maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[mlir] Add to shape.is_broadcastable description

This commit is contained in:
Tres Popp 2020-11-03 10:23:54 +01:00
parent d05d42199f
commit ca1bcdff4b
1 changed files with 6 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
mlir/include/mlir/Dialect/Shape/IR/ShapeOps.td
View File

@ -188,6 +188,11 @@ def Shape_IsBroadcastableOp : Shape_Op<"is_broadcastable", [Commutative]> {
they are broadcastable. This broadcastable follows the same logic as what
shape.broadcast documents.
Concretely, shape.is_broadcastable returning true implies that
shape.broadcast will not give an error, and shape.cstr_broadcastable will
not result in an assertion failure. Similarly, false implies an error or
assertion failure.
Example:
```mlir
%true = shape.is_broadcastable [2,2], [3,1,2]
@ -199,7 +204,7 @@ def Shape_IsBroadcastableOp : Shape_Op<"is_broadcastable", [Commutative]> {
Shape_ShapeOrExtentTensorType:$rhs);
let results = (outs I1:$result);
let assemblyFormat = "$lhs `,` $rhs `:` type($lhs) `,` type($rhs) attr-dict";
let assemblyFormat = "$lhs `,` $rhs attr-dict `:` type($lhs) `,` type($rhs)";
}
def Shape_RankOp : Shape_Op<"rank", [NoSideEffect]> {