[llvm] [AMDGPU][MC][True16] Support VOP2 instructions with true16 format (PR #115233)

[Matt Arsenault via llvm-commits]

================
@@ -467,6 +479,42 @@ class VOP_MAC <ValueType vt0, ValueType vt1=vt0> : VOPProfile <[vt0, vt1, vt1, v
 }
 
 def VOP_MAC_F16 : VOP_MAC <f16>;
+def VOP_MAC_F16_t16 : VOP_MAC <f16> {
----------------
arsenm wrote:

This is a lot of copy paste. Is there a way to avoid replicating so many lets? 

https://github.com/llvm/llvm-project/pull/115233