[llvm] [AMDGPU][True16][MC] added missing testlines for t16 test (PR #135823)

[Joe Nash via llvm-commits]

================
@@ -1114,16 +1114,16 @@ v_lshrrev_b16_e64_dpp v5.l, v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0] fi:1
 v_lshrrev_b16_e64_dpp v255.l, v255.l, v255.l dpp8:[0,0,0,0,0,0,0,0] fi:0
 // GFX11: v_lshrrev_b16_e64_dpp v255.l, v255.l, v255.l dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x00,0x39,0xd7,0xe9,0xfe,0x03,0x00,0xff,0x00,0x00,0x00]
 
-v_lshrrev_b16_e64_dpp v5.h, v1.h, v2.h dpp8:[7,6,5,4,3,2,1,0]
+v_lshrrev_b16_e64_dpp v5.h, v1.h, v2.h op_sel:[1,1,1] dpp8:[7,6,5,4,3,2,1,0]
----------------
Sisyph wrote:

What is the point of adding op_sel operand all over? We don't have it on every 16 bit instruction instruction either, even after this patch. Probably can just drop all the line changes that just add op_sel.

https://github.com/llvm/llvm-project/pull/135823