[llvm] [AMDGPU][GlobalISel] Add BF16 widening to V2BF16 for packed instructions (PR #214370)

[Lukas Sommer via llvm-commits]

================

----------------
sommerlukas wrote:

I think the implementation already handles the uniform case (`inreg`), but would be good to have a test for it.

Also, one test that shows that fast-math flags are preserved by the transformation would be useful.

https://github.com/llvm/llvm-project/pull/214370