[Mlir-commits] [mlir] [mlir] Add direct vectorization lowering for `tensor.pack` ops (PR #78660)

[Han-Chung Wang]

https://github.com/hanhanW requested changes to this pull request.

Two big comments + few nits.

1. A method can be refactored to `Tensor/Utils/`.
2. How to handle the padding value for transfer_read is unclear to me. @dcaballe can you provide some guidance?

https://github.com/llvm/llvm-project/pull/78660