dependence analysis

Patch from Preston Briggs <preston.briggs@gmail.com>.

This is an updated version of the dependence-analysis patch, including an MIV
test based on Banerjee's inequalities.

It's a fairly complete implementation of the paper

    Practical Dependence Testing
    Gina Goff, Ken Kennedy, and Chau-Wen Tseng
    PLDI 1991

It cannot yet propagate constraints between coupled RDIV subscripts (discussed
in Section 5.3.2 of the paper).

It's organized as a FunctionPass with a single entry point that supports testing
for dependence between two instructions in a function. If there's no dependence,
it returns null. If there's a dependence, it returns a pointer to a Dependence
which can be queried about details (what kind of dependence, is it loop
independent, direction and distance vector entries, etc). I haven't included
every imaginable feature, but there's a good selection that should be adequate
for supporting many loop transformations. Of course, it can be extended as
necessary.

Included in the patch file are many test cases, commented with C code showing
the loops and array references.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165708 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/Analysis/DependenceAnalysis.h

@@ -0,0 +1,891 @@
+//===-- llvm/Analysis/DependenceAnalysis.h -------------------- -*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// DependenceAnalysis is an LLVM pass that analyses dependences between memory
+// accesses. Currently, it is an implementation of the approach described in
+//
+//            Practical Dependence Testing
+//            Goff, Kennedy, Tseng
+//            PLDI 1991
+//
+// There's a single entry point that analyzes the dependence between a pair
+// of memory references in a function, returning either NULL, for no dependence,
+// or a more-or-less detailed description of the dependence between them.
+//
+// Please note that this is work in progress and the interface is subject to
+// change.
+//
+// Plausible changes:
+//    Return a set of more precise dependences instead of just one dependence
+//    summarizing all.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_ANALYSIS_DEPENDENCEANALYSIS_H
+#define LLVM_ANALYSIS_DEPENDENCEANALYSIS_H
+
+#include "llvm/BasicBlock.h"
+#include "llvm/Function.h"
+#include "llvm/Instruction.h"
+#include "llvm/Pass.h"
+#include "llvm/ADT/SmallBitVector.h"
+#include "llvm/Analysis/ScalarEvolution.h"
+#include "llvm/Analysis/ScalarEvolutionExpressions.h"
+#include "llvm/Analysis/AliasAnalysis.h"
+#include "llvm/Analysis/LoopInfo.h"
+#include "llvm/Support/raw_ostream.h"
+
+
+namespace llvm {
+  class AliasAnalysis;
+  class ScalarEvolution;
+  class SCEV;
+  class Value;
+  class raw_ostream;
+
+  /// Dependence - This class represents a dependence between two memory
+  /// memory references in a function. It contains minimal information and
+  /// is used in the very common situation where the compiler is unable to
+  /// determine anything beyond the existence of a dependence; that is, it
+  /// represents a confused dependence (see also FullDependence). In most
+  /// cases (for output, flow, and anti dependences), the dependence implies
+  /// an ordering, where the source must preceed the destination; in contrast,
+  /// input dependences are unordered.
+  class Dependence {
+  public:
+    Dependence(const Instruction *Source,
+               const Instruction *Destination) :
+      Src(Source), Dst(Destination) {}
+    virtual ~Dependence() {}
+
+    /// Dependence::DVEntry - Each level in the distance/direction vector
+    /// has a direction (or perhaps a union of several directions), and
+    /// perhaps a distance.
+    struct DVEntry {
+      enum { NONE = 0,
+             LT = 1,
+             EQ = 2,
+             LE = 3,
+             GT = 4,
+             NE = 5,
+             GE = 6,
+             ALL = 7 };
+      unsigned char Direction : 3; // Init to ALL, then refine.
+      bool Scalar    : 1; // Init to true.
+      bool PeelFirst : 1; // Peeling the first iteration will break dependence.
+      bool PeelLast  : 1; // Peeling the last iteration will break the dependence.
+      bool Splitable : 1; // Splitting the loop will break dependence.
+      const SCEV *Distance; // NULL implies no distance available.
+      DVEntry() : Direction(ALL), Scalar(true), PeelFirst(false),
+                  PeelLast(false), Splitable(false), Distance(NULL) { }
+    };
+
+    /// getSrc - Returns the source instruction for this dependence.
+    ///
+    const Instruction *getSrc() const { return Src; }
+
+    /// getDst - Returns the destination instruction for this dependence.
+    ///
+    const Instruction *getDst() const { return Dst; }
+
+    /// isInput - Returns true if this is an input dependence.
+    ///
+    bool isInput() const;
+
+    /// isOutput - Returns true if this is an output dependence.
+    ///
+    bool isOutput() const;
+
+    /// isFlow - Returns true if this is a flow (aka true) dependence.
+    ///
+    bool isFlow() const;
+
+    /// isAnti - Returns true if this is an anti dependence.
+    ///
+    bool isAnti() const;
+
+    /// isOrdered - Returns true if dependence is Output, Flow, or Anti
+    ///
+    bool isOrdered() const { return isOutput() || isFlow() || isAnti(); }
+
+    /// isUnordered - Returns true if dependence is Input
+    ///
+    bool isUnordered() const { return isInput(); }
+
+    /// isLoopIndependent - Returns true if this is a loop-independent
+    /// dependence.
+    virtual bool isLoopIndependent() const { return true; }
+
+    /// isConfused - Returns true if this dependence is confused
+    /// (the compiler understands nothing and makes worst-case
+    /// assumptions).
+    virtual bool isConfused() const { return true; }
+
+    /// isConsistent - Returns true if this dependence is consistent
+    /// (occurs every time the source and destination are executed).
+    virtual bool isConsistent() const { return false; }
+
+    /// getLevels - Returns the number of common loops surrounding the
+    /// souce and destination of the dependence.
+    virtual unsigned getLevels() const { return 0; }
+
+    /// getDirection - Returns the direction associated with a particular
+    /// level.
+    virtual unsigned getDirection(unsigned Level) const { return DVEntry::ALL; }
+
+    /// getDistance - Returns the distance (or NULL) associated with a
+    /// particular level.
+    virtual const SCEV *getDistance(unsigned Level) const { return NULL; }
+
+    /// isPeelFirst - Returns true if peeling the first iteration from
+    /// this loop will break this dependence.
+    virtual bool isPeelFirst(unsigned Level) const { return false; }
+
+    /// isPeelLast - Returns true if peeling the last iteration from
+    /// this loop will break this dependence.
+    virtual bool isPeelLast(unsigned Level) const { return false; }
+
+    /// isSplitable - Returns true if splitting this loop will break
+    /// the dependence.
+    virtual bool isSplitable(unsigned Level) const { return false; }
+
+    /// isScalar - Returns true if a particular level is scalar; that is,
+    /// if no subscript in the source or destination mention the induction
+    /// variable associated with the loop at this level.
+    virtual bool isScalar(unsigned Level) const;
+
+    /// dump - For debugging purposes, dumps a dependence to OS.
+    ///
+    void dump(raw_ostream &OS) const;
+  private:
+    const Instruction *Src, *Dst;
+    friend class DependenceAnalysis;
+  };
+
+
+  /// FullDependence - This class represents a dependence between two memory
+  /// references in a function. It contains detailed information about the
+  /// dependence (direction vectors, etc) and is used when the compiler is
+  /// able to accurately analyze the interaction of the references; that is,
+  /// it is not a confused dependence (see Dependence). In most cases
