oneapi::mkl::sparse::optimize_trsv¶
Performs internal optimizations for oneapi::mkl::sparse::trsv by
analyzing the provided matrix structure and operation parameters.
Description¶
The oneapi::mkl::sparse::optimize_trsv routine analyzes matrix structure and performs optimizations. Optimized data is then stored in the matrix handle.
Note
Refer to Exceptions for a detailed description of the exceptions thrown.
API¶
Syntax¶
Note
Currently, complex types are not supported.
Using SYCL buffers:
namespace oneapi::mkl::sparse {
void optimize_trsv (
cl::sycl::queue &queue,
oneapi::mkl::uplo uplo_flag,
oneapi::mkl::transpose transpose_flag,
oneapi::mkl::diag diag_flag,
oneapi::mkl::sparse::matrix_handle_t handle)
}
Using USM pointers:
Note
Currently, the USM API might be a blocking call.
namespace oneapi::mkl::sparse {
cl::sycl::event optimize_trsv (
cl::sycl::queue &queue,
oneapi::mkl::uplo uplo_flag,
oneapi::mkl::transpose transpose_flag,
oneapi::mkl::diag diag_flag,
oneapi::mkl::sparse::matrix_handle_t handle,
const std::vector<cl::sycl::event> &dependencies )
}
Include Files¶
oneapi/mkl/spblas.hpp
Input Parameters¶
- queue
Specifies the SYCL command queue which will be used for SYCL kernels execution.
- uplo_flag
Specifies which part of the matrix is to be processed.
oneapi::mkl::uplo::lowerThe lower triangular matrix part is processed.
oneapi::mkl::uplo::upperThe upper triangular matrix part is processed.
- transpose_flag
Specifies operation
op()on input matrix.oneapi::mkl::transpose::nontransNon-transpose,
op(A)=A.oneapi::mkl::transpose::transTranspose,
op(A)=AT.oneapi::mkl::transpose::conjtransConjugate transpose,
op(A)=AH.Note
Currently, the only supported case for operation is
oneapi::mkl::transpose::nontrans.- diag_flag
Specifies if the diagonal used for computations is unit or not.
oneapi::mkl::diag::nonunitDiagonal elements might not be equal to one.
oneapi::mkl::diag::unitDiagonal elements are equal to one.
- handle
Handle to object containing sparse matrix and other internal data. Created using one of the
oneapi::mkl::sparse::set_<sparse_matrix_type>_dataroutines.Note
Currently, the only supported case for <sparse_matrix_type> is csr.
- dependencies
A vector of type
std::vector<cl::sycl::event>containing the list of events that theoneapi::mkl::sparse::optimize_trsvroutine depends on.Return Values (USM Only)¶
- cl::sycl::event
SYCL event which can be waited upon or added as a dependency for the completion of the
optimize_trsvroutine.