From: Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com>
Date: Mon, 21 Jan 2019 19:11:26 +0000 (+0000)
Subject: [AMDGPU] Fixed hazard recognizer to walk predecessors
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=e2069ebfee1c6b2390bd6607c7cec2647a51c305;p=llvm

[AMDGPU] Fixed hazard recognizer to walk predecessors

Fixes two problems with GCNHazardRecognizer:
1. It only scans up to 5 instructions emitted earlier.
2. It does not take control flow into account. An earlier instruction
from the previous basic block is not necessarily a predecessor.
At the same time a real predecessor block is not scanned.

The patch provides a way to distinguish between scheduler and
hazard recognizer mode. It is OK to work with emitted instructions
in the scheduler because we do not really know what will be emitted
later and its order. However, when pass works as a hazard recognizer
the schedule is already finalized, and we have full access to the
instructions for the whole function, so we can properly traverse
predecessors and their instructions.

Differential Revision: https://reviews.llvm.org/D56923

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@351759 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/lib/Target/AMDGPU/GCNHazardRecognizer.cpp b/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
index bb1c6dbff2b..4af8a457a0e 100644
--- a/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
+++ b/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
@@ -37,6 +37,7 @@ using namespace llvm;
 //===----------------------------------------------------------------------===//
 
 GCNHazardRecognizer::GCNHazardRecognizer(const MachineFunction &MF) :
+  IsHazardRecognizerMode(false),
   CurrCycleInstr(nullptr),
   MF(MF),
   ST(MF.getSubtarget<GCNSubtarget>()),
@@ -172,10 +173,19 @@ GCNHazardRecognizer::getHazardType(SUnit *SU, int Stalls) {
 }
 
 unsigned GCNHazardRecognizer::PreEmitNoops(SUnit *SU) {
-  return PreEmitNoops(SU->getInstr());
+  IsHazardRecognizerMode = false;
+  return PreEmitNoopsCommon(SU->getInstr());
 }
 
 unsigned GCNHazardRecognizer::PreEmitNoops(MachineInstr *MI) {
+  IsHazardRecognizerMode = true;
+  CurrCycleInstr = MI;
+  unsigned W = PreEmitNoopsCommon(MI);
+  CurrCycleInstr = nullptr;
+  return W;
+}
+
+unsigned GCNHazardRecognizer::PreEmitNoopsCommon(MachineInstr *MI) {
   int WaitStates = std::max(0, checkAnyInstHazards(MI));
 
   if (SIInstrInfo::isSMRD(*MI))
@@ -231,7 +241,7 @@ void GCNHazardRecognizer::AdvanceCycle() {
   // Do not track non-instructions which do not affect the wait states.
   // If included, these instructions can lead to buffer overflow such that
   // detectable hazards are missed.
-  if (CurrCycleInstr->getOpcode() == AMDGPU::IMPLICIT_DEF)
+  if (CurrCycleInstr->isImplicitDef())
     return;
   else if (CurrCycleInstr->isDebugInstr())
     return;
@@ -265,41 +275,109 @@ void GCNHazardRecognizer::RecedeCycle() {
 // Helper Functions
 //===----------------------------------------------------------------------===//
 
