[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>
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:

This extra waitcnt is due to `setNonKernelFunctionInitialState`
Without this patch the counters start at
```
*** Block0 ***
    VM_CNT(0): 
    LGKM_CNT(0): 
    EXP_CNT(0): 
    VS_CNT(0): 
```
With the patch:
```
*** Block0 ***
    VM_CNT(63): 
    LGKM_CNT(63): 
    EXP_CNT(7): 
    VS_CNT(63): 
```

I didn't follow the full discussion around the patch so I don't know the context behind this change. I will try to dive deeper this week to provide more meaningful feedback.


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