[Mlir-commits] [mlir] [mlir][x86vector] Lower BF16 vector.contract to FMA using AVX2 BF16 packed ops. (PR #170267)

[Adam Siemieniuk]

================

----------------
adam-smnk wrote:

Could you also add checks for types to one of the cases?
Maybe just to the first one `brgemm_to_fma`.

It acts as a little documentation and helps to see what exactly the pass does at a glance.

https://github.com/llvm/llvm-project/pull/170267