[AMDGPU] Come back patch for the 'Assign register class for cross block values according to the divergence.'

[alex-t]

Summary

After https://reviews.llvm.org/D59990 submit several issues were discovered.
Changes in common code were preserved but AMDGPU specific part was reverted to keep the backend working correctly.

Discovered issues were addressed in the following commits:

• https://reviews.llvm.org/D67662
• https://reviews.llvm.org/D67101
• https://reviews.llvm.org/D63953
• https://reviews.llvm.org/D63731

This change brings back AMDGPU specific changes.

[rampitec]

llvm/lib/Target/AMDGPU/SIISelLowering.cpp

10903

Why SetVector and not SmallPtrSet as usual?

10904

You can do if (!Visited.insert(V)) return false;

llvm/lib/Target/AMDGPU/SIInstrInfo.cpp

3978

What's wrong with isAGPR() call?

[arsenm]

llvm/lib/Target/AMDGPU/SIFixSGPRCopies.cpp

653

Can you split this into a function?

654

This isn't a bool, so shouldn't start with has

664

.isPhysical()

680–693

This seems to be reproducing SIInstrInfo::getOpRegClass

702

SrcReg.isVirtual()

llvm/lib/Target/AMDGPU/SIInstrInfo.cpp

3978

.isVirtual()

[alex-t]

Changed according reviewers requests.

[rampitec]

LGTM

[nhaehnle]

Thank you for persisting through this.

llvm/lib/Target/AMDGPU/SIFixSGPRCopies.cpp

813–814

LLVM coding style is to have the else on the same line as the }.

827–828

Same coding style remark.

llvm/lib/Target/AMDGPU/SIISelLowering.cpp

10903

The logic in this function seems needlessly convoluted. Instead of tracking Result, it should be possible to just return true in a number of places, right?

llvm/lib/Target/AMDGPU/SIFixSGPRCopies.cpp

for (unsigned I = 1, N = MI.getNumOperands(); I != N; I += 2) {
 
     MI.getOperand(I).setReg(TmpReg);
   }
 
   CopyUse.eraseFromParent();
   return true;
 }
 
-static bool phiHasVGPROperands(const MachineInstr &PHI,
-                               const MachineRegisterInfo &MRI,
-                               const SIRegisterInfo *TRI,
-                               const SIInstrInfo *TII) {
-  for (unsigned i = 1; i < PHI.getNumOperands(); i += 2) {
-    Register Reg = PHI.getOperand(i).getReg();
-    if (TRI->hasVGPRs(MRI.getRegClass(Reg)))
-      return true;
-  }
-  return false;
-}
-
-static bool phiHasBreakDef(const MachineInstr &PHI,
-                           const MachineRegisterInfo &MRI,
-                           SmallSet<unsigned, 8> &Visited) {
-  for (unsigned i = 1; i < PHI.getNumOperands(); i += 2) {
-    Register Reg = PHI.getOperand(i).getReg();
-    if (Visited.count(Reg))
-      continue;
-
-    Visited.insert(Reg);
-
-    MachineInstr *DefInstr = MRI.getVRegDef(Reg);
-    switch (DefInstr->getOpcode()) {
-    default:
-      break;
-    case AMDGPU::SI_IF_BREAK:
-      return true;
-    case AMDGPU::PHI:
-      if (phiHasBreakDef(*DefInstr, MRI, Visited))
-        return true;
-    }
-  }
-  return false;
-}
-
-static bool hasTerminatorThatModifiesExec(const MachineBasicBlock &MBB,
-                                          const TargetRegisterInfo &TRI) {
-  for (MachineBasicBlock::const_iterator I = MBB.getFirstTerminator(),
-       E = MBB.end(); I != E; ++I) {
-    if (I->modifiesRegister(AMDGPU::EXEC, &TRI))
-      return true;
-  }
-  return false;
-}
-
 static bool isSafeToFoldImmIntoCopy(const MachineInstr *Copy,
                                     const MachineInstr *MoveImm,
                                     const SIInstrInfo *TII,
                                     unsigned &SMovOp,
                                     int64_t &Imm) {
   if (Copy->getOpcode() != AMDGPU::COPY)
     return false;
 
if (Predicate(MBB))
       return true;
 
     Worklist.append(MBB->pred_begin(), MBB->pred_end());
   }
 
   return false;
 }
 
-static bool predsHasDivergentTerminator(MachineBasicBlock *MBB,
-                                        const TargetRegisterInfo *TRI) {
-  return searchPredecessors(MBB, nullptr, [TRI](MachineBasicBlock *MBB) {
-           return hasTerminatorThatModifiesExec(*MBB, *TRI); });
-}
-
 // Checks if there is potential path From instruction To instruction.
 // If CutOff is specified and it sits in between of that path we ignore
 // a higher portion of the path and report it is not reachable.
 static bool isReachable(const MachineInstr *From,
                         const MachineInstr *To,
                         const MachineBasicBlock *CutOff,
                         MachineDominatorTree &MDT) {
   // If either From block dominates To block or instructions are in the same
for (MachineBasicBlock::iterator I = MBB.begin(), E = MBB.end();
           }
           TII->moveToVALU(MI, MDT);
         } else if (isSGPRToVGPRCopy(SrcRC, DstRC, *TRI)) {
           tryChangeVGPRtoSGPRinCopy(MI, TRI, TII);
         }
 
         break;
       }
       case AMDGPU::PHI: {
-        Register Reg = MI.getOperand(0).getReg();
-        if (!TRI->isSGPRClass(MRI.getRegClass(Reg)))
-          break;
+        unsigned hasVGPRUses = 0;
+        SetVector<const MachineInstr *> worklist;
+        worklist.insert(&MI);
+        while (!worklist.empty()) {
+          const MachineInstr *Instr = worklist.pop_back_val();
+          unsigned Reg = Instr->getOperand(0).getReg();
+          for (const auto &Use : MRI.use_operands(Reg)) {
+            const MachineInstr *UseMI = Use.getParent();
+            if (UseMI->isCopy() || UseMI->isRegSequence()) {
+              if (UseMI->isCopy() &&
+                  Register::isPhysicalRegister(UseMI->getOperand(0).getReg()) &&
+                  !TRI->isSGPRReg(MRI, UseMI->getOperand(0).getReg())) {
+                hasVGPRUses++;
+              }
+              worklist.insert(UseMI);
+              continue;
+            }
 
-        // We don't need to fix the PHI if the common dominator of the
-        // two incoming blocks terminates with a uniform branch.
-        bool HasVGPROperand = phiHasVGPROperands(MI, MRI, TRI, TII);
-        if (MI.getNumExplicitOperands() == 5 && !HasVGPROperand) {
-          MachineBasicBlock *MBB0 = MI.getOperand(2).getMBB();
-          MachineBasicBlock *MBB1 = MI.getOperand(4).getMBB();
+            if (UseMI->isPHI()) {
+              const TargetRegisterClass *UseRC = MRI.getRegClass(Use.getReg());
+              if (!TRI->isSGPRReg(MRI, Use.getReg()) &&
+                  UseRC != &AMDGPU::VReg_1RegClass)
+                hasVGPRUses++;
+              continue;
+            }
 
-          if (!predsHasDivergentTerminator(MBB0, TRI) &&
-              !predsHasDivergentTerminator(MBB1, TRI)) {
-            LLVM_DEBUG(dbgs()
-                       << "Not fixing PHI for uniform branch: " << MI << '\n');
+            unsigned OpNo = UseMI->getOperandNo(&Use);
+            const MCInstrDesc &Desc = TII->get(UseMI->getOpcode());
+            if (!Desc.isPseudo() && Desc.OpInfo &&
+                OpNo < Desc.getNumOperands() &&
+                Desc.OpInfo[OpNo].RegClass != -1) {
+              const TargetRegisterClass *OpRC =
+                  TRI->getRegClass(Desc.OpInfo[OpNo].RegClass);
+              if (!TRI->isSGPRClass(OpRC) && OpRC != &AMDGPU::VS_32RegClass &&
+                  OpRC != &AMDGPU::VS_64RegClass) {
+                hasVGPRUses++;
+              }
+            }
+          }
+        }
+        bool hasVGPRInput = false;
+        for (unsigned i = 1; i < MI.getNumOperands(); i += 2) {
+          unsigned InputReg = MI.getOperand(i).getReg();
+          MachineInstr *Def = MRI.getVRegDef(InputReg);
+          if (TRI->isVGPR(MRI, InputReg)) {
+            if (Def->isCopy()) {
+              unsigned SrcReg = Def->getOperand(1).getReg();
+              const TargetRegisterClass *RC =
+                  Register::isVirtualRegister(SrcReg)
+                      ? MRI.getRegClass(SrcReg)
+                      : TRI->getPhysRegClass(SrcReg);
+              if (TRI->isSGPRClass(RC))
+                continue;
+            }
+            hasVGPRInput = true;
+            break;
+          } else if (Def->isCopy() &&
+                     TRI->isVGPR(MRI, Def->getOperand(1).getReg())) {
+            hasVGPRInput = true;
             break;
           }
         }
+        unsigned PHIRes = MI.getOperand(0).getReg();
+        const TargetRegisterClass *RC0 = MRI.getRegClass(PHIRes);
 
-        // If a PHI node defines an SGPR and any of its operands are VGPRs,
-        // then we need to move it to the VALU.
-        //
-        // Also, if a PHI node defines an SGPR and has all SGPR operands
-        // we must move it to the VALU, because the SGPR operands will
-        // all end up being assigned the same register, which means
-        // there is a potential for a conflict if different threads take
-        // different control flow paths.
-        //
-        // For Example:
-        //
-        // sgpr0 = def;
-        // ...
-        // sgpr1 = def;
-        // ...
-        // sgpr2 = PHI sgpr0, sgpr1
-        // use sgpr2;
-        //
-        // Will Become:
-        //
-        // sgpr2 = def;
-        // ...
-        // sgpr2 = def;
-        // ...
-        // use sgpr2
-        //
-        // The one exception to this rule is when one of the operands
-        // is defined by a SI_BREAK, SI_IF_BREAK, or SI_ELSE_BREAK
-        // instruction.  In this case, there we know the program will
-        // never enter the second block (the loop) without entering
-        // the first block (where the condition is computed), so there
-        // is no chance for values to be over-written.
-
-        SmallSet<unsigned, 8> Visited;
-        if (HasVGPROperand || !phiHasBreakDef(MI, MRI, Visited)) {
+        if ((!TRI->isVGPR(MRI, PHIRes) && RC0 != &AMDGPU::VReg_1RegClass) &&
+            (hasVGPRInput || hasVGPRUses > 1)) {
           LLVM_DEBUG(dbgs() << "Fixing PHI: " << MI);
-          TII->moveToVALU(MI, MDT);
+          TII->moveToVALU(MI);
+        } else {
+          LLVM_DEBUG(dbgs() << "Legalizing PHI: " << MI);
+          TII->legalizeOperands(MI, MDT);
         }
 
         break;
       }
       case AMDGPU::REG_SEQUENCE:
         if (TRI->hasVectorRegisters(TII->getOpRegClass(MI, 0)) ||
             !hasVectorOperands(MI, TRI)) {
           foldVGPRCopyIntoRegSequence(MI, TRI, TII, MRI);
for (MachineBasicBlock::iterator I = MBB.begin(), E = MBB.end();
       }
     }
   }
 
   if (MF.getTarget().getOptLevel() > CodeGenOpt::None && EnableM0Merge)
     hoistAndMergeSGPRInits(AMDGPU::M0, MRI, TRI, *MDT, TII);
 
   return true;
 }

llvm/lib/Target/AMDGPU/SIISelLowering.h

public:
   bool denormalsEnabledForType(EVT VT) const;
 
   bool isKnownNeverNaNForTargetNode(SDValue Op,
                                     const SelectionDAG &DAG,
                                     bool SNaN = false,
                                     unsigned Depth = 0) const override;
   AtomicExpansionKind shouldExpandAtomicRMWInIR(AtomicRMWInst *) const override;
 
+  virtual const TargetRegisterClass *
+  getRegClassFor(MVT VT, bool isDivergent) const override;
+  virtual bool requiresUniformRegister(MachineFunction &MF,
+                                       const Value *V) const override;
   Align getPrefLoopAlignment(MachineLoop *ML) const override;
 
   void allocateHSAUserSGPRs(CCState &CCInfo,
                             MachineFunction &MF,
                             const SIRegisterInfo &TRI,
                             SIMachineFunctionInfo &Info) const;
 
   void allocateSystemSGPRs(CCState &CCInfo,

llvm/lib/Target/AMDGPU/SIISelLowering.cpp

return (AS == AMDGPUAS::LOCAL_ADDRESS && Subtarget->hasLDSFPAtomics()) ?
       AtomicExpansionKind::None : AtomicExpansionKind::CmpXChg;
   }
   default:
     break;
   }
 
   return AMDGPUTargetLowering::shouldExpandAtomicRMWInIR(RMW);
 }
+
+const TargetRegisterClass *
+SITargetLowering::getRegClassFor(MVT VT, bool isDivergent) const {
+  const TargetRegisterClass *RC = TargetLoweringBase::getRegClassFor(VT, false);
+  const SIRegisterInfo *TRI = Subtarget->getRegisterInfo();
+  if (RC == &AMDGPU::VReg_1RegClass && !isDivergent)
+    return Subtarget->getWavefrontSize() == 64 ? &AMDGPU::SReg_64RegClass
+                                               : &AMDGPU::SReg_32RegClass;
+  if (!TRI->isSGPRClass(RC) && !isDivergent)
+    return TRI->getEquivalentSGPRClass(RC);
+  else if (TRI->isSGPRClass(RC) && isDivergent)
+    return TRI->getEquivalentVGPRClass(RC);
+
+  return RC;
+}
+
+static bool hasCFUser(const Value *V, SetVector<const Value *> &Visited) {
+  if (Visited.count(V))
+    return false;
+  Visited.insert(V);
+  bool Result = false;
+  for (auto U : V->users()) {
+    if (const IntrinsicInst *Intrinsic = dyn_cast<IntrinsicInst>(U)) {
+      if (V == U->getOperand(1)) {
+        switch (Intrinsic->getIntrinsicID()) {
+        default:
+          Result = false;
+          break;
+        case Intrinsic::amdgcn_if_break:
+        case Intrinsic::amdgcn_if:
+        case Intrinsic::amdgcn_else:
+          Result = true;
+          break;
+        }
+      }
+      if (V == U->getOperand(0)) {
+        switch (Intrinsic->getIntrinsicID()) {
+        default:
+          Result = false;
+          break;
+        case Intrinsic::amdgcn_end_cf:
+        case Intrinsic::amdgcn_loop:
+          Result = true;
+          break;
+        }
+      }
+    } else {
+      Result = hasCFUser(U, Visited);
+    }
+    if (Result)
+      break;
+  }
+  return Result;
+}
+
+bool SITargetLowering::requiresUniformRegister(MachineFunction &MF,
+                                               const Value *V) const {
+  if (const IntrinsicInst *Intrinsic = dyn_cast<IntrinsicInst>(V)) {
+    switch (Intrinsic->getIntrinsicID()) {
+    default:
+      return false;
+    case Intrinsic::amdgcn_if_break:
+      return true;
+    }
+  }
+  if (const ExtractValueInst *ExtValue = dyn_cast<ExtractValueInst>(V)) {
+    if (const IntrinsicInst *Intrinsic =
+            dyn_cast<IntrinsicInst>(ExtValue->getOperand(0))) {
+      switch (Intrinsic->getIntrinsicID()) {
+      default:
+        return false;
+      case Intrinsic::amdgcn_if:
+      case Intrinsic::amdgcn_else: {
+        ArrayRef<unsigned> Indices = ExtValue->getIndices();
+        if (Indices.size() == 1 && Indices[0] == 1) {
+          return true;
+        }
+      }
+      }
+    }
+  }
+  if (const CallInst *CI = dyn_cast<CallInst>(V)) {
+    if (isa<InlineAsm>(CI->getCalledValue())) {
+      const SIRegisterInfo *SIRI = Subtarget->getRegisterInfo();
+      ImmutableCallSite CS(CI);
+      TargetLowering::AsmOperandInfoVector TargetConstraints = ParseConstraints(
+          MF.getDataLayout(), Subtarget->getRegisterInfo(), CS);
+      for (auto &TC : TargetConstraints) {
+        if (TC.Type == InlineAsm::isOutput) {
+          ComputeConstraintToUse(TC, SDValue());
+          unsigned AssignedReg;
+          const TargetRegisterClass *RC;
+          std::tie(AssignedReg, RC) = getRegForInlineAsmConstraint(
+              SIRI, TC.ConstraintCode, TC.ConstraintVT);
+          if (RC) {
+            MachineRegisterInfo &MRI = MF.getRegInfo();
+            if (AssignedReg != 0 && SIRI->isSGPRReg(MRI, AssignedReg))
+              return true;
+            else if (SIRI->isSGPRClass(RC))
+              return true;
+          }
+        }
+      }
+    }
+  }
+  SetVector<const Value *> Visited;
+  return hasCFUser(V, Visited);
+}

llvm/lib/Target/AMDGPU/SIInstrInfo.cpp

if (Src1.isReg() && RI.isVGPR(MRI, Src1.getReg())) {
       BuildMI(*MI.getParent(), MI, DL, get(AMDGPU::V_READFIRSTLANE_B32), Reg)
           .add(Src1);
       Src1.ChangeToRegister(Reg, false);
     }
     return;
   }
 
   // No VOP2 instructions support AGPRs.
-  if (Src0.isReg() && RI.isAGPR(MRI, Src0.getReg()))
+  if (Src0.isReg() && RI.hasAGPRs(Register::isVirtualRegister(Src0.getReg())
+                                      ? MRI.getRegClass(Src0.getReg())
+                                      : RI.getPhysRegClass(Src0.getReg())))
     legalizeOpWithMove(MI, Src0Idx);
 
-  if (Src1.isReg() && RI.isAGPR(MRI, Src1.getReg()))
+  if (Src1.isReg() && RI.hasAGPRs(Register::isVirtualRegister(Src1.getReg())
+                                      ? MRI.getRegClass(Src1.getReg())
+                                      : RI.getPhysRegClass(Src1.getReg())))
     legalizeOpWithMove(MI, Src1Idx);
 
   // VOP2 src0 instructions support all operand types, so we don't need to check
   // their legality. If src1 is already legal, we don't need to do anything.
   if (isLegalRegOperand(MRI, InstrDesc.OpInfo[Src1Idx], Src1))
     return;
 
   // Special case: V_READLANE_B32 accepts only immediate or SGPR operands for
void SIInstrInfo::legalizeGenericOperand(MachineBasicBlock &InsertMBB,
   Op.setReg(DstReg);
   Op.setSubReg(0);
 
   MachineInstr *Def = MRI.getVRegDef(OpReg);
   if (!Def)
     return;
 
   // Try to eliminate the copy if it is copying an immediate value.
-  if (Def->isMoveImmediate())
+  if (Def->isMoveImmediate() && DstRC != &AMDGPU::VReg_1RegClass)
     FoldImmediate(*Copy, *Def, OpReg, &MRI);
 
   bool ImpDef = Def->isImplicitDef();
   while (!ImpDef && Def && Def->isCopy()) {
     Def = MRI.getUniqueVRegDef(Def->getOperand(1).getReg());
     ImpDef = Def && Def->isImplicitDef();
   }
   if (!RI.isSGPRClass(DstRC) && !Copy->readsRegister(AMDGPU::EXEC, &RI) &&
if (MI.getOpcode() == AMDGPU::PHI) {
     }
 
     // If any of the operands are VGPR registers, then they all most be
     // otherwise we will create illegal VGPR->SGPR copies when legalizing
     // them.
     if (VRC || !RI.isSGPRClass(getOpRegClass(MI, 0))) {
       if (!VRC) {
         assert(SRC);
-        VRC = RI.hasAGPRs(getOpRegClass(MI, 0)) ? RI.getEquivalentAGPRClass(SRC)
-                                                : RI.getEquivalentVGPRClass(SRC);
+        if (getOpRegClass(MI, 0) == &AMDGPU::VReg_1RegClass) {
+          VRC = &AMDGPU::VReg_1RegClass;
+        } else
+          VRC = RI.hasAGPRs(getOpRegClass(MI, 0))
+                    ? RI.getEquivalentAGPRClass(SRC)
       }
       RC = VRC;
     } else {
       RC = SRC;
     }
 
     // Update all the operands so they have the same type.
     for (unsigned I = 1, E = MI.getNumOperands(); I != E; I += 2) {
if (RI.hasAGPRs(SrcRC)) {
         break;
       default:
         NewDstRC = RI.getEquivalentVGPRClass(NewDstRC);
       }
 
       if (!NewDstRC)
         return nullptr;
     } else {
-       if (RI.hasVGPRs(NewDstRC))
+      if (RI.hasVGPRs(NewDstRC) || NewDstRC == &AMDGPU::VReg_1RegClass)
         return nullptr;
 
