[llvm] [AMDGPU][True16][MC] add fake16 error and promote test (PR #135984)

[Joe Nash via llvm-commits]

================
@@ -1,89 +0,0 @@
-// RUN: not llvm-mc -triple=amdgcn -mcpu=gfx1100 -mattr=-real-true16,+wavefrontsize32 -show-encoding %s 2>&1 | FileCheck --check-prefix=GFX11 --implicit-check-not=error: %s
----------------
Sisyph wrote:

broxigarchen and I discussed it briefly. These tests were part of the initial bringup of GFX11 when we needed to disable registers over 128 on VOP12C, so the naming conventions were not well established at that time. The name is of course open to discussion. One factor is it is perhaps confusing to have both t16 and fake16 in the test name.

https://github.com/llvm/llvm-project/pull/135984