[SCEV][LV] Add SCEV Predicates and use them to re-implement stride versioning

[sbaranga]

Summary

SCEV Predicates represent conditions that typically cannot be derived from
static analysis, but can be used to reduce SCEV expressions to forms which are
usable for different optimizers.

ScalarEvolution now has the rewriteUsingPredicate method which can simplify a
SCEV expression using a SCEVPredicateSet. The normal workflow of a pass using
SCEVPredicates would be to hold a SCEVPredicateSet and every time assumptions
need to be made a new SCEV Predicate would be created and added to the set.
Each time after calling getSCEV, the user will call the rewriteUsingPredicate
method.

We add two types of predicates
SCEVPredicateSet - implements a set of predicates
SCEVEqualPredicate - tests for equality between two SCEV expressions

We use the SCEVEqualPredicate to re-implement stride versioning. Every time we
version a stride, we will add a SCEVEqualPredicate to the context.
Instead of adding specific stride checks, LoopVectorize now adds a more
generic SCEV check.

We only need to add support for this in the LoopVectorizer since this is the
only pass that will do stride versioning.

[sbaranga]

Hi,

I've cloned this from http://reviews.llvm.org/D12905, since the old comments were getting in the way.

This is also an updated version where I hope all the old issues have been solved.

This still depends on http://reviews.llvm.org/D13242.

Thanks,
Silviu

[jmolloy]

Hi Silviu,

It looks like Michael and Sanjoy have done most of the heavy lifting on this review, so for me I think it's in a good shape by this point.

I have a bunch of comments though.

James

include/llvm/Analysis/LoopAccessAnalysis.h

181

It doesn't make sense to me that this is plural when it doesn't relate to a set/list/vector of items. It's just one predicate, that happens to be a union.

In fact, why is this a unionpredicate anyway? Why can't it just be the superclass?

include/llvm/Analysis/ScalarEvolution.h

51

The sorting seems off here.

172

Is there a need for this separator line? I can't see any prior art anywhere else in the file

184

Why is this an unsigned short and not an enum SCEVPredicateTypes?

187

These don't match the usual LLVM style of enum naming. Normally we use a prefix, underscore then an UpperCamelCase identifier:

P_Set, P_Equal

207

What does Depth mean here? does it make sense to have a default parameter for people who "just want" to print something?

209

If you're going to use \brief, keep the first sentence separate from the rest of the text with an empty line.

214

Is it guaranteed that the values are contiguous and that no other instrucitons are interleaved between them? (i assume not, best to make this explicit).

265

Remove unneeded blank line.

323

Unneeded blank line.

335

Surely PUNION would be more appropriate?

lib/Analysis/LoopAccessAnalysis.cpp

130

Removed useful newline

lib/Analysis/ScalarEvolution.cpp

9505

You can just do:

return {static_cast..., static_cast...};

Yay C++11!

9532

Either all braces or no braces - don't mix braces in if/else statements.

9540

Can use C++11 syntax here too.

9547

You could probably use std::bind here.

9555

and here.

lib/Transforms/Vectorize/LoopVectorize.cpp

410–412

bypassssssss

[sbaranga]

Thanks, James! Replies inline.

include/llvm/Analysis/LoopAccessAnalysis.h

181

There are two ways to see it: as a collection of predicates or as one predicate. If we are adding more predicates to it maybe it makes sense to call it Preds?

We need this to be a union predicate because we're using the union predicate specific methods (that is we're adding new predicates to it, which we can only with the union predicates). I don't expect there would aver be a need to have something different then a union predicate there.

include/llvm/Analysis/ScalarEvolution.h

207

Depth is for indentation. Having the Depth be 0 by default makes sense to me.

[sbaranga]

Addressing comments received from James.

• renamed enum members to P_Union, P_Equal
• renamed SCEVPredicateTypes to SCEVPredicateKind
• renamed SCEVPredicateType to 'Kind'
• now kind is of type SCEVPredicateKind instead of unsigned short
• etc

[sbaranga]

lib/Analysis/ScalarEvolution.cpp

9547

I've tried using bind here but the code comes out horrible. For example:

std::any_of(SCEVPreds.begin(), SCEVPreds.end(),

std::bind(&SCEVPredicate::implies, std::placeholders::_1, N));

This requires more characters to write and seems more difficult to read. Maybe we should skip using bind here?

[sbaranga]

Ping? If there's anything I can do to make the review process go faster, please let me know.

-Silviu

[sanjoy]

The SCEV parts of the change is looking much better now. I didn't read through the logic carefully this time, and I only have minor stylistic issues. I'm happy to give a LGTM for the SCEV bits contingent on the stylistic issues getting addressed.

include/llvm/Analysis/ScalarEvolution.h

265

Use a default value for Depth here as well.

Also, very minor, you might want to override operator<< too, just for consistency with the rest of the codebase.

lib/Analysis/LoopAccessAnalysis.cpp

111–117

Use cast<>

lib/Analysis/ScalarEvolution.cpp

9386

Can we name this function better? I don't have a better suggestion though.

9391

When can I->getParent() be not equal to Loc->getParent()?

[jmolloy]

The non-SCEV stuff LGTM.

[anemet]

Non-SCEV parts LGTM too.

Silviu,

I guess one thing that's missing form your summary which is another advantage to this approach that now we will only issue stride-checks when we actually had to assume stride=1 during analysis. Correct?

Thanks,
Adam

[sbaranga]

Thanks for the reviews!

In D13595#274745, @anemet wrote:

I guess one thing that's missing form your summary which is another advantage to this approach that now we will only issue stride-checks when we actually had to assume stride=1 during analysis. Correct?

We're not currently changing that behaviour (we're always adding the SCEVEqualPredicate when we see a pointer that we can version). Although that is certainly something we could do in the future.

Thanks,
Silviu

[sbaranga]

Address review comments from Sanjoy.

[sbaranga]

Is this ok to commit? Maybe we could maybe handle the getFirstInst as a follow-up?

Thanks,
Silviu

lib/Analysis/ScalarEvolution.cpp

9386

I don't have any good idea here.

It should also probably be moved into some place where it can be shared with LoopAccessAnalysis, but I don't know where exactly it would fit.

9391

This was part of the original "getFirstInst" implementation lifted out of LoopVectorize. This can potentially happen when theIRBuilder is folding instructions outside of the current basic block produced by the SCEV expander (I think the SCEV expander is able to produce such instructions - at least for SCEVUnknowns).

[sanjoy]

lib/Analysis/ScalarEvolution.cpp

9391

I know I'm bikeshedding a lot on this, but I think a better utility would be

BasicBlock *getValueParent(Value *V) {
  if (I = dyn_cast<Instruction>(V))
    return I->getParent();
  return nullptr;
}

then where you call getFirstInst you could instead do

if (!FirstInst && getValueParent(C) == Loc)
  FirstInst = cast<Instruction>(C);

I think that will be clearer and almost as concise -- reading getFirstInst(A,B,C) does not really tell me anything about what it is supposed to do, especially since one of the parameters is named FirstInst.

[sbaranga]

Change the RT check generation interface to return a Value*, instead of a pair of instructions.

We were previosly returning a pair of instructions to confirm with the existing versioning
interfaces. However, that created a bunch of problems, and made the checking code less nice.

It also turns out that we don't really need to return the first added instruction (and it would
be easy for a user to get anyway).

[sbaranga]

lib/Analysis/ScalarEvolution.cpp

9391

I've removed the versioning interface that was causing us to use this function (I should have probably done so the when you've previously asked for it).

We're now returning a Value*, so no need to use this getFirstInst function (which was removed). This removes a whole bunch of other problems (we aren't casting Value * to Instruction * anymore), so it should be much nicer.

[hfinkel]

lib/Analysis/ScalarEvolution.cpp

70

We currently have SCEVExpander use SCEV, but not the other-way around. Could you move the IR-building code into SCEVExpander to avoid changing the layering here?

[sbaranga]

Resolve the layering issue raised by Hal.

• the SCEVExpander now has an expandCodeForPredicate method which we use to generate the checks.
• removed the generateGuardCond/generateCheck methods.

[hfinkel]

Why is all of the SCEVPredicate code in ScalarEvolution.{cpp.h}, as opposed to being in its own files? Is there a two-way coupling that I'm missing, or will there be one in the future?

[sbaranga]

Hi Hal,

In D13595#277106, @hfinkel wrote:

Why is all of the SCEVPredicate code in ScalarEvolution.{cpp.h}, as opposed to being in its own files? Is there a two-way coupling that I'm missing, or will there be one in the future?

Currently we use the memory pool from ScalarEvolution for the allocation of Predicates.

In the future I plan to make ScalarEvolution give some answers for getBackedgeCount which will be guarded by SCEVPredicates, so there will probably a tight coupling there.

Also, there's also a lot of commonality between the SCEV rewritting use cases and some of the reasoning that SCEV does already (at least that's what I observed for overflows and sext/zext handling). So there might be some opportunity for sharing code in these cases.

Thanks,
Silviu

[hfinkel]

In D13595#277123, @sbaranga wrote:

Hi Hal,

In D13595#277106, @hfinkel wrote:

Why is all of the SCEVPredicate code in ScalarEvolution.{cpp.h}, as opposed to being in its own files? Is there a two-way coupling that I'm missing, or will there be one in the future?

Currently we use the memory pool from ScalarEvolution for the allocation of Predicates.

In the future I plan to make ScalarEvolution give some answers for getBackedgeCount which will be guarded by SCEVPredicates, so there will probably a tight coupling there.

Also, there's also a lot of commonality between the SCEV rewritting use cases and some of the reasoning that SCEV does already (at least that's what I observed for overflows and sext/zext handling). So there might be some opportunity for sharing code in these cases.

Thanks,
Silviu

In that case, LGTM too.

[sbaranga]

@sanjoy: are you happy with the current form of the patch? I think the previous issues should have been solved.

Thanks,
Silviu

[sanjoy]

lgtm

[sbaranga]

Committed in r251800. Thanks all for the hard work you've put in reviewing this patch!

-Silviu

[mmarjieh]

include/llvm/Analysis/ScalarEvolutionExpander.h

154–157

Is the comment wrong? I see that in the implementation you do a invert of the operation.

