Add - 13 vs 14#

Next section compares an older to a newer version of the same operator after both definition are converted into markdown text. Green means an addition to the newer version, red means a deletion. Anything else is unchanged.

Files changed (1) hide show
  1. Add13 → Add14 +2 -8
Add13 → Add14 RENAMED
@@ -1 +1 @@
1
1
  Performs element-wise binary addition (with Numpy-style broadcasting support).
2
2
  This operator supports **multidirectional (i.e., Numpy-style) broadcasting**; for more details please check Broadcasting in ONNX <https://github.com/onnx/onnx/blob/master/docs/Broadcasting.md>_.
3
-
4
- (Opset 14 change): Extend supported types to include uint8, int8, uint16, and int16.
5
3
  **Inputs**
6
4
  * **A** (heterogeneous) - **T**:
7
5
  First operand.
8
6
  * **B** (heterogeneous) - **T**:
9
7
  Second operand.
10
8
  **Outputs**
11
9
  * **C** (heterogeneous) - **T**:
12
10
  Result, has same element type as two inputs
13
11
  **Type Constraints**
14
12
  * **T** in (
15
13
  tensor(bfloat16),
16
14
  tensor(double),
17
15
  tensor(float),
18
16
  tensor(float16),
19
- tensor(int16),
20
17
  tensor(int32),
21
18
  tensor(int64),
22
- tensor(int8),
23
- tensor(uint16),
24
19
  tensor(uint32),
25
- tensor(uint64),
20
+ tensor(uint64)
26
- tensor(uint8)
27
21
  ):
28
- Constrain input and output types to all numeric tensors.? ^^^
22
+ Constrain input and output types to high-precision numeric tensors.? ^^^^^^^^^^^^^^