[Mlir-commits] [mlir] [mlir][amdgpu] Add scaled_ext_packed{8, 16} operations (PR #159830)

[Erick Ochoa Lopez]

amd-eochoalo wrote:

between https://github.com/llvm/llvm-project/pull/159830/commits/f92db34c23bcade79c941bcc8f58605ea2ab6c10 and https://github.com/llvm/llvm-project/pull/159830/commits/c3832b09bed55cbcaa40d6643ce56f0398ddcab4 I prefer  https://github.com/llvm/llvm-project/pull/159830/commits/f92db34c23bcade79c941bcc8f58605ea2ab6c10. By having two optional attributes which are in an XOR-relationship the constructors for this operation will always require a nullptr and getting the attributes will always get a `std::optional<int32_t>`. 

Between https://github.com/llvm/llvm-project/pull/159830/commits/f92db34c23bcade79c941bcc8f58605ea2ab6c10 and merging these two operations into their distinct operation, one thing to notice is that we will need a verifier to make sure the types are correctly matched. (Not a big deal). We also need to choose a name for this operation since `scaled_ext_packed` is already taken. Maybe `scaled_ext_packed_8_or_16`?

https://github.com/llvm/llvm-project/pull/159830