Edit

Share via

DML_ELEMENT_WISE_ADD_OPERATOR_DESC structure (directml.h)

  • Article

Adds every element in ATensor to its corresponding element in BTensor, placing the result into the corresponding element of OutputTensor.

f(a, b) = a + b

This operator supports in-place execution, meaning that OutputTensor is permitted to alias one or more of the input tensors during binding.

Syntax

struct DML_ELEMENT_WISE_ADD_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

A newer version of this operator, DML_ELEMENT_WISE_ADD1_OPERATOR_DESC, was introduced in DML_FEATURE_LEVEL_2_0.

Availability

This operator was introduced in DML_FEATURE_LEVEL_1_0.

Tensor constraints

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

Tensor support

DML_FEATURE_LEVEL_5_1 and above

Tensor Kind Supported dimension counts Supported data types
ATensor Input 1 to 8 FLOAT32, FLOAT16, INT64, INT32, INT16, INT8, UINT64, UINT32, UINT16, UINT8
BTensor Input 1 to 8 FLOAT32, FLOAT16, INT64, INT32, INT16, INT8, UINT64, UINT32, UINT16, UINT8
OutputTensor Output 1 to 8 FLOAT32, FLOAT16, INT64, INT32, INT16, INT8, UINT64, UINT32, UINT16, UINT8

DML_FEATURE_LEVEL_4_1 and above

Tensor Kind Supported dimension counts Supported data types
ATensor Input 1 to 8 FLOAT32, FLOAT16, INT64, INT32, UINT64, UINT32
BTensor Input 1 to 8 FLOAT32, FLOAT16, INT64, INT32, UINT64, UINT32
OutputTensor Output 1 to 8 FLOAT32, FLOAT16, INT64, INT32, UINT64, UINT32

DML_FEATURE_LEVEL_3_0 and above

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

DML_FEATURE_LEVEL_2_1 and above

Tensor Kind Supported dimension counts Supported data types
ATensor Input 4 to 5 FLOAT32, FLOAT16, INT32, UINT32
BTensor Input 4 to 5 FLOAT32, FLOAT16, INT32, UINT32
OutputTensor Output 4 to 5 FLOAT32, FLOAT16, INT32, UINT32

DML_FEATURE_LEVEL_1_0 and above

Tensor Kind Supported dimension counts Supported data types
ATensor Input 4 to 5 FLOAT32, FLOAT16
BTensor Input 4 to 5 FLOAT32, FLOAT16
OutputTensor Output 4 to 5 FLOAT32, FLOAT16

Requirements

Requirement Value
Header directml.h

See also

DML_ELEMENT_WISE_ADD1_OPERATOR_DESC