Mul - 7 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Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.
- Mul7 → Mul14 +2 -9
Mul7 → Mul14
RENAMED
|
@@ -1 +1 @@
|
|
|
1
1
|
Performs element-wise binary multiplication (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
|
-
tensor(bfloat16),
|
|
16
13
|
tensor(double),
|
|
17
14
|
tensor(float),
|
|
18
15
|
tensor(float16),
|
|
19
|
-
tensor(int16),
|
|
20
16
|
tensor(int32),
|
|
21
17
|
tensor(int64),
|
|
22
|
-
tensor(int8),
|
|
23
|
-
tensor(uint16),
|
|
24
18
|
tensor(uint32),
|
|
25
|
-
tensor(uint64)
|
|
19
|
+
tensor(uint64)
|
|
26
|
-
tensor(uint8)
|
|
27
20
|
):
|
|
28
|
-
Constrain input and output types to
|
|
21
|
+
Constrain input and output types to high-precision numeric tensors.? ^^^^^^^^^^^^^^
|