[LoopUnroll] Pass SCEV to getUnrollingPreferences hook. NFCI.

[hfinkel]

LGTM

llvm/trunk/include/llvm/Analysis/TargetTransformInfo.h

struct UnrollingPreferences {
     bool UpperBound;
     /// Allow peeling off loop iterations for loops with low dynamic tripcount.
     bool AllowPeeling;
   };
 
   /// \brief Get target-customized preferences for the generic loop unrolling
   /// transformation. The caller will initialize UP with the current
   /// target-independent defaults.
-  void getUnrollingPreferences(Loop *L, UnrollingPreferences &UP) const;
+  void getUnrollingPreferences(Loop *L, ScalarEvolution &,
+                               UnrollingPreferences &UP) const;
 
   /// @}
 
   /// \name Scalar Target Information
   /// @{
 
   /// \brief Flags indicating the kind of support for population count.
   ///
public:
   virtual unsigned getEstimatedNumberOfCaseClusters(const SwitchInst &SI,
                                                     unsigned &JTSize) = 0;
   virtual int getUserCost(const User *U) = 0;
   virtual bool hasBranchDivergence() = 0;
   virtual bool isSourceOfDivergence(const Value *V) = 0;
   virtual bool isAlwaysUniform(const Value *V) = 0;
   virtual unsigned getFlatAddressSpace() = 0;
   virtual bool isLoweredToCall(const Function *F) = 0;
-  virtual void getUnrollingPreferences(Loop *L, UnrollingPreferences &UP) = 0;
+  virtual void getUnrollingPreferences(Loop *L, ScalarEvolution &,
+                                       UnrollingPreferences &UP) = 0;
   virtual bool isLegalAddImmediate(int64_t Imm) = 0;
   virtual bool isLegalICmpImmediate(int64_t Imm) = 0;
   virtual bool isLegalAddressingMode(Type *Ty, GlobalValue *BaseGV,
                                      int64_t BaseOffset, bool HasBaseReg,
                                      int64_t Scale,
                                      unsigned AddrSpace) = 0;
   virtual bool isLSRCostLess(TargetTransformInfo::LSRCost &C1,
                              TargetTransformInfo::LSRCost &C2) = 0;
public:
 
   unsigned getFlatAddressSpace() override {
     return Impl.getFlatAddressSpace();
   }
 
   bool isLoweredToCall(const Function *F) override {
     return Impl.isLoweredToCall(F);
   }
-  void getUnrollingPreferences(Loop *L, UnrollingPreferences &UP) override {
-    return Impl.getUnrollingPreferences(L, UP);
+  void getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
+                               UnrollingPreferences &UP) override {
+    return Impl.getUnrollingPreferences(L, SE, UP);
   }
   bool isLegalAddImmediate(int64_t Imm) override {
     return Impl.isLegalAddImmediate(Imm);
   }
   bool isLegalICmpImmediate(int64_t Imm) override {
     return Impl.isLegalICmpImmediate(Imm);
   }
   bool isLegalAddressingMode(Type *Ty, GlobalValue *BaseGV, int64_t BaseOffset,

llvm/trunk/include/llvm/Analysis/TargetTransformInfoImpl.h

if (Name == "pow" || Name == "powf" || Name == "powl" || Name == "exp2" ||
         Name == "floorf" || Name == "ceil" || Name == "round" ||
         Name == "ffs" || Name == "ffsl" || Name == "abs" || Name == "labs" ||
         Name == "llabs")
       return false;
 
     return true;
   }
 
-  void getUnrollingPreferences(Loop *, TTI::UnrollingPreferences &) {}
+  void getUnrollingPreferences(Loop *, ScalarEvolution &,
+                               TTI::UnrollingPreferences &) {}
 
   bool isLegalAddImmediate(int64_t Imm) { return false; }
 
   bool isLegalICmpImmediate(int64_t Imm) { return false; }
 
   bool isLegalAddressingMode(Type *Ty, GlobalValue *BaseGV, int64_t BaseOffset,
                              bool HasBaseReg, int64_t Scale,
                              unsigned AddrSpace) {

llvm/trunk/include/llvm/CodeGen/BasicTTIImpl.h

unsigned getOperationCost(unsigned Opcode, Type *Ty, Type *OpTy) {
     }
     }
 
     return BaseT::getOperationCost(Opcode, Ty, OpTy);
   }
 
   unsigned getInliningThresholdMultiplier() { return 1; }
 
-  void getUnrollingPreferences(Loop *L, TTI::UnrollingPreferences &UP) {
+  void getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
+                               TTI::UnrollingPreferences &UP) {
     // This unrolling functionality is target independent, but to provide some
     // motivation for its intended use, for x86:
 
