[llvm] [AMDGPU][GlobalISel] Allow bitcast of bf16 (PR #81674)

[Rahul Joshi via llvm-commits]

jurahul wrote:

Also, looks like there is some thinking in adding bf16 as a LLT, but the comment at the top of LowLevetType.h says:

```
/// Other information required for correct selection is expected to be carried
/// by the opcode, or non-type flags. For example the distinction between G_ADD
/// and G_FADD for int/float or fast-math flags.
```

Does that mean adding bf16 support means adding new fields to GMIR classes like G_FADD instead to carry the type?

https://github.com/llvm/llvm-project/pull/81674