-int GCNHazardRecognizer::getWaitStatesSince(
-    function_ref<bool(MachineInstr *)> IsHazard) {
+typedef function_ref<bool(MachineInstr *, int WaitStates)> IsExpiredFn;
+
+// Returns a minimum wait states since \p I walking all predecessors.
+// Only scans until \p IsExpired does not return true.
+// Can only be run in a hazard recognizer mode.
+static int getWaitStatesSince(GCNHazardRecognizer::IsHazardFn IsHazard,
+                              MachineBasicBlock *MBB,
+                              MachineBasicBlock::reverse_instr_iterator I,
+                              int WaitStates,
+                              IsExpiredFn IsExpired,
+                              DenseSet<const MachineBasicBlock *> &Visited) {
+
+  for (auto E = MBB->rend() ; I != E; ++I) {
+    if (IsHazard(&*I))
+      return WaitStates;
+
+    if (I->isInlineAsm() || I->isImplicitDef() || I->isDebugInstr())
+      continue;
+
+    WaitStates += SIInstrInfo::getNumWaitStates(*I);
+
+    if (IsExpired(&*I, WaitStates))
+      return std::numeric_limits<int>::max();
+  }
+
+  int MinWaitStates = WaitStates;
+  bool Found = false;
+  for (MachineBasicBlock *Pred : MBB->predecessors()) {
+    if (!Visited.insert(Pred).second)
+      continue;
+
+    int W = getWaitStatesSince(IsHazard, Pred, Pred->instr_rbegin(),
+                               WaitStates, IsExpired, Visited);
+
+    if (W == std::numeric_limits<int>::max())
+      continue;
+
+    MinWaitStates = Found ? std::min(MinWaitStates, W) : W;
+    if (IsExpired(nullptr, MinWaitStates))
+      return MinWaitStates;
+
+    Found = true;
+  }
+
+  if (Found)
+    return MinWaitStates;
+
+  return std::numeric_limits<int>::max();
+}
+
+static int getWaitStatesSince(GCNHazardRecognizer::IsHazardFn IsHazard,
+                              MachineInstr *MI,
+                              IsExpiredFn IsExpired) {
+  DenseSet<const MachineBasicBlock *> Visited;
+  return getWaitStatesSince(IsHazard, MI->getParent(),
+                            std::next(MI->getReverseIterator()),
+                            0, IsExpired, Visited);
+}
+
+int GCNHazardRecognizer::getWaitStatesSince(IsHazardFn IsHazard, int Limit) {
+  if (IsHazardRecognizerMode) {
+    auto IsExpiredFn = [Limit] (MachineInstr *, int WaitStates) {
+      return WaitStates >= Limit;
+    };
+    return ::getWaitStatesSince(IsHazard, CurrCycleInstr, IsExpiredFn);
+  }
+
   int WaitStates = 0;
   for (MachineInstr *MI : EmittedInstrs) {
     if (MI) {
       if (IsHazard(MI))
         return WaitStates;
 
-      unsigned Opcode = MI->getOpcode();
-      if (Opcode == AMDGPU::INLINEASM)
+      if (MI->isInlineAsm())
         continue;
     }
     ++WaitStates;
+
+    if (WaitStates >= Limit)
+      break;
   }
   return std::numeric_limits<int>::max();
 }
 
-int GCNHazardRecognizer::getWaitStatesSinceDef(
-    unsigned Reg, function_ref<bool(MachineInstr *)> IsHazardDef) {
+int GCNHazardRecognizer::getWaitStatesSinceDef(unsigned Reg,
+                                               IsHazardFn IsHazardDef,
+                                               int Limit) {
   const SIRegisterInfo *TRI = ST.getRegisterInfo();
 
   auto IsHazardFn = [IsHazardDef, TRI, Reg] (MachineInstr *MI) {
     return IsHazardDef(MI) && MI->modifiesRegister(Reg, TRI);
   };
 
-  return getWaitStatesSince(IsHazardFn);
+  return getWaitStatesSince(IsHazardFn, Limit);
 }
 
-int GCNHazardRecognizer::getWaitStatesSinceSetReg(
-    function_ref<bool(MachineInstr *)> IsHazard) {
+int GCNHazardRecognizer::getWaitStatesSinceSetReg(IsHazardFn IsHazard,
+                                                  int Limit) {
   auto IsHazardFn = [IsHazard] (MachineInstr *MI) {
     return isSSetReg(MI->getOpcode()) && IsHazard(MI);
   };
 
-  return getWaitStatesSince(IsHazardFn);
+  return getWaitStatesSince(IsHazardFn, Limit);
 }
 
 //===----------------------------------------------------------------------===//
@@ -397,7 +475,8 @@ int GCNHazardRecognizer::checkSMRDHazards(MachineInstr *SMRD) {
     if (!Use.isReg())
       continue;
     int WaitStatesNeededForUse =
-        SmrdSgprWaitStates - getWaitStatesSinceDef(Use.getReg(), IsHazardDefFn);
+        SmrdSgprWaitStates - getWaitStatesSinceDef(Use.getReg(), IsHazardDefFn,
+                                                   SmrdSgprWaitStates);
     WaitStatesNeeded = std::max(WaitStatesNeeded, WaitStatesNeededForUse);
 
