse CSR matrix \(D\).
[in]	csr_row_ptr_D	- array of `m+1` elements that point to the start of every row of the sparse CSR matrix \(D\).
[in]	csr_col_ind_D	- array of `nnz_D` elements containing the column indices of the sparse CSR matrix \(D\).
[in]	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 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]	info_C	- structure that holds meta data for the sparse CSR matrix \(C\).
[in]	temp_buffer	- temporary storage buffer allocated by the user, size is returned by rocsparse_scsrgemm_buffer_size(), rocsparse_dcsrgemm_buffer_size(), rocsparse_ccsrgemm_buffer_size(), or rocsparse_zcsrgemm_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`, `k`, `nnz_A`, `nnz_B`, or `nnz_D` is invalid.
rocsparse_status_invalid_pointer	`alpha` and `beta` are invalid, `descr_A`, `csr_val_A`, `csr_row_ptr_A`, `csr_col_ind_A`, `descr_B`, `csr_val_B`, `csr_row_ptr_B`, or `csr_col_ind_B` are invalid if `alpha` is valid, `descr_D`, `csr_val_D`, `csr_row_ptr_D`, or `csr_col_ind_D` are invalid if `beta` is valid, or `csr_val_C`, `csr_row_ptr_C`, `csr_col_ind_C`, `info_C`, or `temp_buffer` are invalid.
rocsparse_status_memory_error	additional buffer for long rows could not be allocated.
rocsparse_status_not_implemented	`trans_A` != `rocsparse_operation_none`, `trans_B` != `rocsparse_operation_none`, or `rocsparse_matrix_type` != `rocsparse_matrix_type_general`.

Example: This example multiplies two CSR matrices with a scalar alpha and adds the result to another CSR matrix.
// Initialize scalar multipliers

float alpha = 2.0f;

float beta = 1.0f;

// Create matrix descriptors

rocsparse_mat_descr descr_A;

rocsparse_mat_descr descr_B;

rocsparse_mat_descr descr_C;

rocsparse_mat_descr descr_D;

rocsparse_create_mat_descr(&descr_A);

rocsparse_create_mat_descr(&descr_B);

rocsparse_create_mat_descr(&descr_C);

rocsparse_create_mat_descr(&descr_D);

// Create matrix info structure

rocsparse_mat_info info_C;

rocsparse_create_mat_info(&info_C);

// Set pointer mode

rocsparse_set_pointer_mode(handle, rocsparse_pointer_mode_host);

// Query rocsparse for the required buffer size

size_t buffer_size;

rocsparse_scsrgemm_buffer_size(handle,

rocsparse_operation_none,

rocsparse_operation_none,

m,

n,

k,

&alpha,

descr_A,

nnz_A,

csr_row_ptr_A,

csr_col_ind_A,

descr_B,

nnz_B,

csr_row_ptr_B,

csr_col_ind_B,

&beta,

descr_D,

nnz_D,

csr_row_ptr_D,

csr_col_ind_D,

info_C,

&buffer_size);

// Allocate buffer

void* buffer;

hipMalloc(&buffer, buffer_size);

// Obtain number of total non-zero entries in C and row pointers of C

rocsparse_int nnz_C;

hipMalloc((void**)&csr_row_ptr_C, sizeof(rocsparse_int) * (m + 1));

rocsparse_csrgemm_nnz(handle,

rocsparse_operation_none,

rocsparse_operation_none,

m,

n,

k,

descr_A,

nnz_A,

csr_row_ptr_A,

csr_col_ind_A,

descr_B,

nnz_B,

csr_row_ptr_B,

csr_col_ind_B,

descr_D,

nnz_D,

csr_row_ptr_D,

csr_col_ind_D,

descr_C,

csr_row_ptr_C,

&nnz_C,

info_C,

buffer);

// Compute column indices and values of C

hipMalloc((void**)&csr_col_ind_C, sizeof(rocsparse_int) * nnz_C);

hipMalloc((void**)&csr_val_C, sizeof(float) * nnz_C);

rocsparse_scsrgemm(handle,

rocsparse_operation_none,

rocsparse_operation_none,

m,

n,

k,

&alpha,

descr_A,

nnz_A,

csr_val_A,

csr_row_ptr_A,

csr_col_ind_A,

descr_B,

nnz_B,

csr_val_B,

csr_row_ptr_B,

csr_col_ind_B,

&beta,

descr_D,

nnz_D,

csr_val_D,

csr_row_ptr_D,

csr_col_ind_D,

descr_C,

csr_val_C,

csr_row_ptr_C,

csr_col_ind_C,

info_C,

buffer);

hipfort_rocsparse::rocsparse_create_mat_descr
Create a matrix descriptor.
Definition hipfort_rocsparse.F90:436

hipfort_rocsparse::rocsparse_create_mat_info
Create a matrix info structure.
Definition hipfort_rocsparse.F90:795

hipfort_rocsparse::rocsparse_csrgemm_nnz
Sparse matrix sparse matrix multiplication using the CSR storage format.
Definition hipfort_rocsparse.F90:13233

hipfort_rocsparse::rocsparse_scsrgemm_buffer_size
Definition hipfort_rocsparse.F90:12963

hipfort_rocsparse::rocsparse_scsrgemm
Sparse matrix sparse matrix multiplication using the CSR storage format.
Definition hipfort_rocsparse.F90:13529

hipfort_rocsparse::rocsparse_set_pointer_mode
Specify the pointer mode.
Definition hipfort_rocsparse.F90:320

hipfort_rocsparse_enums::rocsparse_operation_none
@ rocsparse_operation_none
Definition hipfort_rocsparse_enums.F90:35

hipfort_rocsparse_enums::rocsparse_pointer_mode_host
@ rocsparse_pointer_mode_host
Definition hipfort_rocsparse_enums.F90:104

Member Function/Subroutine Documentation