[llvm] [AMDGPU] Introduce orderign parameter to atomic intrinsics and introduce new llvm.amdgcn.image.atomic.load intrinsic. (PR #73613)

[Nicolai Hähnle via llvm-commits]

https://github.com/nhaehnle commented:

Thank you for making the `nosync` adjustment. Though now, it looks like `nosync` has to be added back to most of the other image intrinsics.

https://github.com/llvm/llvm-project/pull/73613