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

[Jay Foad via llvm-commits]

================
@@ -809,6 +809,10 @@ def SReg_32 : SIRegisterClass<"AMDGPU", [i32, f32, i16, f16, bf16, v2i16, v2f16,
   let BaseClassOrder = 32;
 }
 
+def SGPR_NULL128 : SIReg<"null">;
----------------
jayfoad wrote:

I don't know why (or if) SGPR_NULL64 needs to have subregs. Maybe something to investigate later.

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