[AMDGPU] Remove one case of vmcnt loop header flushing for GFX12 (llv…

…m#105550)

When a loop contains a VMEM load whose result is only used outside the
loop, do not bother to flush vmcnt in the loop head on GFX12. A wait for
vmcnt will be required inside the loop anyway, because VMEM instructions
can write their VGPR results out of order.

llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp

@@ -2390,7 +2390,7 @@ bool SIInsertWaitcnts::shouldFlushVmCnt(MachineLoop *ML,
   }
   if (!ST->hasVscnt() && HasVMemStore && !HasVMemLoad && UsesVgprLoadedOutside)
     return true;
-  return HasVMemLoad && UsesVgprLoadedOutside;
+  return HasVMemLoad && UsesVgprLoadedOutside && ST->hasVmemWriteVgprInOrder();
 }
 
 bool SIInsertWaitcnts::runOnMachineFunction(MachineFunction &MF) {

llvm/test/CodeGen/AMDGPU/waitcnt-vmcnt-loop.mir

@@ -295,7 +295,7 @@ body:             |
 # GFX12-LABEL: waitcnt_vm_loop2
 # GFX12-LABEL: bb.0:
 # GFX12: BUFFER_LOAD_FORMAT_X_IDXEN
-# GFX12: S_WAIT_LOADCNT 0
+# GFX12-NOT: S_WAIT_LOADCNT 0
 # GFX12-LABEL: bb.1:
 # GFX12: S_WAIT_LOADCNT 0
 # GFX12-LABEL: bb.2:
@@ -342,7 +342,7 @@ body:             |
 # GFX12-LABEL: waitcnt_vm_loop2_store
 # GFX12-LABEL: bb.0:
 # GFX12: BUFFER_LOAD_FORMAT_X_IDXEN
-# GFX12: S_WAIT_LOADCNT 0
+# GFX12-NOT: S_WAIT_LOADCNT 0
 # GFX12-LABEL: bb.1:
 # GFX12: S_WAIT_LOADCNT 0
 # GFX12-LABEL: bb.2:
@@ -499,9 +499,9 @@ body:             |
 # GFX12-LABEL: waitcnt_vm_loop2_reginterval
 # GFX12-LABEL: bb.0:
 # GFX12: GLOBAL_LOAD_DWORDX4
-# GFX12: S_WAIT_LOADCNT 0
-# GFX12-LABEL: bb.1:
 # GFX12-NOT: S_WAIT_LOADCNT 0
+# GFX12-LABEL: bb.1:
+# GFX12: S_WAIT_LOADCNT 0
 # GFX12-LABEL: bb.2:
 name:            waitcnt_vm_loop2_reginterval
 body:             |
@@ -600,7 +600,7 @@ body:             |
 # GFX12-LABEL: bb.0:
 # GFX12: BUFFER_LOAD_FORMAT_X_IDXEN
 # GFX12: BUFFER_LOAD_FORMAT_X_IDXEN
-# GFX12: S_WAIT_LOADCNT 0
+# GFX12-NOT: S_WAIT_LOADCNT 0
 # GFX12-LABEL: bb.1:
 # GFX12: S_WAIT_LOADCNT 0
 # GFX12-LABEL: bb.2: