[llvm-branch-commits] [llvm] [AMDGPU] Fold sudot intrinsics with a zero multiplicand (PR #226479)

[Matt Arsenault via llvm-branch-commits]

https://github.com/arsenm approved this pull request.

This theoretically belongs in InstSimplify but I'm not sure if we ever finalized a policy on how to handle target intrinsics there 

https://github.com/llvm/llvm-project/pull/226479