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

[Benjamin Maxwell]

================
@@ -427,12 +427,88 @@ struct TransposeOpToArmSMELowering
   }
 };
 
+/// Conversion pattern for vector.outerproduct.
+///
+/// If the vector.outerproduct is masked (and the mask from a
+/// vector.create_mask), then the mask is decomposed into two 1-D masks for the
+/// operands.
----------------
MacDue wrote:

s/vector.outerproduct/arm_sme.outerproduct/g :P 

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