[Mlir-commits] [mlir] [mlir][GPU] Improve handling of GPU bounds (PR #95166)

[Krzysztof Drewniak]

krzysz00 wrote:

@grypp The intent of that code is that the `func.func` *could* be modelling a GPU kernel when you're using a non-upstream lowering flow

https://github.com/llvm/llvm-project/pull/95166