[Mlir-commits] [mlir] [mlir][ArmSME] Support lowering masked vector.outerproduct ops to SME (PR #69604)

[Cullen Rhodes]

================
@@ -97,3 +97,21 @@ func.func @arm_sme_move_tile_slice_to_vector__bad_result_type(%tile : vector<[4]
   %0 = arm_sme.move_tile_slice_to_vector %tile[%tile_slice_index] : vector<[2]xf64> from vector<[4]x[4]xf32>
   return %0 : vector<[2]xf64>
 }
+
+// -----
+
+func.func @arm_sme_outproduct__bad_result_type(%vecA: vector<[2]xi16>, %vecB: vector<[2]xi16>) -> vector<[2]x[2]xi16>
----------------
c-rhodes wrote:

nit: `outproduct` -> `outerproduct` (and below, inc `roundtrip.mlir`)

```suggestion
func.func @arm_sme_outerproduct__bad_result_type(%vecA: vector<[2]xi16>, %vecB: vector<[2]xi16>) -> vector<[2]x[2]xi16>
```

https://github.com/llvm/llvm-project/pull/69604