Div - 13 vs 14

Files changed (1) hide show
  1. Div13 → Div14 +8 -2
Div13 → Div14 RENAMED
@@ -1 +1 @@
1
1
  Performs element-wise binary division (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.
3
5
  **Inputs**
4
6
  * **A** (heterogeneous) - **T**:
5
7
  First operand.
6
8
  * **B** (heterogeneous) - **T**:
7
9
  Second operand.
8
10
  **Outputs**
9
11
  * **C** (heterogeneous) - **T**:
10
12
  Result, has same element type as two inputs
11
13
  **Type Constraints**
12
14
  * **T** in (
13
15
  tensor(bfloat16),
14
16
  tensor(double),
15
17
  tensor(float),
16
18
  tensor(float16),
19
+ tensor(int16),
17
20
  tensor(int32),
18
21
  tensor(int64),
22
+ tensor(int8),
23
+ tensor(uint16),
19
24
  tensor(uint32),
20
- tensor(uint64)
25
+ tensor(uint64),
26
+ tensor(uint8)
21
27
  ):
22
- Constrain input and output types to high-precision numeric tensors.? ^^^^^^^^^^^^^^
28
+ Constrain input and output types to all numeric tensors.? ^^^