     // According to the Intel 64 and IA-32 Architectures Optimization Reference
     // Manual, Intel Core models and later have a loop stream detector (and
     // associated uop queue) that can benefit from partial unrolling.
     // The relevant requirements are:
     //  - The loop must have no more than 4 (8 for Nehalem and later) branches

llvm/trunk/lib/Analysis/TargetTransformInfo.cpp

unsigned TargetTransformInfo::getFlatAddressSpace() const {
   return TTIImpl->getFlatAddressSpace();
 }
 
 bool TargetTransformInfo::isLoweredToCall(const Function *F) const {
   return TTIImpl->isLoweredToCall(F);
 }
 
 void TargetTransformInfo::getUnrollingPreferences(
-    Loop *L, UnrollingPreferences &UP) const {
-  return TTIImpl->getUnrollingPreferences(L, UP);
+    Loop *L, ScalarEvolution &SE, UnrollingPreferences &UP) const {
+  return TTIImpl->getUnrollingPreferences(L, SE, UP);
 }
 
 bool TargetTransformInfo::isLegalAddImmediate(int64_t Imm) const {
   return TTIImpl->isLegalAddImmediate(Imm);
 }
 
 bool TargetTransformInfo::isLegalICmpImmediate(int64_t Imm) const {
   return TTIImpl->isLegalICmpImmediate(Imm);

llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.h

public:
   int getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
                          const Instruction *I = nullptr);
 
   int getMemoryOpCost(unsigned Opcode, Type *Src, unsigned Alignment,
                       unsigned AddressSpace, const Instruction *I = nullptr);
 
   int getCostOfKeepingLiveOverCall(ArrayRef<Type *> Tys);
 
-  void getUnrollingPreferences(Loop *L, TTI::UnrollingPreferences &UP);
+  void getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
+                               TTI::UnrollingPreferences &UP);
 
   Value *getOrCreateResultFromMemIntrinsic(IntrinsicInst *Inst,
                                            Type *ExpectedType);
 
   bool getTgtMemIntrinsic(IntrinsicInst *Inst, MemIntrinsicInfo &Info);
 
   int getInterleavedMemoryOpCost(unsigned Opcode, Type *VecTy, unsigned Factor,
                                  ArrayRef<unsigned> Indices, unsigned Alignment,

llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

int AArch64TTIImpl::getCostOfKeepingLiveOverCall(ArrayRef<Type *> Tys) {
   }
   return Cost;
 }
 
 unsigned AArch64TTIImpl::getMaxInterleaveFactor(unsigned VF) {
   return ST->getMaxInterleaveFactor();
 }
 
-void AArch64TTIImpl::getUnrollingPreferences(Loop *L,
+void AArch64TTIImpl::getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
                                              TTI::UnrollingPreferences &UP) {
   // Enable partial unrolling and runtime unrolling.
-  BaseT::getUnrollingPreferences(L, UP);
+  BaseT::getUnrollingPreferences(L, SE, UP);
 
   // For inner loop, it is more likely to be a hot one, and the runtime check
   // can be promoted out from LICM pass, so the overhead is less, let's try
   // a larger threshold to unroll more loops.
   if (L->getLoopDepth() > 1)
     UP.PartialThreshold *= 2;
 
   // Disable partial & runtime unrolling on -Os.

llvm/trunk/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h

public:
   explicit AMDGPUTTIImpl(const AMDGPUTargetMachine *TM, const Function &F)
     : BaseT(TM, F.getParent()->getDataLayout()),
       ST(TM->getSubtargetImpl(F)),
       TLI(ST->getTargetLowering()),
       IsGraphicsShader(AMDGPU::isShader(F.getCallingConv())) {}
 
   bool hasBranchDivergence() { return true; }
 
-  void getUnrollingPreferences(Loop *L, TTI::UnrollingPreferences &UP);
+  void getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
+                               TTI::UnrollingPreferences &UP);
 