     // This fixes what appears to be undocumented hardware behavior in SI where
@@ -410,7 +489,8 @@ int GCNHazardRecognizer::checkSMRDHazards(MachineInstr *SMRD) {
     if (IsBufferSMRD) {
       int WaitStatesNeededForUse =
         SmrdSgprWaitStates - getWaitStatesSinceDef(Use.getReg(),
-                                                   IsBufferHazardDefFn);
+                                                   IsBufferHazardDefFn,
+                                                   SmrdSgprWaitStates);
       WaitStatesNeeded = std::max(WaitStatesNeeded, WaitStatesNeededForUse);
     }
   }
@@ -434,7 +514,8 @@ int GCNHazardRecognizer::checkVMEMHazards(MachineInstr* VMEM) {
       continue;
 
     int WaitStatesNeededForUse =
-        VmemSgprWaitStates - getWaitStatesSinceDef(Use.getReg(), IsHazardDefFn);
+        VmemSgprWaitStates - getWaitStatesSinceDef(Use.getReg(), IsHazardDefFn,
+                                                   VmemSgprWaitStates);
     WaitStatesNeeded = std::max(WaitStatesNeeded, WaitStatesNeededForUse);
   }
   return WaitStatesNeeded;
@@ -454,13 +535,16 @@ int GCNHazardRecognizer::checkDPPHazards(MachineInstr *DPP) {
     if (!Use.isReg() || !TRI->isVGPR(MF.getRegInfo(), Use.getReg()))
       continue;
     int WaitStatesNeededForUse =
-        DppVgprWaitStates - getWaitStatesSinceDef(Use.getReg());
+        DppVgprWaitStates - getWaitStatesSinceDef(Use.getReg(),
+                              [](MachineInstr *) { return true; },
+                              DppVgprWaitStates);
     WaitStatesNeeded = std::max(WaitStatesNeeded, WaitStatesNeededForUse);
   }
 
   WaitStatesNeeded = std::max(
       WaitStatesNeeded,
-      DppExecWaitStates - getWaitStatesSinceDef(AMDGPU::EXEC, IsHazardDefFn));
+      DppExecWaitStates - getWaitStatesSinceDef(AMDGPU::EXEC, IsHazardDefFn,
+                                                DppExecWaitStates));
 
   return WaitStatesNeeded;
 }
@@ -472,7 +556,8 @@ int GCNHazardRecognizer::checkDivFMasHazards(MachineInstr *DivFMas) {
   // instruction.
   const int DivFMasWaitStates = 4;
   auto IsHazardDefFn = [TII] (MachineInstr *MI) { return TII->isVALU(*MI); };
-  int WaitStatesNeeded = getWaitStatesSinceDef(AMDGPU::VCC, IsHazardDefFn);
+  int WaitStatesNeeded = getWaitStatesSinceDef(AMDGPU::VCC, IsHazardDefFn,
+                                               DivFMasWaitStates);
 
   return DivFMasWaitStates - WaitStatesNeeded;
 }
@@ -485,7 +570,7 @@ int GCNHazardRecognizer::checkGetRegHazards(MachineInstr *GetRegInstr) {
   auto IsHazardFn = [TII, GetRegHWReg] (MachineInstr *MI) {
     return GetRegHWReg == getHWReg(TII, *MI);
   };
-  int WaitStatesNeeded = getWaitStatesSinceSetReg(IsHazardFn);
+  int WaitStatesNeeded = getWaitStatesSinceSetReg(IsHazardFn, GetRegWaitStates);
 
   return GetRegWaitStates - WaitStatesNeeded;
 }
@@ -499,7 +584,7 @@ int GCNHazardRecognizer::checkSetRegHazards(MachineInstr *SetRegInstr) {
   auto IsHazardFn = [TII, HWReg] (MachineInstr *MI) {
     return HWReg == getHWReg(TII, *MI);
   };
-  int WaitStatesNeeded = getWaitStatesSinceSetReg(IsHazardFn);
+  int WaitStatesNeeded = getWaitStatesSinceSetReg(IsHazardFn, SetRegWaitStates);
   return SetRegWaitStates - WaitStatesNeeded;
 }
 
@@ -570,7 +655,7 @@ int GCNHazardRecognizer::checkVALUHazardsHelper(const MachineOperand &Def,
     TRI->regsOverlap(MI->getOperand(DataIdx).getReg(), Reg);
   };
   int WaitStatesNeededForDef =
-    VALUWaitStates - getWaitStatesSince(IsHazardFn);
+    VALUWaitStates - getWaitStatesSince(IsHazardFn, VALUWaitStates);
   WaitStatesNeeded = std::max(WaitStatesNeeded, WaitStatesNeededForDef);
 
   return WaitStatesNeeded;
@@ -635,7 +720,8 @@ int GCNHazardRecognizer::checkRWLaneHazards(MachineInstr *RWLane) {
   };
 
   const int RWLaneWaitStates = 4;
-  int WaitStatesSince = getWaitStatesSinceDef(LaneSelectReg, IsHazardFn);
+  int WaitStatesSince = getWaitStatesSinceDef(LaneSelectReg, IsHazardFn,
+                                              RWLaneWaitStates);
   return RWLaneWaitStates - WaitStatesSince;
 }
 