+  /// (for output, flow, and anti dependences), the dependence implies an
+  /// ordering, where the source must preceed the destination; in contrast,
+  /// input dependences are unordered.
+  class FullDependence : public Dependence {
+  public:
+    FullDependence(const Instruction *Src,
+                   const Instruction *Dst,
+                   bool LoopIndependent,
+                   unsigned Levels);
+    ~FullDependence() {
+      delete DV;
+    }
+
+    /// isLoopIndependent - Returns true if this is a loop-independent
+    /// dependence.
+    bool isLoopIndependent() const { return LoopIndependent; }
+
+    /// isConfused - Returns true if this dependence is confused
+    /// (the compiler understands nothing and makes worst-case
+    /// assumptions).
+    bool isConfused() const { return false; }
+
+    /// isConsistent - Returns true if this dependence is consistent
+    /// (occurs every time the source and destination are executed).
+    bool isConsistent() const { return Consistent; }
+
+    /// getLevels - Returns the number of common loops surrounding the
+    /// souce and destination of the dependence.
+    unsigned getLevels() const { return Levels; }
+
+    /// getDirection - Returns the direction associated with a particular
+    /// level.
+    unsigned getDirection(unsigned Level) const;
+
+    /// getDistance - Returns the distance (or NULL) associated with a
+    /// particular level.
+    const SCEV *getDistance(unsigned Level) const;
+
+    /// isPeelFirst - Returns true if peeling the first iteration from
+    /// this loop will break this dependence.
+    bool isPeelFirst(unsigned Level) const;
+
+    /// isPeelLast - Returns true if peeling the last iteration from
+    /// this loop will break this dependence.
+    bool isPeelLast(unsigned Level) const;
+
+    /// isSplitable - Returns true if splitting the loop will break
+    /// the dependence.
+    bool isSplitable(unsigned Level) const;
+
+    /// isScalar - Returns true if a particular level is scalar; that is,
+    /// if no subscript in the source or destination mention the induction
+    /// variable associated with the loop at this level.
+    bool isScalar(unsigned Level) const;
+  private:
+    unsigned short Levels;
+    bool LoopIndependent;
+    bool Consistent; // Init to true, then refine.
+    DVEntry *DV;
+    friend class DependenceAnalysis;
+  };
+
+
+  /// DependenceAnalysis - This class is the main dependence-analysis driver.
+  ///
+  class DependenceAnalysis : public FunctionPass {
+    void operator=(const DependenceAnalysis &);     // do not implement
+    DependenceAnalysis(const DependenceAnalysis &); // do not implement
+  public:
+    /// depends - Tests for a dependence between the Src and Dst instructions.
+    /// Returns NULL if no dependence; otherwise, returns a Dependence (or a
+    /// FullDependence) with as much information as can be gleaned.
+    /// The flag PossiblyLoopIndependent should be set by the caller
+    /// if it appears that control flow can reach from Src to Dst
+    /// without traversing a loop back edge.
+    Dependence *depends(const Instruction *Src,
+                        const Instruction *Dst,
+                        bool PossiblyLoopIndependent);
+
+    /// getSplitIteration - Give a dependence that's splitable at some
+    /// particular level, return the iteration that should be used to split
+    /// the loop.
+    ///
+    /// Generally, the dependence analyzer will be used to build
+    /// a dependence graph for a function (basically a map from instructions
+    /// to dependences). Looking for cycles in the graph shows us loops
+    /// that cannot be trivially vectorized/parallelized.
+    ///
+    /// We can try to improve the situation by examining all the dependences
+    /// that make up the cycle, looking for ones we can break.
+    /// Sometimes, peeling the first or last iteration of a loop will break
+    /// dependences, and there are flags for those possibilities.
+    /// Sometimes, splitting a loop at some other iteration will do the trick,
+    /// and we've got a flag for that case. Rather than waste the space to
+    /// record the exact iteration (since we rarely know), we provide
+    /// a method that calculates the iteration. It's a drag that it must work
+    /// from scratch, but wonderful in that it's possible.
+    ///
+    /// Here's an example:
+    ///
+    ///    for (i = 0; i < 10; i++)
+    ///        A[i] = ...
+    ///        ... = A[11 - i]
+    ///
+    /// There's a loop-carried flow dependence from the store to the load,
+    /// found by the weak-crossing SIV test. The dependence will have a flag,
+    /// indicating that the dependence can be broken by splitting the loop.
+    /// Calling getSplitIteration will return 5.
+    /// Splitting the loop breaks the dependence, like so:
+    ///
+    ///    for (i = 0; i <= 5; i++)
+    ///        A[i] = ...
+    ///        ... = A[11 - i]
+    ///    for (i = 6; i < 10; i++)
+    ///        A[i] = ...
+    ///        ... = A[11 - i]
+    ///
+    /// breaks the dependence and allows us to vectorize/parallelize
+    /// both loops.
+    const SCEV *getSplitIteration(const Dependence *Dep, unsigned Level);
+
+  private:
+    AliasAnalysis *AA;
+    ScalarEvolution *SE;
+    LoopInfo *LI;
+    Function *F;
+
+    /// Subscript - This private struct represents a pair of subscripts from
+    /// a pair of potentially multi-dimensional array references. We use a
+    /// vector of them to guide subscript partitioning.
+    struct Subscript {
+      const SCEV *Src;
+      const SCEV *Dst;
+      enum ClassificationKind { ZIV, SIV, RDIV, MIV, NonLinear } Classification;
+      SmallBitVector Loops;
+      SmallBitVector GroupLoops;
+      SmallBitVector Group;
+    };
+
+    struct CoefficientInfo {
+      const SCEV *Coeff;
+      const SCEV *PosPart;
+      const SCEV *NegPart;
+      const SCEV *Iterations;
+    };
+
+    struct BoundInfo {
+      const SCEV *Iterations;
+      const SCEV *Upper[8];
+      const SCEV *Lower[8];
+      unsigned char Direction;
+      unsigned char DirSet;
+    };
+
+    /// Constraint - This private class represents a constraint, as defined
+    /// in the paper
+    ///
+    ///           Practical Dependence Testing
+    ///           Goff, Kennedy, Tseng
+    ///           PLDI 1991
+    ///
+    /// There are 5 kinds of constraint, in a hierarchy.
+    ///   1) Any - indicates no constraint, any dependence is possible.
+    ///   2) Line - A line ax + by = c, where a, b, and c are parameters,
+    ///             representing the dependence equation.
+    ///   3) Distance - The value d of the dependence distance;
+    ///   4) Point - A point <x, y> representing the dependence from
+    ///              iteration x to iteration y.
+    ///   5) Empty - No dependence is possible.
+    class Constraint {
+    private:
+      enum ConstraintKind { Empty, Point, Distance, Line, Any } Kind;
+      ScalarEvolution *SE;
+      const SCEV *A;
+      const SCEV *B;
+      const SCEV *C;
+      const Loop *AssociatedLoop;
+    public:
+      /// isEmpty - Return true if the constraint is of kind Empty.
+      bool isEmpty() const { return Kind == Empty; }
+
+      /// isPoint - Return true if the constraint is of kind Point.
+      bool isPoint() const { return Kind == Point; }
+
+      /// isDistance - Return true if the constraint is of kind Distance.
+      bool isDistance() const { return Kind == Distance; }
+
+      /// isLine - Return true if the constraint is of kind Line.
+      /// Since Distance's can also be represented as Lines, we also return
+      /// true if the constraint is of kind Distance.
+      bool isLine() const { return Kind == Line || Kind == Distance; }
+
+      /// isAny - Return true if the constraint is of kind Any;
+      bool isAny() const { return Kind == Any; }
+
+      /// getX - If constraint is a point <X, Y>, returns X.
