[Mlir-commits] [mlir] [mlir][x86] Lower vector.contract to packed type tiled dot-product. (PR #182810)

[Adam Siemieniuk]

================
@@ -71,5 +71,16 @@ def ApplyShuffleVectorFMAOpsPatternsOp : Op<Transform_Dialect,
   let assemblyFormat = "attr-dict";
 }
 
+def ApplyVectorContractToPackedTypeTiledDotProductPatternsOp : Op<Transform_Dialect,
----------------
adam-smnk wrote:

nit: The name's really close to `apply_patterns_x86_vector_contract_to_packed_type_dot_product` which makes it a bit confusing. These rewrites focus specifically on AMX, right?
I'd suggest simplifying the name and mentioning AMX explicitly.

https://github.com/llvm/llvm-project/pull/182810