       NewDstRC = RI.getEquivalentVGPRClass(NewDstRC);
       if (!NewDstRC)
         return nullptr;
     }
 
     return NewDstRC;

llvm/test/CodeGen/AMDGPU/atomicrmw-nand.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
 
 define i32 @atomic_nand_i32_lds(i32 addrspace(3)* %ptr) nounwind {
 ; GCN-LABEL: atomic_nand_i32_lds:
 ; GCN:       ; %bb.0:
 ; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GCN-NEXT:    ds_read_b32 v2, v0
+; GCN-NEXT:    ds_read_b32 v1, v0
 ; GCN-NEXT:    s_mov_b64 s[4:5], 0
 ; GCN-NEXT:  BB0_1: ; %atomicrmw.start
 ; GCN-NEXT:    ; =>This Inner Loop Header: Depth=1
 ; GCN-NEXT:    s_waitcnt lgkmcnt(0)
+; GCN-NEXT:    v_mov_b32_e32 v2, v1
 ; GCN-NEXT:    v_not_b32_e32 v1, v2
 ; GCN-NEXT:    v_or_b32_e32 v1, -5, v1
 ; GCN-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
 ; GCN-NEXT:    ds_cmpst_rtn_b32 v1, v0, v2, v1
 ; GCN-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
 ; GCN-NEXT:    buffer_wbinvl1_vol
 ; GCN-NEXT:    v_cmp_eq_u32_e32 vcc, v1, v2
-; GCN-NEXT:    v_mov_b32_e32 v2, v1
 ; GCN-NEXT:    s_or_b64 s[4:5], vcc, s[4:5]
 ; GCN-NEXT:    s_andn2_b64 exec, exec, s[4:5]
 ; GCN-NEXT:    s_cbranch_execnz BB0_1
 ; GCN-NEXT:  ; %bb.2: ; %atomicrmw.end
 ; GCN-NEXT:    s_or_b64 exec, exec, s[4:5]
 ; GCN-NEXT:    v_mov_b32_e32 v0, v1
 ; GCN-NEXT:    s_setpc_b64 s[30:31]
   %result = atomicrmw nand i32 addrspace(3)* %ptr, i32 4 seq_cst
   ret i32 %result
 }
 
 define i32 @atomic_nand_i32_global(i32 addrspace(1)* %ptr) nounwind {
 ; GCN-LABEL: atomic_nand_i32_global:
 ; GCN:       ; %bb.0:
 ; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GCN-NEXT:    global_load_dword v3, v[0:1], off
+; GCN-NEXT:    global_load_dword v2, v[0:1], off
 ; GCN-NEXT:    s_mov_b64 s[4:5], 0
 ; GCN-NEXT:  BB1_1: ; %atomicrmw.start
 ; GCN-NEXT:    ; =>This Inner Loop Header: Depth=1
 ; GCN-NEXT:    s_waitcnt vmcnt(0)
+; GCN-NEXT:    v_mov_b32_e32 v3, v2
 ; GCN-NEXT:    v_not_b32_e32 v2, v3
 ; GCN-NEXT:    v_or_b32_e32 v2, -5, v2
 ; GCN-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
 ; GCN-NEXT:    global_atomic_cmpswap v2, v[0:1], v[2:3], off glc
 ; GCN-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
 ; GCN-NEXT:    buffer_wbinvl1_vol
 ; GCN-NEXT:    v_cmp_eq_u32_e32 vcc, v2, v3
-; GCN-NEXT:    v_mov_b32_e32 v3, v2
 ; GCN-NEXT:    s_or_b64 s[4:5], vcc, s[4:5]
 ; GCN-NEXT:    s_andn2_b64 exec, exec, s[4:5]
 ; GCN-NEXT:    s_cbranch_execnz BB1_1
 ; GCN-NEXT:  ; %bb.2: ; %atomicrmw.end
 ; GCN-NEXT:    s_or_b64 exec, exec, s[4:5]
 ; GCN-NEXT:    v_mov_b32_e32 v0, v2
 ; GCN-NEXT:    s_setpc_b64 s[30:31]
   %result = atomicrmw nand i32 addrspace(1)* %ptr, i32 4 seq_cst
   ret i32 %result
 }
 
 define i32 @atomic_nand_i32_flat(i32* %ptr) nounwind {
 ; GCN-LABEL: atomic_nand_i32_flat:
 ; GCN:       ; %bb.0:
 ; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GCN-NEXT:    flat_load_dword v3, v[0:1]
+; GCN-NEXT:    flat_load_dword v2, v[0:1]
 ; GCN-NEXT:    s_mov_b64 s[4:5], 0
 ; GCN-NEXT:  BB2_1: ; %atomicrmw.start
 ; GCN-NEXT:    ; =>This Inner Loop Header: Depth=1
 ; GCN-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN-NEXT:    v_mov_b32_e32 v3, v2
 ; GCN-NEXT:    v_not_b32_e32 v2, v3
 ; GCN-NEXT:    v_or_b32_e32 v2, -5, v2
 ; GCN-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
 ; GCN-NEXT:    flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
 ; GCN-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
 ; GCN-NEXT:    buffer_wbinvl1_vol
 ; GCN-NEXT:    s_waitcnt lgkmcnt(0)
 ; GCN-NEXT:    v_cmp_eq_u32_e32 vcc, v2, v3
-; GCN-NEXT:    v_mov_b32_e32 v3, v2
 ; GCN-NEXT:    s_or_b64 s[4:5], vcc, s[4:5]
 ; GCN-NEXT:    s_andn2_b64 exec, exec, s[4:5]
 ; GCN-NEXT:    s_cbranch_execnz BB2_1
 ; GCN-NEXT:  ; %bb.2: ; %atomicrmw.end
 ; GCN-NEXT:    s_or_b64 exec, exec, s[4:5]
 ; GCN-NEXT:    v_mov_b32_e32 v0, v2
 ; GCN-NEXT:    s_setpc_b64 s[30:31]
   %result = atomicrmw nand i32* %ptr, i32 4 seq_cst
   ret i32 %result
 }

llvm/test/CodeGen/AMDGPU/branch-relaxation.ll

 
 bb3:
   store volatile i32 %cnd, i32 addrspace(1)* %arg
   ret void
 }
 
 ; GCN-LABEL: {{^}}uniform_conditional_min_long_forward_vcnd_branch:
 ; GCN: s_load_dword [[CND:s[0-9]+]]
-; GCN-DAG: v_mov_b32_e32 [[V_CND:v[0-9]+]], [[CND]]
+
 ; GCN-DAG: v_cmp_eq_f32_e64 [[UNMASKED:s\[[0-9]+:[0-9]+\]]], [[CND]], 0
 ; GCN-DAG: s_and_b64 vcc, exec, [[UNMASKED]]
 ; GCN: s_cbranch_vccz [[LONGBB:BB[0-9]+_[0-9]+]]
 
 ; GCN-NEXT: [[LONG_JUMP:BB[0-9]+_[0-9]+]]: ; %bb0
 ; GCN-NEXT: s_getpc_b64 s{{\[}}[[PC_LO:[0-9]+]]:[[PC_HI:[0-9]+]]{{\]}}
 ; GCN-NEXT: s_add_u32 s[[PC_LO]], s[[PC_LO]], [[ENDBB:BB[0-9]+_[0-9]+]]-([[LONG_JUMP]]+4)
 ; GCN-NEXT: s_addc_u32 s[[PC_HI]], s[[PC_HI]], 0
 ; GCN-NEXT: s_setpc_b64 s{{\[}}[[PC_LO]]:[[PC_HI]]{{\]}}
 
 ; GCN-NEXT: [[LONGBB]]:
 ; GCN: v_nop_e64
 ; GCN: v_nop_e64
 ; GCN: v_nop_e64
 ; GCN: v_nop_e64
 
 ; GCN: [[ENDBB]]:
+; GCN: v_mov_b32_e32 [[V_CND:v[0-9]+]], [[CND]]
 ; GCN: buffer_store_dword [[V_CND]]
 ; GCN: s_endpgm
 define amdgpu_kernel void @uniform_conditional_min_long_forward_vcnd_branch(float addrspace(1)* %arg, float %cnd) #0 {
 bb0:
   %cmp = fcmp oeq float %cnd, 0.0
   br i1 %cmp, label %bb3, label %bb2 ; + 8 dword branch
 
 bb2:

llvm/test/CodeGen/AMDGPU/branch-uniformity.ll

 ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck %s
 
 ; The branch instruction in LOOP49 has a uniform condition, but PHI instructions
 ; introduced by the structurizecfg pass previously caused a false divergence
 ; which ended up in an assertion (or incorrect code) because
 ; SIAnnotateControlFlow and structurizecfg had different ideas about which
 ; branches are uniform.
 ;
 ; CHECK-LABEL: {{^}}main:
 ; CHECK: ; %LOOP49
-; CHECK: v_cmp_ne_u32_e32 vcc,
-; CHECK: s_cbranch_vccnz
+; CHECK: s_cmp_lg_u32 s{{[0-9]+}}, 0
+; CHECK: s_cbranch_scc1
 ; CHECK: ; %ENDIF53
 define amdgpu_vs float @main(i32 %in) {
 main_body:
   %cmp = mul i32 %in, 2
   br label %LOOP
 
 LOOP:                                             ; preds = %ENDLOOP48, %main_body
   %counter = phi i32 [ 0, %main_body ], [ %counter.next, %ENDLOOP48 ]

llvm/test/CodeGen/AMDGPU/commute-shifts.ll

 ; SI-NEXT:    s_mov_b32 s7, s0
 ; SI-NEXT:    image_load v2, v0, s[0:7] dmask:0x1 unorm
 ; SI-NEXT:    v_and_b32_e32 v0, 7, v0
 ; SI-NEXT:    s_waitcnt vmcnt(0)
 ; SI-NEXT:    v_lshrrev_b32_e32 v0, v0, v2
 ; SI-NEXT:    v_and_b32_e32 v0, 1, v0
 ; SI-NEXT:    v_cmp_eq_u32_e32 vcc, 1, v0
 ; SI-NEXT:    v_cndmask_b32_e32 v0, 0, v1, vcc
-; SI-NEXT:    v_cvt_pkrtz_f16_f32_e32 v0, v0, v0
+; SI-NEXT:    v_cvt_pkrtz_f16_f32_e32 v0, s0, v0
 ; SI-NEXT:    ; return to shader part epilog
 ;
 ; VI-LABEL: main:
 ; VI:       ; %bb.0: ; %bb
 ; VI-NEXT:    v_cvt_i32_f32_e32 v0, v0
 ; VI-NEXT:    s_mov_b32 s0, 0
 ; VI-NEXT:    s_mov_b32 s1, s0
 ; VI-NEXT:    s_mov_b32 s2, s0
 ; VI-NEXT:    s_mov_b32 s3, s0
 ; VI-NEXT:    s_mov_b32 s4, s0
 ; VI-NEXT:    s_mov_b32 s5, s0
 ; VI-NEXT:    s_mov_b32 s6, s0
 ; VI-NEXT:    s_mov_b32 s7, s0
 ; VI-NEXT:    image_load v2, v0, s[0:7] dmask:0x1 unorm
 ; VI-NEXT:    v_and_b32_e32 v0, 7, v0
 ; VI-NEXT:    s_waitcnt vmcnt(0)
 ; VI-NEXT:    v_lshrrev_b32_e32 v0, v0, v2
 ; VI-NEXT:    v_and_b32_e32 v0, 1, v0
 ; VI-NEXT:    v_cmp_eq_u32_e32 vcc, 1, v0
 ; VI-NEXT:    v_cndmask_b32_e32 v0, 0, v1, vcc
-; VI-NEXT:    v_cvt_pkrtz_f16_f32 v0, v0, v0
+; VI-NEXT:    v_cvt_pkrtz_f16_f32 v0, s0, v0
 ; VI-NEXT:    ; return to shader part epilog
 bb:
   %tmp = fptosi float %arg0 to i32
   %tmp1 = call <4 x float> @llvm.amdgcn.image.load.1d.v4f32.i32(i32 15, i32 undef, <8 x i32> undef, i32 0, i32 0)
   %tmp2.f = extractelement <4 x float> %tmp1, i32 0
   %tmp2 = bitcast float %tmp2.f to i32
   %tmp3 = and i32 %tmp, 7
   %tmp4 = shl i32 1, %tmp3

llvm/test/CodeGen/AMDGPU/control-flow-fastregalloc.ll

 
 endif:
   %tmp4 = phi i32 [ %val, %if ], [ 0, %entry ]
   store i32 %tmp4, i32 addrspace(1)* %out
   ret void
 }
 
 ; GCN-LABEL: {{^}}divergent_loop:
-; VGPR: workitem_private_segment_byte_size = 16{{$}}
+; VGPR: workitem_private_segment_byte_size = 12{{$}}
 
 ; GCN: {{^}}; %bb.0:
 
 ; GCN: s_mov_b32 m0, -1
 ; GCN: ds_read_b32 [[LOAD0:v[0-9]+]]
 
 ; GCN: v_cmp_eq_u32_e64 [[CMP0:s\[[0-9]+:[0-9]\]]], s{{[0-9]+}}, v0
 

 
 ; GCN-NEXT: ; mask branch [[END:BB[0-9]+_[0-9]+]]
 ; GCN-NEXT: s_cbranch_execz [[END]]
 
 
 ; GCN: [[LOOP:BB[0-9]+_[0-9]+]]:
 ; GCN: buffer_load_dword v[[VAL_LOOP_RELOAD:[0-9]+]], off, s[0:3], s7 offset:[[LOAD0_OFFSET]] ; 4-byte Folded Reload
 ; GCN: v_subrev_i32_e32 [[VAL_LOOP:v[0-9]+]], vcc, v{{[0-9]+}}, v[[VAL_LOOP_RELOAD]]
-; GCN: v_cmp_ne_u32_e32 vcc,
-; GCN: s_and_b64 vcc, exec, vcc
+; GCN: s_cmp_lg_u32
 ; GCN: buffer_store_dword [[VAL_LOOP]], off, s[0:3], s7 offset:[[VAL_SUB_OFFSET:[0-9]+]] ; 4-byte Folded Spill
-; GCN-NEXT: s_cbranch_vccnz [[LOOP]]
+; GCN-NEXT: s_cbranch_scc1 [[LOOP]]
 
 
 ; GCN: [[END]]:
 ; VGPR: v_readlane_b32 s[[S_RELOAD_SAVEEXEC_LO:[0-9]+]], [[SPILL_VGPR]], [[SAVEEXEC_LO_LANE]]
 ; VGPR: v_readlane_b32 s[[S_RELOAD_SAVEEXEC_HI:[0-9]+]], [[SPILL_VGPR]], [[SAVEEXEC_HI_LANE]]
 
 ; VMEM: buffer_load_dword v[[V_RELOAD_SAVEEXEC_LO:[0-9]+]], off, s[0:3], s7 offset:24 ; 4-byte Folded Reload
 ; VMEM: s_waitcnt vmcnt(0)

llvm/test/CodeGen/AMDGPU/copy-illegal-type.ll

 ; SI-NEXT:    buffer_store_dword v0, off, s[8:11], 0
 ; SI-NEXT:    s_endpgm
 ;
 ; VI-LABEL: test_copy_v4i8_extra_use:
 ; VI:       ; %bb.0:
 ; VI-NEXT:    s_load_dwordx4 s[4:7], s[0:1], 0x24
 ; VI-NEXT:    s_load_dwordx2 s[0:1], s[0:1], 0x34
 ; VI-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
-; VI-NEXT:    s_movk_i32 s10, 0xff00
+; VI-NEXT:    s_movk_i32 s8, 0xff00
 ; VI-NEXT:    s_mov_b32 s3, 0xf000
 ; VI-NEXT:    s_mov_b32 s2, -1
 ; VI-NEXT:    s_waitcnt lgkmcnt(0)
 ; VI-NEXT:    v_mov_b32_e32 v1, s1
 ; VI-NEXT:    v_add_u32_e32 v0, vcc, s0, v0
 ; VI-NEXT:    v_addc_u32_e32 v1, vcc, 0, v1, vcc
 ; VI-NEXT:    flat_load_dword v0, v[0:1]
 ; VI-NEXT:    s_mov_b32 s0, s6
 ; VI-NEXT:    s_mov_b32 s1, s7
-; VI-NEXT:    s_movk_i32 s8, 0xff
+; VI-NEXT:    s_movk_i32 s9, 0xff
 ; VI-NEXT:    s_mov_b32 s6, s2
 ; VI-NEXT:    s_mov_b32 s7, s3
-; VI-NEXT:    s_movk_i32 s9, 0x900
+; VI-NEXT:    s_movk_i32 s10, 0x900
 ; VI-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
 ; VI-NEXT:    v_lshrrev_b32_e32 v1, 16, v0
-; VI-NEXT:    v_and_b32_e32 v3, s10, v1
+; VI-NEXT:    v_and_b32_e32 v3, s8, v1
 ; VI-NEXT:    v_add_u16_e32 v1, 9, v1
-; VI-NEXT:    v_and_b32_e32 v1, s8, v1
+; VI-NEXT:    v_and_b32_e32 v1, s9, v1
 ; VI-NEXT:    buffer_store_dword v0, off, s[4:7], 0
-; VI-NEXT:    v_and_b32_e32 v2, s10, v0
+; VI-NEXT:    v_and_b32_e32 v2, s8, v0
 ; VI-NEXT:    v_add_u16_e32 v0, 9, v0
-; VI-NEXT:    v_and_b32_e32 v0, s8, v0
+; VI-NEXT:    v_and_b32_e32 v0, s9, v0
 ; VI-NEXT:    v_or_b32_e32 v1, v3, v1
 ; VI-NEXT:    v_or_b32_e32 v0, v2, v0
-; VI-NEXT:    v_add_u16_e32 v1, s9, v1
-; VI-NEXT:    v_add_u16_e32 v0, s9, v0
+; VI-NEXT:    v_add_u16_e32 v1, s10, v1
+; VI-NEXT:    v_add_u16_e32 v0, s10, v0
 ; VI-NEXT:    v_lshlrev_b32_e32 v1, 16, v1
 ; VI-NEXT:    v_or_b32_e32 v0, v0, v1
 ; VI-NEXT:    buffer_store_dword v0, off, s[0:3], 0
 ; VI-NEXT:    s_endpgm
   %tid.x = call i32 @llvm.amdgcn.workitem.id.x()
   %gep = getelementptr <4 x i8>, <4 x i8> addrspace(1)* %in, i32 %tid.x
   %val = load <4 x i8>, <4 x i8> addrspace(1)* %gep, align 4
   %add = add <4 x i8> %val, <i8 9, i8 9, i8 9, i8 9>

 ; SI-NEXT:    buffer_store_dword v1, off, s[4:7], 0
 ; SI-NEXT:    buffer_store_dword v0, off, s[8:11], 0
 ; SI-NEXT:    s_endpgm
 ;
 ; VI-LABEL: test_copy_v4i8_x2_extra_use:
 ; VI:       ; %bb.0:
 ; VI-NEXT:    s_load_dwordx8 s[0:7], s[0:1], 0x24
 ; VI-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
-; VI-NEXT:    s_movk_i32 s14, 0xff00
-; VI-NEXT:    s_movk_i32 s12, 0xff
-; VI-NEXT:    s_movk_i32 s13, 0x900
+; VI-NEXT:    s_movk_i32 s12, 0xff00
+; VI-NEXT:    s_movk_i32 s13, 0xff
+; VI-NEXT:    s_movk_i32 s14, 0x900
 ; VI-NEXT:    s_waitcnt lgkmcnt(0)
 ; VI-NEXT:    v_mov_b32_e32 v1, s7
 ; VI-NEXT:    v_add_u32_e32 v0, vcc, s6, v0
 ; VI-NEXT:    v_addc_u32_e32 v1, vcc, 0, v1, vcc
 ; VI-NEXT:    flat_load_dword v0, v[0:1]
 ; VI-NEXT:    s_mov_b32 s7, 0xf000
 ; VI-NEXT:    s_mov_b32 s6, -1
 ; VI-NEXT:    s_mov_b32 s8, s2
 ; VI-NEXT:    s_mov_b32 s9, s3
 ; VI-NEXT:    s_mov_b32 s10, s6
 ; VI-NEXT:    s_mov_b32 s11, s7
 ; VI-NEXT:    s_mov_b32 s2, s6
 ; VI-NEXT:    s_mov_b32 s3, s7
 ; VI-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
 ; VI-NEXT:    v_lshrrev_b32_e32 v1, 16, v0
-; VI-NEXT:    v_and_b32_e32 v4, s14, v1
+; VI-NEXT:    v_and_b32_e32 v4, s12, v1
 ; VI-NEXT:    v_add_u16_e32 v1, 9, v1
 ; VI-NEXT:    v_add_u16_e32 v3, 9, v0
-; VI-NEXT:    v_and_b32_e32 v1, s12, v1
+; VI-NEXT:    v_and_b32_e32 v1, s13, v1
 ; VI-NEXT:    v_or_b32_e32 v1, v4, v1
-; VI-NEXT:    v_and_b32_e32 v2, s14, v0
-; VI-NEXT:    v_and_b32_e32 v3, s12, v3
+; VI-NEXT:    v_and_b32_e32 v2, s12, v0
+; VI-NEXT:    v_and_b32_e32 v3, s13, v3
 ; VI-NEXT:    v_or_b32_e32 v2, v2, v3
-; VI-NEXT:    v_add_u16_e32 v1, s13, v1
-; VI-NEXT:    v_add_u16_e32 v2, s13, v2
+; VI-NEXT:    v_add_u16_e32 v1, s14, v1
+; VI-NEXT:    v_add_u16_e32 v2, s14, v2
 ; VI-NEXT:    v_lshlrev_b32_e32 v1, 16, v1
 ; VI-NEXT:    v_or_b32_e32 v1, v2, v1
 ; VI-NEXT:    buffer_store_dword v0, off, s[0:3], 0
 ; VI-NEXT:    buffer_store_dword v1, off, s[8:11], 0
 ; VI-NEXT:    buffer_store_dword v0, off, s[4:7], 0
 ; VI-NEXT:    s_endpgm
   %tid.x = call i32 @llvm.amdgcn.workitem.id.x()
   %in.ptr = getelementptr <4 x i8>, <4 x i8> addrspace(1)* %in, i32 %tid.x

llvm/test/CodeGen/AMDGPU/cse-phi-incoming-val.ll

 ; RUN: llc < %s -mtriple=amdgcn--amdpal -mcpu=gfx900 -verify-machineinstrs | FileCheck %s
 
 ; Check that the redundant immediate MOV instruction
 ; (by-product of handling phi nodes) is not found
 ; in the generated code.
 
