DML_ELEMENT_WISE_DIFFERENCE_SQUARE_OPERATOR_DESC structure (directml.h)

Subtracts each element of BTensor from the corresponding element of ATensor, multiplies the result by itself, and places the result into the corresponding element of OutputTensor.

f(a, b) = (a - b) * (a - b)

This operator supports in-place execution, meaning that OutputTensor is permitted to alias ATensor or BTensor during binding.

Syntax

struct DML_ELEMENT_WISE_DIFFERENCE_SQUARE_OPERATOR_DESC {
  const DML_TENSOR_DESC *ATensor;
  const DML_TENSOR_DESC *BTensor;
  const DML_TENSOR_DESC *OutputTensor;
};

Members

ATensor

Type: const DML_TENSOR_DESC*

A tensor containing the left-hand side inputs.

BTensor

Type: const DML_TENSOR_DESC*

A tensor containing the right-hand side inputs.

OutputTensor

Type: const DML_TENSOR_DESC*

The output tensor to write the results to.

Remarks

Availability

This operator was introduced in DML_FEATURE_LEVEL_3_1.

Tensor constraints

ATensor, BTensor, and OutputTensor must have the same DataType, DimensionCount, and Sizes.

Tensor support

Tensor Kind Supported dimension counts Supported data types
ATensor Input 1 to 8 FLOAT32, FLOAT16, INT32, UINT32
BTensor Input 1 to 8 FLOAT32, FLOAT16, INT32, UINT32
OutputTensor Output 1 to 8 FLOAT32, FLOAT16, INT32, UINT32

Requirements

Requirement Value
Minimum supported client Windows Build 22000
Minimum supported server Windows Build 22000
Header directml.h