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

[Andrzej Warzyński]

================
@@ -14,6 +14,12 @@
 // REDEFINE: %{entry_point} = test_outerproduct_with_accumulator_4x4xf32
 // RUN: %{compile} | %{run} | FileCheck %s --check-prefix=WITH-ACC
----------------
banach-space wrote:

[nit] It would be good to only compile once, see e.g. https://github.com/llvm/llvm-project/blob/640274ff1fe17852615564a80d9f8c69b67f1d59/mlir/test/Integration/Dialect/Vector/CPU/ArmSVE/test-contraction.mlir#L1-L20

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