[llvm] [AMDGPU][True16][CodeGen] Implement sgpr folding in true16 (PR #128929)

[Joe Nash via llvm-commits]

================
@@ -1040,6 +1053,14 @@ void SIFoldOperandsImpl::foldOperand(
       }
     }
 
+    // Allow immediates COPYd into sgpr_lo16 to be further folded while
----------------
Sisyph wrote:

Yes, to indicate the use of the COPY instruction. But if it's confusing I'd be happy to change it.

https://github.com/llvm/llvm-project/pull/128929