   TTI::PopcntSupportKind getPopcntSupport(unsigned TyWidth) {
     assert(isPowerOf2_32(TyWidth) && "Ty width must be power of 2");
     return TTI::PSK_FastHardware;
   }
 
   unsigned getHardwareNumberOfRegisters(bool Vector) const;
   unsigned getNumberOfRegisters(bool Vector) const;

llvm/trunk/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp

if (const PHINode *PHI = dyn_cast<PHINode>(V)) {
                   return SubLoop->contains(PHI); }))
         return true;
     } else if (Depth < 10 && dependsOnLocalPhi(L, V, Depth+1))
       return true;
   }
   return false;
 }
 
-void AMDGPUTTIImpl::getUnrollingPreferences(Loop *L,
+void AMDGPUTTIImpl::getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
                                             TTI::UnrollingPreferences &UP) {
   UP.Threshold = 300; // Twice the default.
   UP.MaxCount = UINT_MAX;
   UP.Partial = true;
 
   // TODO: Do we want runtime unrolling?
 
   // Maximum alloca size than can fit registers. Reserve 16 registers.

llvm/trunk/lib/Target/Hexagon/HexagonTargetTransformInfo.h

explicit HexagonTTIImpl(const HexagonTargetMachine *TM, const Function &F)
         TLI(ST->getTargetLowering()) {}
 
   /// \name Scalar TTI Implementations
   /// @{
 
   TTI::PopcntSupportKind getPopcntSupport(unsigned IntTyWidthInBit) const;
 
   // The Hexagon target can unroll loops with run-time trip counts.
-  void getUnrollingPreferences(Loop *L, TTI::UnrollingPreferences &UP);
+  void getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
+                               TTI::UnrollingPreferences &UP);
 
   // L1 cache prefetch.
   unsigned getPrefetchDistance() const;
   unsigned getCacheLineSize() const;
 
   /// @}
 
   /// \name Vector TTI Implementations

llvm/trunk/lib/Target/Hexagon/HexagonTargetTransformInfo.cpp

 TargetTransformInfo::PopcntSupportKind
 HexagonTTIImpl::getPopcntSupport(unsigned IntTyWidthInBit) const {
   // Return Fast Hardware support as every input  < 64 bits will be promoted
   // to 64 bits.
   return TargetTransformInfo::PSK_FastHardware;
 }
 
 // The Hexagon target can unroll loops with run-time trip counts.
-void HexagonTTIImpl::getUnrollingPreferences(Loop *L,
+void HexagonTTIImpl::getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
                                              TTI::UnrollingPreferences &UP) {
   UP.Runtime = UP.Partial = true;
 }
 
 unsigned HexagonTTIImpl::getNumberOfRegisters(bool vector) const {
   return vector ? 0 : 32;
 }
 

llvm/trunk/lib/Target/NVPTX/NVPTXTargetTransformInfo.h

public:
   int getArithmeticInstrCost(
       unsigned Opcode, Type *Ty,
       TTI::OperandValueKind Opd1Info = TTI::OK_AnyValue,
       TTI::OperandValueKind Opd2Info = TTI::OK_AnyValue,
       TTI::OperandValueProperties Opd1PropInfo = TTI::OP_None,
       TTI::OperandValueProperties Opd2PropInfo = TTI::OP_None,
       ArrayRef<const Value *> Args = ArrayRef<const Value *>());
 
-  void getUnrollingPreferences(Loop *L, TTI::UnrollingPreferences &UP);
+  void getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
+                               TTI::UnrollingPreferences &UP);
 };
 
 } // end namespace llvm
 
 #endif

llvm/trunk/lib/Target/NVPTX/NVPTXTargetTransformInfo.cpp

case ISD::AND:
     if (LT.second.SimpleTy == MVT::i64)
       return 2 * LT.first;
     // Delegate other cases to the basic TTI.
     return BaseT::getArithmeticInstrCost(Opcode, Ty, Opd1Info, Opd2Info,
                                          Opd1PropInfo, Opd2PropInfo);
   }
 }
 
-void NVPTXTTIImpl::getUnrollingPreferences(Loop *L,
+void NVPTXTTIImpl::getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
                                            TTI::UnrollingPreferences &UP) {
-  BaseT::getUnrollingPreferences(L, UP);
+  BaseT::getUnrollingPreferences(L, SE, UP);
 