+      /// Otherwise assert.
+      const SCEV *getX() const;
+
+      /// getY - If constraint is a point <X, Y>, returns Y.
+      /// Otherwise assert.
+      const SCEV *getY() const;
+
+      /// getA - If constraint is a line AX + BY = C, returns A.
+      /// Otherwise assert.
+      const SCEV *getA() const;
+
+      /// getB - If constraint is a line AX + BY = C, returns B.
+      /// Otherwise assert.
+      const SCEV *getB() const;
+
+      /// getC - If constraint is a line AX + BY = C, returns C.
+      /// Otherwise assert.
+      const SCEV *getC() const;
+
+      /// getD - If constraint is a distance, returns D.
+      /// Otherwise assert.
+      const SCEV *getD() const;
+
+      /// getAssociatedLoop - Returns the loop associated with this constraint.
+      const Loop *getAssociatedLoop() const;
+
+      /// setPoint - Change a constraint to Point.
+      void setPoint(const SCEV *X, const SCEV *Y, const Loop *CurrentLoop);
+
+      /// setLine - Change a constraint to Line.
+      void setLine(const SCEV *A, const SCEV *B,
+                   const SCEV *C, const Loop *CurrentLoop);
+
+      /// setDistance - Change a constraint to Distance.
+      void setDistance(const SCEV *D, const Loop *CurrentLoop);
+
+      /// setEmpty - Change a constraint to Empty.
+      void setEmpty();
+
+      /// setAny - Change a constraint to Any.
+      void setAny(ScalarEvolution *SE);
+
+      /// dump - For debugging purposes. Dumps the constraint
+      /// out to OS.
+      void dump(raw_ostream &OS) const;
+    };
+
+
+    /// establishNestingLevels - Examines the loop nesting of the Src and Dst
+    /// instructions and establishes their shared loops. Sets the variables
+    /// CommonLevels, SrcLevels, and MaxLevels.
+    /// The source and destination instructions needn't be contained in the same
+    /// loop. The routine establishNestingLevels finds the level of most deeply
+    /// nested loop that contains them both, CommonLevels. An instruction that's
+    /// not contained in a loop is at level = 0. MaxLevels is equal to the level
+    /// of the source plus the level of the destination, minus CommonLevels.
+    /// This lets us allocate vectors MaxLevels in length, with room for every
+    /// distinct loop referenced in both the source and destination subscripts.
+    /// The variable SrcLevels is the nesting depth of the source instruction.
+    /// It's used to help calculate distinct loops referenced by the destination.
+    /// Here's the map from loops to levels:
+    ///            0 - unused
+    ///            1 - outermost common loop
+    ///          ... - other common loops
+    /// CommonLevels - innermost common loop
+    ///          ... - loops containing Src but not Dst
+    ///    SrcLevels - innermost loop containing Src but not Dst
+    ///          ... - loops containing Dst but not Src
+    ///    MaxLevels - innermost loop containing Dst but not Src
+    /// Consider the follow code fragment:
+    ///    for (a = ...) {
+    ///      for (b = ...) {
+    ///        for (c = ...) {
+    ///          for (d = ...) {
+    ///            A[] = ...;
+    ///          }
+    ///        }
+    ///        for (e = ...) {
+    ///          for (f = ...) {
+    ///            for (g = ...) {
+    ///              ... = A[];
+    ///            }
+    ///          }
+    ///        }
+    ///      }
+    ///    }
+    /// If we're looking at the possibility of a dependence between the store
+    /// to A (the Src) and the load from A (the Dst), we'll note that they
+    /// have 2 loops in common, so CommonLevels will equal 2 and the direction
+    /// vector for Result will have 2 entries. SrcLevels = 4 and MaxLevels = 7.
+    /// A map from loop names to level indices would look like
+    ///     a - 1
+    ///     b - 2 = CommonLevels
+    ///     c - 3
+    ///     d - 4 = SrcLevels
+    ///     e - 5
+    ///     f - 6
+    ///     g - 7 = MaxLevels
+    void establishNestingLevels(const Instruction *Src,
+                                const Instruction *Dst);
+
+    unsigned CommonLevels, SrcLevels, MaxLevels;
+
+    /// mapSrcLoop - Given one of the loops containing the source, return
+    /// its level index in our numbering scheme.
+    unsigned mapSrcLoop(const Loop *SrcLoop) const;
+
+    /// mapDstLoop - Given one of the loops containing the destination,
+    /// return its level index in our numbering scheme.
+    unsigned mapDstLoop(const Loop *DstLoop) const;
+
+    /// isLoopInvariant - Returns true if Expression is loop invariant
+    /// in LoopNest.
+    bool isLoopInvariant(const SCEV *Expression, const Loop *LoopNest) const;
+
+    /// removeMatchingExtensions - Examines a subscript pair.
+    /// If the source and destination are identically sign (or zero)
+    /// extended, it strips off the extension in an effort to
+    /// simplify the actual analysis.
+    void removeMatchingExtensions(Subscript *Pair);
+
+    /// collectCommonLoops - Finds the set of loops from the LoopNest that
+    /// have a level <= CommonLevels and are referred to by the SCEV Expression.
+    void collectCommonLoops(const SCEV *Expression,
+                            const Loop *LoopNest,
+                            SmallBitVector &Loops) const;
+
+    /// checkSrcSubscript - Examines the SCEV Src, returning true iff it's
+    /// linear. Collect the set of loops mentioned by Src.
+    bool checkSrcSubscript(const SCEV *Src,
+                           const Loop *LoopNest,
+                           SmallBitVector &Loops);
+
+    /// checkDstSubscript - Examines the SCEV Dst, returning true iff it's
+    /// linear. Collect the set of loops mentioned by Dst.
+    bool checkDstSubscript(const SCEV *Dst,
+                           const Loop *LoopNest,
+                           SmallBitVector &Loops);
+
+    /// isKnownPredicate - Compare X and Y using the predicate Pred.
+    /// Basically a wrapper for SCEV::isKnownPredicate,
+    /// but tries harder, especially in the presense of sign and zero
+    /// extensions and symbolics.
+    bool isKnownPredicate(ICmpInst::Predicate Pred,
+                          const SCEV *X,
+                          const SCEV *Y) const;
+
+    /// collectUpperBound - All subscripts are the same type (on my machine,
+    /// an i64). The loop bound may be a smaller type. collectUpperBound
+    /// find the bound, if available, and zero extends it to the Type T.
+    /// (I zero extend since the bound should always be >= 0.)
+    /// If no upper bound is available, return NULL.
+    const SCEV *collectUpperBound(const Loop *l, Type *T) const;
+
+    /// collectConstantUpperBound - Calls collectUpperBound(), then
+    /// attempts to cast it to SCEVConstant. If the cast fails,
+    /// returns NULL.
+    const SCEVConstant *collectConstantUpperBound(const Loop *l, Type *T) const;
+
+    /// classifyPair - Examines the subscript pair (the Src and Dst SCEVs)
+    /// and classifies it as either ZIV, SIV, RDIV, MIV, or Nonlinear.
+    /// Collects the associated loops in a set.
+    Subscript::ClassificationKind classifyPair(const SCEV *Src,
+                                           const Loop *SrcLoopNest,
+                                           const SCEV *Dst,
+                                           const Loop *DstLoopNest,
+                                           SmallBitVector &Loops);
+
+    /// testZIV - Tests the ZIV subscript pair (Src and Dst) for dependence.
+    /// Returns true if any possible dependence is disproved.
+    /// If there might be a dependence, returns false.
+    /// If the dependence isn't proven to exist,
+    /// marks the Result as inconsistent.
+    bool testZIV(const SCEV *Src,
+                 const SCEV *Dst,
+                 FullDependence &Result) const;
+
+    /// testSIV - Tests the SIV subscript pair (Src and Dst) for dependence.
