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

[Jakub Kuderski via cfe-commits]

kuhar wrote:

> High level question: I don't understand why you call this a "gather" operation. What do you mean by that? Isn't it semantically just a memcpy, or a (global/buffer) load followed by a (LDS) store?

This is more like a subgroup operation because the destination offset is uniform.

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