   // Enable partial unrolling and runtime unrolling, but reduce the
   // threshold.  This partially unrolls small loops which are often
   // unrolled by the PTX to SASS compiler and unrolling earlier can be
   // beneficial.
   UP.Partial = UP.Runtime = true;
   UP.PartialThreshold = UP.Threshold / 4;
 }

llvm/trunk/lib/Target/PowerPC/PPCTargetTransformInfo.h

public:
   using BaseT::getIntImmCost;
   int getIntImmCost(const APInt &Imm, Type *Ty);
 
   int getIntImmCost(unsigned Opcode, unsigned Idx, const APInt &Imm, Type *Ty);
   int getIntImmCost(Intrinsic::ID IID, unsigned Idx, const APInt &Imm,
                     Type *Ty);
 
   TTI::PopcntSupportKind getPopcntSupport(unsigned TyWidth);
-  void getUnrollingPreferences(Loop *L, TTI::UnrollingPreferences &UP);
+  void getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
+                               TTI::UnrollingPreferences &UP);
 
   /// @}
 
   /// \name Vector TTI Implementations
   /// @{
 
   bool enableAggressiveInterleaving(bool LoopHasReductions);
   bool expandMemCmp(Instruction *I, unsigned &MaxLoadSize);

llvm/trunk/lib/Target/PowerPC/PPCTargetTransformInfo.cpp

if (Idx == ImmIdx && Imm.getBitWidth() <= 64) {
 
     if (ShiftedFree && (Imm.getZExtValue() & 0xFFFF) == 0)
       return TTI::TCC_Free;
   }
 
   return PPCTTIImpl::getIntImmCost(Imm, Ty);
 }
 
-void PPCTTIImpl::getUnrollingPreferences(Loop *L,
+void PPCTTIImpl::getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
                                          TTI::UnrollingPreferences &UP) {
   if (ST->getDarwinDirective() == PPC::DIR_A2) {
     // The A2 is in-order with a deep pipeline, and concatenation unrolling
     // helps expose latency-hiding opportunities to the instruction scheduler.
     UP.Partial = UP.Runtime = true;
 
     // We unroll a lot on the A2 (hundreds of instructions), and the benefits
     // often outweigh the cost of a division to compute the trip count.
     UP.AllowExpensiveTripCount = true;
   }
 
-  BaseT::getUnrollingPreferences(L, UP);
+  BaseT::getUnrollingPreferences(L, SE, UP);
 }
 
 bool PPCTTIImpl::enableAggressiveInterleaving(bool LoopHasReductions) {
   // On the A2, always unroll aggressively. For QPX unaligned loads, we depend
   // on combining the loads generated for consecutive accesses, and failure to
   // do so is particularly expensive. This makes it much more likely (compared
   // to only using concatenation unrolling).
   if (ST->getDarwinDirective() == PPC::DIR_A2)

llvm/trunk/lib/Target/SystemZ/SystemZTargetTransformInfo.h

public:
   int getIntImmCost(const APInt &Imm, Type *Ty);
 
   int getIntImmCost(unsigned Opcode, unsigned Idx, const APInt &Imm, Type *Ty);
   int getIntImmCost(Intrinsic::ID IID, unsigned Idx, const APInt &Imm,
                     Type *Ty);
 
   TTI::PopcntSupportKind getPopcntSupport(unsigned TyWidth);
 
-  void getUnrollingPreferences(Loop *L, TTI::UnrollingPreferences &UP);
+  void getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
+                               TTI::UnrollingPreferences &UP);
 
   /// @}
 
   /// \name Vector TTI Implementations
   /// @{
 
   unsigned getNumberOfRegisters(bool Vector);
   unsigned getRegisterBitWidth(bool Vector) const;

llvm/trunk/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp

 TargetTransformInfo::PopcntSupportKind
 SystemZTTIImpl::getPopcntSupport(unsigned TyWidth) {
   assert(isPowerOf2_32(TyWidth) && "Type width must be power of 2");
   if (ST->hasPopulationCount() && TyWidth <= 64)
     return TTI::PSK_FastHardware;
   return TTI::PSK_Software;
 }
 