+    /// Things of the form [c1 + a1*i] and [c2 + a2*j], where
+    /// i and j are induction variables, c1 and c2 are loop invariant,
+    /// and a1 and a2 are constant.
+    /// Returns true if any possible dependence is disproved.
+    /// If there might be a dependence, returns false.
+    /// Sets appropriate direction vector entry and, when possible,
+    /// the distance vector entry.
+    /// If the dependence isn't proven to exist,
+    /// marks the Result as inconsistent.
+    bool testSIV(const SCEV *Src,
+                 const SCEV *Dst,
+                 unsigned &Level,
+                 FullDependence &Result,
+                 Constraint &NewConstraint,
+                 const SCEV *&SplitIter) const;
+
+    /// testRDIV - Tests the RDIV subscript pair (Src and Dst) for dependence.
+    /// Things of the form [c1 + a1*i] and [c2 + a2*j]
+    /// where i and j are induction variables, c1 and c2 are loop invariant,
+    /// and a1 and a2 are constant.
+    /// With minor algebra, this test can also be used for things like
+    /// [c1 + a1*i + a2*j][c2].
+    /// Returns true if any possible dependence is disproved.
+    /// If there might be a dependence, returns false.
+    /// Marks the Result as inconsistent.
+    bool testRDIV(const SCEV *Src,
+                  const SCEV *Dst,
+                  FullDependence &Result) const;
+
+    /// testMIV - Tests the MIV subscript pair (Src and Dst) for dependence.
+    /// Returns true if dependence disproved.
+    /// Can sometimes refine direction vectors.
+    bool testMIV(const SCEV *Src,
+                 const SCEV *Dst,
+                 const SmallBitVector &Loops,
+                 FullDependence &Result) const;
+
+    /// strongSIVtest - Tests the strong SIV subscript pair (Src and Dst)
+    /// for dependence.
+    /// Things of the form [c1 + a*i] and [c2 + a*i],
+    /// where i is an induction variable, c1 and c2 are loop invariant,
+    /// and a is a constant
+    /// Returns true if any possible dependence is disproved.
+    /// If there might be a dependence, returns false.
+    /// Sets appropriate direction and distance.
+    bool strongSIVtest(const SCEV *Coeff,
+                       const SCEV *SrcConst,
+                       const SCEV *DstConst,
+                       const Loop *CurrentLoop,
+                       unsigned Level,
+                       FullDependence &Result,
+                       Constraint &NewConstraint) const;
+
+    /// weakCrossingSIVtest - Tests the weak-crossing SIV subscript pair
+    /// (Src and Dst) for dependence.
+    /// Things of the form [c1 + a*i] and [c2 - a*i],
+    /// where i is an induction variable, c1 and c2 are loop invariant,
+    /// and a is a constant.
+    /// Returns true if any possible dependence is disproved.
+    /// If there might be a dependence, returns false.
+    /// Sets appropriate direction entry.
+    /// Set consistent to false.
+    /// Marks the dependence as splitable.
+    bool weakCrossingSIVtest(const SCEV *SrcCoeff,
+                             const SCEV *SrcConst,
+                             const SCEV *DstConst,
+                             const Loop *CurrentLoop,
+                             unsigned Level,
+                             FullDependence &Result,
+                             Constraint &NewConstraint,
+                             const SCEV *&SplitIter) const;
+
+    /// ExactSIVtest - Tests the SIV subscript pair
+    /// (Src and Dst) for dependence.
+    /// Things of the form [c1 + a1*i] and [c2 + a2*i],
+    /// where i is an induction variable, c1 and c2 are loop invariant,
+    /// and a1 and a2 are constant.
+    /// Returns true if any possible dependence is disproved.
+    /// If there might be a dependence, returns false.
+    /// Sets appropriate direction entry.
+    /// Set consistent to false.
+    bool exactSIVtest(const SCEV *SrcCoeff,
+                      const SCEV *DstCoeff,
+                      const SCEV *SrcConst,
+                      const SCEV *DstConst,
+                      const Loop *CurrentLoop,
+                      unsigned Level,
+                      FullDependence &Result,
+                      Constraint &NewConstraint) const;
+
+    /// weakZeroSrcSIVtest - Tests the weak-zero SIV subscript pair
+    /// (Src and Dst) for dependence.
+    /// Things of the form [c1] and [c2 + a*i],
+    /// where i is an induction variable, c1 and c2 are loop invariant,
+    /// and a is a constant. See also weakZeroDstSIVtest.
+    /// Returns true if any possible dependence is disproved.
+    /// If there might be a dependence, returns false.
+    /// Sets appropriate direction entry.
+    /// Set consistent to false.
+    /// If loop peeling will break the dependence, mark appropriately.
+    bool weakZeroSrcSIVtest(const SCEV *DstCoeff,
+                            const SCEV *SrcConst,
+                            const SCEV *DstConst,
+                            const Loop *CurrentLoop,
+                            unsigned Level,
+                            FullDependence &Result,
+                            Constraint &NewConstraint) const;
+
+    /// weakZeroDstSIVtest - Tests the weak-zero SIV subscript pair
+    /// (Src and Dst) for dependence.
+    /// Things of the form [c1 + a*i] and [c2],
+    /// where i is an induction variable, c1 and c2 are loop invariant,
+    /// and a is a constant. See also weakZeroSrcSIVtest.
+    /// Returns true if any possible dependence is disproved.
+    /// If there might be a dependence, returns false.
+    /// Sets appropriate direction entry.
+    /// Set consistent to false.
+    /// If loop peeling will break the dependence, mark appropriately.
+    bool weakZeroDstSIVtest(const SCEV *SrcCoeff,
+                            const SCEV *SrcConst,
+                            const SCEV *DstConst,
+                            const Loop *CurrentLoop,
+                            unsigned Level,
+                            FullDependence &Result,
+                            Constraint &NewConstraint) const;
+
+    /// exactRDIVtest - Tests the RDIV subscript pair for dependence.
+    /// Things of the form [c1 + a*i] and [c2 + b*j],
+    /// where i and j are induction variable, c1 and c2 are loop invariant,
+    /// and a and b are constants.
+    /// Returns true if any possible dependence is disproved.
+    /// Marks the result as inconsistant.
+    /// Works in some cases that symbolicRDIVtest doesn't,
+    /// and vice versa.
+    bool exactRDIVtest(const SCEV *SrcCoeff,
+                       const SCEV *DstCoeff,
+                       const SCEV *SrcConst,
+                       const SCEV *DstConst,
+                       const Loop *SrcLoop,
+                       const Loop *DstLoop,
+                       FullDependence &Result) const;
+
+    /// symbolicRDIVtest - Tests the RDIV subscript pair for dependence.
+    /// Things of the form [c1 + a*i] and [c2 + b*j],
+    /// where i and j are induction variable, c1 and c2 are loop invariant,
+    /// and a and b are constants.
+    /// Returns true if any possible dependence is disproved.
+    /// Marks the result as inconsistant.
+    /// Works in some cases that exactRDIVtest doesn't,
+    /// and vice versa. Can also be used as a backup for
+    /// ordinary SIV tests.
+    bool symbolicRDIVtest(const SCEV *SrcCoeff,
+                          const SCEV *DstCoeff,
+                          const SCEV *SrcConst,
+                          const SCEV *DstConst,
+                          const Loop *SrcLoop,
+                          const Loop *DstLoop) const;
+
+    /// gcdMIVtest - Tests an MIV subscript pair for dependence.
+    /// Returns true if any possible dependence is disproved.
+    /// Marks the result as inconsistant.
+    /// Can sometimes disprove the equal direction for 1 or more loops.
+    //  Can handle some symbolics that even the SIV tests don't get,
