sdsdot (USM Version)

Computes a vector-vector dot product with double precision.

Syntax

event sdsdot(queue &exec_queue, std::int64_t n, float sb, const float *x, std::int64_t incx, const float *y, std::int64_t incy, float *result, const vector_class<event> &dependencies = {})

sdsdot supports the Host, CPU, and GPU devices.

Description

The sdsdot routines perform a dot product between two vectors with double precision:

image0

Input Parameters

exec_queue

The queue where the routine should be executed.

n

Number of elements in vectors x and y.

sb

Single precision scalar to be added to the dot product.

x

Pointer to the input vector x. The array must be of size at least (1 + (n - 1)*abs(incx)). See Matrix and Vector Storage for more details.

incx

Stride of vector x.

y

Pointer to the input vector y. The array must be of size at least (1 + (n - 1)*abs(incxy)). See Matrix and Vector Storage for more details.

incy

Stride of vector y.

dependencies

List of events to wait for before starting computation, if any. If omitted, defaults to no dependencies.

Output Parameters

result

Pointer to where the result (a scalar) will be stored. If n < 0 the result is sb.

Return Values

Output event to wait on to ensure computation is complete.