 ; CHECK-LABEL: {{^}}mov_opt:
-; CHECK: v_mov_b32_e32 {{v[0-9]+}}, 1.0
+; CHECK: s_mov_b32 [[SREG:s[0-9]+]], 1.0
 ; CHECK: %bb.1:
 ; CHECK-NOT: v_mov_b32_e32 {{v[0-9]+}}, 1.0
-; CHECK: BB0_2:
+; CHECK: BB0_4:
+; CHECK: v_mov_b32_e32 v{{[0-9]+}}, [[SREG]]
 
 define amdgpu_ps void @mov_opt(i32 %arg, i32 inreg %arg1, i32 inreg %arg2) local_unnamed_addr #0 {
 bb:
   %tmp = icmp eq i32 %arg1, 0
   br i1 %tmp, label %bb3, label %bb10
 
 bb3:                                              ; preds = %bb
   %tmp4 = icmp eq i32 %arg2, 0

llvm/test/CodeGen/AMDGPU/divergent-branch-uniform-condition.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck %s
 
 ; This module creates a divergent branch. The branch is marked as divergent by
 ; the divergence analysis but the condition is not. This test ensures that the
 ; divergence of the branch is tested, not its condition, so that branch is
 ; correctly emitted as divergent.
 
 target triple = "amdgcn-mesa-mesa3d"
 
 define amdgpu_ps void @main(i32, float) {
 ; CHECK-LABEL: main:
 ; CHECK:       ; %bb.0: ; %start
 ; CHECK-NEXT:    v_readfirstlane_b32 s0, v0
 ; CHECK-NEXT:    s_mov_b32 m0, s0
-; CHECK-NEXT:    s_mov_b64 s[4:5], 0
+; CHECK-NEXT:    s_mov_b32 s0, 0
 ; CHECK-NEXT:    v_interp_p1_f32_e32 v0, v1, attr0.x
-; CHECK-NEXT:    v_cmp_nlt_f32_e64 s[0:1], 0, v0
-; CHECK-NEXT:    v_mov_b32_e32 v1, 0
-; CHECK-NEXT:    ; implicit-def: $sgpr8_sgpr9
+; CHECK-NEXT:    v_cmp_nlt_f32_e32 vcc, 0, v0
+; CHECK-NEXT:    s_mov_b64 s[4:5], 0
 ; CHECK-NEXT:    ; implicit-def: $sgpr6_sgpr7
 ; CHECK-NEXT:    ; implicit-def: $sgpr2_sgpr3
 ; CHECK-NEXT:    s_branch BB0_3
 ; CHECK-NEXT:  BB0_1: ; %Flow1
 ; CHECK-NEXT:    ; in Loop: Header=BB0_3 Depth=1
 ; CHECK-NEXT:    s_or_b64 exec, exec, s[8:9]
-; CHECK-NEXT:    s_mov_b64 s[8:9], 0
+; CHECK-NEXT:    s_mov_b64 s[10:11], 0
 ; CHECK-NEXT:  BB0_2: ; %Flow
 ; CHECK-NEXT:    ; in Loop: Header=BB0_3 Depth=1
-; CHECK-NEXT:    s_and_b64 s[10:11], exec, s[6:7]
-; CHECK-NEXT:    s_or_b64 s[10:11], s[10:11], s[4:5]
+; CHECK-NEXT:    s_and_b64 s[8:9], exec, s[6:7]
+; CHECK-NEXT:    s_or_b64 s[8:9], s[8:9], s[4:5]
 ; CHECK-NEXT:    s_andn2_b64 s[2:3], s[2:3], exec
-; CHECK-NEXT:    s_and_b64 s[4:5], s[8:9], exec
+; CHECK-NEXT:    s_and_b64 s[4:5], s[10:11], exec
 ; CHECK-NEXT:    s_or_b64 s[2:3], s[2:3], s[4:5]
-; CHECK-NEXT:    s_mov_b64 s[4:5], s[10:11]
-; CHECK-NEXT:    s_andn2_b64 exec, exec, s[10:11]
+; CHECK-NEXT:    s_mov_b64 s[4:5], s[8:9]
+; CHECK-NEXT:    s_andn2_b64 exec, exec, s[8:9]
 ; CHECK-NEXT:    s_cbranch_execz BB0_6
 ; CHECK-NEXT:  BB0_3: ; %loop
 ; CHECK-NEXT:    ; =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    v_cmp_gt_u32_e32 vcc, 32, v1
-; CHECK-NEXT:    s_and_b64 vcc, exec, vcc
 ; CHECK-NEXT:    s_or_b64 s[6:7], s[6:7], exec
-; CHECK-NEXT:    s_or_b64 s[8:9], s[8:9], exec
-; CHECK-NEXT:    s_cbranch_vccz BB0_2
+; CHECK-NEXT:    s_cmp_lt_u32 s0, 32
+; CHECK-NEXT:    s_mov_b64 s[10:11], -1
+; CHECK-NEXT:    s_cbranch_scc0 BB0_2
 ; CHECK-NEXT:  ; %bb.4: ; %endif1
 ; CHECK-NEXT:    ; in Loop: Header=BB0_3 Depth=1
 ; CHECK-NEXT:    s_mov_b64 s[6:7], -1
-; CHECK-NEXT:    s_and_saveexec_b64 s[8:9], s[0:1]
+; CHECK-NEXT:    s_and_saveexec_b64 s[8:9], vcc
 ; CHECK-NEXT:    s_xor_b64 s[8:9], exec, s[8:9]
 ; CHECK-NEXT:    ; mask branch BB0_1
 ; CHECK-NEXT:    s_cbranch_execz BB0_1
 ; CHECK-NEXT:  BB0_5: ; %endif2
 ; CHECK-NEXT:    ; in Loop: Header=BB0_3 Depth=1
-; CHECK-NEXT:    v_add_u32_e32 v1, 1, v1
+; CHECK-NEXT:    s_add_i32 s0, s0, 1
 ; CHECK-NEXT:    s_xor_b64 s[6:7], exec, -1
 ; CHECK-NEXT:    s_branch BB0_1
 ; CHECK-NEXT:  BB0_6: ; %Flow2
-; CHECK-NEXT:    s_or_b64 exec, exec, s[10:11]
+; CHECK-NEXT:    s_or_b64 exec, exec, s[8:9]
 ; CHECK-NEXT:    v_mov_b32_e32 v1, 0
 ; CHECK-NEXT:    s_and_saveexec_b64 s[0:1], s[2:3]
 ; CHECK-NEXT:    ; mask branch BB0_8
 ; CHECK-NEXT:  BB0_7: ; %if1
 ; CHECK-NEXT:    v_sqrt_f32_e32 v1, v0
 ; CHECK-NEXT:  BB0_8: ; %endloop
 ; CHECK-NEXT:    s_or_b64 exec, exec, s[0:1]
 ; CHECK-NEXT:    exp mrt0 v1, v1, v1, v1 done vm

llvm/test/CodeGen/AMDGPU/extract_subvector_vec4_vec3.ll

 ; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
 ; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx900 < %s -stop-after=amdgpu-isel | FileCheck -check-prefix=GCN %s
 
 ; We want to see a BUFFER_LOAD, some register shuffling, and a BUFFER_STORE.
 ; Specifically, we do not want to see a BUFFER_STORE that says "store into
 ; stack" in the middle.
 
 define amdgpu_hs void @main([0 x i8] addrspace(6)* inreg %arg) {
   ; GCN-LABEL: name: main
   ; GCN: bb.0.main_body:
   ; GCN:   [[S_MOV_B32_:%[0-9]+]]:sreg_32_xm0 = S_MOV_B32 0
   ; GCN:   [[DEF:%[0-9]+]]:sreg_32_xm0 = IMPLICIT_DEF
   ; GCN:   [[COPY:%[0-9]+]]:vgpr_32 = COPY [[DEF]]
   ; GCN:   [[DEF1:%[0-9]+]]:sreg_128 = IMPLICIT_DEF
   ; GCN:   [[BUFFER_LOAD_DWORDX4_OFFEN:%[0-9]+]]:vreg_128 = BUFFER_LOAD_DWORDX4_OFFEN [[COPY]], [[DEF1]], [[S_MOV_B32_]], 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load 16 from custom TargetCustom7, align 1, addrspace 4)
-  ; GCN:   [[COPY1:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_DWORDX4_OFFEN]].sub2
-  ; GCN:   [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_DWORDX4_OFFEN]].sub1
-  ; GCN:   [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_DWORDX4_OFFEN]].sub0
+  ; GCN:   [[COPY1:%[0-9]+]]:sgpr_32 = COPY [[BUFFER_LOAD_DWORDX4_OFFEN]].sub2
+  ; GCN:   [[COPY2:%[0-9]+]]:sgpr_32 = COPY [[BUFFER_LOAD_DWORDX4_OFFEN]].sub1
+  ; GCN:   [[COPY3:%[0-9]+]]:sgpr_32 = COPY [[BUFFER_LOAD_DWORDX4_OFFEN]].sub0
   ; GCN:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_96 = REG_SEQUENCE killed [[COPY3]], %subreg.sub0, killed [[COPY2]], %subreg.sub1, killed [[COPY1]], %subreg.sub2
   ; GCN:   [[COPY4:%[0-9]+]]:vreg_96 = COPY [[REG_SEQUENCE]]
   ; GCN:   [[DEF2:%[0-9]+]]:sreg_32_xm0 = IMPLICIT_DEF
   ; GCN:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[DEF2]]
   ; GCN:   [[DEF3:%[0-9]+]]:sreg_128 = IMPLICIT_DEF
   ; GCN:   BUFFER_STORE_DWORDX3_OFFEN_exact killed [[COPY4]], [[COPY5]], [[DEF3]], [[S_MOV_B32_]], 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 12 into custom TargetCustom7, align 1, addrspace 4)
   ; GCN:   S_ENDPGM 0
 main_body:

llvm/test/CodeGen/AMDGPU/fabs.ll

define amdgpu_kernel void @s_fabs_f32(float addrspace(1)* %out, float %in) {
   store float %fabs, float addrspace(1)* %out
   ret void
 }
 
 ; FUNC-LABEL: {{^}}fabs_v2f32:
 ; R600: |{{(PV|T[0-9])\.[XYZW]}}|
 ; R600: |{{(PV|T[0-9])\.[XYZW]}}|
 
-; GCN: v_and_b32
-; GCN: v_and_b32
+; GCN: s_and_b32
+; GCN: s_and_b32
 define amdgpu_kernel void @fabs_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %in) {
   %fabs = call <2 x float> @llvm.fabs.v2f32(<2 x float> %in)
   store <2 x float> %fabs, <2 x float> addrspace(1)* %out
   ret void
 }
 
 ; FUNC-LABEL: {{^}}fabs_v4f32:
 ; R600: |{{(PV|T[0-9])\.[XYZW]}}|
 ; R600: |{{(PV|T[0-9])\.[XYZW]}}|
 ; R600: |{{(PV|T[0-9])\.[XYZW]}}|
 ; R600: |{{(PV|T[0-9])\.[XYZW]}}|
 
-; GCN: v_and_b32
-; GCN: v_and_b32
-; GCN: v_and_b32
-; GCN: v_and_b32
+; GCN: s_and_b32
+; GCN: s_and_b32
+; GCN: s_and_b32
+; GCN: s_and_b32
 define amdgpu_kernel void @fabs_v4f32(<4 x float> addrspace(1)* %out, <4 x float> %in) {
   %fabs = call <4 x float> @llvm.fabs.v4f32(<4 x float> %in)
   store <4 x float> %fabs, <4 x float> addrspace(1)* %out
   ret void
 }
 
 ; GCN-LABEL: {{^}}fabs_fn_fold:
 ; SI: s_load_dwordx2 s{{\[}}[[ABS_VALUE:[0-9]+]]:[[MUL_VAL:[0-9]+]]{{\]}}, s[{{[0-9]+:[0-9]+}}], 0xb

llvm/test/CodeGen/AMDGPU/fdiv32-to-rcp-folding.ll

define amdgpu_kernel void @div_minus_1_by_minus_x_25ulp(float addrspace(1)* %arg) {
   %neg = fsub float -0.000000e+00, %load
   %div = fdiv float -1.000000e+00, %neg, !fpmath !0
   store float %div, float addrspace(1)* %arg, align 4
   ret void
 }
 
 ; GCN-LABEL: {{^}}div_v4_1_by_x_25ulp:
 ; GCN-DAG:        s_load_dwordx4 s{{\[}}[[VAL0:[0-9]+]]:[[VAL3:[0-9]+]]], s[{{[0-9:]+}}], 0x0{{$}}
-; GCN-DENORM-DAG: s_mov_b32 [[L:s[0-9]+]], 0x6f800000
+; GCN-DENORM-DAG: v_mov_b32_e32 [[L:v[0-9]+]], 0x6f800000
 ; GCN-DENORM-DAG: v_mov_b32_e32 [[S:v[0-9]+]], 0x2f800000
-; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |v{{[0-9]+}}|, [[L]]
+; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |s{{[0-9]+}}|, [[L]]
 ; GCN-DENORM-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
-; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |v{{[0-9]+}}|, [[L]]
+; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |s{{[0-9]+}}|, [[L]]
 ; GCN-DENORM-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
-; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |v{{[0-9]+}}|, [[L]]
+; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |s{{[0-9]+}}|, [[L]]
 ; GCN-DENORM-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
-; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |v{{[0-9]+}}|, [[L]]
+; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |s{{[0-9]+}}|, [[L]]
 ; GCN-DENORM-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
 ; GCN-DENORM-DAG: v_mul_f32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
 ; GCN-DENORM-DAG: v_mul_f32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
 ; GCN-DENORM-DAG: v_mul_f32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
 ; GCN-DENORM-DAG: v_mul_f32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
 ; GCN-DENORM-DAG: v_rcp_f32_e32
 ; GCN-DENORM-DAG: v_rcp_f32_e32
 ; GCN-DENORM-DAG: v_rcp_f32_e32

 define amdgpu_kernel void @div_v4_1_by_x_25ulp(<4 x float> addrspace(1)* %arg) {
   %load = load <4 x float>, <4 x float> addrspace(1)* %arg, align 16
   %div = fdiv <4 x float> <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>, %load, !fpmath !0
   store <4 x float> %div, <4 x float> addrspace(1)* %arg, align 16
   ret void
 }
 
 ; GCN-LABEL: {{^}}div_v4_minus_1_by_x_25ulp:
-; GCN-DENORM-DAG: s_mov_b32 [[L:s[0-9]+]], 0x6f800000
+; GCN-DENORM-DAG: v_mov_b32_e32 [[L:v[0-9]+]], 0x6f800000
 ; GCN-DENORM-DAG: v_mov_b32_e32 [[S:v[0-9]+]], 0x2f800000
-; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |v{{[0-9]+}}|, [[L]]
+; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |s{{[0-9]+}}|, [[L]]
 ; GCN-DENORM-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
-; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |v{{[0-9]+}}|, [[L]]
+; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |s{{[0-9]+}}|, [[L]]
 ; GCN-DENORM-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
-; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |v{{[0-9]+}}|, [[L]]
+; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |s{{[0-9]+}}|, [[L]]
 ; GCN-DENORM-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
-; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |v{{[0-9]+}}|, [[L]]
+; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |s{{[0-9]+}}|, [[L]]
 ; GCN-DENORM-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
 ; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, s{{[0-9]+}}, -v{{[0-9]+}}
 ; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, s{{[0-9]+}}, -v{{[0-9]+}}
 ; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, s{{[0-9]+}}, -v{{[0-9]+}}
 ; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, s{{[0-9]+}}, -v{{[0-9]+}}
 ; GCN-DENORM-DAG: v_rcp_f32_e32
 ; GCN-DENORM-DAG: v_rcp_f32_e32
 ; GCN-DENORM-DAG: v_rcp_f32_e32

 define amdgpu_kernel void @div_v4_minus_1_by_x_25ulp(<4 x float> addrspace(1)* %arg) {
   %load = load <4 x float>, <4 x float> addrspace(1)* %arg, align 16
   %div = fdiv <4 x float> <float -1.000000e+00, float -1.000000e+00, float -1.000000e+00, float -1.000000e+00>, %load, !fpmath !0
   store <4 x float> %div, <4 x float> addrspace(1)* %arg, align 16
   ret void
 }
 
 ; GCN-LABEL: {{^}}div_v4_1_by_minus_x_25ulp:
-; GCN-DENORM-DAG: s_mov_b32 [[L:s[0-9]+]], 0x6f800000
+; GCN-DENORM-DAG: v_mov_b32_e32 [[L:v[0-9]+]], 0x6f800000
 ; GCN-DENORM-DAG: v_mov_b32_e32 [[S:v[0-9]+]], 0x2f800000
-; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |v{{[0-9]+}}|, [[L]]
+; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |s{{[0-9]+}}|, [[L]]
 ; GCN-DENORM-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
-; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |v{{[0-9]+}}|, [[L]]
+; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |s{{[0-9]+}}|, [[L]]
 ; GCN-DENORM-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
-; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |v{{[0-9]+}}|, [[L]]
+; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |s{{[0-9]+}}|, [[L]]
 ; GCN-DENORM-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
-; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |v{{[0-9]+}}|, [[L]]
+; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |s{{[0-9]+}}|, [[L]]
 ; GCN-DENORM-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
 ; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, -s{{[0-9]+}}, v{{[0-9]+}}
 ; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, -s{{[0-9]+}}, v{{[0-9]+}}
 ; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, -s{{[0-9]+}}, v{{[0-9]+}}
 ; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, -s{{[0-9]+}}, v{{[0-9]+}}
 ; GCN-DENORM-DAG: v_rcp_f32_e32
 ; GCN-DENORM-DAG: v_rcp_f32_e32
 ; GCN-DENORM-DAG: v_rcp_f32_e32
define amdgpu_kernel void @div_v4_1_by_minus_x_25ulp(<4 x float> addrspace(1)* %arg) {
   %neg = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %load
   %div = fdiv <4 x float> <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>, %neg, !fpmath !0
   store <4 x float> %div, <4 x float> addrspace(1)* %arg, align 16
   ret void
 }
 