+    /// so we use it as a backup for everything.
+    bool gcdMIVtest(const SCEV *Src,
+                    const SCEV *Dst,
+                    FullDependence &Result) const;
+
+    /// banerjeeMIVtest - Tests an MIV subscript pair for dependence.
+    /// Returns true if any possible dependence is disproved.
+    /// Marks the result as inconsistant.
+    /// Computes directions.
+    bool banerjeeMIVtest(const SCEV *Src,
+                         const SCEV *Dst,
+                         const SmallBitVector &Loops,
+                         FullDependence &Result) const;
+
+    /// collectCoefficientInfo - Walks through the subscript,
+    /// collecting each coefficient, the associated loop bounds,
+    /// and recording its positive and negative parts for later use.
+    CoefficientInfo *collectCoeffInfo(const SCEV *Subscript,
+                                      bool SrcFlag,
+                                      const SCEV *&Constant) const;
+
+    /// getPositivePart - X^+ = max(X, 0).
+    ///
+    const SCEV *getPositivePart(const SCEV *X) const;
+
+    /// getNegativePart - X^- = min(X, 0).
+    ///
+    const SCEV *getNegativePart(const SCEV *X) const;
+
+    /// getLowerBound - Looks through all the bounds info and
+    /// computes the lower bound given the current direction settings
+    /// at each level.
+    const SCEV *getLowerBound(BoundInfo *Bound) const;
+
+    /// getUpperBound - Looks through all the bounds info and
+    /// computes the upper bound given the current direction settings
+    /// at each level.
+    const SCEV *getUpperBound(BoundInfo *Bound) const;
+
+    /// exploreDirections - Hierarchically expands the direction vector
+    /// search space, combining the directions of discovered dependences
+    /// in the DirSet field of Bound. Returns the number of distinct
+    /// dependences discovered. If the dependence is disproved,
+    /// it will return 0.
+    unsigned exploreDirections(unsigned Level,
+                               CoefficientInfo *A,
+                               CoefficientInfo *B,
+                               BoundInfo *Bound,
+                               const SmallBitVector &Loops,
+                               unsigned &DepthExpanded,
+                               const SCEV *Delta) const;
+
+    /// testBounds - Returns true iff the current bounds are plausible.
+    ///
+    bool testBounds(unsigned char DirKind,
+                    unsigned Level,
+                    BoundInfo *Bound,
+                    const SCEV *Delta) const;
+
+    /// findBoundsALL - Computes the upper and lower bounds for level K
+    /// using the * direction. Records them in Bound.
+    void findBoundsALL(CoefficientInfo *A,
+                       CoefficientInfo *B,
+                       BoundInfo *Bound,
+                       unsigned K) const;
+
+    /// findBoundsLT - Computes the upper and lower bounds for level K
+    /// using the < direction. Records them in Bound.
+    void findBoundsLT(CoefficientInfo *A,
+                      CoefficientInfo *B,
+                      BoundInfo *Bound,
+                      unsigned K) const;
+
+    /// findBoundsGT - Computes the upper and lower bounds for level K
+    /// using the > direction. Records them in Bound.
+    void findBoundsGT(CoefficientInfo *A,
+                      CoefficientInfo *B,
+                      BoundInfo *Bound,
+                      unsigned K) const;
+
+    /// findBoundsEQ - Computes the upper and lower bounds for level K
+    /// using the = direction. Records them in Bound.
+    void findBoundsEQ(CoefficientInfo *A,
+                      CoefficientInfo *B,
+                      BoundInfo *Bound,
+                      unsigned K) const;
+
+    /// intersectConstraints - Updates X with the intersection
+    /// of the Constraints X and Y. Returns true if X has changed.
+    bool intersectConstraints(Constraint *X,
+                              const Constraint *Y);
+
+    /// propagate - Review the constraints, looking for opportunities
+    /// to simplify a subscript pair (Src and Dst).
+    /// Return true if some simplification occurs.
+    /// If the simplification isn't exact (that is, if it is conservative
+    /// in terms of dependence), set consistent to false.
+    bool propagate(const SCEV *&Src,
+                   const SCEV *&Dst,
+                   SmallBitVector &Loops,
+                   SmallVector<Constraint, 4> &Constraints,
+                   bool &Consistent);
+
+    /// propagateDistance - Attempt to propagate a distance
+    /// constraint into a subscript pair (Src and Dst).
+    /// Return true if some simplification occurs.
+    /// If the simplification isn't exact (that is, if it is conservative
+    /// in terms of dependence), set consistent to false.
+    bool propagateDistance(const SCEV *&Src,
+                           const SCEV *&Dst,
+                           Constraint &CurConstraint,
+                           bool &Consistent);
+
+    /// propagatePoint - Attempt to propagate a point
+    /// constraint into a subscript pair (Src and Dst).
+    /// Return true if some simplification occurs.
+    bool propagatePoint(const SCEV *&Src,
+                        const SCEV *&Dst,
+                        Constraint &CurConstraint);
+
+    /// propagateLine - Attempt to propagate a line
+    /// constraint into a subscript pair (Src and Dst).
+    /// Return true if some simplification occurs.
+    /// If the simplification isn't exact (that is, if it is conservative
+    /// in terms of dependence), set consistent to false.
+    bool propagateLine(const SCEV *&Src,
+                       const SCEV *&Dst,
+                       Constraint &CurConstraint,
+                       bool &Consistent);
+
+    /// findCoefficient - Given a linear SCEV,
+    /// return the coefficient corresponding to specified loop.
+    /// If there isn't one, return the SCEV constant 0.
+    /// For example, given a*i + b*j + c*k, returning the coefficient
+    /// corresponding to the j loop would yield b.
+    const SCEV *findCoefficient(const SCEV *Expr,
+                                const Loop *TargetLoop) const;
+
+    /// zeroCoefficient - Given a linear SCEV,
+    /// return the SCEV given by zeroing out the coefficient
+    /// corresponding to the specified loop.
+    /// For example, given a*i + b*j + c*k, zeroing the coefficient
+    /// corresponding to the j loop would yield a*i + c*k.
+    const SCEV *zeroCoefficient(const SCEV *Expr,
+                                const Loop *TargetLoop) const;
+
+    /// addToCoefficient - Given a linear SCEV Expr,
+    /// return the SCEV given by adding some Value to the
+    /// coefficient corresponding to the specified TargetLoop.
+    /// For example, given a*i + b*j + c*k, adding 1 to the coefficient
+    /// corresponding to the j loop would yield a*i + (b+1)*j + c*k.
+    const SCEV *addToCoefficient(const SCEV *Expr,
+                                 const Loop *TargetLoop,
+                                 const SCEV *Value)  const;
+
+    /// updateDirection - Update direction vector entry
+    /// based on the current constraint.
+    void updateDirection(Dependence::DVEntry &Level,
+                         const Constraint &CurConstraint) const;
+  public:
+    static char ID; // Class identification, replacement for typeinfo
+    DependenceAnalysis() : FunctionPass(ID) {
+      initializeDependenceAnalysisPass(*PassRegistry::getPassRegistry());
+    };
+
+    bool runOnFunction(Function &F);
+    void releaseMemory();
+    void getAnalysisUsage(AnalysisUsage &) const;
+    void print(raw_ostream &, const Module * = 0) const;
+  }; // class DependenceAnalysis
+
+  /// createDependenceAnalysisPass - This creates an instance of the
+  /// DependenceAnalysis pass.
+  FunctionPass *createDependenceAnalysisPass();
+
+} // namespace llvm
+
+#endif

