[llvm] [clang] [AMDGPU] Adding the amdgpu-num-work-groups function attribute (PR #75647)

[Krzysztof Drewniak via llvm-commits]

krzysz00 wrote:

@arsenm It's entirely possible that max dispatch size per dimension is the right feature instead, now that you mention it (I keep forgetting we have a grid).

Currently I was thinking this'll be useful for `KnownBits`-type info, so ... yeah, per-dimension

https://github.com/llvm/llvm-project/pull/75647