 ; GCN-LABEL: {{^}}div_v4_minus_1_by_minus_x_25ulp:
 ; GCN-DAG:        s_load_dwordx4 s{{\[}}[[VAL0:[0-9]+]]:[[VAL3:[0-9]+]]], s[{{[0-9:]+}}], 0x0{{$}}
-; GCN-DENORM-DAG: s_mov_b32 [[L:s[0-9]+]], 0x6f800000
+; GCN-DENORM-DAG: v_mov_b32_e32 [[L:v[0-9]+]], 0x6f800000
 ; GCN-DENORM-DAG: v_mov_b32_e32 [[S:v[0-9]+]], 0x2f800000
-; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |v{{[0-9]+}}|, [[L]]
+; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |s{{[0-9]+}}|, [[L]]
 ; GCN-DENORM-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
-; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |v{{[0-9]+}}|, [[L]]
+; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |s{{[0-9]+}}|, [[L]]
 ; GCN-DENORM-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
-; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |v{{[0-9]+}}|, [[L]]
+; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |s{{[0-9]+}}|, [[L]]
 ; GCN-DENORM-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
-; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |v{{[0-9]+}}|, [[L]]
+; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |s{{[0-9]+}}|, [[L]]
 ; GCN-DENORM-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
 ; GCN-DENORM-DAG: v_mul_f32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
 ; GCN-DENORM-DAG: v_mul_f32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
 ; GCN-DENORM-DAG: v_mul_f32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
 ; GCN-DENORM-DAG: v_mul_f32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
 ; GCN-DENORM-DAG: v_rcp_f32_e32
 ; GCN-DENORM-DAG: v_rcp_f32_e32
 ; GCN-DENORM-DAG: v_rcp_f32_e32
define amdgpu_kernel void @div_v4_minus_1_by_minus_x_25ulp(<4 x float> addrspace(1)* %arg) {
   %load = load <4 x float>, <4 x float> addrspace(1)* %arg, align 16
   %neg = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %load
   %div = fdiv <4 x float> <float -1.000000e+00, float -1.000000e+00, float -1.000000e+00, float -1.000000e+00>, %neg, !fpmath !0
   store <4 x float> %div, <4 x float> addrspace(1)* %arg, align 16
   ret void
 }
 
 ; GCN-LABEL: {{^}}div_v4_c_by_x_25ulp:
-; GCN-DAG:        s_mov_b32 [[L:s[0-9]+]], 0x6f800000
-; GCN-DAG:        v_mov_b32_e32 [[S:v[0-9]+]], 0x2f800000
 ; GCN-DENORM-DAG: v_div_scale_f32 {{.*}}, 2.0{{$}}
 ; GCN-DENORM-DAG: v_div_scale_f32 {{.*}}, 2.0{{$}}
 ; GCN-DENORM-DAG: v_div_scale_f32 {{.*}}, -2.0{{$}}
 ; GCN-DENORM-DAG: v_div_scale_f32 {{.*}}, -2.0{{$}}
 ; GCN-DENORM-DAG: v_rcp_f32_e32
 ; GCN-DENORM-DAG: v_rcp_f32_e32
 
-; GCN-DAG:        v_cmp_gt_f32_e64 vcc, |v{{[0-9]+}}|, [[L]]
+; GCN-DAG:        v_mov_b32_e32 [[L:v[0-9]+]], 0x6f800000
+; GCN-DAG:        v_mov_b32_e32 [[S:v[0-9]+]], 0x2f800000
+
+; GCN-DAG:        v_cmp_gt_f32_e64 vcc, |s{{[0-9]+}}|, [[L]]
 ; GCN-DAG:        v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
-; GCN-DAG:        v_cmp_gt_f32_e64 vcc, |v{{[0-9]+}}|, [[L]]
+; GCN-DAG:        v_cmp_gt_f32_e64 vcc, |s{{[0-9]+}}|, [[L]]
 ; GCN-DAG:        v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
 
 ; GCN-DENORM-DAG: v_mul_f32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
 ; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, s{{[0-9]+}}, -v{{[0-9]+}}
 ; GCN-DENORM-DAG: v_rcp_f32_e32 [[RCP1:v[0-9]+]], v{{[0-9]+}}
 ; GCN-DENORM-DAG: v_mul_f32_e32 v{{[0-9]+}}, v{{[0-9]+}}, [[RCP1]]
 ; GCN-DENORM-DAG: v_rcp_f32_e32 [[RCP2:v[0-9]+]], v{{[0-9]+}}
 ; GCN-DENORM-DAG: v_mul_f32_e32 v{{[0-9]+}}, v{{[0-9]+}}, [[RCP2]]

 define amdgpu_kernel void @div_v4_c_by_x_25ulp(<4 x float> addrspace(1)* %arg) {
   %load = load <4 x float>, <4 x float> addrspace(1)* %arg, align 16
   %div = fdiv <4 x float> <float 2.000000e+00, float 1.000000e+00, float -1.000000e+00, float -2.000000e+00>, %load, !fpmath !0
   store <4 x float> %div, <4 x float> addrspace(1)* %arg, align 16
   ret void
 }
 
 ; GCN-LABEL: {{^}}div_v4_c_by_minus_x_25ulp:
-; GCN-DAG:        s_mov_b32 [[L:s[0-9]+]], 0x6f800000
-; GCN-DAG:        v_mov_b32_e32 [[S:v[0-9]+]], 0x2f800000
 ; GCN-DENORM-DAG: v_div_scale_f32 {{.*}}, -2.0{{$}}
 ; GCN-DENORM-DAG: v_div_scale_f32 {{.*}}, -2.0{{$}}
 ; GCN-DENORM-DAG: v_div_scale_f32 {{.*}}, -2.0{{$}}
 ; GCN-DENORM-DAG: v_div_scale_f32 {{.*}}, -2.0{{$}}
 ; GCN-DENORM-DAG: v_rcp_f32_e32
 ; GCN-DENORM-DAG: v_rcp_f32_e32
 
-; GCN-DAG:        v_cmp_gt_f32_e64 vcc, |v{{[0-9]+}}|, [[L]]
+; GCN-DAG:        v_mov_b32_e32 [[L:v[0-9]+]], 0x6f800000
+; GCN-DAG:        v_mov_b32_e32 [[S:v[0-9]+]], 0x2f800000
+
+; GCN-DAG:        v_cmp_gt_f32_e64 vcc, |s{{[0-9]+}}|, [[L]]
 ; GCN-DAG:        v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
-; GCN-DAG:        v_cmp_gt_f32_e64 vcc, |v{{[0-9]+}}|, [[L]]
+; GCN-DAG:        v_cmp_gt_f32_e64 vcc, |s{{[0-9]+}}|, [[L]]
 ; GCN-DAG:        v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
 
 ; GCN-DENORM-DAG: v_mul_f32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
 ; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, -s{{[0-9]+}}, v{{[0-9]+}}
 ; GCN-DENORM-DAG: v_rcp_f32_e32 [[RCP1:v[0-9]+]], v{{[0-9]+}}
 ; GCN-DENORM-DAG: v_mul_f32_e32 v{{[0-9]+}}, v{{[0-9]+}}, [[RCP1]]
 ; GCN-DENORM-DAG: v_rcp_f32_e32 [[RCP2:v[0-9]+]], v{{[0-9]+}}
 ; GCN-DENORM-DAG: v_mul_f32_e32 v{{[0-9]+}}, v{{[0-9]+}}, [[RCP2]]

llvm/test/CodeGen/AMDGPU/fmin_legacy.ll

define amdgpu_kernel void @s_test_fmin_legacy_subreg_inputs_f32(float addrspace(1)* %out, <4 x float> %reg0) #0 {
    %r3 = select i1 %r2, float %r1, float %r0
    store float %r3, float addrspace(1)* %out
    ret void
 }
 
 ; FUNC-LABEL: {{^}}s_test_fmin_legacy_ule_f32:
 ; GCN-DAG: s_load_dwordx2 s{{\[}}[[A:[0-9]+]]:[[B:[0-9]+]]{{\]}}, s{{\[[0-9]+:[0-9]+\]}}, {{0xb|0x2c}}
 
-; GCN-DAG: v_mov_b32_e32 [[VB:v[0-9]+]], s[[B]]
+; SI-SAFE: v_mov_b32_e32 [[VA:v[0-9]+]], s[[A]]
 
-; SI-SAFE: v_min_legacy_f32_e64 {{v[0-9]+}}, [[VB]], s[[A]]
+; GCN-NONAN: v_mov_b32_e32 [[VB:v[0-9]+]], s[[B]]
+
+; VI-SAFE: v_mov_b32_e32 [[VB:v[0-9]+]], s[[B]]
+
+; SI-SAFE: v_min_legacy_f32_e32 {{v[0-9]+}}, s[[B]], [[VA]]
 
 ; VI-SAFE: v_mov_b32_e32 [[VA:v[0-9]+]], s[[A]]
 ; VI-SAFE: v_cmp_ngt_f32_e32 vcc, s[[A]], [[VB]]
 ; VI-SAFE: v_cndmask_b32_e32 v{{[0-9]+}}, [[VB]], [[VA]]
 
 ; GCN-NONAN: v_min_f32_e32 {{v[0-9]+}}, s[[A]], [[VB]]
 define amdgpu_kernel void @s_test_fmin_legacy_ule_f32(float addrspace(1)* %out, float %a, float %b) #0 {
   %cmp = fcmp ule float %a, %b

llvm/test/CodeGen/AMDGPU/fmul-2-combine-multi-use.ll

define amdgpu_kernel void @multiple_use_fadd_fmac_f32(float addrspace(1)* %out, float %x, [8 x i32], float %y) #0 {
   store volatile float %mul2, float addrspace(1)* %out
   store volatile float %mad, float addrspace(1)* %out.gep.1
   ret void
 }
 
 ; GCN-LABEL: {{^}}multiple_use_fadd_fmad_f32:
 ; GCN-DAG:   v_add_f32_e64 [[MUL2:v[0-9]+]], |[[X:s[0-9]+]]|, |s{{[0-9]+}}|
 ; SIVI-DAG:  v_mad_f32 [[MAD:v[0-9]+]], |[[X]]|, 2.0, v{{[0-9]+}}
-; GFX10-DAG: v_fma_f32 [[MAD:v[0-9]+]], 2.0, |[[X]]|, v{{[0-9]+}}
+; GFX10-DAG: v_fma_f32 [[MAD:v[0-9]+]], |[[X]]|, 2.0, s{{[0-9]+}}
 ; GCN-DAG:   buffer_store_dword [[MUL2]]
 ; GCN-DAG:   buffer_store_dword [[MAD]]
 ; GCN:       s_endpgm
 define amdgpu_kernel void @multiple_use_fadd_fmad_f32(float addrspace(1)* %out, float %x, float %y) #0 {
   %out.gep.1 = getelementptr float, float addrspace(1)* %out, i32 1
   %x.abs = call float @llvm.fabs.f32(float %x)
   %mul2 = fmul fast float %x.abs, 2.0
   %mad = fadd fast float %mul2, %y

llvm/test/CodeGen/AMDGPU/fneg-fabs.ll

 ; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI -check-prefix=FUNC %s
 ; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI -check-prefix=FUNC %s
 ; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=R600 -check-prefix=FUNC %s
 
 ; FUNC-LABEL: {{^}}fneg_fabs_fadd_f32:
 ; SI-NOT: and
-; SI: v_sub_f32_e64 {{v[0-9]+}}, {{v[0-9]+}}, |{{s[0-9]+}}|
+; SI: v_sub_f32_e64 {{v[0-9]+}}, {{s[0-9]+}}, |{{v[0-9]+}}|
 define amdgpu_kernel void @fneg_fabs_fadd_f32(float addrspace(1)* %out, float %x, float %y) {
   %fabs = call float @llvm.fabs.f32(float %x)
   %fsub = fsub float -0.000000e+00, %fabs
   %fadd = fadd float %y, %fsub
   store float %fadd, float addrspace(1)* %out, align 4
   ret void
 }
 
 ; FUNC-LABEL: {{^}}fneg_fabs_fmul_f32:
 ; SI-NOT: and
-; SI: v_mul_f32_e64 {{v[0-9]+}}, {{v[0-9]+}}, -|{{s[0-9]+}}|
+; SI: v_mul_f32_e64 {{v[0-9]+}}, {{s[0-9]+}}, -|{{v[0-9]+}}|
 ; SI-NOT: and
 define amdgpu_kernel void @fneg_fabs_fmul_f32(float addrspace(1)* %out, float %x, float %y) {
   %fabs = call float @llvm.fabs.f32(float %x)
   %fsub = fsub float -0.000000e+00, %fabs
   %fmul = fmul float %y, %fsub
   store float %fmul, float addrspace(1)* %out, align 4
   ret void
 }

 ; FUNC-LABEL: {{^}}fneg_fabs_v2f32:
 ; R600: |{{(PV|T[0-9])\.[XYZW]}}|
 ; R600: -PV
 ; R600: |{{(PV|T[0-9])\.[XYZW]}}|
 ; R600: -PV
 
 ; FIXME: In this case two uses of the constant should be folded
 ; SI: s_brev_b32 [[SIGNBITK:s[0-9]+]], 1{{$}}
-; SI: v_or_b32_e32 v{{[0-9]+}}, [[SIGNBITK]], v{{[0-9]+}}
-; SI: v_or_b32_e32 v{{[0-9]+}}, [[SIGNBITK]], v{{[0-9]+}}
+; SI: s_or_b32 s{{[0-9]+}}, s{{[0-9]+}}, [[SIGNBITK]]
+; SI: s_or_b32 s{{[0-9]+}}, s{{[0-9]+}}, [[SIGNBITK]]
 define amdgpu_kernel void @fneg_fabs_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %in) {
   %fabs = call <2 x float> @llvm.fabs.v2f32(<2 x float> %in)
   %fsub = fsub <2 x float> <float -0.000000e+00, float -0.000000e+00>, %fabs
   store <2 x float> %fsub, <2 x float> addrspace(1)* %out
   ret void
 }
 
 ; FUNC-LABEL: {{^}}fneg_fabs_v4f32:
 ; SI: s_brev_b32 [[SIGNBITK:s[0-9]+]], 1{{$}}
-; SI: v_or_b32_e32 v{{[0-9]+}}, [[SIGNBITK]], v{{[0-9]+}}
-; SI: v_or_b32_e32 v{{[0-9]+}}, [[SIGNBITK]], v{{[0-9]+}}
-; SI: v_or_b32_e32 v{{[0-9]+}}, [[SIGNBITK]], v{{[0-9]+}}
-; SI: v_or_b32_e32 v{{[0-9]+}}, [[SIGNBITK]], v{{[0-9]+}}
+; SI: s_or_b32 s{{[0-9]+}}, s{{[0-9]+}}, [[SIGNBITK]]
+; SI: s_or_b32 s{{[0-9]+}}, s{{[0-9]+}}, [[SIGNBITK]]
+; SI: s_or_b32 s{{[0-9]+}}, s{{[0-9]+}}, [[SIGNBITK]]
+; SI: s_or_b32 s{{[0-9]+}}, s{{[0-9]+}}, [[SIGNBITK]]
 define amdgpu_kernel void @fneg_fabs_v4f32(<4 x float> addrspace(1)* %out, <4 x float> %in) {
   %fabs = call <4 x float> @llvm.fabs.v4f32(<4 x float> %in)
   %fsub = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %fabs
   store <4 x float> %fsub, <4 x float> addrspace(1)* %out
   ret void
 }
 
 declare float @fabs(float) readnone
 declare float @llvm.fabs.f32(float) readnone
 declare <2 x float> @llvm.fabs.v2f32(<2 x float>) readnone
 declare <4 x float> @llvm.fabs.v4f32(<4 x float>) readnone

llvm/test/CodeGen/AMDGPU/fneg.ll

define amdgpu_kernel void @s_fneg_f32(float addrspace(1)* %out, float %in) {
   ret void
 }
 
 ; FUNC-LABEL: {{^}}s_fneg_v2f32:
 ; R600: -PV
 ; R600: -PV
 
 ; GCN: s_brev_b32 [[SIGNBIT:s[0-9]+]], 1
-; GCN: v_xor_b32
-; GCN: v_xor_b32
+; GCN: s_xor_b32
+; GCN: s_xor_b32
 define amdgpu_kernel void @s_fneg_v2f32(<2 x float> addrspace(1)* nocapture %out, <2 x float> %in) {
   %fneg = fsub <2 x float> <float -0.000000e+00, float -0.000000e+00>, %in
   store <2 x float> %fneg, <2 x float> addrspace(1)* %out
   ret void
 }
 
 ; FUNC-LABEL: {{^}}s_fneg_v4f32:
 ; R600: -PV
 ; R600: -T
 ; R600: -PV
 ; R600: -PV
 
-; GCN: v_xor_b32
-; GCN: v_xor_b32
-; GCN: v_xor_b32
-; GCN: v_xor_b32
+; GCN: s_xor_b32
+; GCN: s_xor_b32
+; GCN: s_xor_b32
+; GCN: s_xor_b32
 define amdgpu_kernel void @s_fneg_v4f32(<4 x float> addrspace(1)* nocapture %out, <4 x float> %in) {
   %fneg = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %in
   store <4 x float> %fneg, <4 x float> addrspace(1)* %out
   ret void
 }
 
 ; DAGCombiner will transform:
 ; (fneg (f32 bitcast (i32 a))) => (f32 bitcast (xor (i32 a), 0x80000000))

llvm/test/CodeGen/AMDGPU/fsub.ll

define amdgpu_kernel void @s_fsub_f32(float addrspace(1)* %out, float %a, float %b) {
   store float %sub, float addrspace(1)* %out, align 4
   ret void
 }
 
 ; FUNC-LABEL: {{^}}fsub_v2f32:
 ; R600-DAG: ADD {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[3].X, -KC0[3].Z
 ; R600-DAG: ADD {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[2].W, -KC0[3].Y
 
-; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
-; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
+; SI: v_sub_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
+; SI: v_sub_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
 define amdgpu_kernel void @fsub_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %a, <2 x float> %b) {
   %sub = fsub <2 x float> %a, %b
   store <2 x float> %sub, <2 x float> addrspace(1)* %out, align 8
   ret void
 }
 
 ; FUNC-LABEL: {{^}}v_fsub_v4f32:
 ; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], -T[0-9]+\.[XYZW]}}
define amdgpu_kernel void @v_fsub_v4f32(<4 x float> addrspace(1)* %out, <4 x float> addrspace(1)* %in) {
   %a = load <4 x float>, <4 x float> addrspace(1)* %in, align 16
   %b = load <4 x float>, <4 x float> addrspace(1)* %b_ptr, align 16
   %result = fsub <4 x float> %a, %b
   store <4 x float> %result, <4 x float> addrspace(1)* %out, align 16
   ret void
 }
 
 ; FUNC-LABEL: {{^}}s_fsub_v4f32:
-; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
-; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
-; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
-; SI: v_subrev_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
+; SI: v_sub_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
+; SI: v_sub_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
+; SI: v_sub_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
+; SI: v_sub_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
 ; SI: s_endpgm
 define amdgpu_kernel void @s_fsub_v4f32(<4 x float> addrspace(1)* %out, <4 x float> %a, <4 x float> %b) {
   %result = fsub <4 x float> %a, %b
   store <4 x float> %result, <4 x float> addrspace(1)* %out, align 16
   ret void
 }
 
 ; FUNC-LABEL: {{^}}v_fneg_fsub_f32:

llvm/test/CodeGen/AMDGPU/i1-copy-from-loop.ll

 ; RUN: llc -mtriple=amdgcn-- -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
 ; RUN: llc -mtriple=amdgcn-- -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
 
 ; SI-LABEL: {{^}}i1_copy_from_loop:
 ;
-; SI: ; %Flow
-; SI-DAG:  s_andn2_b64       [[LCSSA_ACCUM:s\[[0-9]+:[0-9]+\]]], [[LCSSA_ACCUM]], exec
-; SI-DAG:  s_and_b64         [[CC_MASK2:s\[[0-9]+:[0-9]+\]]], [[CC_ACCUM:s\[[0-9]+:[0-9]+\]]], exec
-; SI:      s_or_b64          [[LCSSA_ACCUM]], [[LCSSA_ACCUM]], [[CC_MASK2]]
+; SI: [[LOOP:BB0_[0-9]+]]:  ; %Flow1
+; SI:   s_or_b64 exec, exec, [[EXIT_MASK:s\[[0-9]+:[0-9]+\]]]
+; SI:   ; %Flow
+; SI:  s_and_b64 [[ACCUM_MASK:s\[[0-9]+:[0-9]+\]]], [[CC_MASK:s\[[0-9]+:[0-9]+\]]], exec
+; SI:  s_or_b64  [[I1_VALUE:s\[[0-9]+:[0-9]+\]]], s[6:7], [[ACCUM_MASK]]
+; SI:  s_cbranch_execz [[FOR_END_LABEL:BB0_[0-9]+]]
 
