onemkl::sparse::gemvdot¶

Computes a sparse matrix-vector product with dot product.

Syntax

Note

Currently, complex types are not supported.

Using SYCL buffers:

void onemkl::sparse::gemvdot(cl::sycl::queue &queue, onemkl::transpose transpose_val, fp alpha, matrixHandle_t handle, cl::sycl::buffer<fp, 1> &x, fp beta, cl::sycl::buffer<fp, 1> &y, cl::sycl::buffer<fp, 1> &d)¶

Using USM pointers:

void onemkl::sparse::gemvdot(cl::sycl::queue &queue, onemkl::transpose transpose_val, fp alpha, matrixHandle_t handle, fp *x, fp beta, fp *y, fp *d)¶

Include Files

mkl_spblas_sycl.hpp

Description

Note

Refer to Supported Types for a list of supported <fp> and <intType> and refer to Exceptions for a detailed description of the exceptions thrown. The onemkl::sparse::gemvdot routine computes a sparse matrix-vector product and dot product defined as

y := alpha*op(A)*x + beta*y

d := x * y

where:

A is a general sparse matrix, alpha, beta, and d are scalars, x and y are vectors.

Input Parameters

queue

Specifies the SYCL command queue which will be used for SYCL kernels execution.

transpose_val

Specifies operation op() on input matrix.

onemkl::transpose::nontrans	Non-transpose, `op(A)` = `A`.
onemkl::transpose::trans	Transpose, `op(A)` = `A`^T.
onemkl::transpose::conjtrans	Conjugate transpose, `op(A)` = `A`^H.

Note

Currently, the only supported case for operation is onemkl::transpose::nontrans.

alpha

Specifies the scalar alpha.

handle

Handle to object containing sparse matrix and other internal data. Created using one of the onemkl::sparse::set<sparse_matrix_type>structure routines.

Note

Currently, the only supported case for <sparse_matrix_type> is CSR.

x

SYCL or USM memory object containing an array of size at least equal to the number of columns of input matrix if op = onemkl::transpose::nontrans and at least the number of rows of input matrix otherwise.

beta

Specifies the scalar beta.

y

SYCL or USM memory object containing an array of size at least equal to the number of columns of input matrix if op = onemkl::transpose::nontrans and at least the number of rows of input matrix otherwise.

Output Parameters

y: Overwritten by the updated vector y.
d: Overwritten by the dot product of x and y.

Parent topic: Sparse BLAS Routines