forked from OSchip/llvm-project
[mlir][Tensor] Improve documentation of verification behavior of InsertSliceOp.
This commit is contained in:
parent
2124b2f0e6
commit
0fb24a85cb
|
@ -549,6 +549,11 @@ def Tensor_InsertSliceOp : Tensor_OpWithOffsetSizesAndStrides<"insert_slice", [
|
|||
The rank-altering behavior of tensor.insert_slice matches the rank-reducing
|
||||
behavior of tensor.extract_slice.
|
||||
|
||||
Verification in the rank-reduced case:
|
||||
======================================
|
||||
The same verification discussion and mechanisms apply as for ExtractSliceOp.
|
||||
Unlike ExtractSliceOp however, there is no need for a specific inference.
|
||||
|
||||
Example:
|
||||
|
||||
```
|
||||
|
|
Loading…
Reference in New Issue