[llvm-branch-commits] [llvm] [AMDGPU] Fold provably out-of-bounds raw buffer loads/stores (PR #227402)

[Matt Arsenault via llvm-branch-commits]

https://github.com/arsenm commented:

I'm not sure InstCombine is the right place for this transform. Won't this miss fat pointer load/store?

Does instcombine do this for regular load and store?

https://github.com/llvm/llvm-project/pull/227402