This page contains proposed changes for a future release of ROCm. Read the latest Linux release of ROCm documentation for your production environments.

rocsparse_spsm Interface Reference

rocsparse_spsm Interface Reference#

HIPFORT API Reference: hipfort_rocsparse::rocsparse_spsm Interface Reference
hipfort_rocsparse::rocsparse_spsm Interface Reference

Sparse triangular system solve. More...

Public Member Functions

integer(kind(rocsparse_status_success)) function rocsparse_spsm_ (handle, trans_A, trans_B, alpha, matA, matB, matC, compute_type, alg, stage, buffer_size, temp_buffer)
 

Detailed Description

Sparse triangular system solve.

rocsparse_spsm_solve solves a sparse triangular linear system of a sparse \(m \times m\) matrix, defined in CSR or COO storage format, a dense solution matrix \(C\) and the right-hand side \(B\) that is multiplied by \(\alpha\), such that

\[ op(A) \cdot C = \alpha \cdot op(B), \]

with

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

and

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

Note
SpSM requires three stages to complete. The first stage rocsparse_spsm_stage_buffer_size will return the size of the temporary storage buffer that is required for subsequent calls. The second stage rocsparse_spsm_stage_preprocess will preprocess data that would be saved in the temporary storage buffer. In the final stage rocsparse_spsm_stage_compute, the actual computation is performed.
If rocsparse_spsm_stage_auto is selected, rocSPARSE will automatically detect which stage is required based on the following indicators: If temp_buffer is equal to nullptr, the required buffer size will be returned. If buffer_size is equal to nullptr, analysis will be performed. Otherwise, the SpSM preprocess and the SpSM algorithm will be executed.
This function is non blocking and executed asynchronously with respect to the host. It may return before the actual computation has finished.
Currently, only trans_A == rocsparse_operation_none and trans_A == rocsparse_operation_transpose is supported. Currently, only trans_B == rocsparse_operation_none and trans_B == rocsparse_operation_transpose is supported.
Parameters
[in]handlehandle to the rocsparse library context queue.
[in]trans_Amatrix operation type for the sparse matrix A.
[in]trans_Bmatrix operation type for the dense matrix B.
[in]alphascalar \(\alpha\).
[in]matAsparse matrix descriptor.
[in]matBdense matrix descriptor.
[in,out]matCdense matrix descriptor.
[in]compute_typefloating point precision for the SpSM computation.
[in]algSpSM algorithm for the SpSM computation.
[in]stageSpSM stage for the SpSM computation.
[out]buffer_sizenumber of bytes of the temporary storage buffer.
[in]temp_buffertemporary storage buffer allocated by the user. When a nullptr is passed, the required allocation size (in bytes) is written to buffer_size and function returns without performing the SpSM operation.
Return values
rocsparse_status_successthe operation completed successfully.
rocsparse_status_invalid_handlethe library context was not initialized.
rocsparse_status_invalid_pointeralpha, matA, matB, matC, descr or buffer_size pointer is invalid.
rocsparse_status_not_implementedtrans_A, trans_B, compute_type, stage or alg is currently not supported.

Member Function/Subroutine Documentation

◆ rocsparse_spsm_()

integer(kind(rocsparse_status_success)) function hipfort_rocsparse::rocsparse_spsm::rocsparse_spsm_ ( type(c_ptr), value  handle,
integer(kind(rocsparse_operation_none)), value  trans_A,
integer(kind(rocsparse_operation_none)), value  trans_B,
type(c_ptr), value  alpha,
type(c_ptr), value  matA,
type(c_ptr), value  matB,
type(c_ptr), value  matC,
integer(kind(rocsparse_datatype_f32_r)), value  compute_type,
integer(kind(rocsparse_spsm_alg_default)), value  alg,
integer(kind(rocsparse_spsm_stage_auto)), value  stage,
integer(c_size_t)  buffer_size,
type(c_ptr), value  temp_buffer 
)

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