I am talking about this:
The result will be of type i1 and will have a value of 0 when the
predicate is false and 1 otherwise.

include/llvm/Analysis/LoopAccessAnalysis.h

 
 namespace llvm {
 
 class Value;
 class DataLayout;
 class ScalarEvolution;
 class Loop;
 class SCEV;
+class SCEVUnionPredicate;
 
 /// Optimization analysis message produced during vectorization. Messages inform
 /// the user why vectorization did not occur.
 class LoopAccessReport {
   std::string Message;
   const Instruction *Instr;
 
 protected:
struct Dependence {
     bool isPossiblyBackward() const;
 
     /// \brief Print the dependence.  \p Instr is used to map the instruction
     /// indices to instructions.
     void print(raw_ostream &OS, unsigned Depth,
                const SmallVectorImpl<Instruction *> &Instrs) const;
   };
 
-  MemoryDepChecker(ScalarEvolution *Se, const Loop *L)
+  MemoryDepChecker(ScalarEvolution *Se, const Loop *L,
+                   SCEVUnionPredicate &Preds)
       : SE(Se), InnermostLoop(L), AccessIdx(0),
         ShouldRetryWithRuntimeCheck(false), SafeForVectorization(true),
-        RecordInterestingDependences(true) {}
+        RecordInterestingDependences(true), Preds(Preds) {}
 
   /// \brief Register the location (instructions are given increasing numbers)
   /// of a write access.
   void addAccess(StoreInst *SI) {
     Value *Ptr = SI->getPointerOperand();
     Accesses[MemAccessInfo(Ptr, true)].push_back(AccessIdx);
     InstMap.push_back(SI);
     ++AccessIdx;
private:
   /// Otherwise, this function returns true signaling a possible dependence.
   Dependence::DepType isDependent(const MemAccessInfo &A, unsigned AIdx,
                                   const MemAccessInfo &B, unsigned BIdx,
                                   const ValueToValueMap &Strides);
 
   /// \brief Check whether the data dependence could prevent store-load
   /// forwarding.
   bool couldPreventStoreLoadForward(unsigned Distance, unsigned TypeByteSize);
+
+  /// The SCEV predicate containing all the SCEV-related assumptions.
+  /// The dependence checker needs this in order to convert SCEVs of pointers
+  /// to more accurate expressions in the context of existing assumptions.
+  /// We also need this in case assumptions about SCEV expressions need to
+  /// be made in order to avoid unknown dependences. For example we might
+  /// assume a unit stride for a pointer in order to prove that a memory access
+  /// is strided and doesn't wrap.
+  SCEVUnionPredicate &Preds;
 };
 
 /// \brief Holds information about the memory runtime legality checks to verify
 /// that a group of pointers do not overlap.
 class RuntimePointerChecking {
 public:
   struct PointerInfo {
     /// Holds the pointer value that we need to check.
public:
   /// Reset the state of the pointer runtime information.
   void reset() {
     Need = false;
     Pointers.clear();
     Checks.clear();
   }
 
   /// Insert a pointer and calculate the start and end SCEVs.
+  /// \p We need Preds in order to compute the SCEV expression of the pointer
+  /// according to the assumptions that we've made during the analysis.
+  /// The method might also version the pointer stride according to \p Strides,
+  /// and change \p Preds.
   void insert(Loop *Lp, Value *Ptr, bool WritePtr, unsigned DepSetId,
-              unsigned ASId, const ValueToValueMap &Strides);
+              unsigned ASId, const ValueToValueMap &Strides,
+              SCEVUnionPredicate &Preds);
 
   /// \brief No run-time memory checking is necessary.
   bool empty() const { return Pointers.empty(); }
 
   /// A grouping of pointers. A single memcheck is required between
   /// two groups.
   struct CheckingPtrGroup {
     /// \brief Create a new pointer checking group containing a single
public:
 
   /// \brief Checks existence of store to invariant address inside loop.
   /// If the loop has any store to invariant address, then it returns true,
   /// else returns false.
   bool hasStoreToLoopInvariantAddress() const {
     return StoreToLoopInvariantAddress;
   }
 
+  /// The SCEV predicate contains all the SCEV-related assumptions.
+  /// The is used to keep track of the minimal set of assumptions on SCEV
+  /// expressions that the analysis needs to make in order to return a
+  /// meaningful result. All SCEV expressions during the analysis should be
+  /// re-written (and therefore simplified) according to Preds.
+  /// A user of LoopAccessAnalysis will need to emit the runtime checks
+  /// associated with this predicate.
+  SCEVUnionPredicate Preds;
+
 private:
   /// \brief Analyze the loop.  Substitute symbolic strides using Strides.
   void analyzeLoop(const ValueToValueMap &Strides);
 
   /// \brief Check if the structure of the loop allows it to be analyzed by this
   /// pass.
   bool canAnalyzeLoop();
 
private:
   /// \brief The diagnostics report generated for the analysis.  E.g. why we
   /// couldn't analyze the loop.
   Optional<LoopAccessReport> Report;
 };
 
 Value *stripIntegerCast(Value *V);
 
 ///\brief Return the SCEV corresponding to a pointer with the symbolic stride
-///replaced with constant one.
+/// replaced with constant one, assuming \p Preds is true.
+///
+/// If necessary this method will version the stride of the pointer according
+/// to \p PtrToStride and therefore add a new predicate to \p Preds.
 ///
 /// If \p OrigPtr is not null, use it to look up the stride value instead of \p
 /// Ptr.  \p PtrToStride provides the mapping between the pointer value and its
 /// stride as collected by LoopVectorizationLegality::collectStridedAccess.
 const SCEV *replaceSymbolicStrideSCEV(ScalarEvolution *SE,
                                       const ValueToValueMap &PtrToStride,
-                                      Value *Ptr, Value *OrigPtr = nullptr);
+                                      SCEVUnionPredicate &Preds, Value *Ptr,
+                                      Value *OrigPtr = nullptr);
 
 /// \brief Check the stride of the pointer and ensure that it does not wrap in
-/// the address space.
+/// the address space, assuming \p Preds is true.
+///
+/// If necessary this method will version the stride of the pointer according
+/// to \p PtrToStride and therefore add a new predicate to \p Preds.
 int isStridedPtr(ScalarEvolution *SE, Value *Ptr, const Loop *Lp,
-                 const ValueToValueMap &StridesMap);
+                 const ValueToValueMap &StridesMap, SCEVUnionPredicate &Preds);
 
 /// \brief This analysis provides dependence information for the memory accesses
 /// of a loop.
 ///
 /// It runs the analysis for a loop on demand.  This can be initiated by
 /// querying the loop access info via LAA::getInfo.  getInfo return a
 /// LoopAccessInfo object.  See this class for the specifics of what information
 /// is provided.

include/llvm/Analysis/ScalarEvolution.h

namespace llvm {
   class Type;
   class ScalarEvolution;
   class DataLayout;
   class TargetLibraryInfo;
   class LLVMContext;
   class Loop;
   class LoopInfo;
   class Operator;
-  class SCEVUnknown;
-  class SCEVAddRecExpr;
   class SCEV;
-  template<> struct FoldingSetTrait<SCEV>;
+  class SCEVAddRecExpr;
+  class SCEVConstant;
+  class SCEVExpander;
+  class SCEVPredicate;
+  class SCEVUnknown;
+
+  template <> struct FoldingSetTrait<SCEV>;
+  template <> struct FoldingSetTrait<SCEVPredicate>;
 
   /// This class represents an analyzed expression in the program.  These are
   /// opaque objects that the client is not allowed to do much with directly.
   ///
   class SCEV : public FoldingSetNode {
     friend struct FoldingSetTrait<SCEV>;
 
     /// A reference to an Interned FoldingSetNodeID for this node.  The
namespace llvm {
   /// operations are valid on this class, it is just a marker.
   struct SCEVCouldNotCompute : public SCEV {
     SCEVCouldNotCompute();
 
     /// Methods for support type inquiry through isa, cast, and dyn_cast:
     static bool classof(const SCEV *S);
   };
 
