[Mlir-commits] [mlir] [mlir][gpu] Add innermost-first policy when mapping loops to GPU IDs (PR #160634)

[Georgios Pinitas]

GeorgeARM wrote:

> What I'm claiming is that we should have a loop interchange transform and use that to take care of this. However, I recognize the amount of work on that side is significantly greater. Could you add a TODO, saying replace this once we have an interchange/reordering transform?

I see your point and I will add a TODO in the code itself for this to be revisited later.
But I feel that loop interchange is different semantically; as it is an actual IR semantic transformation and can have more involved side-effects as mentioned above while the other is just a binding problem.

https://github.com/llvm/llvm-project/pull/160634