-void SystemZTTIImpl::getUnrollingPreferences(Loop *L,
+void SystemZTTIImpl::getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
                                              TTI::UnrollingPreferences &UP) {
   // Find out if L contains a call, what the machine instruction count
   // estimate is, and how many stores there are.
   bool HasCall = false;
   unsigned NumStores = 0;
   for (auto &BB : L->blocks())
     for (auto &I : *BB) {
       if (isa<CallInst>(&I) || isa<InvokeInst>(&I)) {

llvm/trunk/lib/Transforms/Scalar/LoopUnrollPass.cpp

 /// A magic value for use with the Threshold parameter to indicate
 /// that the loop unroll should be performed regardless of how much
 /// code expansion would result.
 static const unsigned NoThreshold = UINT_MAX;
 
 /// Gather the various unrolling parameters based on the defaults, compiler
 /// flags, TTI overrides and user specified parameters.
 static TargetTransformInfo::UnrollingPreferences gatherUnrollingPreferences(
-    Loop *L, const TargetTransformInfo &TTI, int OptLevel,
+    Loop *L, ScalarEvolution &SE, const TargetTransformInfo &TTI, int OptLevel,
     Optional<unsigned> UserThreshold, Optional<unsigned> UserCount,
     Optional<bool> UserAllowPartial, Optional<bool> UserRuntime,
     Optional<bool> UserUpperBound) {
   TargetTransformInfo::UnrollingPreferences UP;
 
   // Set up the defaults
   UP.Threshold = OptLevel > 2 ? 300 : 150;
   UP.MaxPercentThresholdBoost = 400;
static TargetTransformInfo::UnrollingPreferences gatherUnrollingPreferences(
   UP.Runtime = false;
   UP.AllowRemainder = true;
   UP.AllowExpensiveTripCount = false;
   UP.Force = false;
   UP.UpperBound = false;
   UP.AllowPeeling = true;
 
   // Override with any target specific settings
-  TTI.getUnrollingPreferences(L, UP);
+  TTI.getUnrollingPreferences(L, SE, UP);
 
   // Apply size attributes
   if (L->getHeader()->getParent()->optForSize()) {
     UP.Threshold = UP.OptSizeThreshold;
     UP.PartialThreshold = UP.PartialOptSizeThreshold;
   }
 
   // Apply any user values specified by cl::opt
static uint64_t getUnrolledLoopSize(
   assert(LoopSize >= UP.BEInsns && "LoopSize should not be less than BEInsns!");
   return (uint64_t)(LoopSize - UP.BEInsns) * UP.Count + UP.BEInsns;
 }
 
 // Returns true if unroll count was set explicitly.
 // Calculates unroll count and writes it to UP.Count.
 static bool computeUnrollCount(
     Loop *L, const TargetTransformInfo &TTI, DominatorTree &DT, LoopInfo *LI,
-    ScalarEvolution *SE, OptimizationRemarkEmitter *ORE, unsigned &TripCount,
+    ScalarEvolution &SE, OptimizationRemarkEmitter *ORE, unsigned &TripCount,
     unsigned MaxTripCount, unsigned &TripMultiple, unsigned LoopSize,
     TargetTransformInfo::UnrollingPreferences &UP, bool &UseUpperBound) {
   // Check for explicit Count.
   // 1st priority is unroll count set by "unroll-count" option.
   bool UserUnrollCount = UnrollCount.getNumOccurrences() > 0;
   if (UserUnrollCount) {
     UP.Count = UnrollCount;
     UP.AllowExpensiveTripCount = true;
if (getUnrolledLoopSize(LoopSize, UP) < UP.Threshold) {
       TripCount = FullUnrollTripCount;
       TripMultiple = UP.UpperBound ? 1 : TripMultiple;
       return ExplicitUnroll;
     } else {
       // The loop isn't that small, but we still can fully unroll it if that
       // helps to remove a significant number of instructions.
       // To check that, run additional analysis on the loop.
       if (Optional<EstimatedUnrollCost> Cost = analyzeLoopUnrollCost(
-              L, FullUnrollTripCount, DT, *SE, TTI,
+              L, FullUnrollTripCount, DT, SE, TTI,
               UP.Threshold * UP.MaxPercentThresholdBoost / 100)) {
         unsigned Boost =
             getFullUnrollBoostingFactor(*Cost, UP.MaxPercentThresholdBoost);
         if (Cost->UnrolledCost < UP.Threshold * Boost / 100) {
           UseUpperBound = (MaxTripCount == FullUnrollTripCount);
           TripCount = FullUnrollTripCount;
           TripMultiple = UP.UpperBound ? 1 : TripMultiple;
           return ExplicitUnroll;
if (UP.Count > UP.MaxCount)
     UP.Count = UP.MaxCount;
   DEBUG(dbgs() << "  partially unrolling with count: " << UP.Count << "\n");
   if (UP.Count < 2)
     UP.Count = 0;
   return ExplicitUnroll;
 }
 