+  /// SCEVPredicate - This class represents an assumption made using SCEV
+  /// expressions which can be checked at run-time.
+  class SCEVPredicate : public FoldingSetNode {
+    friend struct FoldingSetTrait<SCEVPredicate>;
+
+    /// A reference to an Interned FoldingSetNodeID for this node.  The
+    /// ScalarEvolution's BumpPtrAllocator holds the data.
+    FoldingSetNodeIDRef FastID;
+
+  public:
+    enum SCEVPredicateKind { P_Union, P_Equal };
+
+  protected:
+    SCEVPredicateKind Kind;
+
+  public:
+    SCEVPredicate(const FoldingSetNodeIDRef ID, SCEVPredicateKind Kind);
+
+    virtual ~SCEVPredicate() {}
+
+    SCEVPredicateKind getKind() const { return Kind; }
+
+    /// \brief Returns the estimated complexity of this predicate.
+    /// This is roughly measured in the number of run-time checks required.
+    virtual unsigned getComplexity() { return 1; }
+
+    /// \brief Returns true if the predicate is always true. This means that no
+    /// assumptions were made and nothing needs to be checked at run-time.
+    virtual bool isAlwaysTrue() const = 0;
+
+    /// \brief Returns true if this predicate implies \p N.
+    virtual bool implies(const SCEVPredicate *N) const = 0;
+
+    /// \brief Prints a textual representation of this predicate with an
+    /// indentation of \p Depth.
+    virtual void print(raw_ostream &OS, unsigned Depth = 0) const = 0;
+
+    /// \brief Returns the SCEV to which this predicate applies, or nullptr
+    /// if this is a SCEVUnionPredicate.
+    virtual const SCEV *getExpr() const = 0;
+  };
+
+  inline raw_ostream &operator<<(raw_ostream &OS, const SCEVPredicate &P) {
+    P.print(OS);
+    return OS;
+  }
+
+  // Specialize FoldingSetTrait for SCEVPredicate to avoid needing to compute
+  // temporary FoldingSetNodeID values.
+  template <>
+  struct FoldingSetTrait<SCEVPredicate>
+      : DefaultFoldingSetTrait<SCEVPredicate> {
+
+    static void Profile(const SCEVPredicate &X, FoldingSetNodeID &ID) {
+      ID = X.FastID;
+    }
+
+    static bool Equals(const SCEVPredicate &X, const FoldingSetNodeID &ID,
+                       unsigned IDHash, FoldingSetNodeID &TempID) {
+      return ID == X.FastID;
+    }
+    static unsigned ComputeHash(const SCEVPredicate &X,
+                                FoldingSetNodeID &TempID) {
+      return X.FastID.ComputeHash();
+    }
+  };
+
+  /// SCEVEqualPredicate - This class represents an assumption that two SCEV
+  /// expressions are equal, and this can be checked at run-time. We assume
+  /// that the left hand side is a SCEVUnknown and the right hand side a
+  /// constant.
+  class SCEVEqualPredicate : public SCEVPredicate {
+    /// We assume that LHS == RHS, where LHS is a SCEVUnknown and RHS a
+    /// constant.
+    const SCEVUnknown *LHS;
+    const SCEVConstant *RHS;
+
+  public:
+    SCEVEqualPredicate(const FoldingSetNodeIDRef ID, const SCEVUnknown *LHS,
+                       const SCEVConstant *RHS);
+
+    /// Implementation of the SCEVPredicate interface
+    bool implies(const SCEVPredicate *N) const override;
+    void print(raw_ostream &OS, unsigned Depth = 0) const override;
+    bool isAlwaysTrue() const override;
+    const SCEV *getExpr() const;
+
+    /// \brief Returns the left hand side of the equality.
+    const SCEVUnknown *getLHS() const { return LHS; }
+
+    /// \brief Returns the right hand side of the equality.
+    const SCEVConstant *getRHS() const { return RHS; }
+
+    /// Methods for support type inquiry through isa, cast, and dyn_cast:
+    static inline bool classof(const SCEVPredicate *P) {
+      return P->getKind() == P_Equal;
+    }
+  };
+
+  /// SCEVUnionPredicate - This class represents a composition of other
+  /// SCEV predicates, and is the class that most clients will interact with.
+  /// This is equivalent to a logical "AND" of all the predicates in the union.
+  class SCEVUnionPredicate : public SCEVPredicate {
+  private:
+    typedef DenseMap<const SCEV *, SmallVector<const SCEVPredicate *, 4>>
+        PredicateMap;
+
+    /// Vector with references to all predicates in this union.
+    SmallVector<const SCEVPredicate *, 16> Preds;
+    /// Maps SCEVs to predicates for quick look-ups.
+    PredicateMap SCEVToPreds;
+
+  public:
+    SCEVUnionPredicate();
+
+    const SmallVectorImpl<const SCEVPredicate *> &getPredicates() const {
+      return Preds;
+    }
+
+    /// \brief Adds a predicate to this union.
+    void add(const SCEVPredicate *N);
+
+    /// \brief Returns a reference to a vector containing all predicates
+    /// which apply to \p Expr.
+    ArrayRef<const SCEVPredicate *> getPredicatesForExpr(const SCEV *Expr);
+
+    /// Implementation of the SCEVPredicate interface
+    bool isAlwaysTrue() const override;
+    bool implies(const SCEVPredicate *N) const override;
+    void print(raw_ostream &OS, unsigned Depth) const;
+    const SCEV *getExpr() const override;
+
+    /// \brief We estimate the complexity of a union predicate as the size
+    /// number of predicates in the union.
+    unsigned getComplexity() override { return Preds.size(); }
+
+    /// Methods for support type inquiry through isa, cast, and dyn_cast:
+    static inline bool classof(const SCEVPredicate *P) {
+      return P->getKind() == P_Union;
+    }
+  };
+
   /// The main scalar evolution driver. Because client code (intentionally)
   /// can't do much with the SCEV objects directly, they must ask this class
   /// for services.
   class ScalarEvolution {
   public:
     /// An enum describing the relationship between a SCEV and a loop.
     enum LoopDisposition {
       LoopVariant,    ///< The SCEV is loop-variant (unknown).
       LoopInvariant,  ///< The SCEV is loop-invariant.
       LoopComputable  ///< The SCEV varies predictably with the loop.
     };
 
     /// An enum describing the relationship between a SCEV and a basic block.
     enum BlockDisposition {
       DoesNotDominateBlock,  ///< The SCEV does not dominate the block.
       DominatesBlock,        ///< The SCEV dominates the block.
       ProperlyDominatesBlock ///< The SCEV properly dominates the block.
     };
 
     /// Convenient NoWrapFlags manipulation that hides enum casts and is
     /// visible in the ScalarEvolution name space.
     static SCEV::NoWrapFlags LLVM_ATTRIBUTE_UNUSED_RESULT
     maskFlags(SCEV::NoWrapFlags Flags, int Mask) {
       return (SCEV::NoWrapFlags)(Flags & Mask);
     }
     static SCEV::NoWrapFlags LLVM_ATTRIBUTE_UNUSED_RESULT
     setFlags(SCEV::NoWrapFlags Flags, SCEV::NoWrapFlags OnFlags) {
       return (SCEV::NoWrapFlags)(Flags | OnFlags);
     }
     static SCEV::NoWrapFlags LLVM_ATTRIBUTE_UNUSED_RESULT
void delinearize(const SCEV *Expr,
                      const SCEV *ElementSize);
 
     /// Return the DataLayout associated with the module this SCEV instance is
     /// operating on.
     const DataLayout &getDataLayout() const {
       return F.getParent()->getDataLayout();
     }
 
+    const SCEVPredicate *getEqualPredicate(const SCEVUnknown *LHS,
+                                           const SCEVConstant *RHS);
+
+    /// Re-writes the SCEV according to the Predicates in \p Preds.
+    const SCEV *rewriteUsingPredicate(const SCEV *Scev, SCEVUnionPredicate &A);
+
   private:
     /// Compute the backedge taken count knowing the interval difference, the
     /// stride and presence of the equality in the comparison.
     const SCEV *computeBECount(const SCEV *Delta, const SCEV *Stride,
                                bool Equality);
 
     /// Verify if an linear IV with positive stride can overflow when in a
     /// less-than comparison, knowing the invariant term of the comparison,
     /// the stride and the knowledge of NSW/NUW flags on the recurrence.
     bool doesIVOverflowOnLT(const SCEV *RHS, const SCEV *Stride,
                             bool IsSigned, bool NoWrap);
 
     /// Verify if an linear IV with negative stride can overflow when in a
     /// greater-than comparison, knowing the invariant term of the comparison,
     /// the stride and the knowledge of NSW/NUW flags on the recurrence.
     bool doesIVOverflowOnGT(const SCEV *RHS, const SCEV *Stride,
                             bool IsSigned, bool NoWrap);
 
   private:
     FoldingSet<SCEV> UniqueSCEVs;
+    FoldingSet<SCEVPredicate> UniquePreds;
     BumpPtrAllocator SCEVAllocator;
 
     /// The head of a linked list of all SCEVUnknown values that have been
     /// allocated. This is used by releaseMemory to locate them all and call
     /// their destructors.
     SCEVUnknown *FirstUnknown;
   };
 

include/llvm/Analysis/ScalarEvolutionExpander.h

unsigned replaceCongruentIVs(Loop *L, const DominatorTree *DT,
                                  SmallVectorImpl<WeakVH> &DeadInsts,
                                  const TargetTransformInfo *TTI = nullptr);
 
     /// \brief Insert code to directly compute the specified SCEV expression
     /// into the program.  The inserted code is inserted into the specified
     /// block.
     Value *expandCodeFor(const SCEV *SH, Type *Ty, Instruction *I);
 
+    /// \brief Generates a code sequence that evaluates this predicate.
+    /// The inserted instructions will be at position \p Loc.
+    /// The result will be of type i1 and will have a value of 0 when the
+    /// predicate is false and 1 otherwise.
+    Value *expandCodeForPredicate(const SCEVPredicate *Pred, Instruction *Loc);
+
+    /// \brief A specialized variant of expandCodeForPredicate, handling the
+    /// case when we are expanding code for a SCEVEqualPredicate.
+    Value *expandEqualPredicate(const SCEVEqualPredicate *Pred,
+                                Instruction *Loc);
+
+    /// \brief A specialized variant of expandCodeForPredicate, handling the
+    /// case when we are expanding code for a SCEVUnionPredicate.
+    Value *expandUnionPredicate(const SCEVUnionPredicate *Pred,
+                                Instruction *Loc);
+
     /// \brief Set the current IV increment loop and position.
     void setIVIncInsertPos(const Loop *L, Instruction *Pos) {
       assert(!CanonicalMode &&
              "IV increment positions are not supported in CanonicalMode");
       IVIncInsertLoop = L;
       IVIncInsertPos = Pos;
     }
 

lib/Analysis/LoopAccessAnalysis.cpp

Value *llvm::stripIntegerCast(Value *V) {
   if (CastInst *CI = dyn_cast<CastInst>(V))
     if (CI->getOperand(0)->getType()->isIntegerTy())
       return CI->getOperand(0);
   return V;
 }
 
 const SCEV *llvm::replaceSymbolicStrideSCEV(ScalarEvolution *SE,
                                             const ValueToValueMap &PtrToStride,
+                                            SCEVUnionPredicate &Preds,
                                             Value *Ptr, Value *OrigPtr) {
-
   const SCEV *OrigSCEV = SE->getSCEV(Ptr);
 
   // If there is an entry in the map return the SCEV of the pointer with the
   // symbolic stride replaced by one.
   ValueToValueMap::const_iterator SI =
       PtrToStride.find(OrigPtr ? OrigPtr : Ptr);
   if (SI != PtrToStride.end()) {
     Value *StrideVal = SI->second;
 
     // Strip casts.
     StrideVal = stripIntegerCast(StrideVal);
 
     // Replace symbolic stride by one.
     Value *One = ConstantInt::get(StrideVal->getType(), 1);
     ValueToValueMap RewriteMap;
     RewriteMap[StrideVal] = One;
 
