[Mlir-commits] [mlir] [mlir][gpu] Fix crash in transform.gpu.map_nested_forall_to_threads with zero iterations (PR #170282)

[Matthias Springer]

matthias-springer wrote:

Could the GPU dialect maintainers take a look or dispatch this PR to reviewers? @fabianmcg

It's also possible that this code is effectively abandoned. I believe this was at some point used in IREE, but I can't see any uses there.


https://github.com/llvm/llvm-project/pull/170282