[llvm] [AMDGPU][MC] Allow null where 128b or larger dst reg is expected (PR #115200)

[Matt Arsenault via llvm-commits]

https://github.com/arsenm commented:

Manual also states "NULL may not be used as an S#, V# or T#."

Can you add some mimg and mubuf/mtbuf cases? I don't think we can tell from just the operand that the use context is one of these 

https://github.com/llvm/llvm-project/pull/115200