-    const SCEV *ByOne =
-        SCEVParameterRewriter::rewrite(OrigSCEV, *SE, RewriteMap, true);
+    const auto *U = cast<SCEVUnknown>(SE->getSCEV(StrideVal));
+    const auto *CT =
+        static_cast<const SCEVConstant *>(SE->getOne(StrideVal->getType()));
+
+    Preds.add(SE->getEqualPredicate(U, CT));
+
+    const SCEV *ByOne = SE->rewriteUsingPredicate(OrigSCEV, Preds);
     DEBUG(dbgs() << "LAA: Replacing SCEV: " << *OrigSCEV << " by: " << *ByOne
                  << "\n");
     return ByOne;
   }
 
   // Otherwise, just return the SCEV of the original pointer.
-  return SE->getSCEV(Ptr);
+  return OrigSCEV;
 }
 
 void RuntimePointerChecking::insert(Loop *Lp, Value *Ptr, bool WritePtr,
                                     unsigned DepSetId, unsigned ASId,
-                                    const ValueToValueMap &Strides) {
+                                    const ValueToValueMap &Strides,
+                                    SCEVUnionPredicate &Preds) {
   // Get the stride replaced scev.
-  const SCEV *Sc = replaceSymbolicStrideSCEV(SE, Strides, Ptr);
+  const SCEV *Sc = replaceSymbolicStrideSCEV(SE, Strides, Preds, Ptr);
   const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(Sc);
   assert(AR && "Invalid addrec expression");
   const SCEV *Ex = SE->getBackedgeTakenCount(Lp);
 
   const SCEV *ScStart = AR->getStart();
   const SCEV *ScEnd = AR->evaluateAtIteration(Ex, *SE);
   const SCEV *Step = AR->getStepRecurrence(*SE);
 
   // For expressions with negative step, the upper bound is ScStart and the
   // lower bound is ScEnd.
   if (const SCEVConstant *CStep = dyn_cast<const SCEVConstant>(Step)) {
     if (CStep->getValue()->isNegative())

 /// dependence checking.
 class AccessAnalysis {
 public:
   /// \brief Read or write access location.
   typedef PointerIntPair<Value *, 1, bool> MemAccessInfo;
   typedef SmallPtrSet<MemAccessInfo, 8> MemAccessInfoSet;
 
   AccessAnalysis(const DataLayout &Dl, AliasAnalysis *AA, LoopInfo *LI,
-                 MemoryDepChecker::DepCandidates &DA)
-      : DL(Dl), AST(*AA), LI(LI), DepCands(DA),
-        IsRTCheckAnalysisNeeded(false) {}
+                 MemoryDepChecker::DepCandidates &DA, SCEVUnionPredicate &Preds)
+      : DL(Dl), AST(*AA), LI(LI), DepCands(DA), IsRTCheckAnalysisNeeded(false),
+        Preds(Preds) {}
 
   /// \brief Register a load  and whether it is only read from.
   void addLoad(MemoryLocation &Loc, bool IsReadOnly) {
     Value *Ptr = const_cast<Value*>(Loc.Ptr);
     AST.add(Ptr, MemoryLocation::UnknownSize, Loc.AATags);
     Accesses.insert(MemAccessInfo(Ptr, false));
     if (IsReadOnly)
       ReadOnlyPtr.insert(Ptr);
private:
   /// \brief Initial processing of memory accesses determined that we may need
   /// to add memchecks.  Perform the analysis to determine the necessary checks.
   ///
   /// Note that, this is different from isDependencyCheckNeeded.  When we retry
   /// memcheck analysis without dependency checking
   /// (i.e. ShouldRetryWithRuntimeCheck), isDependencyCheckNeeded is cleared
   /// while this remains set if we have potentially dependent accesses.
   bool IsRTCheckAnalysisNeeded;
+
+  /// The SCEV predicate containing all the SCEV-related assumptions.
+  SCEVUnionPredicate &Preds;
 };
 
 } // end anonymous namespace
 
 /// \brief Check whether a pointer can participate in a runtime bounds check.
 static bool hasComputableBounds(ScalarEvolution *SE,
-                                const ValueToValueMap &Strides, Value *Ptr) {
-  const SCEV *PtrScev = replaceSymbolicStrideSCEV(SE, Strides, Ptr);
+                                const ValueToValueMap &Strides, Value *Ptr,
+                                Loop *L, SCEVUnionPredicate &Preds) {
+  const SCEV *PtrScev = replaceSymbolicStrideSCEV(SE, Strides, Preds, Ptr);
   const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(PtrScev);
   if (!AR)
     return false;
 
   return AR->isAffine();
 }
 
 bool AccessAnalysis::canCheckPtrAtRT(RuntimePointerChecking &RtCheck,
for (auto A : AS) {
       bool IsWrite = Accesses.count(MemAccessInfo(Ptr, true));
       MemAccessInfo Access(Ptr, IsWrite);
 
       if (IsWrite)
         ++NumWritePtrChecks;
       else
         ++NumReadPtrChecks;
 
-      if (hasComputableBounds(SE, StridesMap, Ptr) &&
+      if (hasComputableBounds(SE, StridesMap, Ptr, TheLoop, Preds) &&
           // When we run after a failing dependency check we have to make sure
           // we don't have wrapping pointers.
           (!ShouldCheckStride ||
-           isStridedPtr(SE, Ptr, TheLoop, StridesMap) == 1)) {
+           isStridedPtr(SE, Ptr, TheLoop, StridesMap, Preds) == 1)) {
         // The id of the dependence set.
         unsigned DepId;
 
         if (IsDepCheckNeeded) {
           Value *Leader = DepCands.getLeaderValue(Access).getPointer();
           unsigned &LeaderId = DepSetId[Leader];
           if (!LeaderId)
             LeaderId = RunningDepId++;
           DepId = LeaderId;
         } else
           // Each access has its own dependence set.
           DepId = RunningDepId++;
 
-        RtCheck.insert(TheLoop, Ptr, IsWrite, DepId, ASId, StridesMap);
+        RtCheck.insert(TheLoop, Ptr, IsWrite, DepId, ASId, StridesMap, Preds);
 
         DEBUG(dbgs() << "LAA: Found a runtime check ptr:" << *Ptr << '\n');
       } else {
         DEBUG(dbgs() << "LAA: Can't find bounds for ptr:" << *Ptr << '\n');
         CanDoRT = false;
       }
     }
 
if (OBO->hasNoSignedWrap() &&
         return OpAR->getLoop() == L && OpAR->getNoWrapFlags(SCEV::FlagNSW);
     }
 
   return false;
 }
 
 /// \brief Check whether the access through \p Ptr has a constant stride.
 int llvm::isStridedPtr(ScalarEvolution *SE, Value *Ptr, const Loop *Lp,
-                       const ValueToValueMap &StridesMap) {
+                       const ValueToValueMap &StridesMap,
+                       SCEVUnionPredicate &Preds) {
   Type *Ty = Ptr->getType();
   assert(Ty->isPointerTy() && "Unexpected non-ptr");
 
   // Make sure that the pointer does not point to aggregate types.
   auto *PtrTy = cast<PointerType>(Ty);
   if (PtrTy->getElementType()->isAggregateType()) {
     DEBUG(dbgs() << "LAA: Bad stride - Not a pointer to a scalar type"
           << *Ptr << "\n");
     return 0;
   }
 
-  const SCEV *PtrScev = replaceSymbolicStrideSCEV(SE, StridesMap, Ptr);
+  const SCEV *PtrScev = replaceSymbolicStrideSCEV(SE, StridesMap, Preds, Ptr);
 
   const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(PtrScev);
   if (!AR) {
     DEBUG(dbgs() << "LAA: Bad stride - Not an AddRecExpr pointer "
           << *Ptr << " SCEV: " << *PtrScev << "\n");
     return 0;
   }
 
MemoryDepChecker::isDependent(const MemAccessInfo &A, unsigned AIdx,
   if (!AIsWrite && !BIsWrite)
     return Dependence::NoDep;
 
   // We cannot check pointers in different address spaces.
   if (APtr->getType()->getPointerAddressSpace() !=
       BPtr->getType()->getPointerAddressSpace())
     return Dependence::Unknown;
 
-  const SCEV *AScev = replaceSymbolicStrideSCEV(SE, Strides, APtr);
-  const SCEV *BScev = replaceSymbolicStrideSCEV(SE, Strides, BPtr);
+  const SCEV *AScev = replaceSymbolicStrideSCEV(SE, Strides, Preds, APtr);
+  const SCEV *BScev = replaceSymbolicStrideSCEV(SE, Strides, Preds, BPtr);
 
-  int StrideAPtr = isStridedPtr(SE, APtr, InnermostLoop, Strides);
-  int StrideBPtr = isStridedPtr(SE, BPtr, InnermostLoop, Strides);
+  int StrideAPtr = isStridedPtr(SE, APtr, InnermostLoop, Strides, Preds);
+  int StrideBPtr = isStridedPtr(SE, BPtr, InnermostLoop, Strides, Preds);
 
   const SCEV *Src = AScev;
   const SCEV *Sink = BScev;
 
   // If the induction step is negative we have to invert source and sink of the
   // dependence.
   if (StrideAPtr < 0) {
     //Src = BScev;
void LoopAccessInfo::analyzeLoop(const ValueToValueMap &Strides) {
   if (!Stores.size()) {
     DEBUG(dbgs() << "LAA: Found a read-only loop!\n");
     CanVecMem = true;
     return;
   }
 
   MemoryDepChecker::DepCandidates DependentAccesses;
   AccessAnalysis Accesses(TheLoop->getHeader()->getModule()->getDataLayout(),
-                          AA, LI, DependentAccesses);
+                          AA, LI, DependentAccesses, Preds);
 
