AMDGPU: Fix inserting waitcnts before kill uses

[arsenm]

82cbc9330a4dc61e867864d96b0dbec74abaca89

llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp

 ///  The "score bracket" is bound by the lower bound and upper bound
 ///  scores (*_score_LB and *_score_ub respectively).
 bool SIInsertWaitcnts::generateWaitcntInstBefore(
     MachineInstr &MI, WaitcntBrackets &ScoreBrackets,
     MachineInstr *OldWaitcntInstr) {
   setForceEmitWaitcnt();
   bool IsForceEmitWaitcnt = isForceEmitWaitcnt();
 
-  if (MI.isDebugInstr())
+  if (MI.isMetaInstruction())
     return false;
 
   AMDGPU::Waitcnt Wait;
 
   // See if this instruction has a forced S_WAITCNT VM.
   // TODO: Handle other cases of NeedsWaitcntVmBefore()
   if (MI.getOpcode() == AMDGPU::BUFFER_WBINVL1 ||
       MI.getOpcode() == AMDGPU::BUFFER_WBINVL1_SC ||

llvm/test/CodeGen/AMDGPU/waitcnt-meta-instructions.mir

+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs -run-pass=si-insert-waitcnts -o - %s | FileCheck -check-prefix=GCN %s
+
+# Make sure no waitcnt is inserted for meta instruction uses.
+
+---
+
+name: waitcnt_kill
+
+body:             |
+  bb.0:
+    liveins: $vgpr0_vgpr1
+    ; GCN-LABEL: name: waitcnt_kill
+    ; GCN: S_WAITCNT 0
+    ; GCN: $vgpr0 = GLOBAL_LOAD_DWORD $vgpr0_vgpr1, 0, 0, 0, 0, implicit $exec
+    ; GCN: KILL $vgpr0
+    $vgpr0 = GLOBAL_LOAD_DWORD $vgpr0_vgpr1, 0, 0, 0, 0, implicit $exec
+    KILL $vgpr0
+...
+
+---
+
+name: waitcnt_implicit_def
+
+body:             |
+  bb.0:
+    liveins: $vgpr0_vgpr1
+    ; GCN-LABEL: name: waitcnt_implicit_def
+    ; GCN: S_WAITCNT 0
+    ; GCN: $vgpr0 = GLOBAL_LOAD_DWORD $vgpr0_vgpr1, 0, 0, 0, 0, implicit $exec
+    ; GCN: $vgpr0 = IMPLICIT_DEF
+    $vgpr0 = GLOBAL_LOAD_DWORD $vgpr0_vgpr1, 0, 0, 0, 0, implicit $exec
+    $vgpr0 = IMPLICIT_DEF
+...
+
+---
+
+name: waitcnt_eh_label
+
+body:             |
+  bb.0:
+    liveins: $vgpr0_vgpr1, $vgpr2
+    ; GCN-LABEL: name: waitcnt_eh_label
+    ; GCN: S_WAITCNT 0
+    ; GCN: $vgpr0 = GLOBAL_LOAD_DWORD $vgpr0_vgpr1, 0, 0, 0, 0, implicit $exec
+    ; GCN: EH_LABEL <mcsymbol Ltmp0>, implicit $vgpr0
+    $vgpr0 = GLOBAL_LOAD_DWORD $vgpr0_vgpr1, 0, 0, 0, 0, implicit $exec
+    EH_LABEL <mcsymbol Ltmp0>, implicit $vgpr0
+
+...
+
+---
+
+name: waitcnt_cfi
+
+body:             |
+  bb.0:
+    liveins: $vgpr0_vgpr1, $vgpr2
+    ; GCN-LABEL: name: waitcnt_cfi
+    ; GCN: S_WAITCNT 0
+    ; GCN: $vgpr0 = GLOBAL_LOAD_DWORD $vgpr0_vgpr1, 0, 0, 0, 0, implicit $exec
+    ; GCN: CFI_INSTRUCTION offset $vgpr0_lo16, 16
+    $vgpr0 = GLOBAL_LOAD_DWORD $vgpr0_vgpr1, 0, 0, 0, 0, implicit $exec
+    CFI_INSTRUCTION offset $vgpr0, 16
+
+...