[llvm] [mlir] [MLIR] Generalize expand_shape to take shape as explicit input (PR #69267)

[via llvm-commits]

================
@@ -2237,6 +2237,17 @@ FailureOr<MemRefType> ExpandShapeOp::computeExpandedType(
                          srcType.getMemorySpace());
 }
 
+LogicalResult ExpandShapeOp::inferOutputShape(
+    OpBuilder &b, Location loc, MemRefType expandedType,
+    ArrayRef<ReassociationIndices> reassociation,
+    ArrayRef<OpFoldResult> inputShape,
+    std::pair<SmallVector<int64_t>, SmallVector<Value>> &outputShape) {
+  auto expandedTensorType =
----------------
MaheshRavishankar wrote:

Note: This triggered the suggestion of using `ShapedType` in `inferExpandShapeOutputShape` to avoid having to do this.

https://github.com/llvm/llvm-project/pull/69267