 static bool tryToUnrollLoop(Loop *L, DominatorTree &DT, LoopInfo *LI,
-                            ScalarEvolution *SE, const TargetTransformInfo &TTI,
+                            ScalarEvolution &SE, const TargetTransformInfo &TTI,
                             AssumptionCache &AC, OptimizationRemarkEmitter &ORE,
                             bool PreserveLCSSA, int OptLevel,
                             Optional<unsigned> ProvidedCount,
                             Optional<unsigned> ProvidedThreshold,
                             Optional<bool> ProvidedAllowPartial,
                             Optional<bool> ProvidedRuntime,
                             Optional<bool> ProvidedUpperBound) {
   DEBUG(dbgs() << "Loop Unroll: F[" << L->getHeader()->getParent()->getName()
                << "] Loop %" << L->getHeader()->getName() << "\n");
   if (HasUnrollDisablePragma(L)) 
     return false;
   if (!L->isLoopSimplifyForm()) { 
     DEBUG(
         dbgs() << "  Not unrolling loop which is not in loop-simplify form.\n");
     return false;
   }
 
   unsigned NumInlineCandidates;
   bool NotDuplicatable;
   bool Convergent;
   TargetTransformInfo::UnrollingPreferences UP = gatherUnrollingPreferences(
-      L, TTI, OptLevel, ProvidedThreshold, ProvidedCount, ProvidedAllowPartial,
-      ProvidedRuntime, ProvidedUpperBound);
+      L, SE, TTI, OptLevel, ProvidedThreshold, ProvidedCount,
+      ProvidedAllowPartial, ProvidedRuntime, ProvidedUpperBound);
   // Exit early if unrolling is disabled.
   if (UP.Threshold == 0 && (!UP.Partial || UP.PartialThreshold == 0))
     return false;
   unsigned LoopSize = ApproximateLoopSize(
       L, NumInlineCandidates, NotDuplicatable, Convergent, TTI, &AC, UP.BEInsns);
   DEBUG(dbgs() << "  Loop Size = " << LoopSize << "\n");
   if (NotDuplicatable) {
     DEBUG(dbgs() << "  Not unrolling loop which contains non-duplicatable"
static bool tryToUnrollLoop(Loop *L, DominatorTree &DT, LoopInfo *LI,
   unsigned TripMultiple = 1;
   // If there are multiple exiting blocks but one of them is the latch, use the
   // latch for the trip count estimation. Otherwise insist on a single exiting
   // block for the trip count estimation.
   BasicBlock *ExitingBlock = L->getLoopLatch();
   if (!ExitingBlock || !L->isLoopExiting(ExitingBlock))
     ExitingBlock = L->getExitingBlock();
   if (ExitingBlock) {
-    TripCount = SE->getSmallConstantTripCount(L, ExitingBlock);
-    TripMultiple = SE->getSmallConstantTripMultiple(L, ExitingBlock);
+    TripCount = SE.getSmallConstantTripCount(L, ExitingBlock);
+    TripMultiple = SE.getSmallConstantTripMultiple(L, ExitingBlock);
   }
 
   // If the loop contains a convergent operation, the prelude we'd add
   // to do the first few instructions before we hit the unrolled loop
   // is unsafe -- it adds a control-flow dependency to the convergent
   // operation.  Therefore restrict remainder loop (try unrollig without).
   //
   // TODO: This is quite conservative.  In practice, convergent_op()
   // is likely to be called unconditionally in the loop.  In this
   // case, the program would be ill-formed (on most architectures)
   // unless n were the same on all threads in a thread group.
   // Assuming n is the same on all threads, any kind of unrolling is
   // safe.  But currently llvm's notion of convergence isn't powerful
   // enough to express this.
   if (Convergent)
     UP.AllowRemainder = false;
 
