Visible to Intel only — GUID: GUID-C23F23DC-05C5-4493-BFF6-79708CD7F64B
Visible to Intel only — GUID: GUID-C23F23DC-05C5-4493-BFF6-79708CD7F64B
scal
Computes the product of a vector by a scalar.
Description
The scal routines computes a scalar-vector product. The operation is defined as:
where:
x is a vector of n elements
alpha is a scalar
scal supports the following precisions:
T |
Ts |
---|---|
sycl::half |
sycl::half |
oneapi::mkl::bfloat16 |
oneapi::mkl::bfloat16 |
float |
float |
double |
double |
std::complex<float> |
std::complex<float> |
std::complex<double> |
std::complex<double> |
std::complex<float> |
float |
std::complex<double> |
double |
scal (Buffer Version)
Syntax
namespace oneapi::mkl::blas::column_major {
void scal(sycl::queue &queue,
std::int64_t n,
Ts alpha,
sycl::buffer<T,1> &x,
std::int64_t incx)
}
namespace oneapi::mkl::blas::row_major {
void scal(sycl::queue &queue,
std::int64_t n,
Ts alpha,
sycl::buffer<T,1> &x,
std::int64_t incx)
}
Input Parameters
- queue
-
The queue where the routine should be executed.
- n
-
Number of elements in vector x.
- alpha
-
Specifies the scalar alpha.
- x
-
Buffer holding input vector x. Size of the buffer must be at least (1 + (n - 1)*abs(incx)). See Matrix Storage for more details.
- incx
-
Stride of vector x.
Output Parameters
- x
-
Buffer holding updated buffer x.
scal (USM Version)
Syntax
namespace oneapi::mkl::blas::column_major {
sycl::event scal(sycl::queue &queue,
std::int64_t n,
oneapi::mkl::value_or_pointer<Ts> alpha,
T *x,
std::int64_t incx,
const std::vector<sycl::event> &dependencies = {})
}
namespace oneapi::mkl::blas::row_major {
sycl::event scal(sycl::queue &queue,
std::int64_t n,
oneapi::mkl::value_or_pointer<Ts> alpha,
T *x,
std::int64_t incx,
const std::vector<sycl::event> &dependencies = {})
}
Input Parameters
- queue
-
The queue where the routine should be executed.
- n
-
Number of elements in vector x.
- alpha
-
Specifies the scalar alpha. See Scalar Arguments for more information on the value_or_pointer data type.
- x
-
Pointer to the input vector x. Size of the array must be at least (1 + (n - 1)*abs(incx)). See Matrix Storage for more details.
- incx
-
Stride of vector x.
Output Parameters
- x
-
Pointer to updated array x.
Return Values
Output event to wait on to ensure computation is complete.