Dot

Applicable Products

Function Description

API function

• asdBlasMakeDotPlan: initializes the Dot operator configuration corresponding to the handle.
• asdBlasSdot: computes the dot product of two real number vectors.
• asdBlasCdotu: computes the dot product of two complex number vectors.
• asdBlasCdotc: computes the dot product of one complex number vector after conjugation and another complex number vector.

Formula:

• asdBlasSdot formula:
  • Example:

    Input x:

    [1.0, 2.0]

    Input y:

    [1.0, 2.0]

    After the Sdot operator is called, the output result is as follows:

    5.0

• asdBlasCdotu formula: ,

  where x[i] and y[i] are complex numbers.

  • Example:

    Input x:

    [ 0.1554+0.8840j, -0.3564-0.2552j]

    Input y:

    [-0.1404+1.3380j, -0.4876+0.1842j]

    After the Cdotu operator is called, the output result is as follows:

    -0.9838+0.1425j

• asdBlasCdotc formula: ,

  where x[i] and y[i] are complex numbers, and conj indicates the conjugate operation.

  • Example:

    Input x:

    [ 0.1554+0.8840j, -0.3564-0.2552j]

    Input y:

    [-0.1404+1.3380j, -0.4876+0.1842j]

    After the Cdotc operator is called, the output result is as follows:

    1.2877-0.1420j

Function Prototype

• AspbStatus asdBlasMakeDotPlan(asdBlasHandle handle)
• AspbStatus asdBlasSdot(asdBlasHandle handle, const int64_t n, aclTensor *x, const int64_t incx, aclTensor *y,const int64_t incy, aclTensor *result)
• AspbStatus asdBlasCdotu(asdBlasHandle handle, const int64_t n, aclTensor *x, const int64_t incx, aclTensor *y,const int64_t incy, aclTensor *result)
• AspbStatus asdBlasCdotc(asdBlasHandle handle, const int64_t n, aclTensor *x, const int64_t incx, aclTensor *y,const int64_t incy, aclTensor *result)

Parameter Description

• asdBlasMakeDotPlan

  Parameter	Input/Output	Type	Description
  handle	Input	asdBlasHandle	Handle of the Dot operator.

• asdBlasSdot & asdBlasCdotu & asdBlasCdotc

  Parameter	Input/Output	Type	Description
  handle	Input	asdBlasHandle	Handle of the Dot operator.
  n	Input	const char	Number of elements in vector x or vector y.
  x	Input	aclTensor *	x in the formula, which is a tensor on the device. The data format can be ND, and the shape is [n]. For Sdot, the supported data type is FLOAT32. For Cdotc and Cdotu, the supported data type is COMPLEX64.
  incx	Input	const int64_t	Memory address increment between consecutive elements of vector x (currently restricted to 1).
  y	Input	aclTensor *	y in the formula, which is a tensor on the device. The data format can be ND, and the shape is [n]. For Sdot, the supported data type is FLOAT32. For Cdotc and Cdotu, the supported data type is COMPLEX64.
  incy	Input	const int64_t	Memory address increment between consecutive elements of vector y (currently restricted to 1).
  result	Output	aclTensor *	result in the formula, which is a tensor on the device. The supported data type is FLOAT32. It contains only one element. The data format supports ND, and the shape is [1].

Return Value Description

For details about the return values, see Return Value.

Constraints

• asdBlasMakeDotPlan: none.
• asdBlasSdot
  • The input element count n currently supports the range [1, 6.71e+06].
  • The input shape of the operator is [n], and the output shape is [1].
  • The operator does not support the calculation for three or more dimensions.
• asdBlasCdotu & asdBlasCdotc
  • The input element count n currently supports the range [1, 6.71e+06].
  • The input shape of the operator is [n], and the output shape is [1].
  • The operator does not support the calculation for three or more dimensions.

Calling Example

For details about the operator calling example, see Dot.