[Mlir-commits] [mlir] [mlir] Add normalize pass to MLIR (PR #186647)

[Renato Golin]

https://github.com/rengolin commented:

I'm slightly worried about the recursive complexity. If we allow original ops moving over each other, could this have unstable results?

@arun-thmn has a similar pass for x86, but there are some differences on how much to actually move around. My concern here is that the sequence of IR will make a difference at the instruction scheduling at the lower levels, so some movements are good, others may hurt. (we have seen this when lowering to LLVM).

Final note is about moving ops across different regions. Control flow region semantics are more well known, but what if the region is inside an op where the semantics isn't clear? For example, it changes the address space, or there's an implicit communication barrier, etc?


https://github.com/llvm/llvm-project/pull/186647