@@ -650,7 +736,7 @@ int GCNHazardRecognizer::checkRFEHazards(MachineInstr *RFE) {
   auto IsHazardFn = [TII] (MachineInstr *MI) {
     return getHWReg(TII, *MI) == AMDGPU::Hwreg::ID_TRAPSTS;
   };
-  int WaitStatesNeeded = getWaitStatesSinceSetReg(IsHazardFn);
+  int WaitStatesNeeded = getWaitStatesSinceSetReg(IsHazardFn, RFEWaitStates);
   return RFEWaitStates - WaitStatesNeeded;
 }
 
@@ -674,7 +760,8 @@ int GCNHazardRecognizer::checkAnyInstHazards(MachineInstr *MI) {
       return MI->getOpcode() == AMDGPU::S_MOV_FED_B32;
     };
     int WaitStatesNeededForUse =
-        MovFedWaitStates - getWaitStatesSinceDef(Use.getReg(), IsHazardFn);
+        MovFedWaitStates - getWaitStatesSinceDef(Use.getReg(), IsHazardFn,
+                                                 MovFedWaitStates);
     WaitStatesNeeded = std::max(WaitStatesNeeded, WaitStatesNeededForUse);
   }
 
@@ -687,5 +774,6 @@ int GCNHazardRecognizer::checkReadM0Hazards(MachineInstr *MI) {
   auto IsHazardFn = [TII] (MachineInstr *MI) {
     return TII->isSALU(*MI);
   };
-  return SMovRelWaitStates - getWaitStatesSinceDef(AMDGPU::M0, IsHazardFn);
+  return SMovRelWaitStates - getWaitStatesSinceDef(AMDGPU::M0, IsHazardFn,
+                                                   SMovRelWaitStates);
 }
diff --git a/lib/Target/AMDGPU/GCNHazardRecognizer.h b/lib/Target/AMDGPU/GCNHazardRecognizer.h
index cc29d74a548..2a6a2deed2c 100644
--- a/lib/Target/AMDGPU/GCNHazardRecognizer.h
+++ b/lib/Target/AMDGPU/GCNHazardRecognizer.h
@@ -30,6 +30,13 @@ class SIRegisterInfo;
 class GCNSubtarget;
 
 class GCNHazardRecognizer final : public ScheduleHazardRecognizer {
+public:
+  typedef function_ref<bool(MachineInstr *)> IsHazardFn;
+
+private:
+  // Distinguish if we are called from scheduler or hazard recognizer
+  bool IsHazardRecognizerMode;
+
   // This variable stores the instruction that has been emitted this cycle. It
   // will be added to EmittedInstrs, when AdvanceCycle() or RecedeCycle() is
   // called.
@@ -53,11 +60,9 @@ class GCNHazardRecognizer final : public ScheduleHazardRecognizer {
 
   void addClauseInst(const MachineInstr &MI);
 
-  int getWaitStatesSince(function_ref<bool(MachineInstr *)> IsHazard);
-  int getWaitStatesSinceDef(unsigned Reg,
-                            function_ref<bool(MachineInstr *)> IsHazardDef =
-                                [](MachineInstr *) { return true; });
-  int getWaitStatesSinceSetReg(function_ref<bool(MachineInstr *)> IsHazard);
+  int getWaitStatesSince(IsHazardFn IsHazard, int Limit);
+  int getWaitStatesSinceDef(unsigned Reg, IsHazardFn IsHazardDef, int Limit);
+  int getWaitStatesSinceSetReg(IsHazardFn IsHazard, int Limit);
 
   int checkSoftClauseHazards(MachineInstr *SMEM);
   int checkSMRDHazards(MachineInstr *SMRD);
@@ -84,6 +89,7 @@ public:
   void EmitNoop() override;
   unsigned PreEmitNoops(SUnit *SU) override;
   unsigned PreEmitNoops(MachineInstr *) override;
+  unsigned PreEmitNoopsCommon(MachineInstr *);
   void AdvanceCycle() override;
   void RecedeCycle() override;
 };
diff --git a/lib/Target/AMDGPU/SIInstrInfo.cpp b/lib/Target/AMDGPU/SIInstrInfo.cpp
index 595945e11f1..88bab949a81 100644
--- a/lib/Target/AMDGPU/SIInstrInfo.cpp
+++ b/lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -1152,7 +1152,7 @@ void SIInstrInfo::insertReturn(MachineBasicBlock &MBB) const {
   }
 }
 
