[llvm] [AMDGPU][SIInsertWaitcnts] Do not add s_waitcnt when the counters are known to be 0 already (PR #72830)

[Pierre van Houtryve via llvm-commits]

Juan Manuel MARTINEZ =?utf-8?q?CAAMAÑO?= <juamarti at amd.com>,pvanhout
 <pierre.vanhoutryve at amd.com>,pvanhout <pierre.vanhoutryve at amd.com>,pvanhout
 <pierre.vanhoutryve at amd.com>,pvanhout <pierre.vanhoutryve at amd.com>
Message-ID:
In-Reply-To: <llvm.org/llvm/llvm-project/pull/72830 at github.com>


================
@@ -45,6 +45,7 @@ define void @back_off_barrier_no_fence(ptr %in, ptr %out) #0 {
 ; GFX11-BACKOFF-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GFX11-BACKOFF-NEXT:    flat_load_b32 v0, v[0:1]
 ; GFX11-BACKOFF-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX11-BACKOFF-NEXT:    s_waitcnt_vscnt null, 0x0
----------------
Pierre-vh wrote:

Without it there's quite a few more changes, e.g.
- MSG_DEALLOC_VGPRS is back in `llvm.amdgcn.set.inactive.chain.arg.ll`
- `atomicrmw-expand.ll` has a few missing `s_waitcnt_vscnt null, 0x0` which I'm not sure if it's good or bad

Given that the PSDB passes with the changes I assume they're here for a reason, but Juan cannot tell us why right now so I don't know what the reasoning is

https://github.com/llvm/llvm-project/pull/72830