GreaterOrEqual - 12 vs 16

Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.

GreaterOrEqual12 → GreaterOrEqual16 RENAMED
@@ -1 +1 @@
1
1
  Returns the tensor resulted from performing the greater_equal logical operation
2
2
  elementwise on the input tensors A and B (with Numpy-style broadcasting support).
3
3
  This operator supports **multidirectional (i.e., Numpy-style) broadcasting**; for more details please check [Broadcasting in ONNX](https://github.com/onnx/onnx/blob/main/docs/Broadcasting.md).
4
4
  #### Function Body
5
5
  The function definition for this operator.
6
6
  <
7
7
  domain: "",
8
- opset_import: ["" : 12]
8
+ opset_import: ["" : 16]
9
9
  >
10
10
  GreaterOrEqual (A, B) => (C)
11
11
  {
12
12
  O1 = Greater (A, B)
13
13
  O2 = Equal (A, B)
14
14
  C = Or (O1, O2)
15
15
  }
16
16
  ### Inputs
17
17
  - **A** (heterogeneous) - **T**:
18
18
  First input operand for the logical operator.
19
19
  - **B** (heterogeneous) - **T**:
20
20
  Second input operand for the logical operator.
21
21
  ### Outputs
22
22
  - **C** (heterogeneous) - **T1**:
23
23
  Result tensor.
24
24
  ### Type Constraints
25
- * **T** in ( tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8) ):
25
+ * **T** in ( tensor(bfloat16), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8) ):
26
26
  Constrain input types to all numeric tensors.
27
27
  * **T1** in ( tensor(bool) ):
28
28
  Constrain output to boolean tensor.