 ; SI: ; %for.body
-; SI:      v_cmp_gt_u32_e64  [[CC_SREG:s\[[0-9]+:[0-9]+\]]], 4,
-; SI-DAG:  s_andn2_b64       [[CC_ACCUM]], [[CC_ACCUM]], exec
-; SI-DAG:  s_and_b64         [[CC_MASK:s\[[0-9]+:[0-9]+\]]], [[CC_SREG]], exec
-; SI:      s_or_b64          [[CC_ACCUM]], [[CC_ACCUM]], [[CC_MASK]]
+; SI:      v_cmp_lt_u32_e64  [[CC_MASK]], s{{[0-9]+}}, 4
 
-; SI: ; %Flow1
-; SI:      s_or_b64          [[CC_ACCUM]], [[CC_ACCUM]], exec
-
-; SI: ; %for.end
-; SI:      s_and_saveexec_b64 {{s\[[0-9]+:[0-9]+\]}}, [[LCSSA_ACCUM]]
+; SI: [[FOR_END_LABEL]]
+; SI:      s_or_b64 exec, exec, [[EXIT_MASK]]
+; SI:      s_and_saveexec_b64 {{s\[[0-9]+:[0-9]+\]}}, [[I1_VALUE]]
+; SI:      s_cbranch_execz [[EXIT:BB0_[0-9]+]]
+; SI: [[EXIT]]
+; SI-NEXT: s_endpgm
 
 define amdgpu_ps void @i1_copy_from_loop(<4 x i32> inreg %rsrc, i32 %tid) {
 entry:
   br label %for.body
 
 for.body:
   %i = phi i32 [0, %entry], [%i.inc, %end.loop]
   %cc = icmp ult i32 %i, 4

llvm/test/CodeGen/AMDGPU/i1-copy-phi-uniform-branch.ll

 ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
 
 ; GCN-LABEL: {{^}}test_dont_clobber_scc:
 
 ; GCN: ; %entry
 ; GCN:      s_cmp_eq_u32    s0, 0
 ; GCN:      s_cbranch_scc1  [[PREEXIT:BB[0-9_]+]]
 
 ; GCN: ; %blocka
-; GCN:      s_xor_b64       s[{{[0-9:]+}}], exec, -1
 ; GCN:      s_cmp_eq_u32    s1, 0
 ; GCN:      s_cbranch_scc1  [[EXIT:BB[0-9_]+]]
 
 ; GCN: [[PREEXIT]]:
 ; GCN: [[EXIT]]:
 
 define amdgpu_vs float @test_dont_clobber_scc(i32 inreg %uni, i32 inreg %uni2) #0 {
 entry:

llvm/test/CodeGen/AMDGPU/implicit-def-muse.ll

 ; RUN: llc -march=amdgcn -stop-after=amdgpu-isel -verify-machineinstrs -o - %s | FileCheck %s
 
 ; CHECK-LABEL: vcopy_i1_undef
-; CHECK: [[IMPDEF0:%[0-9]+]]:vreg_1 = IMPLICIT_DEF
+; CHECK: [[IMPDEF0:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
 ; CHECK-NOT: COPY
-; CHECK: [[IMPDEF1:%[0-9]+]]:vreg_1 = IMPLICIT_DEF
+; CHECK: [[IMPDEF1:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
 ; CHECK-NOT: COPY [[IMPDEF0]]
 ; CHECK-NOT: COPY [[IMPDEF1]]
 ; CHECK: .false:
 define <2 x float> @vcopy_i1_undef(<2 x float> addrspace(1)* %p) {
 entry:
   br i1 undef, label %exit, label %false
 
 false:

llvm/test/CodeGen/AMDGPU/insert_vector_elt.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -verify-machineinstrs -mtriple=amdgcn-amd-amdhsa -mcpu=kaveri -mattr=-flat-for-global,+max-private-element-size-16 < %s | FileCheck -enable-var-scope -check-prefixes=GCN,SI,GCN-NO-TONGA %s
 ; RUN: llc -verify-machineinstrs -mtriple=amdgcn-amd-amdhsa -mcpu=tonga -mattr=-flat-for-global -mattr=+max-private-element-size-16 < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI,GCN-TONGA %s
 
 ; FIXME: Broken on evergreen
 ; FIXME: For some reason the 8 and 16 vectors are being stored as
 ; individual elements instead of 128-bit stores.
 
 
 ; FIXME: Why is the constant moved into the intermediate register and
 ; not just directly into the vector component?
 define amdgpu_kernel void @insertelement_v4f32_0(<4 x float> addrspace(1)* %out, <4 x float> %a) nounwind {
 ; SI-LABEL: insertelement_v4f32_0:
 ; SI:       ; %bb.0:
 ; SI-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
 ; SI-NEXT:    s_load_dwordx4 s[4:7], s[4:5], 0x4
-; SI-NEXT:    s_mov_b32 s8, 0x40a00000
-; SI-NEXT:    s_mov_b32 s3, 0x100f000
-; SI-NEXT:    s_mov_b32 s2, -1
 ; SI-NEXT:    s_waitcnt lgkmcnt(0)
+; SI-NEXT:    s_mov_b32 s4, 0x40a00000
 ; SI-NEXT:    v_mov_b32_e32 v0, s4
+; SI-NEXT:    s_mov_b32 s3, 0x100f000
+; SI-NEXT:    s_mov_b32 s2, -1
 ; SI-NEXT:    v_mov_b32_e32 v1, s5
 ; SI-NEXT:    v_mov_b32_e32 v2, s6
 ; SI-NEXT:    v_mov_b32_e32 v3, s7
-; SI-NEXT:    v_mov_b32_e32 v0, s8
 ; SI-NEXT:    buffer_store_dwordx4 v[0:3], off, s[0:3], 0
 ; SI-NEXT:    s_endpgm
 ;
 ; VI-LABEL: insertelement_v4f32_0:
 ; VI:       ; %bb.0:
 ; VI-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
 ; VI-NEXT:    s_load_dwordx4 s[4:7], s[4:5], 0x10
-; VI-NEXT:    s_mov_b32 s8, 0x40a00000
-; VI-NEXT:    s_mov_b32 s3, 0x1100f000
-; VI-NEXT:    s_mov_b32 s2, -1
 ; VI-NEXT:    s_waitcnt lgkmcnt(0)
+; VI-NEXT:    s_mov_b32 s4, 0x40a00000
 ; VI-NEXT:    v_mov_b32_e32 v0, s4
+; VI-NEXT:    s_mov_b32 s3, 0x1100f000
+; VI-NEXT:    s_mov_b32 s2, -1
 ; VI-NEXT:    v_mov_b32_e32 v1, s5
 ; VI-NEXT:    v_mov_b32_e32 v2, s6
 ; VI-NEXT:    v_mov_b32_e32 v3, s7
-; VI-NEXT:    v_mov_b32_e32 v0, s8
 ; VI-NEXT:    buffer_store_dwordx4 v[0:3], off, s[0:3], 0
 ; VI-NEXT:    s_endpgm
   %vecins = insertelement <4 x float> %a, float 5.000000e+00, i32 0
   store <4 x float> %vecins, <4 x float> addrspace(1)* %out, align 16
   ret void
 }
 
 define amdgpu_kernel void @insertelement_v4f32_1(<4 x float> addrspace(1)* %out, <4 x float> %a) nounwind {
 ; SI-LABEL: insertelement_v4f32_1:
 ; SI:       ; %bb.0:
 ; SI-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
 ; SI-NEXT:    s_load_dwordx4 s[4:7], s[4:5], 0x4
-; SI-NEXT:    s_mov_b32 s8, 0x40a00000
+; SI-NEXT:    s_waitcnt lgkmcnt(0)
+; SI-NEXT:    s_mov_b32 s5, 0x40a00000
 ; SI-NEXT:    s_mov_b32 s3, 0x100f000
 ; SI-NEXT:    s_mov_b32 s2, -1
-; SI-NEXT:    s_waitcnt lgkmcnt(0)
 ; SI-NEXT:    v_mov_b32_e32 v0, s4
 ; SI-NEXT:    v_mov_b32_e32 v1, s5
 ; SI-NEXT:    v_mov_b32_e32 v2, s6
 ; SI-NEXT:    v_mov_b32_e32 v3, s7
-; SI-NEXT:    v_mov_b32_e32 v1, s8
 ; SI-NEXT:    buffer_store_dwordx4 v[0:3], off, s[0:3], 0
 ; SI-NEXT:    s_endpgm
 ;
 ; VI-LABEL: insertelement_v4f32_1:
 ; VI:       ; %bb.0:
 ; VI-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
 ; VI-NEXT:    s_load_dwordx4 s[4:7], s[4:5], 0x10
-; VI-NEXT:    s_mov_b32 s8, 0x40a00000
+; VI-NEXT:    s_waitcnt lgkmcnt(0)
+; VI-NEXT:    s_mov_b32 s5, 0x40a00000
 ; VI-NEXT:    s_mov_b32 s3, 0x1100f000
 ; VI-NEXT:    s_mov_b32 s2, -1
-; VI-NEXT:    s_waitcnt lgkmcnt(0)
 ; VI-NEXT:    v_mov_b32_e32 v0, s4
 ; VI-NEXT:    v_mov_b32_e32 v1, s5
 ; VI-NEXT:    v_mov_b32_e32 v2, s6
 ; VI-NEXT:    v_mov_b32_e32 v3, s7
-; VI-NEXT:    v_mov_b32_e32 v1, s8
 ; VI-NEXT:    buffer_store_dwordx4 v[0:3], off, s[0:3], 0
 ; VI-NEXT:    s_endpgm
   %vecins = insertelement <4 x float> %a, float 5.000000e+00, i32 1
   store <4 x float> %vecins, <4 x float> addrspace(1)* %out, align 16
   ret void
 }
 
 define amdgpu_kernel void @insertelement_v4f32_2(<4 x float> addrspace(1)* %out, <4 x float> %a) nounwind {
 ; SI-LABEL: insertelement_v4f32_2:
 ; SI:       ; %bb.0:
 ; SI-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
 ; SI-NEXT:    s_load_dwordx4 s[4:7], s[4:5], 0x4
-; SI-NEXT:    s_mov_b32 s8, 0x40a00000
+; SI-NEXT:    s_waitcnt lgkmcnt(0)
+; SI-NEXT:    s_mov_b32 s6, 0x40a00000
 ; SI-NEXT:    s_mov_b32 s3, 0x100f000
 ; SI-NEXT:    s_mov_b32 s2, -1
-; SI-NEXT:    s_waitcnt lgkmcnt(0)
 ; SI-NEXT:    v_mov_b32_e32 v0, s4
-; SI-NEXT:    v_mov_b32_e32 v2, s6
 ; SI-NEXT:    v_mov_b32_e32 v1, s5
+; SI-NEXT:    v_mov_b32_e32 v2, s6
 ; SI-NEXT:    v_mov_b32_e32 v3, s7
-; SI-NEXT:    v_mov_b32_e32 v2, s8
 ; SI-NEXT:    buffer_store_dwordx4 v[0:3], off, s[0:3], 0
 ; SI-NEXT:    s_endpgm
 ;
 ; VI-LABEL: insertelement_v4f32_2:
 ; VI:       ; %bb.0:
 ; VI-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
 ; VI-NEXT:    s_load_dwordx4 s[4:7], s[4:5], 0x10
-; VI-NEXT:    s_mov_b32 s8, 0x40a00000
+; VI-NEXT:    s_waitcnt lgkmcnt(0)
+; VI-NEXT:    s_mov_b32 s6, 0x40a00000
 ; VI-NEXT:    s_mov_b32 s3, 0x1100f000
 ; VI-NEXT:    s_mov_b32 s2, -1
-; VI-NEXT:    s_waitcnt lgkmcnt(0)
 ; VI-NEXT:    v_mov_b32_e32 v0, s4
-; VI-NEXT:    v_mov_b32_e32 v2, s6
 ; VI-NEXT:    v_mov_b32_e32 v1, s5
+; VI-NEXT:    v_mov_b32_e32 v2, s6
 ; VI-NEXT:    v_mov_b32_e32 v3, s7
-; VI-NEXT:    v_mov_b32_e32 v2, s8
 ; VI-NEXT:    buffer_store_dwordx4 v[0:3], off, s[0:3], 0
 ; VI-NEXT:    s_endpgm
   %vecins = insertelement <4 x float> %a, float 5.000000e+00, i32 2
   store <4 x float> %vecins, <4 x float> addrspace(1)* %out, align 16
   ret void
 }
 
 define amdgpu_kernel void @insertelement_v4f32_3(<4 x float> addrspace(1)* %out, <4 x float> %a) nounwind {
 ; SI-LABEL: insertelement_v4f32_3:
 ; SI:       ; %bb.0:
 ; SI-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
 ; SI-NEXT:    s_load_dwordx4 s[4:7], s[4:5], 0x4
-; SI-NEXT:    s_mov_b32 s8, 0x40a00000
+; SI-NEXT:    s_waitcnt lgkmcnt(0)
+; SI-NEXT:    s_mov_b32 s7, 0x40a00000
 ; SI-NEXT:    s_mov_b32 s3, 0x100f000
 ; SI-NEXT:    s_mov_b32 s2, -1
-; SI-NEXT:    s_waitcnt lgkmcnt(0)
 ; SI-NEXT:    v_mov_b32_e32 v0, s4
-; SI-NEXT:    v_mov_b32_e32 v3, s7
 ; SI-NEXT:    v_mov_b32_e32 v1, s5
 ; SI-NEXT:    v_mov_b32_e32 v2, s6
-; SI-NEXT:    v_mov_b32_e32 v3, s8
+; SI-NEXT:    v_mov_b32_e32 v3, s7
 ; SI-NEXT:    buffer_store_dwordx4 v[0:3], off, s[0:3], 0
 ; SI-NEXT:    s_endpgm
 ;
 ; VI-LABEL: insertelement_v4f32_3:
 ; VI:       ; %bb.0:
 ; VI-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
 ; VI-NEXT:    s_load_dwordx4 s[4:7], s[4:5], 0x10
-; VI-NEXT:    s_mov_b32 s8, 0x40a00000
+; VI-NEXT:    s_waitcnt lgkmcnt(0)
+; VI-NEXT:    s_mov_b32 s7, 0x40a00000
 ; VI-NEXT:    s_mov_b32 s3, 0x1100f000
 ; VI-NEXT:    s_mov_b32 s2, -1
-; VI-NEXT:    s_waitcnt lgkmcnt(0)
 ; VI-NEXT:    v_mov_b32_e32 v0, s4
-; VI-NEXT:    v_mov_b32_e32 v3, s7
 ; VI-NEXT:    v_mov_b32_e32 v1, s5
 ; VI-NEXT:    v_mov_b32_e32 v2, s6
-; VI-NEXT:    v_mov_b32_e32 v3, s8
+; VI-NEXT:    v_mov_b32_e32 v3, s7
 ; VI-NEXT:    buffer_store_dwordx4 v[0:3], off, s[0:3], 0
 ; VI-NEXT:    s_endpgm
   %vecins = insertelement <4 x float> %a, float 5.000000e+00, i32 3
   store <4 x float> %vecins, <4 x float> addrspace(1)* %out, align 16
   ret void
 }
 
 define amdgpu_kernel void @insertelement_v4i32_0(<4 x i32> addrspace(1)* %out, <4 x i32> %a) nounwind {

 ; SI-LABEL: insertelement_v3f32_1:
 ; SI:       ; %bb.0:
 ; SI-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
 ; SI-NEXT:    s_load_dwordx4 s[4:7], s[4:5], 0x4
 ; SI-NEXT:    s_mov_b32 s3, 0x100f000
 ; SI-NEXT:    s_mov_b32 s2, -1
 ; SI-NEXT:    v_mov_b32_e32 v1, 0x40a00000
 ; SI-NEXT:    s_waitcnt lgkmcnt(0)
-; SI-NEXT:    v_mov_b32_e32 v2, s6
 ; SI-NEXT:    v_mov_b32_e32 v0, s4
+; SI-NEXT:    v_mov_b32_e32 v2, s6
 ; SI-NEXT:    buffer_store_dwordx3 v[0:2], off, s[0:3], 0
 ; SI-NEXT:    s_endpgm
 ;
 ; VI-LABEL: insertelement_v3f32_1:
 ; VI:       ; %bb.0:
 ; VI-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
 ; VI-NEXT:    s_load_dwordx4 s[4:7], s[4:5], 0x10
 ; VI-NEXT:    s_mov_b32 s3, 0x1100f000
 ; VI-NEXT:    s_mov_b32 s2, -1
 ; VI-NEXT:    v_mov_b32_e32 v1, 0x40a00000
 ; VI-NEXT:    s_waitcnt lgkmcnt(0)
-; VI-NEXT:    v_mov_b32_e32 v2, s6
 ; VI-NEXT:    v_mov_b32_e32 v0, s4
+; VI-NEXT:    v_mov_b32_e32 v2, s6
 ; VI-NEXT:    buffer_store_dwordx3 v[0:2], off, s[0:3], 0
 ; VI-NEXT:    s_endpgm
   %vecins = insertelement <3 x float> %a, float 5.000000e+00, i32 1
   store <3 x float> %vecins, <3 x float> addrspace(1)* %out, align 16
   ret void
 }
 
 define amdgpu_kernel void @insertelement_v3f32_2(<3 x float> addrspace(1)* %out, <3 x float> %a) nounwind {
 ; SI-LABEL: insertelement_v3f32_2:
 ; SI:       ; %bb.0:
 ; SI-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
 ; SI-NEXT:    s_load_dwordx4 s[4:7], s[4:5], 0x4
 ; SI-NEXT:    s_mov_b32 s3, 0x100f000
 ; SI-NEXT:    s_mov_b32 s2, -1
 ; SI-NEXT:    v_mov_b32_e32 v2, 0x40a00000
 ; SI-NEXT:    s_waitcnt lgkmcnt(0)
-; SI-NEXT:    v_mov_b32_e32 v1, s5
 ; SI-NEXT:    v_mov_b32_e32 v0, s4
+; SI-NEXT:    v_mov_b32_e32 v1, s5
 ; SI-NEXT:    buffer_store_dwordx3 v[0:2], off, s[0:3], 0
 ; SI-NEXT:    s_endpgm
 ;
 ; VI-LABEL: insertelement_v3f32_2:
 ; VI:       ; %bb.0:
 ; VI-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
 ; VI-NEXT:    s_load_dwordx4 s[4:7], s[4:5], 0x10
 ; VI-NEXT:    s_mov_b32 s3, 0x1100f000
 ; VI-NEXT:    s_mov_b32 s2, -1
 ; VI-NEXT:    v_mov_b32_e32 v2, 0x40a00000
 ; VI-NEXT:    s_waitcnt lgkmcnt(0)
-; VI-NEXT:    v_mov_b32_e32 v1, s5
 ; VI-NEXT:    v_mov_b32_e32 v0, s4
+; VI-NEXT:    v_mov_b32_e32 v1, s5
 ; VI-NEXT:    buffer_store_dwordx3 v[0:2], off, s[0:3], 0
 ; VI-NEXT:    s_endpgm
   %vecins = insertelement <3 x float> %a, float 5.000000e+00, i32 2
   store <3 x float> %vecins, <3 x float> addrspace(1)* %out, align 16
   ret void
 }
 
 define amdgpu_kernel void @insertelement_v3f32_3(<3 x float> addrspace(1)* %out, <3 x float> %a) nounwind {

