[Mlir-commits] [mlir] [mlir][NVVM] Add InferTypeOpInterface to NVVM ops with deterministic result types (PR #188173)

[Durgadoss R]

durga4github wrote:

1)
Could you please run the GPU/CUDA integration tests locally and confirm if they are still good after this change?
I ask because we do not have coverage in CI for these yet and fixing the issues after a while becomes tedious at times.

2)
Generally, whenever we updated bar/mbar items, we have had a few issues to iron out. So, I request to split this into two parts: 1) All the mbar updates 2) Others to keep triage simpler.

https://github.com/llvm/llvm-project/pull/188173