[llvm] [AMDGPU][True16][MC] update mc test of a few vop1 t16 inst (PR #135588)

[Joe Nash via llvm-commits]

================
@@ -5,6 +5,12 @@
 v_ceil_f16_e32 v128, 0xfe0b
 // GFX12: :[[@LINE-1]]:1: error: operands are not valid for this GPU or mode
 
+v_ceil_f16_e32 v128.h, 0xfe0b
+// GFX12: :[[@LINE-1]]:16: error: invalid operand for instruction
+
+v_ceil_f16_e32 v128.l, 0xfe0b
+// GFX12: :[[@LINE-1]]:16: error: invalid operand for instruction
+
 v_ceil_f16_e32 v255, v1
----------------
Sisyph wrote:

It looks like some more tests in this file should be converted to use 16 bit registers.

https://github.com/llvm/llvm-project/pull/135588