[llvm] [AMDGPU] Improved Lowering of abs(i8/i16) and -abs(i8/i16) (PR #165626)

[Matt Arsenault via llvm-commits]

arsenm wrote:

Can you close this one and continue with https://github.com/llvm/llvm-project/pull/167064/, that's closer to the right solution 

https://github.com/llvm/llvm-project/pull/165626