-unsigned SIInstrInfo::getNumWaitStates(const MachineInstr &MI) const {
+unsigned SIInstrInfo::getNumWaitStates(const MachineInstr &MI) {
   switch (MI.getOpcode()) {
   default: return 1; // FIXME: Do wait states equal cycles?
 
diff --git a/lib/Target/AMDGPU/SIInstrInfo.h b/lib/Target/AMDGPU/SIInstrInfo.h
index de250b9c62c..bdc53f6257e 100644
--- a/lib/Target/AMDGPU/SIInstrInfo.h
+++ b/lib/Target/AMDGPU/SIInstrInfo.h
@@ -837,7 +837,7 @@ public:
   void insertReturn(MachineBasicBlock &MBB) const;
   /// Return the number of wait states that result from executing this
   /// instruction.
-  unsigned getNumWaitStates(const MachineInstr &MI) const;
+  static unsigned getNumWaitStates(const MachineInstr &MI);
 
   /// Returns the operand named \p Op.  If \p MI does not have an
   /// operand named \c Op, this function returns nullptr.
diff --git a/test/CodeGen/AMDGPU/vmem-vcc-hazard.mir b/test/CodeGen/AMDGPU/vmem-vcc-hazard.mir
new file mode 100644
index 00000000000..5ccdf14031c
--- /dev/null
+++ b/test/CodeGen/AMDGPU/vmem-vcc-hazard.mir
@@ -0,0 +1,230 @@
+# RUN: llc -march=amdgcn -mcpu=fiji -verify-machineinstrs -run-pass post-RA-hazard-rec -o - %s | FileCheck -check-prefix=GCN %s
+
+# GCN-LABEL: name: vmem_vcc_fallthrough
+# GCN:      bb.1:
+# GCN-NEXT: S_NOP
+# GCN-NEXT: S_NOP
+# GCN-NEXT: S_NOP
+# GCN-NEXT: S_NOP
+# GCN-NEXT: S_NOP
+# GCN-NEXT: BUFFER_LOAD_DWORD_OFFEN
+---
+name:            vmem_vcc_fallthrough
+body:             |
+  bb.0:
+    successors: %bb.1
+
+    $sgpr0_sgpr1_sgpr2_sgpr3 = IMPLICIT_DEF
+    $vgpr0 = IMPLICIT_DEF
+    $vgpr1 = V_ADDC_U32_e32 $vgpr0, $vgpr0, implicit-def $vcc, implicit $vcc, implicit $exec
+
+  bb.1:
+    $vgpr1 = BUFFER_LOAD_DWORD_OFFEN $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, $vcc_lo, 0, 0, 0, 0, implicit $exec
+...
+# GCN-LABEL: name: vmem_vcc_branch_to_next
+# GCN:      bb.1:
+# GCN-NEXT: S_NOP
+# GCN-NEXT: S_NOP
+# GCN-NEXT: S_NOP
+# GCN-NEXT: S_NOP
+# GCN-NEXT: BUFFER_LOAD_DWORD_OFFEN
+---
+name:            vmem_vcc_branch_to_next
+body:             |
+  bb.0:
+    successors: %bb.1
+
+    $sgpr0_sgpr1_sgpr2_sgpr3 = IMPLICIT_DEF
+    $vgpr0 = IMPLICIT_DEF
+    $vgpr1 = V_ADDC_U32_e32 $vgpr0, $vgpr0, implicit-def $vcc, implicit $vcc, implicit $exec
+    S_BRANCH %bb.1
+
+  bb.1:
+    $vgpr1 = BUFFER_LOAD_DWORD_OFFEN $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, $vcc_lo, 0, 0, 0, 0, implicit $exec
+...
+# GCN-LABEL: name: vmem_vcc_fallthrough_no_hazard_too_far
+# GCN:      bb.1:
+# GCN-NEXT: BUFFER_LOAD_DWORD_OFFEN
+---
+name:            vmem_vcc_fallthrough_no_hazard_too_far
+body:             |
+  bb.0:
