[llvm] AMDGPU: Remove flat/global fmin/fmax intrinsics (PR #105642)

[Gheorghe-Teodor Bercea via llvm-commits]

doru1004 wrote:

> This is exactly why we must remove this intrinsic or anything that acts like it. You, the frontend writer, must semantically know what you can do. The semantics cannot be "do whatever the intrinsic happens to do on this target"

But you're not removing everything that acts like it except for the intrinsic itself. There's nothing illegal about asking for a new style of atomic RMW with a particular set of additional options that happens to match the previous intrinsic.

https://github.com/llvm/llvm-project/pull/105642