 }
 
 define amdgpu_kernel void @dynamic_insertelement_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %a, i32 %b) nounwind {
 ; SI-LABEL: dynamic_insertelement_v2f32:
 ; SI:       ; %bb.0:
 ; SI-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
 ; SI-NEXT:    s_load_dwordx2 s[6:7], s[4:5], 0x2
 ; SI-NEXT:    s_load_dword s4, s[4:5], 0x4
-; SI-NEXT:    v_mov_b32_e32 v2, 0x40a00000
+; SI-NEXT:    v_mov_b32_e32 v0, 0x40a00000
 ; SI-NEXT:    s_mov_b32 s3, 0x100f000
 ; SI-NEXT:    s_mov_b32 s2, -1
 ; SI-NEXT:    s_waitcnt lgkmcnt(0)
-; SI-NEXT:    v_mov_b32_e32 v0, s7
+; SI-NEXT:    v_mov_b32_e32 v1, s7
 ; SI-NEXT:    v_cmp_ne_u32_e64 vcc, s4, 1
-; SI-NEXT:    v_cndmask_b32_e32 v1, v2, v0, vcc
-; SI-NEXT:    v_mov_b32_e32 v0, s6
+; SI-NEXT:    v_cndmask_b32_e32 v1, v0, v1, vcc
+; SI-NEXT:    v_mov_b32_e32 v2, s6
 ; SI-NEXT:    v_cmp_ne_u32_e64 vcc, s4, 0
-; SI-NEXT:    v_cndmask_b32_e32 v0, v2, v0, vcc
+; SI-NEXT:    v_cndmask_b32_e32 v0, v0, v2, vcc
 ; SI-NEXT:    buffer_store_dwordx2 v[0:1], off, s[0:3], 0
 ; SI-NEXT:    s_endpgm
 ;
 ; VI-LABEL: dynamic_insertelement_v2f32:
 ; VI:       ; %bb.0:
 ; VI-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
 ; VI-NEXT:    s_load_dwordx2 s[6:7], s[4:5], 0x8
 ; VI-NEXT:    s_load_dword s4, s[4:5], 0x10
-; VI-NEXT:    v_mov_b32_e32 v2, 0x40a00000
+; VI-NEXT:    v_mov_b32_e32 v0, 0x40a00000
 ; VI-NEXT:    s_mov_b32 s3, 0x1100f000
 ; VI-NEXT:    s_mov_b32 s2, -1
 ; VI-NEXT:    s_waitcnt lgkmcnt(0)
-; VI-NEXT:    v_mov_b32_e32 v0, s7
+; VI-NEXT:    v_mov_b32_e32 v1, s7
 ; VI-NEXT:    v_cmp_ne_u32_e64 vcc, s4, 1
-; VI-NEXT:    v_cndmask_b32_e32 v1, v2, v0, vcc
-; VI-NEXT:    v_mov_b32_e32 v0, s6
+; VI-NEXT:    v_cndmask_b32_e32 v1, v0, v1, vcc
+; VI-NEXT:    v_mov_b32_e32 v2, s6
 ; VI-NEXT:    v_cmp_ne_u32_e64 vcc, s4, 0
-; VI-NEXT:    v_cndmask_b32_e32 v0, v2, v0, vcc
+; VI-NEXT:    v_cndmask_b32_e32 v0, v0, v2, vcc
 ; VI-NEXT:    buffer_store_dwordx2 v[0:1], off, s[0:3], 0
 ; VI-NEXT:    s_endpgm
   %vecins = insertelement <2 x float> %a, float 5.000000e+00, i32 %b
   store <2 x float> %vecins, <2 x float> addrspace(1)* %out, align 8
   ret void
 }
 
 define amdgpu_kernel void @dynamic_insertelement_v3f32(<3 x float> addrspace(1)* %out, <3 x float> %a, i32 %b) nounwind {
 ; SI-LABEL: dynamic_insertelement_v3f32:
 ; SI:       ; %bb.0:
 ; SI-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
 ; SI-NEXT:    s_load_dwordx4 s[8:11], s[4:5], 0x4
 ; SI-NEXT:    s_load_dword s4, s[4:5], 0x8
-; SI-NEXT:    v_mov_b32_e32 v3, 0x40a00000
+; SI-NEXT:    v_mov_b32_e32 v0, 0x40a00000
 ; SI-NEXT:    s_mov_b32 s3, 0x100f000
 ; SI-NEXT:    s_mov_b32 s2, -1
 ; SI-NEXT:    s_waitcnt lgkmcnt(0)
-; SI-NEXT:    v_mov_b32_e32 v2, s10
+; SI-NEXT:    v_mov_b32_e32 v1, s10
 ; SI-NEXT:    v_cmp_ne_u32_e64 vcc, s4, 2
-; SI-NEXT:    v_cndmask_b32_e32 v2, v3, v2, vcc
+; SI-NEXT:    v_cndmask_b32_e32 v2, v0, v1, vcc
 ; SI-NEXT:    v_mov_b32_e32 v1, s9
 ; SI-NEXT:    v_cmp_ne_u32_e64 vcc, s4, 1
-; SI-NEXT:    v_cndmask_b32_e32 v1, v3, v1, vcc
-; SI-NEXT:    v_mov_b32_e32 v0, s8
+; SI-NEXT:    v_cndmask_b32_e32 v1, v0, v1, vcc
+; SI-NEXT:    v_mov_b32_e32 v3, s8
 ; SI-NEXT:    v_cmp_ne_u32_e64 vcc, s4, 0
-; SI-NEXT:    v_cndmask_b32_e32 v0, v3, v0, vcc
+; SI-NEXT:    v_cndmask_b32_e32 v0, v0, v3, vcc
 ; SI-NEXT:    buffer_store_dwordx3 v[0:2], off, s[0:3], 0
 ; SI-NEXT:    s_endpgm
 ;
 ; VI-LABEL: dynamic_insertelement_v3f32:
 ; VI:       ; %bb.0:
 ; VI-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
 ; VI-NEXT:    s_load_dwordx4 s[8:11], s[4:5], 0x10
 ; VI-NEXT:    s_load_dword s4, s[4:5], 0x20
-; VI-NEXT:    v_mov_b32_e32 v3, 0x40a00000
+; VI-NEXT:    v_mov_b32_e32 v0, 0x40a00000
 ; VI-NEXT:    s_mov_b32 s3, 0x1100f000
 ; VI-NEXT:    s_mov_b32 s2, -1
 ; VI-NEXT:    s_waitcnt lgkmcnt(0)
-; VI-NEXT:    v_mov_b32_e32 v2, s10
+; VI-NEXT:    v_mov_b32_e32 v1, s10
 ; VI-NEXT:    v_cmp_ne_u32_e64 vcc, s4, 2
-; VI-NEXT:    v_cndmask_b32_e32 v2, v3, v2, vcc
+; VI-NEXT:    v_cndmask_b32_e32 v2, v0, v1, vcc
 ; VI-NEXT:    v_mov_b32_e32 v1, s9
 ; VI-NEXT:    v_cmp_ne_u32_e64 vcc, s4, 1
-; VI-NEXT:    v_cndmask_b32_e32 v1, v3, v1, vcc
-; VI-NEXT:    v_mov_b32_e32 v0, s8
+; VI-NEXT:    v_cndmask_b32_e32 v1, v0, v1, vcc
+; VI-NEXT:    v_mov_b32_e32 v3, s8
 ; VI-NEXT:    v_cmp_ne_u32_e64 vcc, s4, 0
-; VI-NEXT:    v_cndmask_b32_e32 v0, v3, v0, vcc
+; VI-NEXT:    v_cndmask_b32_e32 v0, v0, v3, vcc
 ; VI-NEXT:    buffer_store_dwordx3 v[0:2], off, s[0:3], 0
 ; VI-NEXT:    s_endpgm
   %vecins = insertelement <3 x float> %a, float 5.000000e+00, i32 %b
   store <3 x float> %vecins, <3 x float> addrspace(1)* %out, align 16
   ret void
 }
 
 define amdgpu_kernel void @dynamic_insertelement_v4f32(<4 x float> addrspace(1)* %out, <4 x float> %a, i32 %b) nounwind {
 ; SI-LABEL: dynamic_insertelement_v4f32:
 ; SI:       ; %bb.0:
 ; SI-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
 ; SI-NEXT:    s_load_dwordx4 s[8:11], s[4:5], 0x4
 ; SI-NEXT:    s_load_dword s4, s[4:5], 0x8
-; SI-NEXT:    v_mov_b32_e32 v4, 0x40a00000
+; SI-NEXT:    v_mov_b32_e32 v0, 0x40a00000
 ; SI-NEXT:    s_mov_b32 s3, 0x100f000
 ; SI-NEXT:    s_mov_b32 s2, -1
 ; SI-NEXT:    s_waitcnt lgkmcnt(0)
-; SI-NEXT:    v_mov_b32_e32 v0, s11
+; SI-NEXT:    v_mov_b32_e32 v1, s11
 ; SI-NEXT:    v_cmp_ne_u32_e64 vcc, s4, 3
-; SI-NEXT:    v_cndmask_b32_e32 v3, v4, v0, vcc
-; SI-NEXT:    v_mov_b32_e32 v0, s10
+; SI-NEXT:    v_cndmask_b32_e32 v3, v0, v1, vcc
+; SI-NEXT:    v_mov_b32_e32 v1, s10
 ; SI-NEXT:    v_cmp_ne_u32_e64 vcc, s4, 2
-; SI-NEXT:    v_cndmask_b32_e32 v2, v4, v0, vcc
-; SI-NEXT:    v_mov_b32_e32 v0, s9
+; SI-NEXT:    v_cndmask_b32_e32 v2, v0, v1, vcc
+; SI-NEXT:    v_mov_b32_e32 v1, s9
 ; SI-NEXT:    v_cmp_ne_u32_e64 vcc, s4, 1
-; SI-NEXT:    v_cndmask_b32_e32 v1, v4, v0, vcc
-; SI-NEXT:    v_mov_b32_e32 v0, s8
+; SI-NEXT:    v_cndmask_b32_e32 v1, v0, v1, vcc
+; SI-NEXT:    v_mov_b32_e32 v4, s8
 ; SI-NEXT:    v_cmp_ne_u32_e64 vcc, s4, 0
-; SI-NEXT:    v_cndmask_b32_e32 v0, v4, v0, vcc
+; SI-NEXT:    v_cndmask_b32_e32 v0, v0, v4, vcc
 ; SI-NEXT:    buffer_store_dwordx4 v[0:3], off, s[0:3], 0
 ; SI-NEXT:    s_endpgm
 ;
 ; VI-LABEL: dynamic_insertelement_v4f32:
 ; VI:       ; %bb.0:
 ; VI-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
 ; VI-NEXT:    s_load_dwordx4 s[8:11], s[4:5], 0x10
 ; VI-NEXT:    s_load_dword s4, s[4:5], 0x20
-; VI-NEXT:    v_mov_b32_e32 v4, 0x40a00000
+; VI-NEXT:    v_mov_b32_e32 v0, 0x40a00000
 ; VI-NEXT:    s_mov_b32 s3, 0x1100f000
 ; VI-NEXT:    s_mov_b32 s2, -1
 ; VI-NEXT:    s_waitcnt lgkmcnt(0)
-; VI-NEXT:    v_mov_b32_e32 v0, s11
+; VI-NEXT:    v_mov_b32_e32 v1, s11
 ; VI-NEXT:    v_cmp_ne_u32_e64 vcc, s4, 3
-; VI-NEXT:    v_cndmask_b32_e32 v3, v4, v0, vcc
-; VI-NEXT:    v_mov_b32_e32 v0, s10
+; VI-NEXT:    v_cndmask_b32_e32 v3, v0, v1, vcc
+; VI-NEXT:    v_mov_b32_e32 v1, s10
 ; VI-NEXT:    v_cmp_ne_u32_e64 vcc, s4, 2
-; VI-NEXT:    v_cndmask_b32_e32 v2, v4, v0, vcc
-; VI-NEXT:    v_mov_b32_e32 v0, s9
+; VI-NEXT:    v_cndmask_b32_e32 v2, v0, v1, vcc
+; VI-NEXT:    v_mov_b32_e32 v1, s9
 ; VI-NEXT:    v_cmp_ne_u32_e64 vcc, s4, 1
-; VI-NEXT:    v_cndmask_b32_e32 v1, v4, v0, vcc
-; VI-NEXT:    v_mov_b32_e32 v0, s8
+; VI-NEXT:    v_cndmask_b32_e32 v1, v0, v1, vcc
+; VI-NEXT:    v_mov_b32_e32 v4, s8
 ; VI-NEXT:    v_cmp_ne_u32_e64 vcc, s4, 0
-; VI-NEXT:    v_cndmask_b32_e32 v0, v4, v0, vcc
+; VI-NEXT:    v_cndmask_b32_e32 v0, v0, v4, vcc
 ; VI-NEXT:    buffer_store_dwordx4 v[0:3], off, s[0:3], 0
 ; VI-NEXT:    s_endpgm
   %vecins = insertelement <4 x float> %a, float 5.000000e+00, i32 %b
   store <4 x float> %vecins, <4 x float> addrspace(1)* %out, align 16
   ret void
 }
 
 define amdgpu_kernel void @dynamic_insertelement_v8f32(<8 x float> addrspace(1)* %out, <8 x float> %a, i32 %b) nounwind {

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.div.scale.ll

define amdgpu_kernel void @test_div_scale_f32_undef_val_val(float addrspace(1)* %out) #0 {
   %result = call { float, i1 } @llvm.amdgcn.div.scale.f32(float undef, float 8.0, i1 false)
   %result0 = extractvalue { float, i1 } %result, 0
   store float %result0, float addrspace(1)* %out, align 4
   ret void
 }
 
 ; SI-LABEL: {{^}}test_div_scale_f32_undef_undef_val:
 ; SI-NOT: v0
-; SI: v_div_scale_f32 v{{[0-9]+}}, s{{\[[0-9]+:[0-9]+\]}}, v0, v0, v0
+; SI: v_div_scale_f32 v{{[0-9]+}}, s{{\[[0-9]+:[0-9]+\]}}, s0, s0, v0
 define amdgpu_kernel void @test_div_scale_f32_undef_undef_val(float addrspace(1)* %out) #0 {
   %result = call { float, i1 } @llvm.amdgcn.div.scale.f32(float undef, float undef, i1 false)
   %result0 = extractvalue { float, i1 } %result, 0
   store float %result0, float addrspace(1)* %out, align 4
   ret void
 }
 
 ; SI-LABEL: {{^}}test_div_scale_f64_val_undef_val:

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.fmed3.ll

 define amdgpu_kernel void @test_fabs_fmed3(float addrspace(1)* %out, float %src0, float %src1, float %src2) #1 {
   %med3 = call float @llvm.amdgcn.fmed3.f32(float %src0, float %src1, float %src2)
   %fabs.med3 = call float @llvm.fabs.f32(float %med3)
   store float %fabs.med3, float addrspace(1)* %out
   ret void
 }
 
 ; GCN-LABEL: {{^}}test_fneg_fmed3_rr_0:
-; GCN: s_brev_b32 [[NEG0:s[0-9]+]], 1
-; GCN: v_med3_f32 v{{[0-9]+}}, -v{{[0-9]+}}, -v{{[0-9]+}}, [[NEG0]]
+; GCN: v_bfrev_b32_e32 [[NEG0:v[0-9]+]], 1
+; GCN: v_med3_f32 v{{[0-9]+}}, -s{{[0-9]+}}, -v{{[0-9]+}}, [[NEG0]]
 define amdgpu_kernel void @test_fneg_fmed3_rr_0(float addrspace(1)* %out, float %src0, float %src1) #1 {
   %med3 = call float @llvm.amdgcn.fmed3.f32(float %src0, float %src1, float 0.0)
   %neg.med3 = fsub float -0.0, %med3
   store float %neg.med3, float addrspace(1)* %out
   ret void
 }
 
 ; FIXME: Worse off from folding this
define amdgpu_kernel void @test_fneg_fmed3_r_inv2pi_0(float addrspace(1)* %out, float %src0) #1 {
   %med3 = call float @llvm.amdgcn.fmed3.f32(float %src0, float 0x3FC45F3060000000, float 0.0)
   %neg.med3 = fsub float -0.0, %med3
   store float %neg.med3, float addrspace(1)* %out
   ret void
 }
 
 ; GCN-LABEL: {{^}}test_fneg_fmed3_r_inv2pi_0_foldable_user:
 ; GCN-DAG: v_bfrev_b32_e32 [[NEG0:v[0-9]+]], 1
-; GCN-DAG: s_mov_b32 [[NEG_INV:s[0-9]+]], 0xbe22f983
-; GCN: v_med3_f32 [[MED3:v[0-9]+]], -v{{[0-9]+}}, [[NEG_INV]], [[NEG0]]
+; GCN-DAG: v_mov_b32_e32 [[NEG_INV:v[0-9]+]], 0xbe22f983
+; GCN: v_med3_f32 [[MED3:v[0-9]+]], -s{{[0-9]+}}, [[NEG_INV]], [[NEG0]]
 ; GCN: v_mul_f32_e32 v{{[0-9]+}}, s{{[0-9]+}}, [[MED3]]
 define amdgpu_kernel void @test_fneg_fmed3_r_inv2pi_0_foldable_user(float addrspace(1)* %out, float %src0, float %mul.arg) #1 {
   %med3 = call float @llvm.amdgcn.fmed3.f32(float %src0, float 0x3FC45F3060000000, float 0.0)
   %neg.med3 = fsub float -0.0, %med3
   %mul = fmul float %neg.med3, %mul.arg
   store float %mul, float addrspace(1)* %out
   ret void
 }
 
 declare float @llvm.amdgcn.fmed3.f32(float, float, float) #0
 declare float @llvm.fabs.f32(float) #0
 
 attributes #0 = { nounwind readnone }
 attributes #1 = { nounwind }

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mov.dpp.ll

define amdgpu_kernel void @dpp_wait_states(i32 addrspace(1)* %out, i32 %in) {
   ret void
 }
 
 ; VI-LABEL: {{^}}dpp_first_in_bb:
 ; VI: ; %endif
 ; PREGFX10-OPT: s_mov_b32
 ; PREGFX10-OPT: s_mov_b32
 ; PREGFX10-NOOPT: s_waitcnt
+; PREGFX10-NOOPT: v_mov_b32_e32
 ; PREGFX10-NOOPT-NEXT: s_nop 0
 ; VI: v_mov_b32_dpp [[VGPR0:v[0-9]+]], v{{[0-9]+}} quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0
 ; PREGFX10-OPT: s_nop 1
 ; VI: v_mov_b32_dpp [[VGPR1:v[0-9]+]], [[VGPR0]] quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0
 ; PREGFX10-OPT: s_nop 1
 ; PREGFX10-NOOPT: s_nop 0
 ; PREGFX10-NOOPT: s_nop 0
 ; VI: v_mov_b32_dpp v{{[0-9]+}}, [[VGPR1]] quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mqsad.pk.u16.u8.ll

 ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
 ; RUN: llc -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
 
 declare i64 @llvm.amdgcn.mqsad.pk.u16.u8(i64, i32, i64) #0
 
 ; GCN-LABEL: {{^}}v_mqsad_pk_u16_u8:
-; GCN: v_mqsad_pk_u16_u8 v[0:1], v[4:5], v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}]
+; GCN: v_mqsad_pk_u16_u8 v[0:1], v[4:5], s{{[0-9]+}}, v[{{[0-9]+:[0-9]+}}]
 ; GCN-DAG: v_mov_b32_e32 v5, v1
 ; GCN-DAG: v_mov_b32_e32 v4, v0
 define amdgpu_kernel void @v_mqsad_pk_u16_u8(i64 addrspace(1)* %out, i64 %src) {
   %tmp = call i64 asm "v_lsrlrev_b64 $0, $1, 1", "={v[4:5]},v"(i64 %src) #0
   %tmp1 = call i64 @llvm.amdgcn.mqsad.pk.u16.u8(i64 %tmp, i32 100, i64 100) #0
   %tmp2 = call i64 asm ";; force constraint", "=v,{v[4:5]}"(i64 %tmp1) #0
   store i64 %tmp2, i64 addrspace(1)* %out, align 4
   ret void

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.qsad.pk.u16.u8.ll

 ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
 ; RUN: llc -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
 
 declare i64 @llvm.amdgcn.qsad.pk.u16.u8(i64, i32, i64) #0
 
 ; GCN-LABEL: {{^}}v_qsad_pk_u16_u8:
-; GCN: v_qsad_pk_u16_u8 v[0:1], v[4:5], v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}]
+; GCN: v_qsad_pk_u16_u8 v[0:1], v[4:5], s{{[0-9]+}}, v[{{[0-9]+:[0-9]+}}]
 ; GCN-DAG: v_mov_b32_e32 v5, v1
 ; GCN-DAG: v_mov_b32_e32 v4, v0
 define amdgpu_kernel void @v_qsad_pk_u16_u8(i64 addrspace(1)* %out, i64 %src) {
   %tmp = call i64 asm "v_lsrlrev_b64 $0, $1, 1", "={v[4:5]},v"(i64 %src) #0
   %tmp1 = call i64 @llvm.amdgcn.qsad.pk.u16.u8(i64 %tmp, i32 100, i64 100) #0
   %tmp2 = call i64 asm ";; force constraint", "=v,{v[4:5]}"(i64 %tmp1) #0
   store i64 %tmp2, i64 addrspace(1)* %out, align 4
   ret void

llvm/test/CodeGen/AMDGPU/loop_break.ll

 ; OPT: call i64 @llvm.amdgcn.if.break.i64.i64(
 ; OPT: call i1 @llvm.amdgcn.loop.i64(i64
 ; OPT: br i1 %{{[0-9]+}}, label %bb9, label %bb1
 
 ; OPT: bb9:
 ; OPT: call void @llvm.amdgcn.end.cf.i64(i64
 
 ; GCN-LABEL: {{^}}break_loop:
-; GCN:      s_mov_b64         [[OUTER_MASK:s\[[0-9]+:[0-9]+\]]], 0{{$}}
+; GCN:      s_mov_b64         [[ACCUM_MASK:s\[[0-9]+:[0-9]+\]]], 0{{$}}
 