include/llvm/Analysis/Passes.h

@@ -178,6 +178,13 @@ namespace llvm {
   /// pass.
   FunctionPass *createLazyValueInfoPass();
 
+  //===--------------------------------------------------------------------===//
+  //
+  // createLoopDependenceAnalysisPass - This creates an instance of the
+  // LoopDependenceAnalysis pass.
+  //
+  LoopPass *createDependenceAnalysisPass();
+
   //===--------------------------------------------------------------------===//
   //
   // createLoopDependenceAnalysisPass - This creates an instance of the
@@ -185,6 +192,8 @@ namespace llvm {
   //
   LoopPass *createLoopDependenceAnalysisPass();
 
+  //===--------------------------------------------------------------------===//
+  //
   // Minor pass prototypes, allowing us to expose them through bugpoint and
   // analyze.
   FunctionPass *createInstCountPass();

include/llvm/InitializePasses.h

@@ -94,6 +94,7 @@ void initializeDCEPass(PassRegistry&);
 void initializeDSEPass(PassRegistry&);
 void initializeDeadInstEliminationPass(PassRegistry&);
 void initializeDeadMachineInstructionElimPass(PassRegistry&);
+void initializeDependenceAnalysisPass(PassRegistry&);
 void initializeDomOnlyPrinterPass(PassRegistry&);
 void initializeDomOnlyViewerPass(PassRegistry&);
 void initializeDomPrinterPass(PassRegistry&);

include/llvm/LinkAllPasses.h

@@ -64,6 +64,7 @@ namespace {
       (void) llvm::createDeadCodeEliminationPass();
       (void) llvm::createDeadInstEliminationPass();
       (void) llvm::createDeadStoreEliminationPass();
+      (void) llvm::createDependenceAnalysisPass();
       (void) llvm::createDomOnlyPrinterPass();
       (void) llvm::createDomPrinterPass();
       (void) llvm::createDomOnlyViewerPass();

lib/Analysis/Analysis.cpp

@@ -31,6 +31,7 @@ void llvm::initializeAnalysis(PassRegistry &Registry) {
   initializeCFGOnlyViewerPass(Registry);
   initializeCFGOnlyPrinterPass(Registry);
   initializePrintDbgInfoPass(Registry);
+  initializeDependenceAnalysisPass(Registry);
   initializeDominanceFrontierPass(Registry);
   initializeDomViewerPass(Registry);
   initializeDomPrinterPass(Registry);

lib/Analysis/CMakeLists.txt

@@ -13,6 +13,7 @@ add_llvm_library(LLVMAnalysis
   CodeMetrics.cpp
   ConstantFolding.cpp
   DbgInfoPrinter.cpp
+  DependenceAnalysis.cpp
   DomPrinter.cpp
   DominanceFrontier.cpp
   IVUsers.cpp

