[Mlir-commits] [mlir] [SCFToGPU] Convert scf.parallel+scf.reduce to gpu.all_reduce (PR #122782)

[Adam Siemieniuk]

adam-smnk wrote:

@tkarna Thanks, looks good 👍 Could you just add a few negative test cases? At least for these newly added checks.
Otherwise, it should be good to go.

https://github.com/llvm/llvm-project/pull/122782