   // Try to find the trip count upper bound if we cannot find the exact trip
   // count.
   bool MaxOrZero = false;
   if (!TripCount) {
-    MaxTripCount = SE->getSmallConstantMaxTripCount(L);
-    MaxOrZero = SE->isBackedgeTakenCountMaxOrZero(L);
+    MaxTripCount = SE.getSmallConstantMaxTripCount(L);
+    MaxOrZero = SE.isBackedgeTakenCountMaxOrZero(L);
     // We can unroll by the upper bound amount if it's generally allowed or if
     // we know that the loop is executed either the upper bound or zero times.
     // (MaxOrZero unrolling keeps only the first loop test, so the number of
     // loop tests remains the same compared to the non-unrolled version, whereas
     // the generic upper bound unrolling keeps all but the last loop test so the
     // number of loop tests goes up which may end up being worse on targets with
     // constriained branch predictor resources so is controlled by an option.)
     // In addition we only unroll small upper bounds.
if (!UP.Count)
     return false;
   // Unroll factor (Count) must be less or equal to TripCount.
   if (TripCount && UP.Count > TripCount)
     UP.Count = TripCount;
 
   // Unroll the loop.
   if (!UnrollLoop(L, UP.Count, TripCount, UP.Force, UP.Runtime,
                   UP.AllowExpensiveTripCount, UseUpperBound, MaxOrZero,
-                  TripMultiple, UP.PeelCount, LI, SE, &DT, &AC, &ORE,
+                  TripMultiple, UP.PeelCount, LI, &SE, &DT, &AC, &ORE,
                   PreserveLCSSA))
     return false;
 
   // If loop has an unroll count pragma or unrolled by explicitly set count
   // mark loop as unrolled to prevent unrolling beyond that requested.
   // If the loop was peeled, we already "used up" the profile information
   // we had, so we don't want to unroll or peel again.
   if (IsCountSetExplicitly || UP.PeelCount)
public:
   bool runOnLoop(Loop *L, LPPassManager &) override {
     if (skipLoop(L))
       return false;
 
     Function &F = *L->getHeader()->getParent();
 
     auto &DT = getAnalysis<DominatorTreeWrapperPass>().getDomTree();
     LoopInfo *LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
-    ScalarEvolution *SE = &getAnalysis<ScalarEvolutionWrapperPass>().getSE();
+    ScalarEvolution &SE = getAnalysis<ScalarEvolutionWrapperPass>().getSE();
     const TargetTransformInfo &TTI =
         getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
     auto &AC = getAnalysis<AssumptionCacheTracker>().getAssumptionCache(F);
     // For the old PM, we can't use OptimizationRemarkEmitter as an analysis
     // pass.  Function analyses need to be preserved across loop transformations
     // but ORE cannot be preserved (see comment before the pass definition).
     OptimizationRemarkEmitter ORE(&F);
     bool PreserveLCSSA = mustPreserveAnalysisID(LCSSAID);
PreservedAnalyses LoopUnrollPass::run(Loop &L, LoopAnalysisManager &AM,
   // The API here is quite complex to call, but there are only two interesting
   // states we support: partial and full (or "simple") unrolling. However, to
   // enable these things we actually pass "None" in for the optional to avoid
   // providing an explicit choice.
   Optional<bool> AllowPartialParam, RuntimeParam, UpperBoundParam;
   if (!AllowPartialUnrolling)
     AllowPartialParam = RuntimeParam = UpperBoundParam = false;
   bool Changed = tryToUnrollLoop(
-      &L, AR.DT, &AR.LI, &AR.SE, AR.TTI, AR.AC, *ORE,
+      &L, AR.DT, &AR.LI, AR.SE, AR.TTI, AR.AC, *ORE,
       /*PreserveLCSSA*/ true, OptLevel, /*Count*/ None,
       /*Threshold*/ None, AllowPartialParam, RuntimeParam, UpperBoundParam);
   if (!Changed)
     return PreservedAnalyses::all();
 
   // The parent must not be damaged by unrolling!
 #ifndef NDEBUG
   if (ParentL)