Visible to Intel only — GUID: GUID-C49A9D8F-7FB5-4E58-83B6-0D04CD4BE66A
Visible to Intel only — GUID: GUID-C49A9D8F-7FB5-4E58-83B6-0D04CD4BE66A
oneapi::mkl::sparse::trmv
Computes a sparse matrix-dense vector product over upper or lower triangular parts of the matrix.
Description
The oneapi::mkl::sparse::trmv routine computes a sparse matrix-dense vector product over a triangular part defined as
where and are scalars, is a sparse triangular matrix of size m rows by m columns and and are dense vectors of size m. The operation is a matrix modifier:
For a given matrix decomposition into lower, diagonal and upper parts , the triangular matrix vector product with one of oneapi::mkl::uplo::lower or oneapi::mkl::uplo::upper selected will perform the appropriate matrix product using respectively or for oneapi::mkl::diag::nonunit or if using oneapi::mkl::diag::unit, will perform the appropriate matrix product for or where is the identity matrix.
API
Syntax
Using SYCL buffers:
namespace oneapi::mkl::sparse {
void trmv (
sycl::queue &queue,
oneapi::mkl::uplo uplo_val,
oneapi::mkl::transpose opA,
oneapi::mkl::diag diag_val,
const DATA_TYPE alpha,
oneapi::mkl::sparse::matrix_handle_t A,
sycl::buffer<DATA_TYPE, 1> &x,
const DATA_TYPE beta,
sycl::buffer<DATA_TYPE, 1> &y)
}
Using USM pointers:
namespace oneapi::mkl::sparse {
sycl::event trmv(
sycl::queue &queue,
oneapi::mkl::uplo uplo_val,
oneapi::mkl::transpose opA,
oneapi::mkl::diag
diag_val,
const DATA_TYPE alpha,
oneapi::mkl::sparse::matrix_handle_t A,
const DATA_TYPE *x,
const DATA_TYPE beta,
DATA_TYPE *y,
const std::vector<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_val
-
Specifies which part of the matrix is to be processed.
oneapi::mkl::uplo::lower
The lower triangular matrix part is processed.
oneapi::mkl::uplo::upper
The upper triangular matrix part is processed.
- opA
-
Specifies operation op() on input matrix.
oneapi::mkl::transpose::nontrans
Non-transpose, .
oneapi::mkl::transpose::trans
Transpose, .
oneapi::mkl::transpose::conjtrans
Conjugate transpose, .
NOTE:Currently, the only supported case for operation is oneapi::mkl::transpose::nontrans. - diag_val
-
Specifies if the diagonal used for computations is unit or not.
oneapi::mkl::diag::nonunit
Diagonal elements might not be equal to one.
oneapi::mkl::diag::unit
Diagonal elements are equal to one.
- alpha
-
Specifies the scalar, .
- A
-
Handle to object containing sparse matrix and other internal data. Created using one of the oneapi::mkl::sparse::set_<sparse_matrix_type>_data routines.
NOTE:The supported cases for <sparse_matrix_type> are csr on CPU and GPU devices, and coo only on CPU device. - x
-
SYCL buffer or device-accessible USM pointer of size at least equal to the number of columns of input matrix if opA = oneapi::mkl::transpose::nontrans and at least the number of rows of input matrix otherwise.
- beta
-
Specifies the scalar, .
- y
-
SYCL buffer or device-accessible USM pointer of size at least equal to the number of rows of the input matrix if opA = oneapi::mkl::transpose::nontrans and at least the number of columns of the input matrix otherwise.
- dependencies
-
A vector of type std::vector<sycl::event> containing the list of events that the oneapi::mkl::sparse::trmv routine depends on.
Output Parameters
- y
-
Overwritten by the updated vector, .
Return Values (USM Only)
- sycl::event
-
SYCL event which can be waited upon or added as a dependency for the completion of the trmv routine.
Examples
An example of how to use oneapi::mkl::sparse::trmv with SYCL buffers can be found in the oneMKL installation directory, under:
share/doc/mkl/examples/sycl/sparse_blas/source/csr_trmv.cpp