[llvm] [AMDGPU] Extend wave reduce intrinsics for i32 type (PR #126469)

[Pravin Jagtap via llvm-commits]

pravinjagtap wrote:

> Do these implement the prefix sum / scan?

No, work for adding scan builtins is under development. Given class of intrinsics just performs the reductions (final reduced value will be in SGPR). You will find the use case here https://github.com/llvm/llvm-project/pull/121148


https://github.com/llvm/llvm-project/pull/126469