[llvm] [AMDGPU] Fix code sequence for barrier start in GFX10+ CU Mode (PR #160501)

[Pierre van Houtryve via llvm-commits]

Pierre-vh wrote:

> Quite frankly, I'd rather admit that trying to reduce CU-mode release fences to only VM_VSRC waits was a mistake, and go back to using the same waits there as for WGP-mode.

We never emitted a `vm_vsrc(0)` wait for workgroup release fences in CU mode.

> This pessimizes LDS-only barriers too much.

Which LDS-only barriers ? The check only includes `S_BARRIER`. 

Do you think we should instead pessimize all workgroup release fences in CU mode so they have a wait on storecnt?

https://github.com/llvm/llvm-project/pull/160501