   // Holds the analyzed pointers. We don't want to call GetUnderlyingObjects
   // multiple times on the same object. If the ptr is accessed twice, once
   // for read and once for write, it will only appear once (on the write
   // list). This is okay, since we are going to check for conflicts between
   // writes and between reads and writes, but not between reads and reads.
   ValueSet Seen;
 
for (I = Loads.begin(), IE = Loads.end(); I != IE; ++I) {
     // read list. If we *did* see it before, then it is already in
     // the read-write list. This allows us to vectorize expressions
     // such as A[i] += x;  Because the address of A[i] is a read-write
     // pointer. This only works if the index of A[i] is consecutive.
     // If the address of i is unknown (for example A[B[i]]) then we may
     // read a few words, modify, and write a few words, and some of the
     // words may be written to the same address.
     bool IsReadOnlyPtr = false;
-    if (Seen.insert(Ptr).second || !isStridedPtr(SE, Ptr, TheLoop, Strides)) {
+    if (Seen.insert(Ptr).second ||
+        !isStridedPtr(SE, Ptr, TheLoop, Strides, Preds)) {
       ++NumReads;
       IsReadOnlyPtr = true;
     }
 
     MemoryLocation Loc = MemoryLocation::get(LD);
     // The TBAA metadata could have a control dependency on the predication
     // condition, so we cannot rely on it when determining whether or not we
     // need runtime pointer checks.
LoopAccessInfo::addRuntimeChecks(Instruction *Loc) const {
   return addRuntimeChecks(Loc, PtrRtChecking.getChecks());
 }
 
 LoopAccessInfo::LoopAccessInfo(Loop *L, ScalarEvolution *SE,
                                const DataLayout &DL,
                                const TargetLibraryInfo *TLI, AliasAnalysis *AA,
                                DominatorTree *DT, LoopInfo *LI,
                                const ValueToValueMap &Strides)
-    : PtrRtChecking(SE), DepChecker(SE, L), TheLoop(L), SE(SE), DL(DL),
+    : PtrRtChecking(SE), DepChecker(SE, L, Preds), TheLoop(L), SE(SE), DL(DL),
       TLI(TLI), AA(AA), DT(DT), LI(LI), NumLoads(0), NumStores(0),
       MaxSafeDepDistBytes(-1U), CanVecMem(false),
       StoreToLoopInvariantAddress(false) {
   if (canAnalyzeLoop())
     analyzeLoop(Strides);
 }
 
 void LoopAccessInfo::print(raw_ostream &OS, unsigned Depth) const {
void LoopAccessInfo::print(raw_ostream &OS, unsigned Depth) const {
 
   // List the pair of accesses need run-time checks to prove independence.
   PtrRtChecking.print(OS, Depth);
   OS << "\n";
 
   OS.indent(Depth) << "Store to invariant address was "
                    << (StoreToLoopInvariantAddress ? "" : "not ")
                    << "found in loop.\n";
+
+  OS.indent(Depth) << "SCEV assumptions:\n";
+  Preds.print(OS, Depth);
 }
 
 const LoopAccessInfo &
 LoopAccessAnalysis::getInfo(Loop *L, const ValueToValueMap &Strides) {
   auto &LAI = LoopAccessInfoMap[L];
 
 #ifndef NDEBUG
   assert((!LAI || LAI->NumSymbolicStrides == Strides.size()) &&
          "Symbolic strides changed for loop");
 #endif
 
   if (!LAI) {
     const DataLayout &DL = L->getHeader()->getModule()->getDataLayout();
-    LAI = llvm::make_unique<LoopAccessInfo>(L, SE, DL, TLI, AA, DT, LI,
-                                            Strides);
+    LAI =
+        llvm::make_unique<LoopAccessInfo>(L, SE, DL, TLI, AA, DT, LI, Strides);
 #ifndef NDEBUG
     LAI->NumSymbolicStrides = Strides.size();
 #endif
   }
   return *LAI.get();
 }
 
 void LoopAccessAnalysis::print(raw_ostream &OS, const Module *M) const {

lib/Analysis/ScalarEvolution.cpp

 #include "llvm/ADT/Optional.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/ADT/Statistic.h"
 #include "llvm/Analysis/AssumptionCache.h"
 #include "llvm/Analysis/ConstantFolding.h"
 #include "llvm/Analysis/InstructionSimplify.h"
 #include "llvm/Analysis/LoopInfo.h"
 #include "llvm/Analysis/ScalarEvolutionExpressions.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
 #include "llvm/Analysis/ValueTracking.h"
 #include "llvm/IR/ConstantRange.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/DataLayout.h"
 #include "llvm/IR/DerivedTypes.h"
 #include "llvm/IR/Dominators.h"
 #include "llvm/IR/GetElementPtrTypeIterator.h"
: F(Arg.F), TLI(Arg.TLI), AC(Arg.AC), DT(Arg.DT), LI(Arg.LI),
       ConstantEvolutionLoopExitValue(
           std::move(Arg.ConstantEvolutionLoopExitValue)),
       ValuesAtScopes(std::move(Arg.ValuesAtScopes)),
       LoopDispositions(std::move(Arg.LoopDispositions)),
       BlockDispositions(std::move(Arg.BlockDispositions)),
       UnsignedRanges(std::move(Arg.UnsignedRanges)),
       SignedRanges(std::move(Arg.SignedRanges)),
       UniqueSCEVs(std::move(Arg.UniqueSCEVs)),
+      UniquePreds(std::move(Arg.UniquePreds)),
       SCEVAllocator(std::move(Arg.SCEVAllocator)),
       FirstUnknown(Arg.FirstUnknown) {
   Arg.FirstUnknown = nullptr;
 }
 
 ScalarEvolution::~ScalarEvolution() {
   // Iterate through all the SCEVUnknown instances and call their
   // destructors, so that they release their references to their values.

 
 void ScalarEvolutionWrapperPass::getAnalysisUsage(AnalysisUsage &AU) const {
   AU.setPreservesAll();
   AU.addRequiredTransitive<AssumptionCacheTracker>();
   AU.addRequiredTransitive<LoopInfoWrapperPass>();
   AU.addRequiredTransitive<DominatorTreeWrapperPass>();
   AU.addRequiredTransitive<TargetLibraryInfoWrapperPass>();
 }
+
+const SCEVPredicate *
+ScalarEvolution::getEqualPredicate(const SCEVUnknown *LHS,
+                                   const SCEVConstant *RHS) {
+  FoldingSetNodeID ID;
+  // Unique this node based on the arguments
+  ID.AddInteger(SCEVPredicate::P_Equal);
+  ID.AddPointer(LHS);
+  ID.AddPointer(RHS);
+  void *IP = nullptr;
+  if (const auto *S = UniquePreds.FindNodeOrInsertPos(ID, IP))
+    return S;
+  SCEVEqualPredicate *Eq = new (SCEVAllocator)
+      SCEVEqualPredicate(ID.Intern(SCEVAllocator), LHS, RHS);
+  UniquePreds.InsertNode(Eq, IP);
+  return Eq;
+}
+
+class SCEVPredicateRewriter : public SCEVRewriteVisitor<SCEVPredicateRewriter> {
+public:
+  static const SCEV *rewrite(const SCEV *Scev, ScalarEvolution &SE,
+                             SCEVUnionPredicate &A) {
+    SCEVPredicateRewriter Rewriter(SE, A);
+    return Rewriter.visit(Scev);
+  }
+
+  SCEVPredicateRewriter(ScalarEvolution &SE, SCEVUnionPredicate &P)
+      : SCEVRewriteVisitor(SE), P(P) {}
+
+  const SCEV *visitUnknown(const SCEVUnknown *Expr) {
+    auto ExprPreds = P.getPredicatesForExpr(Expr);
+    for (auto *Pred : ExprPreds)
+      if (const auto *IPred = dyn_cast<const SCEVEqualPredicate>(Pred))
+        if (IPred->getLHS() == Expr)
+          return IPred->getRHS();
+
+    return Expr;
+  }
+
+private:
+  SCEVUnionPredicate &P;
+};
+
+const SCEV *ScalarEvolution::rewriteUsingPredicate(const SCEV *Scev,
+                                                   SCEVUnionPredicate &Preds) {
+  return SCEVPredicateRewriter::rewrite(Scev, *this, Preds);
+}
+
+/// SCEV predicates
+SCEVPredicate::SCEVPredicate(const FoldingSetNodeIDRef ID,
+                             SCEVPredicateKind Kind)
+    : FastID(ID), Kind(Kind) {}
+
+SCEVEqualPredicate::SCEVEqualPredicate(const FoldingSetNodeIDRef ID,
+                                       const SCEVUnknown *LHS,
+                                       const SCEVConstant *RHS)
+    : SCEVPredicate(ID, P_Equal), LHS(LHS), RHS(RHS) {}
+
+bool SCEVEqualPredicate::implies(const SCEVPredicate *N) const {
+  const auto *Op = dyn_cast<const SCEVEqualPredicate>(N);
+
+  if (!Op)
+    return false;
+
+  return Op->LHS == LHS && Op->RHS == RHS;
+}
+
+bool SCEVEqualPredicate::isAlwaysTrue() const { return false; }
+
+const SCEV *SCEVEqualPredicate::getExpr() const { return LHS; }
+
+void SCEVEqualPredicate::print(raw_ostream &OS, unsigned Depth) const {
+  OS.indent(Depth) << "Equal predicate: " << *LHS << " == " << *RHS << "\n";
+}
+
+/// Union predicates don't get cached so create a dummy set ID for it.
+SCEVUnionPredicate::SCEVUnionPredicate()
+    : SCEVPredicate(FoldingSetNodeIDRef(nullptr, 0), P_Union) {}
+
+bool SCEVUnionPredicate::isAlwaysTrue() const {
+  return std::all_of(Preds.begin(), Preds.end(),
+                     [](const SCEVPredicate *I) { return I->isAlwaysTrue(); });
+}
+
+ArrayRef<const SCEVPredicate *>
+SCEVUnionPredicate::getPredicatesForExpr(const SCEV *Expr) {
+  auto I = SCEVToPreds.find(Expr);
+  if (I == SCEVToPreds.end())
+    return ArrayRef<const SCEVPredicate *>();
+  return I->second;
+}
+
+bool SCEVUnionPredicate::implies(const SCEVPredicate *N) const {
+  if (const auto *Set = dyn_cast<const SCEVUnionPredicate>(N))
+    return std::all_of(
+        Set->Preds.begin(), Set->Preds.end(),
+        [this](const SCEVPredicate *I) { return this->implies(I); });
+
+  auto ScevPredsIt = SCEVToPreds.find(N->getExpr());
+  if (ScevPredsIt == SCEVToPreds.end())
+    return false;
+  auto &SCEVPreds = ScevPredsIt->second;
+
+  return std::any_of(SCEVPreds.begin(), SCEVPreds.end(),
+                     [N](const SCEVPredicate *I) { return I->implies(N); });
+}
+
+const SCEV *SCEVUnionPredicate::getExpr() const { return nullptr; }
+
+void SCEVUnionPredicate::print(raw_ostream &OS, unsigned Depth) const {
+  for (auto Pred : Preds)
+    Pred->print(OS, Depth);
+}
+
+void SCEVUnionPredicate::add(const SCEVPredicate *N) {
+  if (const auto *Set = dyn_cast<const SCEVUnionPredicate>(N)) {
+    for (auto Pred : Set->Preds)
+      add(Pred);
+    return;
+  }
+
+  if (implies(N))
+    return;
+
+  const SCEV *Key = N->getExpr();
+  assert(Key && "Only SCEVUnionPredicate doesn't have an "
+                " associated expression!");
+
+  SCEVToPreds[Key].push_back(N);
+  Preds.push_back(N);
+}

lib/Analysis/ScalarEvolutionExpander.cpp

if (const SCEVNAryExpr *NAry = dyn_cast<SCEVNAryExpr>(S)) {
     }
   }
 
   // If we haven't recognized an expensive SCEV pattern, assume it's an
   // expression produced by program code.
   return false;
 }
 
