tpmv¶

Computes a matrix-vector product using a triangular packed matrix.

tpmv supports the following precisions.

T

float

double

std::complex<float>

std::complex<double>

Description

The tpmv routines compute a matrix-vector product with a triangular packed matrix. The operation is defined as

x <- op(A)*x

where:

op(A) is one of op(A) = A, or op(A) = A^T, or op(A) = A^H,

A is an n-by-n unit or non-unit, upper or lower triangular band matrix, supplied in packed form,

x is a vector of length n.

tpmv (Buffer Version)¶

Syntax

void onemkl::blas::tpmv(sycl::queue &queue, onemkl::uplo upper_lower, onemkl::transpose trans, onemkl::diag unit_nonunit, std::int64_t n, sycl::buffer<T, 1> &a, sycl::buffer<T, 1> &x, std::int64_t incx)¶

Input Parameters

queue: The queue where the routine should be executed.
upper_lower: Specifies whether A is upper or lower triangular. See oneMKL defined datatypes for more details.
trans: Specifies op(A), the transposition operation applied to A. See oneMKL defined datatypes for more details.
unit_nonunit: Specifies whether the matrix A is unit triangular or not. See oneMKL defined datatypes for more details.
n: Numbers of rows and columns of A. Must be at least zero.
a: Buffer holding input matrix A. Must have size at least (n*(n+1))/2. See Matrix and Vector Storage for more details.
x: Buffer holding input vector x. The buffer must be of size at least (1 + (n - 1)*abs(incx)). See Matrix and Vector Storage for more details.
incx: Stride of vector x.

Output Parameters

Syntax

sycl::event onemkl::blas::tpmv(sycl::queue &queue, onemkl::uplo upper_lower, onemkl::transpose trans, onemkl::diag unit_nonunit, std::int64_t n, const T *a, T *x, std::int64_t incx, const sycl::vector_class<sycl::event> &dependencies = {})¶

Input Parameters

queue: The queue where the routine should be executed.
upper_lower: Specifies whether A is upper or lower triangular. See oneMKL defined datatypes for more details.
trans: Specifies op(A), the transposition operation applied to A. See oneMKL defined datatypes for more details.
unit_nonunit: Specifies whether the matrix A is unit triangular or not. See oneMKL defined datatypes for more details.
n: Numbers of rows and columns of A. Must be at least zero.
a: Pointer to input matrix A. The array holding input matrix A must have size at least (n*(n+1))/2. See Matrix and Vector Storage for more details.
x: Pointer to input vector x. The array holding input vector x must be of size at least (1 + (n - 1)*abs(incx)). See Matrix and Vector Storage for more details.
incx: Stride of vector x.
dependencies: List of events to wait for before starting computation, if any. If omitted, defaults to no dependencies.

Output Parameters

Return Values

Output event to wait on to ensure computation is complete.

Parent topic: BLAS Level 2 Routines