oneapi::mkl::sparse::symv
Computes a sparse matrix-dense vector product for a symmetric matrix built from the lower or upper triangular of the input matrix.
Description
The oneapi::mkl::sparse::symv routine computes a sparse symmetric matrix-dense vector product for a real symmetric matrix built from the lower or upper triangular portion of the input matrix \(A\) defined as
\[y \leftarrow \alpha\cdot \text{sym}(A)\cdot x + \beta \cdot y\]
where \(\alpha\) and \(\beta\) are scalars, \(A\) is a real-valued square sparse matrix of dimension \(m\) rows and columns, \(\text{sym}()\) is a matrix modifier which symmetrizes the matrix according to the oneapi::mkl::uplo value and \(x\) and \(y\) are dense vectors.
For a given matrix decomposition into lower, diagonal and upper parts \(A = L+D+U\), the symv routine with oneapi::mkl::uplo::lower selected will perform the matrix product with \(\text{sym}(A) = L+D+L^T\) and for oneapi::mkl::uplo::upper will perform the matrix product using \(\text{sym}(A) = U^T+D+U\).
API
Syntax
Using SYCL buffers:
namespace oneapi::mkl::sparse {
void symv (
sycl::queue &queue,
oneapi::mkl::uplo uplo_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 symv (
sycl::queue &queue,
oneapi::mkl::uplo uplo_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 is to be processed.
oneapi::mkl::uplo::lower
The lower part is used for symmetric product.
oneapi::mkl::uplo::upper
The upper part is used for symmetric product.
- alpha
-
Specifies the scalar, \(\alpha\).
- 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.
Formats Supported in sparse::symv() for A
Compressed Sparse Row (CSR) format on CPU/GPU
- x
-
SYCL buffer or device-accessible USM pointer of size at least equal to the number of columns, \(m\), of input matrix.
- beta
-
Specifies the scalar, \(\beta\).
- y
-
SYCL buffer or device-accessible USM pointer of size at least equal to the number of rows, \(m\), of the input matrix.
- dependencies
-
A vector of type std::vector<sycl::event> containing the list of events that the oneapi::mkl::sparse::symv routine depends on.
Output Parameters
- y
-
Overwritten by the updated vector \(y\).
Return Values (USM Only)
- sycl::event
-
SYCL event which can be waited upon or added as a dependency for the completion of the symv routine.
Examples
An example of how to use oneapi::mkl::sparse::symv with SYCL buffers can be found in the oneMKL installation directory, under:
share/doc/mkl/examples/sycl/sparse_blas/source/csr_symv.cpp