+Value *SCEVExpander::expandCodeForPredicate(const SCEVPredicate *Pred,
+                                            Instruction *IP) {
+  assert(IP);
+  switch (Pred->getKind()) {
+  case SCEVPredicate::P_Union:
+    return expandUnionPredicate(cast<SCEVUnionPredicate>(Pred), IP);
+  case SCEVPredicate::P_Equal:
+    return expandEqualPredicate(cast<SCEVEqualPredicate>(Pred), IP);
+  }
+  llvm_unreachable("Unknown SCEV predicate type");
+}
+
+Value *SCEVExpander::expandEqualPredicate(const SCEVEqualPredicate *Pred,
+                                          Instruction *IP) {
+  Value *Expr0 = expandCodeFor(Pred->getLHS(), Pred->getLHS()->getType(), IP);
+  Value *Expr1 = expandCodeFor(Pred->getRHS(), Pred->getRHS()->getType(), IP);
+
+  Builder.SetInsertPoint(IP);
+  auto *I = Builder.CreateICmpNE(Expr0, Expr1, "ident.check");
+  return I;
+}
+
+Value *SCEVExpander::expandUnionPredicate(const SCEVUnionPredicate *Union,
+                                          Instruction *IP) {
+  auto *BoolType = IntegerType::get(IP->getContext(), 1);
+  Value *Check = ConstantInt::getNullValue(BoolType);
+
+  // Loop over all checks in this set.
+  for (auto Pred : Union->getPredicates()) {
+    auto *NextCheck = expandCodeForPredicate(Pred, IP);
+    Builder.SetInsertPoint(IP);
+    Check = Builder.CreateOr(Check, NextCheck);
+  }
+
+  return Check;
+}
+
 namespace {
 // Search for a SCEV subexpression that is not safe to expand.  Any expression
 // that may expand to a !isSafeToSpeculativelyExecute value is unsafe, namely
 // UDiv expressions. We don't know if the UDiv is derived from an IR divide
 // instruction, but the important thing is that we prove the denominator is
 // nonzero before expansion.
 //
 // IVUsers already checks that IV-derived expressions are safe. So this check is

lib/Transforms/Vectorize/LoopVectorize.cpp

static cl::opt<unsigned> MaxNestedScalarReductionIC(
     cl::desc("The maximum interleave count to use when interleaving a scalar "
              "reduction in a nested loop."));
 
 static cl::opt<unsigned> PragmaVectorizeMemoryCheckThreshold(
     "pragma-vectorize-memory-check-threshold", cl::init(128), cl::Hidden,
     cl::desc("The maximum allowed number of runtime memory checks with a "
              "vectorize(enable) pragma."));
 
+static cl::opt<unsigned> VectorizeSCEVCheckThreshold(
+    "vectorize-scev-check-threshold", cl::init(16), cl::Hidden,
+    cl::desc("The maximum number of SCEV checks allowed."));
+
+static cl::opt<unsigned> PragmaVectorizeSCEVCheckThreshold(
+    "pragma-vectorize-scev-check-threshold", cl::init(128), cl::Hidden,
+    cl::desc("The maximum number of SCEV checks allowed with a "
+             "vectorize(enable) pragma"));
+
 namespace {
 
 // Forward declarations.
 class LoopVectorizeHints;
 class LoopVectorizationLegality;
 class LoopVectorizationCostModel;
 class LoopVectorizationRequirements;
 

 /// aspects. The InnerLoopVectorizer relies on the
 /// LoopVectorizationLegality class to provide information about the induction
 /// and reduction variables that were found to a given vectorization factor.
 class InnerLoopVectorizer {
 public:
   InnerLoopVectorizer(Loop *OrigLoop, ScalarEvolution *SE, LoopInfo *LI,
                       DominatorTree *DT, const TargetLibraryInfo *TLI,
                       const TargetTransformInfo *TTI, unsigned VecWidth,
-                      unsigned UnrollFactor)
+                      unsigned UnrollFactor, SCEVUnionPredicate &Preds)
       : OrigLoop(OrigLoop), SE(SE), LI(LI), DT(DT), TLI(TLI), TTI(TTI),
         VF(VecWidth), UF(UnrollFactor), Builder(SE->getContext()),
         Induction(nullptr), OldInduction(nullptr), WidenMap(UnrollFactor),
         TripCount(nullptr), VectorTripCount(nullptr), Legal(nullptr),
-        AddedSafetyChecks(false) {}
+        AddedSafetyChecks(false), Preds(Preds) {}
 
   // Perform the actual loop widening (vectorization).
   // MinimumBitWidths maps scalar integer values to the smallest bitwidth they
   // can be validly truncated to. The cost model has assumed this truncation
   // will happen when vectorizing.
   void vectorize(LoopVectorizationLegality *L,
                  DenseMap<Instruction*,uint64_t> MinimumBitWidths) {
     MinBWs = MinimumBitWidths;
protected:
   /// originated from one scalar instruction.
   typedef SmallVector<Value*, 2> VectorParts;
 
   // When we if-convert we need to create edge masks. We have to cache values
   // so that we don't end up with exponential recursion/IR.
   typedef DenseMap<std::pair<BasicBlock*, BasicBlock*>,
                    VectorParts> EdgeMaskCache;
 
-  /// \brief Add checks for strides that were assumed to be 1.
-  ///
-  /// Returns the last check instruction and the first check instruction in the
-  /// pair as (first, last).
-  std::pair<Instruction *, Instruction *> addStrideCheck(Instruction *Loc);
-
   /// Create an empty loop, based on the loop ranges of the old loop.
   void createEmptyLoop();
   /// Create a new induction variable inside L.
   PHINode *createInductionVariable(Loop *L, Value *Start, Value *End,
                                    Value *Step, Instruction *DL);
   /// Copy and widen the instructions from the old loop.
   virtual void vectorizeLoop();
 
protected:
   /// Returns (and creates if needed) the trip count of the widened loop.
   Value *getOrCreateVectorTripCount(Loop *NewLoop);
 
   /// Emit a bypass check to see if the trip count would overflow, or we
   /// wouldn't have enough iterations to execute one vector loop.
   void emitMinimumIterationCountCheck(Loop *L, BasicBlock *Bypass);
   /// Emit a bypass check to see if the vector trip count is nonzero.
   void emitVectorLoopEnteredCheck(Loop *L, BasicBlock *Bypass);
-  /// Emit bypass checks to check if strides we've assumed to be one really are.
-  void emitStrideChecks(Loop *L, BasicBlock *Bypass);
+  /// Emit a bypass check to see if all of the SCEV assumptions we've
+  /// had to make are correct.
+  void emitSCEVChecks(Loop *L, BasicBlock *Bypass);
   /// Emit bypass checks to check any memory assumptions we may have made.
   void emitMemRuntimeChecks(Loop *L, BasicBlock *Bypass);
-  
   /// This is a helper class that holds the vectorizer state. It maps scalar
   /// instructions to vector instructions. When the code is 'unrolled' then
   /// then a single scalar value is mapped to multiple vector parts. The parts
   /// are stored in the VectorPart type.
   struct ValueMap {
     /// C'tor.  UnrollFactor controls the number of vectors ('parts') that
     /// are mapped.
     ValueMap(unsigned UnrollFactor) : UF(UnrollFactor) {}
protected:
   /// Map of scalar integer values to the smallest bitwidth they can be legally
   /// represented as. The vector equivalents of these values should be truncated
   /// to this type.
   DenseMap<Instruction*,uint64_t> MinBWs;
   LoopVectorizationLegality *Legal;
 
   // Record whether runtime check is added.
   bool AddedSafetyChecks;
+
+  /// The SCEV predicate containing all the SCEV-related assumptions.
+  /// The predicate is used to simplify existing expressions in the
+  /// context of existing SCEV assumptions. Since legality checking is
+  /// not done here, we don't need to use this predicate to record
+  /// further assumptions.
+  SCEVUnionPredicate &Preds;
 };
 
 class InnerLoopUnroller : public InnerLoopVectorizer {
 public:
   InnerLoopUnroller(Loop *OrigLoop, ScalarEvolution *SE, LoopInfo *LI,
                     DominatorTree *DT, const TargetLibraryInfo *TLI,
-                    const TargetTransformInfo *TTI, unsigned UnrollFactor)
-      : InnerLoopVectorizer(OrigLoop, SE, LI, DT, TLI, TTI, 1, UnrollFactor) {}
+                    const TargetTransformInfo *TTI, unsigned UnrollFactor,
+                    SCEVUnionPredicate &Preds)
+      : InnerLoopVectorizer(OrigLoop, SE, LI, DT, TLI, TTI, 1, UnrollFactor,
+                            Preds) {}
 
 private:
   void scalarizeInstruction(Instruction *Instr,
                             bool IfPredicateStore = false) override;
   void vectorizeMemoryInstruction(Instruction *Instr) override;
   Value *getBroadcastInstrs(Value *V) override;
   Value *getStepVector(Value *Val, int StartIdx, Value *Step) override;
   Value *reverseVector(Value *Vec) override;