test/Analysis/DependenceAnalysis/Banerjee.ll

@@ -0,0 +1,595 @@
+; RUN: opt < %s -analyze -basicaa -da | FileCheck %s
+
+; ModuleID = 'Banerjee.bc'
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.6.0"
+
+
+;;  for (long int i = 1; i <= 10; i++)
+;;    for (long int j = 1; j <= 10; j++) {
+;;      A[10*i + j] = ...
+;;      ... = A[10*i + j - 1];
+
+define void @banerjee0(i64* %A, i64* %B, i64 %m, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %entry, %for.inc7
+  %B.addr.04 = phi i64* [ %B, %entry ], [ %scevgep, %for.inc7 ]
+  %i.03 = phi i64 [ 1, %entry ], [ %inc8, %for.inc7 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.cond1.preheader, %for.body3
+  %j.02 = phi i64 [ 1, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i64* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %mul = mul nsw i64 %i.03, 10
+  %add = add nsw i64 %mul, %j.02
+  %arrayidx = getelementptr inbounds i64* %A, i64 %add
+  store i64 0, i64* %arrayidx, align 8
+  %mul4 = mul nsw i64 %i.03, 10
+  %add5 = add nsw i64 %mul4, %j.02
+  %sub = add nsw i64 %add5, -1
+  %arrayidx6 = getelementptr inbounds i64* %A, i64 %sub
+  %0 = load i64* %arrayidx6, align 8
+; CHECK: da analyze - flow [<= <>]!
+  %incdec.ptr = getelementptr inbounds i64* %B.addr.11, i64 1
+  store i64 %0, i64* %B.addr.11, align 8
+  %inc = add nsw i64 %j.02, 1
+  %exitcond = icmp ne i64 %inc, 11
+  br i1 %exitcond, label %for.body3, label %for.inc7
+
+for.inc7:                                         ; preds = %for.body3
+  %scevgep = getelementptr i64* %B.addr.04, i64 10
+  %inc8 = add nsw i64 %i.03, 1
+  %exitcond5 = icmp ne i64 %inc8, 11
+  br i1 %exitcond5, label %for.cond1.preheader, label %for.end9
+
+for.end9:                                         ; preds = %for.inc7
+  ret void
+}
+
+
+;;  for (long int i = 1; i <= n; i++)
+;;    for (long int j = 1; j <= m; j++) {
+;;      A[10*i + j] = ...
+;;      ... = A[10*i + j - 1];
+
+define void @banerjee1(i64* %A, i64* %B, i64 %m, i64 %n) nounwind uwtable ssp {
+entry:
+  %cmp4 = icmp sgt i64 %n, 0
+  br i1 %cmp4, label %for.cond1.preheader.preheader, label %for.end9
+
+for.cond1.preheader.preheader:                    ; preds = %entry
+  %0 = add i64 %n, 1
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %for.cond1.preheader.preheader, %for.inc7
+  %B.addr.06 = phi i64* [ %B.addr.1.lcssa, %for.inc7 ], [ %B, %for.cond1.preheader.preheader ]
+  %i.05 = phi i64 [ %inc8, %for.inc7 ], [ 1, %for.cond1.preheader.preheader ]
+  %1 = add i64 %m, 1
+  %cmp21 = icmp sgt i64 %m, 0
+  br i1 %cmp21, label %for.body3.preheader, label %for.inc7
+
+for.body3.preheader:                              ; preds = %for.cond1.preheader
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.body3.preheader, %for.body3
+  %j.03 = phi i64 [ %inc, %for.body3 ], [ 1, %for.body3.preheader ]
+  %B.addr.12 = phi i64* [ %incdec.ptr, %for.body3 ], [ %B.addr.06, %for.body3.preheader ]
+  %mul = mul nsw i64 %i.05, 10
+  %add = add nsw i64 %mul, %j.03
+  %arrayidx = getelementptr inbounds i64* %A, i64 %add
+  store i64 0, i64* %arrayidx, align 8
+  %mul4 = mul nsw i64 %i.05, 10
+  %add5 = add nsw i64 %mul4, %j.03
+  %sub = add nsw i64 %add5, -1
+  %arrayidx6 = getelementptr inbounds i64* %A, i64 %sub
+  %2 = load i64* %arrayidx6, align 8
+; CHECK: da analyze - flow [* <>]!
+  %incdec.ptr = getelementptr inbounds i64* %B.addr.12, i64 1
+  store i64 %2, i64* %B.addr.12, align 8
+  %inc = add nsw i64 %j.03, 1
+  %exitcond = icmp eq i64 %inc, %1
+  br i1 %exitcond, label %for.inc7.loopexit, label %for.body3
+
+for.inc7.loopexit:                                ; preds = %for.body3
+  %scevgep = getelementptr i64* %B.addr.06, i64 %m
+  br label %for.inc7
+
+for.inc7:                                         ; preds = %for.inc7.loopexit, %for.cond1.preheader
+  %B.addr.1.lcssa = phi i64* [ %B.addr.06, %for.cond1.preheader ], [ %scevgep, %for.inc7.loopexit ]
+  %inc8 = add nsw i64 %i.05, 1
+  %exitcond7 = icmp eq i64 %inc8, %0
+  br i1 %exitcond7, label %for.end9.loopexit, label %for.cond1.preheader
+
+for.end9.loopexit:                                ; preds = %for.inc7
+  br label %for.end9
+
+for.end9:                                         ; preds = %for.end9.loopexit, %entry
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 10; i++)
+;;    for (long int j = 0; j < 10; j++) {
+;;      A[10*i + j] = 0;
+;;      *B++ = A[10*i + j + 100];
+
+define void @banerjee2(i64* %A, i64* %B, i64 %m, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %entry, %for.inc8
+  %B.addr.04 = phi i64* [ %B, %entry ], [ %scevgep, %for.inc8 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc9, %for.inc8 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.cond1.preheader, %for.body3
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i64* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %mul = mul nsw i64 %i.03, 10
+  %add = add nsw i64 %mul, %j.02
+  %arrayidx = getelementptr inbounds i64* %A, i64 %add
+  store i64 0, i64* %arrayidx, align 8
+  %mul4 = mul nsw i64 %i.03, 10
+  %add5 = add nsw i64 %mul4, %j.02
+  %add6 = add nsw i64 %add5, 100
+  %arrayidx7 = getelementptr inbounds i64* %A, i64 %add6
+  %0 = load i64* %arrayidx7, align 8
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i64* %B.addr.11, i64 1
+  store i64 %0, i64* %B.addr.11, align 8
+  %inc = add nsw i64 %j.02, 1
+  %exitcond = icmp ne i64 %inc, 10
+  br i1 %exitcond, label %for.body3, label %for.inc8
+
+for.inc8:                                         ; preds = %for.body3
+  %scevgep = getelementptr i64* %B.addr.04, i64 10
+  %inc9 = add nsw i64 %i.03, 1
+  %exitcond5 = icmp ne i64 %inc9, 10
+  br i1 %exitcond5, label %for.cond1.preheader, label %for.end10
+
+for.end10:                                        ; preds = %for.inc8
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 10; i++)
+;;    for (long int j = 0; j < 10; j++) {
+;;      A[10*i + j] = ...
+;;      ... = A[10*i + j + 99];
+
+define void @banerjee3(i64* %A, i64* %B, i64 %m, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %entry, %for.inc8
+  %B.addr.04 = phi i64* [ %B, %entry ], [ %scevgep, %for.inc8 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc9, %for.inc8 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.cond1.preheader, %for.body3
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i64* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %mul = mul nsw i64 %i.03, 10
+  %add = add nsw i64 %mul, %j.02
+  %arrayidx = getelementptr inbounds i64* %A, i64 %add
+  store i64 0, i64* %arrayidx, align 8
+  %mul4 = mul nsw i64 %i.03, 10
+  %add5 = add nsw i64 %mul4, %j.02
+  %add6 = add nsw i64 %add5, 99
+  %arrayidx7 = getelementptr inbounds i64* %A, i64 %add6
+  %0 = load i64* %arrayidx7, align 8
+; CHECK: da analyze - flow [> >]!
+  %incdec.ptr = getelementptr inbounds i64* %B.addr.11, i64 1
+  store i64 %0, i64* %B.addr.11, align 8
+  %inc = add nsw i64 %j.02, 1
+  %exitcond = icmp ne i64 %inc, 10
+  br i1 %exitcond, label %for.body3, label %for.inc8
+
+for.inc8:                                         ; preds = %for.body3
+  %scevgep = getelementptr i64* %B.addr.04, i64 10
+  %inc9 = add nsw i64 %i.03, 1
+  %exitcond5 = icmp ne i64 %inc9, 10
+  br i1 %exitcond5, label %for.cond1.preheader, label %for.end10
+
+for.end10:                                        ; preds = %for.inc8
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 10; i++)
+;;    for (long int j = 0; j < 10; j++) {
+;;      A[10*i + j] = ...