+    successors: %bb.1
+
+    $sgpr0_sgpr1_sgpr2_sgpr3 = IMPLICIT_DEF
+    $vgpr0 = IMPLICIT_DEF
+    $vgpr1 = V_ADDC_U32_e32 $vgpr0, $vgpr0, implicit-def $vcc, implicit $vcc, implicit $exec
+    $sgpr0 = S_MOV_B32 0
+    $sgpr0 = S_MOV_B32 0
+    $sgpr0 = S_MOV_B32 0
+    $sgpr0 = S_MOV_B32 0
+    $sgpr0 = S_MOV_B32 0
+
+  bb.1:
+    $vgpr1 = BUFFER_LOAD_DWORD_OFFEN $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, $vcc_lo, 0, 0, 0, 0, implicit $exec
+...
+# GCN-LABEL: name: vmem_vcc_fallthrough_no_hazard_nops
+# GCN:      bb.1:
+# GCN-NEXT: BUFFER_LOAD_DWORD_OFFEN
+---
+name:            vmem_vcc_fallthrough_no_hazard_nops
+body:             |
+  bb.0:
+    successors: %bb.1
+
+    $sgpr0_sgpr1_sgpr2_sgpr3 = IMPLICIT_DEF
+    $vgpr0 = IMPLICIT_DEF
+    $vgpr1 = V_ADDC_U32_e32 $vgpr0, $vgpr0, implicit-def $vcc, implicit $vcc, implicit $exec
+    S_NOP 4
+
+  bb.1:
+    $vgpr1 = BUFFER_LOAD_DWORD_OFFEN $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, $vcc_lo, 0, 0, 0, 0, implicit $exec
+...
+# GCN-LABEL: name: vmem_vcc_branch_around
+# GCN:      bb.2:
+# GCN-NEXT: S_NOP
+# GCN-NEXT: S_NOP
+# GCN-NEXT: S_NOP
+# GCN-NEXT: S_NOP
+# GCN-NEXT: BUFFER_LOAD_DWORD_OFFEN
+---
+name:            vmem_vcc_branch_around
+body:             |
+  bb.0:
+    successors: %bb.2
+
+    $sgpr0_sgpr1_sgpr2_sgpr3 = IMPLICIT_DEF
+    $vgpr0 = IMPLICIT_DEF
+    $vgpr1 = V_ADDC_U32_e32 $vgpr0, $vgpr0, implicit-def $vcc, implicit $vcc, implicit $exec
+    S_BRANCH %bb.2
+
+  bb.1:
+    successors: %bb.2
+
+    S_NOP 0
+    S_NOP 0
+    S_NOP 0
+    S_NOP 0
+
+  bb.2:
+    $vgpr1 = BUFFER_LOAD_DWORD_OFFEN $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, $vcc_lo, 0, 0, 0, 0, implicit $exec
+...
+# GCN-LABEL: name: vmem_vcc_branch_backedge
+# GCN:      S_NOP
+# GCN-NEXT: S_NOP
+# GCN-NEXT: S_NOP
+# GCN-NEXT: S_NOP
+# GCN-NEXT: BUFFER_LOAD_DWORD_OFFEN
+---
+name:            vmem_vcc_branch_backedge
+body:             |
+  bb.0:
+    successors: %bb.1
+
+    $vgpr0 = IMPLICIT_DEF
+    $sgpr0_sgpr1_sgpr2_sgpr3 = IMPLICIT_DEF
+    $vgpr1 = BUFFER_LOAD_DWORD_OFFEN $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, $vcc_lo, 0, 0, 0, 0, implicit $exec
+
+  bb.1:
+    $vgpr0 = IMPLICIT_DEF
+    $vgpr1 = V_ADDC_U32_e32 $vgpr0, $vgpr0, implicit-def $vcc, implicit $vcc, implicit $exec
+    S_BRANCH %bb.0
+...
+# GCN-LABEL: name: vmem_vcc_min_of_two
+# GCN:      bb.2:
+# GCN-NEXT: S_NOP
+# GCN-NEXT: S_NOP
+# GCN-NEXT: S_NOP
+# GCN-NEXT: S_NOP
+# GCN-NEXT: S_NOP
+# GCN-NEXT: BUFFER_LOAD_DWORD_OFFEN
+---
+name:            vmem_vcc_min_of_two
+body:             |
+  bb.0:
+    successors: %bb.2
+