 /// Use this class to analyze interleaved accesses only when we can vectorize
 /// a loop. Otherwise it's meaningless to do analysis as the vectorization
 /// on interleaved accesses is unsafe.
 ///
 /// The analysis collects interleave groups and records the relationships
 /// between the member and the group in a map.
 class InterleavedAccessInfo {
 public:
-  InterleavedAccessInfo(ScalarEvolution *SE, Loop *L, DominatorTree *DT)
-      : SE(SE), TheLoop(L), DT(DT) {}
+  InterleavedAccessInfo(ScalarEvolution *SE, Loop *L, DominatorTree *DT,
+                        SCEVUnionPredicate &Preds)
+      : SE(SE), TheLoop(L), DT(DT), Preds(Preds) {}
 
   ~InterleavedAccessInfo() {
     SmallSet<InterleaveGroup *, 4> DelSet;
     // Avoid releasing a pointer twice.
     for (auto &I : InterleaveGroupMap)
       DelSet.insert(I.second);
     for (auto *Ptr : DelSet)
       delete Ptr;
InterleaveGroup *getInterleaveGroup(Instruction *Instr) const {
     return nullptr;
   }
 
 private:
   ScalarEvolution *SE;
   Loop *TheLoop;
   DominatorTree *DT;
 
+  /// The SCEV predicate containing all the SCEV-related assumptions.
+  /// The predicate is used to simplify SCEV expressions in the
+  /// context of existing SCEV assumptions. The interleaved access
+  /// analysis can also add new predicates (for example by versioning
+  /// strides of pointers).
+  SCEVUnionPredicate &Preds;
+
   /// Holds the relationships between the members and the interleave group.
   DenseMap<Instruction *, InterleaveGroup *> InterleaveGroupMap;
 
   /// \brief The descriptor for a strided memory access.
   struct StrideDescriptor {
     StrideDescriptor(int Stride, const SCEV *Scev, unsigned Size,
                      unsigned Align)
         : Stride(Stride), Scev(Scev), Size(Size), Align(Align) {}

 /// induction variable and the different reduction variables.
 class LoopVectorizationLegality {
 public:
   LoopVectorizationLegality(Loop *L, ScalarEvolution *SE, DominatorTree *DT,
                             TargetLibraryInfo *TLI, AliasAnalysis *AA,
                             Function *F, const TargetTransformInfo *TTI,
                             LoopAccessAnalysis *LAA,
                             LoopVectorizationRequirements *R,
-                            const LoopVectorizeHints *H)
+                            const LoopVectorizeHints *H,
+                            SCEVUnionPredicate &Preds)
       : NumPredStores(0), TheLoop(L), SE(SE), TLI(TLI), TheFunction(F),
-        TTI(TTI), DT(DT), LAA(LAA), LAI(nullptr), InterleaveInfo(SE, L, DT),
-        Induction(nullptr), WidestIndTy(nullptr), HasFunNoNaNAttr(false),
-        Requirements(R), Hints(H) {}
+        TTI(TTI), DT(DT), LAA(LAA), LAI(nullptr),
+        InterleaveInfo(SE, L, DT, Preds), Induction(nullptr),
+        WidestIndTy(nullptr), HasFunNoNaNAttr(false), Requirements(R), Hints(H),
+        Preds(Preds) {}
 
   /// ReductionList contains the reduction descriptors for all
   /// of the reductions that were found in the loop.
   typedef DenseMap<PHINode *, RecurrenceDescriptor> ReductionList;
 
   /// InductionList saves induction variables and maps them to the
   /// induction descriptor.
   typedef MapVector<PHINode*, InductionDescriptor> InductionList;
private:
   /// Used to emit an analysis of any legality issues.
   const LoopVectorizeHints *Hints;
 
   ValueToValueMap Strides;
   SmallPtrSet<Value *, 8> StrideSet;
 
   /// While vectorizing these instructions we have to generate a
   /// call to the appropriate masked intrinsic
-  SmallPtrSet<const Instruction*, 8> MaskedOp;
+  SmallPtrSet<const Instruction *, 8> MaskedOp;
+
+  /// The SCEV predicate containing all the SCEV-related assumptions.
+  /// The predicate is used to simplify SCEV expressions in the
+  /// context of existing SCEV assumptions. The analysis will also
+  /// add a minimal set of new predicates if this is required to
+  /// enable vectorization/unrolling.
+  SCEVUnionPredicate &Preds;
 };
 
 /// LoopVectorizationCostModel - estimates the expected speedups due to
 /// vectorization.
 /// In many cases vectorization is not profitable. This can happen because of
 /// a number of reasons. In this class we mainly attempt to predict the
 /// expected speedup/slowdowns due to the supported instruction set. We use the
 /// TargetTransformInfo to query the different backends for the cost of
 /// different operations.
 class LoopVectorizationCostModel {
 public:
   LoopVectorizationCostModel(Loop *L, ScalarEvolution *SE, LoopInfo *LI,
                              LoopVectorizationLegality *Legal,
                              const TargetTransformInfo &TTI,
                              const TargetLibraryInfo *TLI, DemandedBits *DB,
-                             AssumptionCache *AC,
-                             const Function *F, const LoopVectorizeHints *Hints,
-                             SmallPtrSetImpl<const Value *> &ValuesToIgnore)
+                             AssumptionCache *AC, const Function *F,
+                             const LoopVectorizeHints *Hints,
+                             SmallPtrSetImpl<const Value *> &ValuesToIgnore,
+                             SCEVUnionPredicate &Preds)
       : TheLoop(L), SE(SE), LI(LI), Legal(Legal), TTI(TTI), TLI(TLI), DB(DB),
         TheFunction(F), Hints(Hints), ValuesToIgnore(ValuesToIgnore) {}
 
   /// Information about vectorization costs
   struct VectorizationFactor {
     unsigned Width; // Vector width with best cost
     unsigned Cost; // Cost of the loop with that width
   };
if (TC > 0u && TC < TinyTripCountVectorThreshold) {
         DEBUG(dbgs() << "\n");
         emitAnalysisDiag(F, L, Hints, VectorizationReport()
                                           << "vectorization is not beneficial "
                                              "and is not explicitly forced");
         return false;
       }
     }
 
+    SCEVUnionPredicate Preds;
+
     // Check if it is legal to vectorize the loop.
     LoopVectorizationRequirements Requirements;
     LoopVectorizationLegality LVL(L, SE, DT, TLI, AA, F, TTI, LAA,
-                                  &Requirements, &Hints);
+                                  &Requirements, &Hints, Preds);
     if (!LVL.canVectorize()) {
       DEBUG(dbgs() << "LV: Not vectorizing: Cannot prove legality.\n");
       emitMissedWarning(F, L, Hints);
       return false;
     }
 
     // Collect values we want to ignore in the cost model. This includes
     // type-promoting instructions we identified during reduction detection.
     SmallPtrSet<const Value *, 32> ValuesToIgnore;
     CodeMetrics::collectEphemeralValues(L, AC, ValuesToIgnore);
     for (auto &Reduction : *LVL.getReductionVars()) {
       RecurrenceDescriptor &RedDes = Reduction.second;
       SmallPtrSetImpl<Instruction *> &Casts = RedDes.getCastInsts();
       ValuesToIgnore.insert(Casts.begin(), Casts.end());
     }
 
     // Use the cost model.
     LoopVectorizationCostModel CM(L, SE, LI, &LVL, *TTI, TLI, DB, AC, F, &Hints,
-                                  ValuesToIgnore);
+                                  ValuesToIgnore, Preds);
 
     // Check the function attributes to find out if this function should be
     // optimized for size.
     bool OptForSize = Hints.getForce() != LoopVectorizeHints::FK_Enabled &&
                       F->optForSize();
 
     // Compute the weighted frequency of this loop being executed and see if it
     // is less than 20% of the function entry baseline frequency. Note that we
if (!VectorizeLoop && !InterleaveLoop) {
                    << DebugLocStr << '\n');
       DEBUG(dbgs() << "LV: Interleave Count is " << IC << '\n');
     }
 
     if (!VectorizeLoop) {
       assert(IC > 1 && "interleave count should not be 1 or 0");
       // If we decided that it is not legal to vectorize the loop then
       // interleave it.
-      InnerLoopUnroller Unroller(L, SE, LI, DT, TLI, TTI, IC);
+      InnerLoopUnroller Unroller(L, SE, LI, DT, TLI, TTI, IC, Preds);
       Unroller.vectorize(&LVL, CM.MinBWs);
 
       emitOptimizationRemark(F->getContext(), LV_NAME, *F, L->getStartLoc(),
                              Twine("interleaved loop (interleaved count: ") +
                                  Twine(IC) + ")");
     } else {
       // If we decided that it is *legal* to vectorize the loop then do it.
-      InnerLoopVectorizer LB(L, SE, LI, DT, TLI, TTI, VF.Width, IC);
+      InnerLoopVectorizer LB(L, SE, LI, DT, TLI, TTI, VF.Width, IC, Preds);
       LB.vectorize(&LVL, CM.MinBWs);
       ++LoopsVectorized;
 
       // Add metadata to disable runtime unrolling scalar loop when there's no
       // runtime check about strides and memory. Because at this situation,
       // scalar loop is rarely used not worthy to be unrolled.
       if (!LB.IsSafetyChecksAdded())
         AddRuntimeUnrollDisableMetaData(L);
else {
     // We are going to replace this stride by 1 so the cast is safe to ignore.
     //
     //  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
     //  %0 = trunc i64 %indvars.iv to i32
     //  %mul = mul i32 %0, %Stride1
     //  %idxprom = zext i32 %mul to i64  << Safe cast.
     //  %arrayidx = getelementptr inbounds i32* %B, i64 %idxprom
     //
-    Last = replaceSymbolicStrideSCEV(SE, Strides,
+    Last = replaceSymbolicStrideSCEV(SE, Strides, Preds,
                                      Gep->getOperand(InductionOperand), Gep);
     if (const SCEVCastExpr *C = dyn_cast<SCEVCastExpr>(Last))
       Last =
           (C->getSCEVType() == scSignExtend || C->getSCEVType() == scZeroExtend)
               ? C->getOperand()
               : Last;
   }
   if (const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(Last)) {
for (unsigned Width = 0; Width < VF; ++Width) {
       // End if-block.
       if (IfPredicateStore)
         PredicatedStores.push_back(std::make_pair(cast<StoreInst>(Cloned),
                                                   Cmp));
     }
   }
 }
 