 ; GCN: [[LOOP_ENTRY:BB[0-9]+_[0-9]+]]: ; %bb1
-; GCN:      v_cmp_lt_i32_e32  vcc, -1
-; GCN:      s_and_b64         vcc, exec, vcc
-; GCN:      s_or_b64          [[INNER_MASK:s\[[0-9]+:[0-9]+\]]], [[INNER_MASK]], exec
-; GCN:      s_cbranch_vccnz   [[FLOW:BB[0-9]+_[0-9]+]]
+; GCN:     s_add_i32 s4, s4, 1
+; GCN:     s_or_b64 [[INNER_MASK:s\[[0-9]+:[0-9]+\]]], [[INNER_MASK]], exec
+; GCN:     s_cmp_gt_i32 s4, -1
+; GCN:     s_cbranch_scc1   [[FLOW:BB[0-9]+_[0-9]+]]
 
 ; GCN: ; %bb4
 ; GCN:      buffer_load_dword
-; GCN:      v_cmp_ge_i32_e32  vcc,
-; GCN:      s_andn2_b64       [[INNER_MASK]], [[INNER_MASK]], exec
-; GCN:      s_and_b64         [[TMP0:s\[[0-9]+:[0-9]+\]]], vcc, exec
-; GCN:      s_or_b64          [[INNER_MASK]], [[INNER_MASK]], [[TMP0]]
+; GCN:      v_cmp_ge_i32_e32  vcc
+; GCN:      s_andn2_b64 [[INNER_MASK]], [[INNER_MASK]], exec
+; GCN:      s_and_b64 [[BROKEN_MASK:s\[[0-9]+:[0-9]+\]]], vcc, exec
+; GCN:      s_or_b64  [[INNER_MASK]], [[INNER_MASK]], [[BROKEN_MASK]]
 
 ; GCN: [[FLOW]]: ; %Flow
-; GCN:      s_and_b64         [[TMP1:s\[[0-9]+:[0-9]+\]]], exec, [[INNER_MASK]]
-; GCN:      s_or_b64          [[TMP1]], [[TMP1]], [[OUTER_MASK]]
-; GCN:      s_mov_b64         [[OUTER_MASK]], [[TMP1]]
-; GCN:      s_andn2_b64       exec, exec, [[TMP1]]
+; GCN:           ;   in Loop: Header=BB0_1 Depth=1
+; GCN:      s_and_b64         [[BROKEN_MASK]], exec, [[INNER_MASK]]
+; GCN:      s_or_b64          [[BROKEN_MASK]], [[BROKEN_MASK]], [[ACCUM_MASK]]
+; GCN:      s_mov_b64         [[ACCUM_MASK]], [[BROKEN_MASK]]
+; GCN:      s_andn2_b64       exec, exec, [[BROKEN_MASK]]
 ; GCN-NEXT: s_cbranch_execnz  [[LOOP_ENTRY]]
 
 ; GCN: ; %bb.4: ; %bb9
 ; GCN-NEXT: s_endpgm
 define amdgpu_kernel void @break_loop(i32 %arg) #0 {
 bb:
   %id = call i32 @llvm.amdgcn.workitem.id.x()
   %tmp = sub i32 %id, %arg

llvm/test/CodeGen/AMDGPU/madak.ll

 ; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX6,GFX6_8_9,MAD %s
 ; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX8,GFX6_8_9,GFX8_9,GFX8_9_10,MAD %s
 ; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs  -amdgpu-enable-global-sgpr-addr < %s | FileCheck -check-prefixes=GCN,GFX9,GFX6_8_9,GFX8_9,GFX8_9_10,MAD %s
-; RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -amdgpu-enable-global-sgpr-addr < %s | FileCheck -check-prefixes=GCN,GFX10,GFX8_9_10,MAD,GFX10-MAD %s
+; RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -amdgpu-enable-global-sgpr-addr < %s | FileCheck -check-prefixes=GCN,GFX10,GFX8_9_10,GFX10-MAD %s
 ; RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -fp-contract=fast -amdgpu-enable-global-sgpr-addr < %s | FileCheck -check-prefixes=GCN,GFX10,GFX8_9_10,FMA %s
 
 declare i32 @llvm.amdgcn.workitem.id.x() nounwind readnone
 declare float @llvm.fabs.f32(float) nounwind readnone
 
 ; GCN-LABEL: {{^}}madak_f32:
 ; GFX6:   buffer_load_dword [[VA:v[0-9]+]]
 ; GFX6:   buffer_load_dword [[VB:v[0-9]+]]
 ; GFX8: {{flat|global}}_load_dword [[VB:v[0-9]+]]
 ; GFX8: {{flat|global}}_load_dword [[VA:v[0-9]+]]
 ; GFX9: {{flat|global}}_load_dword [[VA:v[0-9]+]]
 ; GFX9: {{flat|global}}_load_dword [[VB:v[0-9]+]]
 ; GFX10: {{flat|global}}_load_dword [[VA:v[0-9]+]]
 ; GFX10: {{flat|global}}_load_dword [[VB:v[0-9]+]]
 ; MAD:   v_madak_f32 {{v[0-9]+}}, [[VA]], [[VB]], 0x41200000
+; GFX10-MAD:   v_madak_f32 {{v[0-9]+}}, [[VA]], [[VB]], 0x41200000
 ; FMA:   v_fmaak_f32 {{v[0-9]+}}, [[VA]], [[VB]], 0x41200000
 define amdgpu_kernel void @madak_f32(float addrspace(1)* noalias %out, float addrspace(1)* noalias %in.a, float addrspace(1)* noalias %in.b) nounwind {
   %tid = tail call i32 @llvm.amdgcn.workitem.id.x() nounwind readnone
   %in.a.gep = getelementptr float, float addrspace(1)* %in.a, i32 %tid
   %in.b.gep = getelementptr float, float addrspace(1)* %in.b, i32 %tid
   %out.gep = getelementptr float, float addrspace(1)* %out, i32 %tid
 
   %a = load float, float addrspace(1)* %in.a.gep, align 4
define amdgpu_kernel void @madak_2_use_f32(float addrspace(1)* noalias %out, float addrspace(1)* noalias %in) nounwind {
   store volatile float %madak0, float addrspace(1)* %out.gep.0, align 4
   store volatile float %madak1, float addrspace(1)* %out.gep.1, align 4
   ret void
 }
 
 ; GCN-LABEL: {{^}}madak_m_inline_imm_f32:
 ; GCN: {{buffer|flat|global}}_load_dword [[VA:v[0-9]+]]
 ; MAD: v_madak_f32 {{v[0-9]+}}, 4.0, [[VA]], 0x41200000
+; GFX10-MAD: v_madak_f32 {{v[0-9]+}}, 4.0, [[VA]], 0x41200000
 ; FMA: v_fmaak_f32 {{v[0-9]+}}, 4.0, [[VA]], 0x41200000
 define amdgpu_kernel void @madak_m_inline_imm_f32(float addrspace(1)* noalias %out, float addrspace(1)* noalias %in.a) nounwind {
   %tid = tail call i32 @llvm.amdgcn.workitem.id.x() nounwind readnone
   %in.a.gep = getelementptr float, float addrspace(1)* %in.a, i32 %tid
   %out.gep = getelementptr float, float addrspace(1)* %out, i32 %tid
 
   %a = load float, float addrspace(1)* %in.a.gep, align 4
 

 ; GFX6:   buffer_load_dword [[VB:v[0-9]+]]
 ; GFX8: {{flat|global}}_load_dword [[VB:v[0-9]+]]
 ; GFX8: {{flat|global}}_load_dword [[VA:v[0-9]+]]
 ; GFX9: {{flat|global}}_load_dword [[VA:v[0-9]+]]
 ; GFX9: {{flat|global}}_load_dword [[VB:v[0-9]+]]
 ; GFX10: {{flat|global}}_load_dword [[VA:v[0-9]+]]
 ; GFX10: {{flat|global}}_load_dword [[VB:v[0-9]+]]
 ; MAD:   v_mad_f32 {{v[0-9]+}}, [[VA]], [[VB]], 4.0
+; GFX10-MAD:   v_mad_f32 {{v[0-9]+}}, [[VA]], [[VB]], 4.0
 ; FMA:   v_fma_f32 {{v[0-9]+}}, [[VA]], [[VB]], 4.0
 define amdgpu_kernel void @madak_inline_imm_f32(float addrspace(1)* noalias %out, float addrspace(1)* noalias %in.a, float addrspace(1)* noalias %in.b) nounwind {
   %tid = tail call i32 @llvm.amdgcn.workitem.id.x() nounwind readnone
   %in.a.gep = getelementptr float, float addrspace(1)* %in.a, i32 %tid
   %in.b.gep = getelementptr float, float addrspace(1)* %in.b, i32 %tid
   %out.gep = getelementptr float, float addrspace(1)* %out, i32 %tid
 
   %a = load float, float addrspace(1)* %in.a.gep, align 4
define amdgpu_kernel void @no_madak_src1_modifier_f32(float addrspace(1)* noalias %out, float addrspace(1)* noalias %in.a, float addrspace(1)* noalias %in.b) nounwind {
   ret void
 }
 
 ; SIFoldOperands should not fold the SGPR copy into the instruction before GFX10
 ; because the implicit immediate already uses the constant bus.
 ; On GFX10+ we can use two scalar operands.
 ; GCN-LABEL: {{^}}madak_constant_bus_violation:
 ; GCN:       s_load_dword [[SGPR0:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, {{0x12|0x48}}
-; GCN:       v_mov_b32_e32 [[SGPR0_VCOPY:v[0-9]+]], [[SGPR0]]
+
 ; GCN:       {{buffer|flat|global}}_load_dword [[VGPR:v[0-9]+]]
-; MAD:       v_madak_f32 [[MADAK:v[0-9]+]], 0.5, [[SGPR0_VCOPY]], 0x42280000
+; MAD:       v_mov_b32_e32 [[MADAK:v[0-9]+]], 0x42280000
+; MAD:       v_mac_f32_e64 [[MADAK]], [[SGPR0]], 0.5
+; GFX10:     v_mov_b32_e32 [[SGPR0_VCOPY:v[0-9]+]], [[SGPR0]]
+; GFX10-MAD: v_madak_f32 [[MADAK:v[0-9]+]], 0.5, [[SGPR0_VCOPY]], 0x42280000
 ; FMA:       v_fmaak_f32 [[MADAK:v[0-9]+]], 0.5, [[SGPR0_VCOPY]], 0x42280000
 ; GCN:       v_mul_f32_e32 [[MUL:v[0-9]+]], [[MADAK]], [[VGPR]]
 ; GFX6:      buffer_store_dword [[MUL]]
 ; GFX8_9_10: {{flat|global}}_store_dword v[{{[0-9:]+}}], [[MUL]]
 define amdgpu_kernel void @madak_constant_bus_violation(i32 %arg1, [8 x i32], float %sgpr0, float %sgpr1) #0 {
 bb:
   %tmp = icmp eq i32 %arg1, 0
   br i1 %tmp, label %bb3, label %bb4

llvm/test/CodeGen/AMDGPU/multilevel-break.ll

 ; GCN:      s_or_b64            exec, exec, [[SAVE_EXEC:s\[[0-9]+:[0-9]+\]]]
 ; GCN:      s_and_b64           [[TMP0]], exec, [[BREAK_INNER:s\[[0-9]+:[0-9]+\]]]
 ; GCN:      s_or_b64            [[TMP0]], [[TMP0]], [[LEFT_INNER]]
 ; GCN:      s_mov_b64           [[LEFT_INNER]], [[TMP0]]
 ; GCN:      s_andn2_b64         exec, exec, [[TMP0]]
 ; GCN:      s_cbranch_execz    [[FLOW2]]
 
 ; GCN: [[INNER_LOOP:BB[0-9]+_[0-9]+]]: ; %LOOP{{$}}
-; GCN:      s_or_b64            [[BREAK_OUTER]], [[BREAK_OUTER]], exec
-; GCN:      s_or_b64            [[BREAK_INNER]], [[BREAK_INNER]], exec
 ; GCN:      s_and_saveexec_b64  [[SAVE_EXEC]], vcc
 
 ; FIXME: duplicate comparison
 ; GCN: ; %ENDIF
 ; GCN-DAG:  v_cmp_eq_u32_e32    vcc,
 ; GCN-DAG:  v_cmp_ne_u32_e64    [[TMP51NEG:s\[[0-9]+:[0-9]+\]]],
-; GCN-DAG:  s_andn2_b64         [[BREAK_OUTER]], [[BREAK_OUTER]], exec
-; GCN-DAG:  s_andn2_b64         [[BREAK_INNER]], [[BREAK_INNER]], exec
-; GCN-DAG:  s_and_b64           [[TMP_EQ:s\[[0-9]+:[0-9]+\]]], vcc, exec
-; GCN-DAG:  s_and_b64           [[TMP_NE:s\[[0-9]+:[0-9]+\]]], [[TMP51NEG]], exec
-; GCN-DAG:  s_or_b64            [[BREAK_OUTER]], [[BREAK_OUTER]], [[TMP_EQ]]
-; GCN-DAG:  s_or_b64            [[BREAK_INNER]], [[BREAK_INNER]], [[TMP_NE]]
 
 ; GCN: [[IF_BLOCK]]: ; %IF
 ; GCN-NEXT: s_endpgm
 define amdgpu_vs void @multi_else_break(<4 x float> %vec, i32 %ub, i32 %cont) {
 main_body:
   br label %LOOP.outer
 
 LOOP.outer:                                       ; preds = %ENDIF, %main_body

 
 ; OPT-LABEL: define amdgpu_kernel void @multi_if_break_loop(
 ; OPT: llvm.amdgcn.if.break
 ; OPT: llvm.amdgcn.loop
 ; OPT: llvm.amdgcn.if.break
 ; OPT: llvm.amdgcn.end.cf
 
 ; GCN-LABEL: {{^}}multi_if_break_loop:
-; GCN:      s_mov_b64          [[LEFT:s\[[0-9]+:[0-9]+\]]], 0{{$}}
+; GCN:      s_mov_b64          [[BROKEN_THREADS_MASK:s\[[0-9]+:[0-9]+\]]], 0{{$}}
 
-; GCN: ; %Flow4
-; GCN:      s_and_b64          [[BREAK:s\[[0-9]+:[0-9]+\]]], exec, [[BREAK]]
-; GCN:      s_or_b64           [[LEFT]], [[BREAK]], [[OLD_LEFT:s\[[0-9]+:[0-9]+\]]]
-; GCN:      s_andn2_b64        exec, exec, [[LEFT]]
-; GCN-NEXT: s_cbranch_execz
-
-; GCN: [[LOOP:BB[0-9]+_[0-9]+]]: ; %bb1{{$}}
-; GCN:      s_mov_b64          [[OLD_LEFT]], [[LEFT]]
+; GCN: [[LOOP:BB[0-9]+_[0-9]+]]: ; %Flow4
+; GCN:      s_and_b64          [[BROKEN_THREADS_MASK]], exec, [[BROKEN_THREADS_MASK]]
+; GCN:      s_or_b64           [[BROKEN_THREADS_MASK]], [[BROKEN_THREADS_MASK]], [[SAVED:s\[[0-9]+:[0-9]+\]]]
+; GCN:      s_andn2_b64        exec, exec, [[BROKEN_THREADS_MASK]]
+; GCN-NEXT: s_cbranch_execz [[LOOP_EXIT:BB[0-9]+_[0-9]+]]
+
+; GCN: ; %bb1{{$}}
+; GCN:      buffer_load_dword  [[LOAD0:v[0-9]+]],
+; GCN:      s_mov_b64          [[SAVED]], [[BROKEN_THREADS_MASK]]
 
 ; GCN: ; %LeafBlock1
-; GCN:      s_mov_b64
-; GCN:      s_mov_b64          [[BREAK]], -1{{$}}
+; GCN:      v_cmp_eq_u32_e32 vcc, 1, [[LOAD0]]
+; GCN:      s_and_b64 vcc, exec, vcc
+; GCN:      s_cbranch_vccz [[FLOW:BB[0-9]+_[0-9]+]]
 
 ; GCN: ; %case1
 ; GCN:      buffer_load_dword  [[LOAD2:v[0-9]+]],
 ; GCN:      v_cmp_ge_i32_e32   vcc, {{v[0-9]+}}, [[LOAD2]]
-; GCN:      s_orn2_b64         [[BREAK]], vcc, exec
-
-; GCN: ; %Flow3
-; GCN:      s_branch           [[FLOW:BB[0-9]+_[0-9]+]]
-
-; GCN:      s_mov_b64          [[BREAK]], -1{{$}}
-
-; GCN: [[FLOW]]: ; %Flow
+; GCN:      s_orn2_b64 [[BROKEN_THREADS_MASK]], vcc, exec
+; GCN:  BB1_{{[0-9]+}}:
+; GCN:      s_mov_b64 [[FALSE_MASK:s\[[0-9]+:[0-9]+\]]], 0
+; GCN:      s_and_b64 vcc, exec, [[FALSE_MASK]]
+; GCN:      s_cbranch_vccz [[LOOP]]
+
+; GCN: ; %LeafBlock
+; GCN:     v_cmp_eq_u32_e32 vcc, 0, [[LOAD0]]
+; GCN:     s_and_b64 vcc, exec, vcc
+; GCN:     s_cbranch_vccz [[LOOP]]
 
 ; GCN: ; %case0
 ; GCN:      buffer_load_dword  [[LOAD1:v[0-9]+]],
-; GCN-DAG:  s_andn2_b64        [[BREAK]], [[BREAK]], exec
 ; GCN-DAG:  v_cmp_ge_i32_e32   vcc, {{v[0-9]+}}, [[LOAD1]]
-; GCN-DAG:  s_and_b64          [[TMP:s\[[0-9]+:[0-9]+\]]], vcc, exec
-; GCN:      s_or_b64           [[BREAK]], [[BREAK]], [[TMP]]
+; GCN:      s_andn2_b64 [[BROKEN_THREADS_MASK]], [[BROKEN_THREADS_MASK]], exec
+; GCN:      s_and_b64 [[TMP_MASK:s\[[0-9]+:[0-9]+\]]], vcc, exec
+; GCN:      s_or_b64 [[BROKEN_THREADS_MASK]], [[BROKEN_THREADS_MASK]], [[TMP_MASK]]
+; GCN:      s_branch [[LOOP]]
+
+; GCN: [[LOOP_EXIT]]: ; %Flow6
+; GCN:  s_or_b64 exec, exec, [[BROKEN_THREADS_MASK]]
 
 define amdgpu_kernel void @multi_if_break_loop(i32 %arg) #0 {
 bb:
   %id = call i32 @llvm.amdgcn.workitem.id.x()
   %tmp = sub i32 %id, %arg
   br label %bb1
 
 bb1:

llvm/test/CodeGen/AMDGPU/select-opt.ll

define amdgpu_kernel void @opt_select_i64_or_cmp_f32(i64 addrspace(1)* %out, float %a, float %b, float %c, i64 %x, i64 %y) #0 {
   %or = or i1 %fcmp0, %fcmp1
   %select = select i1 %or, i64 %x, i64 %y
   store i64 %select, i64 addrspace(1)* %out
   ret void
 }
 
 ; GCN-LABEL: {{^}}regression:
 ; GCN: v_cmp_neq_f32_e64 s{{\[[0-9]+:[0-9]+\]}}, s{{[0-9]+}}, 1.0
-; GCN: v_cmp_neq_f32_e32 vcc, 0, v{{[0-9]+}}
-; GCN: v_cmp_eq_f32_e32 vcc, 0, v{{[0-9]+}}
+; GCN: v_cmp_neq_f32_e64 s{{\[[0-9]+:[0-9]+\]}}, s{{[0-9]+}}, 0
+; GCN: v_cmp_eq_f32_e64 s{{\[[0-9]+:[0-9]+\]}}, s{{[0-9]+}}, 0
 
 define amdgpu_kernel void @regression(float addrspace(1)* %out, float %c0, float %c1) #0 {
 entry:
   %cmp0 = fcmp oeq float %c0, 1.0
   br i1 %cmp0, label %if0, label %endif
 
 if0:
   %cmp1 = fcmp oeq float %c1, 0.0

llvm/test/CodeGen/AMDGPU/sgpr-control-flow.ll

endif:
   store i32 %tmp4, i32 addrspace(1)* %out
   ret void
 }
 
 ; SI-LABEL: {{^}}sgpr_if_else_valu_cmp_phi_br:
 
 ; SI: ; %else
 ; SI:      buffer_load_dword  [[AVAL:v[0-9]+]]
-; SI:      v_cmp_gt_i32_e64   [[PHI:s\[[0-9]+:[0-9]+\]]], 0, [[AVAL]]
+; SI:      v_cmp_gt_i32_e32   vcc, 0, [[AVAL]]
+; SI:      s_and_b64 [[PHI:s\[[0-9]+:[0-9]+\]]], vcc, exec
 