+    $sgpr0_sgpr1_sgpr2_sgpr3 = IMPLICIT_DEF
+    $vgpr0 = IMPLICIT_DEF
+    $vgpr1 = V_ADDC_U32_e32 $vgpr0, $vgpr0, implicit-def $vcc, implicit $vcc, implicit $exec
+    S_NOP 0
+    S_BRANCH %bb.2
+
+  bb.1:
+    successors: %bb.2
+
+    $vgpr1 = V_ADDC_U32_e32 $vgpr0, $vgpr0, implicit-def $vcc, implicit $vcc, implicit $exec
+
+  bb.2:
+    $vgpr1 = BUFFER_LOAD_DWORD_OFFEN $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, $vcc_lo, 0, 0, 0, 0, implicit $exec
+...
+# GCN-LABEL: name: vmem_vcc_self_loop
+# GCN:      S_NOP
+# GCN-NEXT: S_NOP
+# GCN-NEXT: S_NOP
+# GCN-NEXT: S_NOP
+# GCN-NEXT: BUFFER_LOAD_DWORD_OFFEN
+---
+name:            vmem_vcc_self_loop
+body:             |
+  bb.0:
+    successors: %bb.0
+
+    $vgpr0 = IMPLICIT_DEF
+    $sgpr0_sgpr1_sgpr2_sgpr3 = IMPLICIT_DEF
+    $vgpr1 = BUFFER_LOAD_DWORD_OFFEN $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, $vcc_lo, 0, 0, 0, 0, implicit $exec
+    $vgpr1 = V_ADDC_U32_e32 $vgpr0, $vgpr0, implicit-def $vcc, implicit $vcc, implicit $exec
+    S_BRANCH %bb.0
+...
+# GCN-LABEL: name: vmem_vcc_min_of_two_self_loop1
+# GCN:      bb.1:
+# GCN:      $sgpr0 = S_MOV_B32 0
+# GCN-NEXT: S_NOP
+# GCN-NEXT: S_NOP
+# GCN-NEXT: S_NOP
+# GCN-NEXT: S_NOP
+# GCN-NEXT: BUFFER_LOAD_DWORD_OFFEN
+---
+name:            vmem_vcc_min_of_two_self_loop1
+body:             |
+  bb.0:
+    successors: %bb.1
+
+    $sgpr0_sgpr1_sgpr2_sgpr3 = IMPLICIT_DEF
+    $vgpr0 = IMPLICIT_DEF
+    $vgpr1 = V_ADDC_U32_e32 $vgpr0, $vgpr0, implicit-def $vcc, implicit $vcc, implicit $exec
+
+  bb.1:
+    successors: %bb.1
+
+    $sgpr0 = S_MOV_B32 0
+    $vgpr1 = BUFFER_LOAD_DWORD_OFFEN $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, $vcc_lo, 0, 0, 0, 0, implicit $exec
+    $vgpr1 = V_ADDC_U32_e32 $vgpr1, $vgpr1, implicit-def $vcc, implicit $vcc, implicit $exec
+    S_BRANCH %bb.1
+...
+# GCN-LABEL: name: vmem_vcc_min_of_two_self_loop2
+# GCN:      bb.1:
+# GCN:      $sgpr0 = S_MOV_B32 0
+# GCN-NEXT: S_NOP
+# GCN-NEXT: S_NOP
+# GCN-NEXT: S_NOP
+# GCN-NEXT: BUFFER_LOAD_DWORD_OFFEN
+---
+name:            vmem_vcc_min_of_two_self_loop2
+body:             |
+  bb.0:
+    successors: %bb.1
+
+    $sgpr0_sgpr1_sgpr2_sgpr3 = IMPLICIT_DEF
+    $vgpr0 = IMPLICIT_DEF
+    $vgpr1 = V_ADDC_U32_e32 $vgpr0, $vgpr0, implicit-def $vcc, implicit $vcc, implicit $exec
+    S_NOP 0
+
+  bb.1:
+    successors: %bb.1
+
+    $sgpr0 = S_MOV_B32 0
+    $vgpr1 = BUFFER_LOAD_DWORD_OFFEN $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, $vcc_lo, 0, 0, 0, 0, implicit $exec
+    $vgpr1 = V_ADDC_U32_e32 $vgpr1, $vgpr1, implicit-def $vcc, implicit $vcc, implicit $exec
+    S_BRANCH %bb.1
+...