[Mlir-commits] [mlir] [mlir][vector] Constrain broadcast->shape_cast folding (PR #190230)

[Han-Chung Wang]

================
@@ -10,7 +10,12 @@ func.func @mmt4d_to_fma(%A: tensor<16x16x8x1xf32>, %B: tensor<16x16x8x1xf32>, %C
 
 
 // CHECK-LABEL:     @mmt4d_to_fma
-// CHECK-COUNT-8:         vector.fma
+// CHECK-NOT:         linalg.mmt4d
+// Lowering may produce vector.fma (outerproduct) or elementwise arith.mulf +
+// vector.reduction depending on vector.contract lowering; both are valid.
----------------
hanhanW wrote:

I think we should fix the inconsistency. We should either explore a path for the `mmt4d->fma` lowering or just rename this file to `transform-op-mmt4d-to-reduction.mlir`.

I'm thinking if we should just remove the the test, because how to lower `vector.multi_reduction` op is the details of vector lowering, which should be tested in vector dialect instead.

https://github.com/llvm/llvm-project/pull/190230