 ; SI: ; %if
 ; SI:      buffer_load_dword  [[AVAL:v[0-9]+]]
 ; SI-DAG:  v_cmp_eq_u32_e32   [[CMP_ELSE:vcc]], 0, [[AVAL]]
 ; SI-DAG:  s_andn2_b64        [[PHI]], [[PHI]], exec
 ; SI-DAG:  s_and_b64          [[TMP:s\[[0-9]+:[0-9]+\]]], [[CMP_ELSE]], exec
 ; SI:      s_or_b64           [[PHI]], [[PHI]], [[TMP]]
 

llvm/test/CodeGen/AMDGPU/sgpr-copy.ll

 ; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -verify-machineinstrs < %s | FileCheck %s
 ; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck %s
 
 ; CHECK-LABEL: {{^}}phi1:
 ; CHECK: s_buffer_load_dword [[DST:s[0-9]]], {{s\[[0-9]+:[0-9]+\]}}, 0x0
-; CHECK: v_mov_b32_e32 v{{[0-9]}}, [[DST]]
+; CHECK: ; %bb.1: ; %ELSE
+; CHECK: s_xor_b32 s{{[0-9]}}, [[DST]]
 define amdgpu_ps void @phi1(<4 x i32> addrspace(4)* inreg %arg, <4 x i32> addrspace(4)* inreg %arg1, <8 x i32> addrspace(4)* inreg %arg2, i32 inreg %arg3, <2 x i32> %arg4, <2 x i32> %arg5, <2 x i32> %arg6, <3 x i32> %arg7, <2 x i32> %arg8, <2 x i32> %arg9, <2 x i32> %arg10, float %arg11, float %arg12, float %arg13, float %arg14, float %arg15, float %arg16, float %arg17, float %arg18, float %arg19) #0 {
 main_body:
   %tmp = getelementptr <4 x i32>, <4 x i32> addrspace(4)* %arg, i32 0
   %tmp20 = load <4 x i32>, <4 x i32> addrspace(4)* %tmp, !tbaa !0
   %tmp21 = call float @llvm.amdgcn.s.buffer.load.f32(<4 x i32> %tmp20, i32 0, i32 0)
   %tmp22 = call float @llvm.amdgcn.s.buffer.load.f32(<4 x i32> %tmp20, i32 16, i32 0)
   %tmp23 = call float @llvm.amdgcn.s.buffer.load.f32(<4 x i32> %tmp20, i32 32, i32 0)
   %tmp24 = fptosi float %tmp22 to i32

llvm/test/CodeGen/AMDGPU/si-annotate-cf.ll

 
 ; FUNC-LABEL: {{^}}phi_cond_outside_loop:
 
 ; SI:     s_mov_b64         [[LEFT:s\[[0-9]+:[0-9]+\]]], 0
 ; SI:     s_mov_b64         [[PHI:s\[[0-9]+:[0-9]+\]]], 0
 
 ; SI: ; %else
 ; SI:     v_cmp_eq_u32_e64  [[TMP:s\[[0-9]+:[0-9]+\]]],
-; SI:     s_and_b64         [[PHI]], [[TMP]], exec
 
 ; SI: ; %endif
 
 ; SI: [[LOOP_LABEL:BB[0-9]+_[0-9]+]]: ; %loop
 ; SI:     s_mov_b64         [[TMP:s\[[0-9]+:[0-9]+\]]], [[LEFT]]
 ; SI:     s_and_b64         [[TMP1:s\[[0-9]+:[0-9]+\]]], exec, [[PHI]]
 ; SI:     s_or_b64          [[LEFT]], [[TMP1]], [[TMP]]
 ; SI:     s_andn2_b64       exec, exec, [[LEFT]]

llvm/test/CodeGen/AMDGPU/si-fix-sgpr-copies.mir

registers:
   - { id: 7, class: vgpr_32 }
   - { id: 8, class: sreg_32_xm0 }
   - { id: 9, class: vgpr_32 }
   - { id: 10, class: sreg_64 }
   - { id: 11, class: sreg_32_xm0 }
 
 body: |
   ; GCN-LABEL: name: phi_visit_order
-  ; GCN: V_ADD_I32
+  ; GCN: S_ADD_I32
   bb.0:
     liveins: $vgpr0
     %7 = COPY $vgpr0
     %8 = S_MOV_B32 0
 
   bb.1:
     %0 = PHI %8, %bb.0, %0, %bb.1, %2, %bb.2
     %9 = V_MOV_B32_e32 9, implicit $exec

llvm/test/CodeGen/AMDGPU/smrd.ll

main_body:
   call void @llvm.amdgcn.exp.f32(i32 0, i32 15, float %r.1, float %r.1, float %r.1, float %r.2, i1 true, i1 true) #0
   ret void
 }
 
 ; GCN-LABEL: {{^}}smrd_uniform_loop:
 ;
 ; TODO: we should keep the loop counter in an SGPR
 ;
-; GCN: v_readfirstlane_b32
 ; GCN: s_buffer_load_dword
 define amdgpu_ps float @smrd_uniform_loop(<4 x i32> inreg %desc, i32 %bound) #0 {
 main_body:
   br label %loop
 
 loop:
   %counter = phi i32 [ 0, %main_body ], [ %counter.next, %loop ]
   %sum = phi float [ 0.0, %main_body ], [ %sum.next, %loop ]

llvm/test/CodeGen/AMDGPU/subreg-coalescer-undef-use.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -march=amdgcn -mcpu=tahiti -amdgpu-dce-in-ra=0 -o - %s | FileCheck %s
 ; Don't crash when the use of an undefined value is only detected by the
 ; register coalescer because it is hidden with subregister insert/extract.
 target triple="amdgcn--"
 
+define amdgpu_kernel void @foobar(float %a0, float %a1, float addrspace(1)* %out) nounwind {
 ; CHECK-LABEL: foobar:
-; CHECK: s_load_dwordx2 s[4:5], s[0:1], 0x9
-; CHECK-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0xb
-; CHECK-NEXT: v_mbcnt_lo_u32_b32_e64
-; CHECK-NEXT: s_mov_b32 s2, -1
-; CHECK-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
-; CHECK-NEXT: s_waitcnt lgkmcnt(0)
-; CHECK-NEXT: v_mov_b32_e32 v1, s5
-; CHECK-NEXT: s_and_saveexec_b64 s[4:5], vcc
+; CHECK:       ; %bb.0: ; %entry
+; CHECK-NEXT:    s_load_dwordx2 s[4:5], s[0:1], 0x9
+; CHECK-NEXT:    s_load_dwordx2 s[0:1], s[0:1], 0xb
+; CHECK-NEXT:    v_mbcnt_lo_u32_b32_e64 v0, -1, 0
+; CHECK-NEXT:    v_cmp_eq_u32_e32 vcc, 0, v0
+; CHECK-NEXT:    s_mov_b32 s2, -1
+; CHECK-NEXT:    s_waitcnt lgkmcnt(0)
 
-; CHECK: BB0_1:
-; CHECK-NEXT: ; kill: def $vgpr0_vgpr1 killed $sgpr4_sgpr5 killed $exec
-; CHECK-NEXT: ; implicit-def: $vgpr0_vgpr1_vgpr2_vgpr3
+; FIXME: The change related to the fact that
+; DetectDeadLanes pass hit "Copy across incompatible class" SGPR -> VGPR in analysis
+; and hence it cannot derive the fact that the vector element is unused.
+; Such a copies appear because the float4 vectors and their elements in the test are uniform
+; but the PHI node in "ife" block is divergent because of the CF dependency (divergent branch in bb0)
 
-; CHECK: BB0_2:
-; CHECK: s_or_b64 exec, exec, s[4:5]
-; CHECK-NEXT: s_mov_b32 s3, 0xf000
-; CHECK-NEXT: buffer_store_dword v1, off, s[0:3], 0
-; CHECK-NEXT: s_endpgm
-define amdgpu_kernel void @foobar(float %a0, float %a1, float addrspace(1)* %out) nounwind {
+; CHECK-NEXT:    v_mov_b32_e32 v0, s4
+; CHECK-NEXT:    v_mov_b32_e32 v1, s5
+; CHECK-NEXT:    v_mov_b32_e32 v2, s6
+; CHECK-NEXT:    v_mov_b32_e32 v3, s7
+
+; CHECK-NEXT:    s_and_saveexec_b64 s[6:7], vcc
+; CHECK-NEXT:    ; mask branch BB0_2
+; CHECK-NEXT:  BB0_1: ; %ift
+; CHECK-NEXT:    s_mov_b32 s4, s5
+; CHECK-NEXT:    v_mov_b32_e32 v0, s4
+; CHECK-NEXT:    v_mov_b32_e32 v1, s5
+; CHECK-NEXT:    v_mov_b32_e32 v2, s6
+; CHECK-NEXT:    v_mov_b32_e32 v3, s7
+; CHECK-NEXT:  BB0_2: ; %ife
+; CHECK-NEXT:    s_or_b64 exec, exec, s[6:7]
+; CHECK-NEXT:    s_mov_b32 s3, 0xf000
+; CHECK-NEXT:    buffer_store_dword v1, off, s[0:3], 0
+; CHECK-NEXT:    s_endpgm
 entry:
   %v0 = insertelement <4 x float> undef, float %a0, i32 0
   %tid = call i32 @llvm.amdgcn.mbcnt.lo(i32 -1, i32 0) #0
   %cnd = icmp eq i32 %tid, 0
   br i1 %cnd, label %ift, label %ife
 
 ift:
   %v1 = insertelement <4 x float> undef, float %a1, i32 0

llvm/test/CodeGen/AMDGPU/uniform-loop-inside-nonuniform.ll

 ; RUN: llc -march=amdgcn -mcpu=verde < %s | FileCheck %s
 
 ; Test a simple uniform loop that lives inside non-uniform control flow.
 
 ; CHECK-LABEL: {{^}}test1:
 ; CHECK: v_cmp_ne_u32_e32 vcc, 0
 ; CHECK: s_and_saveexec_b64
 ; CHECK-NEXT: ; mask branch
 ; CHECK-NEXT: s_cbranch_execz BB{{[0-9]+_[0-9]+}}
-; CHECK-NEXT: BB{{[0-9]+_[0-9]+}}: ; %loop_body.preheader
 
-; CHECK: [[LOOP_BODY_LABEL:BB[0-9]+_[0-9]+]]:
-; CHECK: s_cbranch_vccz [[LOOP_BODY_LABEL]]
+; CHECK: [[LOOP_BODY_LABEL:BB[0-9]+_[0-9]+]]: ; %loop_body
+; CHECK: s_cbranch_scc0 [[LOOP_BODY_LABEL]]
 
 ; CHECK: s_endpgm
 define amdgpu_ps void @test1(<8 x i32> inreg %rsrc, <2 x i32> %addr.base, i32 %y, i32 %p) {
 main_body:
   %cc = icmp eq i32 %p, 0
   br i1 %cc, label %out, label %loop_body
 
 loop_body:

llvm/test/CodeGen/AMDGPU/use-sgpr-multiple-times.ll

define amdgpu_kernel void @test_literal_use_twice_ternary_op_s_k_k_x2(float addrspace(1)* %out, float %a, float %b) #0 {
   store volatile float %fma0, float addrspace(1)* %out
   store volatile float %fma1, float addrspace(1)* %out
   ret void
 }
 
 ; GCN-LABEL: {{^}}test_s0_s1_k_f32:
 ; SI-DAG: s_load_dwordx2 s{{\[}}[[SGPR0:[0-9]+]]:[[SGPR1:[0-9]+]]{{\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0xb
 ; VI-DAG: s_load_dwordx2 s{{\[}}[[SGPR0:[0-9]+]]:[[SGPR1:[0-9]+]]{{\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0x2c
-; GCN-DAG: s_mov_b32 [[SK0:s[0-9]+]], 0x44800000
+; GCN-DAG: v_mov_b32_e32 [[VK0:v[0-9]+]], 0x44800000
 ; GCN-DAG: v_mov_b32_e32 [[VS1:v[0-9]+]], s[[SGPR1]]
-; GCN-DAG: v_mov_b32_e32 [[VS0:v[0-9]+]], s[[SGPR0]]
 
-; GCN-DAG: v_fma_f32 [[RESULT0:v[0-9]+]], [[VS0]], [[VS1]], [[SK0]]
-; GCN-DAG: s_mov_b32 [[SK1:s[0-9]+]], 0x45800000
-; GCN-DAG: v_fma_f32 [[RESULT1:v[0-9]+]], [[VS0]], [[VS1]], [[SK1]]
+; GCN-DAG: v_fma_f32 [[RESULT0:v[0-9]+]], s[[SGPR0]], [[VS1]], [[VK0]]
+; GCN-DAG: v_mov_b32_e32 [[VK1:v[0-9]+]], 0x45800000
+; GCN-DAG: v_fma_f32 [[RESULT1:v[0-9]+]], s[[SGPR0]], [[VS1]], [[VK1]]
 
 ; GCN: buffer_store_dword [[RESULT0]]
 ; GCN: buffer_store_dword [[RESULT1]]
 define amdgpu_kernel void @test_s0_s1_k_f32(float addrspace(1)* %out, float %a, float %b) #0 {
   %fma0 = call float @llvm.fma.f32(float %a, float %b, float 1024.0) #1
   %fma1 = call float @llvm.fma.f32(float %a, float %b, float 4096.0) #1
   store volatile float %fma0, float addrspace(1)* %out
   store volatile float %fma1, float addrspace(1)* %out

llvm/test/CodeGen/AMDGPU/valu-i1.ll

 ; SI-NEXT: ; mask branch
 ; SI-NEXT: s_cbranch_execz [[LABEL_EXIT:BB[0-9]+_[0-9]+]]
 
 ; SI: s_mov_b64 {{s\[[0-9]+:[0-9]+\]}}, 0{{$}}
 
 ; SI: [[LABEL_LOOP:BB[0-9]+_[0-9]+]]:
 ; SI: buffer_load_dword
 ; SI-DAG: buffer_store_dword
-; SI-DAG: v_cmp_eq_u32_e32 vcc, 0x100
-; SI: s_cbranch_vccz [[LABEL_LOOP]]
+; SI-DAG: s_cmpk_eq_i32 s{{[0-9+]}}, 0x100
+; SI: s_cbranch_scc0 [[LABEL_LOOP]]
 ; SI: [[LABEL_EXIT]]:
 ; SI: s_endpgm
 
 define amdgpu_kernel void @simple_test_v_loop(i32 addrspace(1)* %dst, i32 addrspace(1)* %src) #1 {
 entry:
   %tid = call i32 @llvm.amdgcn.workitem.id.x() nounwind readnone
   %is.0 = icmp ne i32 %tid, 0
   %limit = add i32 %tid, 64

 ; Clear exec bits for workitems that load -1s
 ; SI: [[LABEL_LOOP:BB[0-9]+_[0-9]+]]:
 ; SI: buffer_load_dword [[B:v[0-9]+]]
 ; SI: buffer_load_dword [[A:v[0-9]+]]
 ; SI-DAG: v_cmp_ne_u32_e64 [[NEG1_CHECK_0:s\[[0-9]+:[0-9]+\]]], -1, [[A]]
 ; SI-DAG: v_cmp_ne_u32_e32 [[NEG1_CHECK_1:vcc]], -1, [[B]]
 ; SI: s_and_b64 [[ORNEG1:s\[[0-9]+:[0-9]+\]]], [[NEG1_CHECK_1]], [[NEG1_CHECK_0]]
 ; SI: s_and_saveexec_b64 [[ORNEG2:s\[[0-9]+:[0-9]+\]]], [[ORNEG1]]
-; SI: s_cbranch_execz [[LABEL_FLOW:BB[0-9]+_[0-9]+]]
+; SI: ; mask branch [[LABEL_FLOW:BB[0-9]+_[0-9]+]]
 
 ; SI: BB{{[0-9]+_[0-9]+}}: ; %bb20
 ; SI: buffer_store_dword
 
 ; SI: [[LABEL_FLOW]]:
 ; SI-NEXT: ; in Loop: Header=[[LABEL_LOOP]]
 ; SI-NEXT: s_or_b64 exec, exec, [[ORNEG2]]
 ; SI-NEXT: s_and_b64 [[TMP1:s\[[0-9]+:[0-9]+\]]],

llvm/test/CodeGen/AMDGPU/vgpr-spill-emergency-stack-slot-compute.ll

+; XFAIL: *
 ; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GCNMESA -check-prefix=SIMESA %s
 ; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=fiji -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GCNMESA -check-prefix=VIMESA %s
 ; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GCNMESA -check-prefix=GFX9MESA %s
 ; RUN: llc -march=amdgcn  -mcpu=hawaii -mtriple=amdgcn-unknown-amdhsa -mattr=-code-object-v3 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=CIHSA -check-prefix=HSA %s
 ; RUN: llc -march=amdgcn  -mcpu=fiji -mtriple=amdgcn-unknown-amdhsa -mattr=-code-object-v3 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VIHSA -check-prefix=HSA %s
 
 ; This ends up using all 256 registers and requires register
 ; scavenging which will fail to find an unsued register.

llvm/test/CodeGen/AMDGPU/wave32.ll

 
 ; GCN-LABEL: {{^}}test_loop_with_if_else_break:
 ; GFX1032: s_and_saveexec_b32 s{{[0-9]+}}, vcc_lo
 ; GFX1064: s_and_saveexec_b64 s[{{[0-9:]+}}], vcc{{$}}
 ; GCN:     ; mask branch
 ; GCN:     s_cbranch_execz
 ; GCN:   BB{{.*}}:
 ; GCN:   BB{{.*}}:
-; GFX1032: s_andn2_b32 s{{[0-9]+}}, s{{[0-9]+}}, exec_lo
-; GFX1064: s_andn2_b64 s[{{[0-9:]+}}], s[{{[0-9:]+}}], exec
-; GFX1032: s_or_b32 s{{[0-9]+}}, vcc_lo, s{{[0-9]+}}
-; GFX1032: s_or_b32 s{{[0-9]+}}, s{{[0-9]+}}, s{{[0-9]+}}
-; GFX1064: s_or_b64 s[{{[0-9:]+}}], vcc, s[{{[0-9:]+}}]
-; GFX1064: s_or_b64 s[{{[0-9:]+}}], s[{{[0-9:]+}}], s[{{[0-9:]+}}]
+
+; GFX1032: s_or_b32 [[MASK0:s[0-9]+]], [[MASK0]], vcc_lo
+; GFX1064: s_or_b64 [[MASK0:s\[[0-9:]+\]]], [[MASK0]], vcc
+; GFX1032: s_andn2_b32 [[MASK1:s[0-9]+]], [[MASK1]], exec_lo
+; GFX1064: s_andn2_b64 [[MASK1:s\[[0-9:]+\]]], [[MASK1]], exec
+; GCN:     global_store_dword
+; GFX1032: s_and_b32 [[MASK0]], [[MASK0]], exec_lo
+; GFX1064: s_and_b64 [[MASK0]], [[MASK0]], exec
+; GFX1032: s_or_b32 [[MASK1]], [[MASK1]], [[MASK0]]
+; GFX1064: s_or_b64 [[MASK1]], [[MASK1]], [[MASK0]]
+; GCN:   BB{{.*}}: ; %Flow
+; GFX1032: s_and_b32 [[MASK0:s[0-9]+]], exec_lo, [[MASK1]]
+; GFX1064: s_and_b64 [[MASK0:s\[[0-9:]+\]]], exec, [[MASK1]]
+; GFX1032: s_or_b32  [[MASK0]], [[MASK0]], [[ACC:s[0-9]+]]
+; GFX1064: s_or_b64  [[MASK0]], [[MASK0]], [[ACC:s\[[0-9:]+\]]]
+; GFX1032: s_mov_b32 [[ACC]], [[MASK0]]
+; GFX1064: s_mov_b64 [[ACC]], [[MASK0]]
+; GFX1032: s_andn2_b32 exec_lo, exec_lo, [[MASK0]]
+; GFX1064: s_andn2_b64 exec, exec, [[MASK0]]
 ; GCN:     s_cbranch_execz
 ; GCN:   BB{{.*}}:
+; GCN: s_load_dword [[LOAD:s[0-9]+]]
+; GFX1032: s_or_b32 [[MASK1]], [[MASK1]], exec_lo
+; GFX1064: s_or_b64 [[MASK1]], [[MASK1]], exec
+; GCN: s_cmp_lt_i32 [[LOAD]], 11
 define amdgpu_kernel void @test_loop_with_if_else_break(i32 addrspace(1)* %arg) #0 {
 bb:
   %tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
   %tmp1 = icmp eq i32 %tmp, 0
   br i1 %tmp1, label %.loopexit, label %.preheader
 
 .preheader:
   br label %bb2