[clang] [llvm] [mlir] [AMDGPU] Add a new amdgcn.load.to.lds intrinsic (PR #137425)

[Krzysztof Drewniak via cfe-commits]

krzysz00 wrote:

@jayfoad I still think we need an intrinsic here because a load + an addtid store can be scheduled much different from the asynchronous "gather to LDS" - and because we don't want this load/store to not be optimized

https://github.com/llvm/llvm-project/pull/137425