-static Instruction *getFirstInst(Instruction *FirstInst, Value *V,
-                                 Instruction *Loc) {
-  if (FirstInst)
-    return FirstInst;
-  if (Instruction *I = dyn_cast<Instruction>(V))
-    return I->getParent() == Loc->getParent() ? I : nullptr;
-  return nullptr;
-}
-
-std::pair<Instruction *, Instruction *>
-InnerLoopVectorizer::addStrideCheck(Instruction *Loc) {
-  Instruction *tnullptr = nullptr;
-  if (!Legal->mustCheckStrides())
-    return std::pair<Instruction *, Instruction *>(tnullptr, tnullptr);
-
-  IRBuilder<> ChkBuilder(Loc);
-
-  // Emit checks.
-  Value *Check = nullptr;
-  Instruction *FirstInst = nullptr;
-  for (SmallPtrSet<Value *, 8>::iterator SI = Legal->strides_begin(),
-                                         SE = Legal->strides_end();
-       SI != SE; ++SI) {
-    Value *Ptr = stripIntegerCast(*SI);
-    Value *C = ChkBuilder.CreateICmpNE(Ptr, ConstantInt::get(Ptr->getType(), 1),
-                                       "stride.chk");
-    // Store the first instruction we create.
-    FirstInst = getFirstInst(FirstInst, C, Loc);
-    if (Check)
-      Check = ChkBuilder.CreateOr(Check, C);
-    else
-      Check = C;
-  }
-
-  // We have to do this trickery because the IRBuilder might fold the check to a
-  // constant expression in which case there is no Instruction anchored in a
-  // the block.
-  LLVMContext &Ctx = Loc->getContext();
-  Instruction *TheCheck =
-      BinaryOperator::CreateAnd(Check, ConstantInt::getTrue(Ctx));
-  ChkBuilder.Insert(TheCheck, "stride.not.one");
-  FirstInst = getFirstInst(FirstInst, TheCheck, Loc);
-
-  return std::make_pair(FirstInst, TheCheck);
-}
-
-PHINode *InnerLoopVectorizer::createInductionVariable(Loop *L,
-                                                      Value *Start,
-                                                      Value *End,
-                                                      Value *Step,
+PHINode *InnerLoopVectorizer::createInductionVariable(Loop *L, Value *Start,
+                                                      Value *End, Value *Step,
                                                       Instruction *DL) {
   BasicBlock *Header = L->getHeader();
   BasicBlock *Latch = L->getLoopLatch();
   // As we're just creating this loop, it's possible no latch exists
   // yet. If so, use the header as this will be a single block loop.
   if (!Latch)
     Latch = Header;
 
BasicBlock *NewBB = BB->splitBasicBlock(BB->getTerminator(),
                                           "vector.ph");
   if (L->getParentLoop())
     L->getParentLoop()->addBasicBlockToLoop(NewBB, *LI);
   ReplaceInstWithInst(BB->getTerminator(),
                       BranchInst::Create(Bypass, NewBB, Cmp));
   LoopBypassBlocks.push_back(BB);
 }
 
-void InnerLoopVectorizer::emitStrideChecks(Loop *L,
-                                           BasicBlock *Bypass) {
+void InnerLoopVectorizer::emitSCEVChecks(Loop *L, BasicBlock *Bypass) {
   BasicBlock *BB = L->getLoopPreheader();
-  
-  // Generate the code to check that the strides we assumed to be one are really
-  // one. We want the new basic block to start at the first instruction in a
+  // Generate the code to check that the SCEV assumptions that we made.
+  // We want the new basic block to start at the first instruction in a
   // sequence of instructions that form a check.
-  Instruction *StrideCheck;
-  Instruction *FirstCheckInst;
-  std::tie(FirstCheckInst, StrideCheck) = addStrideCheck(BB->getTerminator());
-  if (!StrideCheck)
+  SCEVExpander Exp(*SE, Bypass->getModule()->getDataLayout(), "scev.check");
+  Value *SCEVCheck = Exp.expandCodeForPredicate(&Preds, BB->getTerminator());
+
+  if (auto *C = dyn_cast<ConstantInt>(SCEVCheck))
+    if (C->isZero())
       return;
 
   // Create a new block containing the stride check.
-  BB->setName("vector.stridecheck");
+  BB->setName("vector.scevcheck");
   auto *NewBB = BB->splitBasicBlock(BB->getTerminator(), "vector.ph");
   if (L->getParentLoop())
     L->getParentLoop()->addBasicBlockToLoop(NewBB, *LI);
   ReplaceInstWithInst(BB->getTerminator(),
-                      BranchInst::Create(Bypass, NewBB, StrideCheck));
+                      BranchInst::Create(Bypass, NewBB, SCEVCheck));
   LoopBypassBlocks.push_back(BB);
   AddedSafetyChecks = true;
 }
 
 void InnerLoopVectorizer::emitMemRuntimeChecks(Loop *L,
                                                BasicBlock *Bypass) {
   BasicBlock *BB = L->getLoopPreheader();
 
void InnerLoopVectorizer::createEmptyLoop() {
   // We need to test whether the backedge-taken count is uint##_max. Adding one
   // to it will cause overflow and an incorrect loop trip count in the vector
   // body. In case of overflow we want to directly jump to the scalar remainder
   // loop.
   emitMinimumIterationCountCheck(Lp, ScalarPH);
   // Now, compare the new count to zero. If it is zero skip the vector loop and
   // jump to the scalar loop.
   emitVectorLoopEnteredCheck(Lp, ScalarPH);
-  // Generate the code to check that the strides we assumed to be one are really
-  // one. We want the new basic block to start at the first instruction in a
-  // sequence of instructions that form a check.
-  emitStrideChecks(Lp, ScalarPH);
+  // Generate the code to check any assumptions that we've made for SCEV
+  // expressions.
+  emitSCEVChecks(Lp, ScalarPH);
+
   // Generate the code that checks in runtime if arrays overlap. We put the
   // checks into a separate block to make the more common case of few elements
   // faster.
   emitMemRuntimeChecks(Lp, ScalarPH);
   
   // Generate the induction variable.
   // The loop step is equal to the vectorization factor (num of SIMD elements)
   // times the unroll factor (num of SIMD instructions).
bool LoopVectorizationLegality::canVectorize() {
   bool UseInterleaved = TTI->enableInterleavedAccessVectorization();
 
   // If an override option has been passed in for interleaved accesses, use it.
   if (EnableInterleavedMemAccesses.getNumOccurrences() > 0)
     UseInterleaved = EnableInterleavedMemAccesses;
 
   // Analyze interleaved memory accesses.
   if (UseInterleaved)
-     InterleaveInfo.analyzeInterleaving(Strides);
 
+  unsigned SCEVThreshold = VectorizeSCEVCheckThreshold;
+  if (Hints->getForce() == LoopVectorizeHints::FK_Enabled)
+    SCEVThreshold = PragmaVectorizeSCEVCheckThreshold;
+
+  if (Preds.getComplexity() > SCEVThreshold) {
+    emitAnalysis(VectorizationReport()
+                 << "Too many SCEV assumptions need to be made and checked "
+                 << "at runtime");
+    DEBUG(dbgs() << "LV: Too many SCEV checks needed.\n");
+    return false;
+  }
+
   // Okay! We can vectorize. At this point we don't have any other mem analysis
   // which may limit our maximum vectorization factor, so just return true with
   // no restrictions.
   return true;
 }
 
 static Type *convertPointerToIntegerType(const DataLayout &DL, Type *Ty) {
   if (Ty->isPointerTy())
if (LAI->hasStoreToLoopInvariantAddress()) {
     emitAnalysis(
         VectorizationReport()
         << "write to a loop invariant address could not be vectorized");
     DEBUG(dbgs() << "LV: We don't allow storing to uniform addresses\n");
     return false;
   }
 
   Requirements->addRuntimePointerChecks(LAI->getNumRuntimePointerChecks());
+  Preds.add(&LAI->Preds);
 
   return true;
 }
 
 bool LoopVectorizationLegality::isInductionVariable(const Value *V) {
   Value *In0 = const_cast<Value*>(V);
   PHINode *PN = dyn_cast_or_null<PHINode>(In0);
   if (!PN)
if (AccessList.empty())
     return;
 
   auto &DL = TheLoop->getHeader()->getModule()->getDataLayout();
   for (auto I : AccessList) {
     LoadInst *LI = dyn_cast<LoadInst>(I);
     StoreInst *SI = dyn_cast<StoreInst>(I);
 
     Value *Ptr = LI ? LI->getPointerOperand() : SI->getPointerOperand();
-    int Stride = isStridedPtr(SE, Ptr, TheLoop, Strides);
+    int Stride = isStridedPtr(SE, Ptr, TheLoop, Strides, Preds);
 
     // The factor of the corresponding interleave group.
     unsigned Factor = std::abs(Stride);
 
     // Ignore the access if the factor is too small or too large.
     if (Factor < 2 || Factor > MaxInterleaveGroupFactor)
       continue;
 
-    const SCEV *Scev = replaceSymbolicStrideSCEV(SE, Strides, Ptr);
+    const SCEV *Scev = replaceSymbolicStrideSCEV(SE, Strides, Preds, Ptr);
     PointerType *PtrTy = dyn_cast<PointerType>(Ptr->getType());
     unsigned Size = DL.getTypeAllocSize(PtrTy->getElementType());
 
     // An alignment of 0 means target ABI alignment.
     unsigned Align = LI ? LI->getAlignment() : SI->getAlignment();
     if (!Align)
       Align = DL.getABITypeAlignment(PtrTy->getElementType());