+;;      ... = A[10*i + j - 100];
+
+define void @banerjee4(i64* %A, i64* %B, i64 %m, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %entry, %for.inc7
+  %B.addr.04 = phi i64* [ %B, %entry ], [ %scevgep, %for.inc7 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc8, %for.inc7 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.cond1.preheader, %for.body3
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i64* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %mul = mul nsw i64 %i.03, 10
+  %add = add nsw i64 %mul, %j.02
+  %arrayidx = getelementptr inbounds i64* %A, i64 %add
+  store i64 0, i64* %arrayidx, align 8
+  %mul4 = mul nsw i64 %i.03, 10
+  %add5 = add nsw i64 %mul4, %j.02
+  %sub = add nsw i64 %add5, -100
+  %arrayidx6 = getelementptr inbounds i64* %A, i64 %sub
+  %0 = load i64* %arrayidx6, align 8
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i64* %B.addr.11, i64 1
+  store i64 %0, i64* %B.addr.11, align 8
+  %inc = add nsw i64 %j.02, 1
+  %exitcond = icmp ne i64 %inc, 10
+  br i1 %exitcond, label %for.body3, label %for.inc7
+
+for.inc7:                                         ; preds = %for.body3
+  %scevgep = getelementptr i64* %B.addr.04, i64 10
+  %inc8 = add nsw i64 %i.03, 1
+  %exitcond5 = icmp ne i64 %inc8, 10
+  br i1 %exitcond5, label %for.cond1.preheader, label %for.end9
+
+for.end9:                                         ; preds = %for.inc7
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 10; i++)
+;;    for (long int j = 0; j < 10; j++) {
+;;      A[10*i + j] = ...
+;;      ... = A[10*i + j - 99];
+
+define void @banerjee5(i64* %A, i64* %B, i64 %m, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %entry, %for.inc7
+  %B.addr.04 = phi i64* [ %B, %entry ], [ %scevgep, %for.inc7 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc8, %for.inc7 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.cond1.preheader, %for.body3
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i64* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %mul = mul nsw i64 %i.03, 10
+  %add = add nsw i64 %mul, %j.02
+  %arrayidx = getelementptr inbounds i64* %A, i64 %add
+  store i64 0, i64* %arrayidx, align 8
+  %mul4 = mul nsw i64 %i.03, 10
+  %add5 = add nsw i64 %mul4, %j.02
+  %sub = add nsw i64 %add5, -99
+  %arrayidx6 = getelementptr inbounds i64* %A, i64 %sub
+  %0 = load i64* %arrayidx6, align 8
+; CHECK: da analyze - flow [< <]!
+  %incdec.ptr = getelementptr inbounds i64* %B.addr.11, i64 1
+  store i64 %0, i64* %B.addr.11, align 8
+  %inc = add nsw i64 %j.02, 1
+  %exitcond = icmp ne i64 %inc, 10
+  br i1 %exitcond, label %for.body3, label %for.inc7
+
+for.inc7:                                         ; preds = %for.body3
+  %scevgep = getelementptr i64* %B.addr.04, i64 10
+  %inc8 = add nsw i64 %i.03, 1
+  %exitcond5 = icmp ne i64 %inc8, 10
+  br i1 %exitcond5, label %for.cond1.preheader, label %for.end9
+
+for.end9:                                         ; preds = %for.inc7
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 10; i++)
+;;    for (long int j = 0; j < 10; j++) {
+;;      A[10*i + j] = ...
+;;      ... = A[10*i + j + 9];
+
+define void @banerjee6(i64* %A, i64* %B, i64 %m, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %entry, %for.inc8
+  %B.addr.04 = phi i64* [ %B, %entry ], [ %scevgep, %for.inc8 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc9, %for.inc8 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.cond1.preheader, %for.body3
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i64* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %mul = mul nsw i64 %i.03, 10
+  %add = add nsw i64 %mul, %j.02
+  %arrayidx = getelementptr inbounds i64* %A, i64 %add
+  store i64 0, i64* %arrayidx, align 8
+  %mul4 = mul nsw i64 %i.03, 10
+  %add5 = add nsw i64 %mul4, %j.02
+  %add6 = add nsw i64 %add5, 9
+  %arrayidx7 = getelementptr inbounds i64* %A, i64 %add6
+  %0 = load i64* %arrayidx7, align 8
+; CHECK: da analyze - flow [=> <>]!
+  %incdec.ptr = getelementptr inbounds i64* %B.addr.11, i64 1
+  store i64 %0, i64* %B.addr.11, align 8
+  %inc = add nsw i64 %j.02, 1
+  %exitcond = icmp ne i64 %inc, 10
+  br i1 %exitcond, label %for.body3, label %for.inc8
+
+for.inc8:                                         ; preds = %for.body3
+  %scevgep = getelementptr i64* %B.addr.04, i64 10
+  %inc9 = add nsw i64 %i.03, 1
+  %exitcond5 = icmp ne i64 %inc9, 10
+  br i1 %exitcond5, label %for.cond1.preheader, label %for.end10
+
+for.end10:                                        ; preds = %for.inc8
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 10; i++)
+;;    for (long int j = 0; j < 10; j++) {
+;;      A[10*i + j] = ...
+;;      ... = A[10*i + j + 10];
+
+define void @banerjee7(i64* %A, i64* %B, i64 %m, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %entry, %for.inc8
+  %B.addr.04 = phi i64* [ %B, %entry ], [ %scevgep, %for.inc8 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc9, %for.inc8 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.cond1.preheader, %for.body3
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i64* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %mul = mul nsw i64 %i.03, 10
+  %add = add nsw i64 %mul, %j.02
+  %arrayidx = getelementptr inbounds i64* %A, i64 %add
+  store i64 0, i64* %arrayidx, align 8
+  %mul4 = mul nsw i64 %i.03, 10
+  %add5 = add nsw i64 %mul4, %j.02
+  %add6 = add nsw i64 %add5, 10
+  %arrayidx7 = getelementptr inbounds i64* %A, i64 %add6
+  %0 = load i64* %arrayidx7, align 8
+; CHECK: da analyze - flow [> <=]!
+  %incdec.ptr = getelementptr inbounds i64* %B.addr.11, i64 1
+  store i64 %0, i64* %B.addr.11, align 8
+  %inc = add nsw i64 %j.02, 1
+  %exitcond = icmp ne i64 %inc, 10
+  br i1 %exitcond, label %for.body3, label %for.inc8
+
+for.inc8:                                         ; preds = %for.body3
+  %scevgep = getelementptr i64* %B.addr.04, i64 10
+  %inc9 = add nsw i64 %i.03, 1
+  %exitcond5 = icmp ne i64 %inc9, 10
+  br i1 %exitcond5, label %for.cond1.preheader, label %for.end10
+
+for.end10:                                        ; preds = %for.inc8
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 10; i++)
+;;    for (long int j = 0; j < 10; j++) {
+;;      A[10*i + j] = ...
+;;      ... = A[10*i + j + 11];
+
+define void @banerjee8(i64* %A, i64* %B, i64 %m, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %entry, %for.inc8
+  %B.addr.04 = phi i64* [ %B, %entry ], [ %scevgep, %for.inc8 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc9, %for.inc8 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.cond1.preheader, %for.body3
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i64* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %mul = mul nsw i64 %i.03, 10
+  %add = add nsw i64 %mul, %j.02
+  %arrayidx = getelementptr inbounds i64* %A, i64 %add
+  store i64 0, i64* %arrayidx, align 8
+  %mul4 = mul nsw i64 %i.03, 10
+  %add5 = add nsw i64 %mul4, %j.02
+  %add6 = add nsw i64 %add5, 11
+  %arrayidx7 = getelementptr inbounds i64* %A, i64 %add6
+  %0 = load i64* %arrayidx7, align 8
+; CHECK: da analyze - flow [> <>]!
+  %incdec.ptr = getelementptr inbounds i64* %B.addr.11, i64 1
+  store i64 %0, i64* %B.addr.11, align 8
+  %inc = add nsw i64 %j.02, 1
+  %exitcond = icmp ne i64 %inc, 10
+  br i1 %exitcond, label %for.body3, label %for.inc8
+
+for.inc8:                                         ; preds = %for.body3
+  %scevgep = getelementptr i64* %B.addr.04, i64 10
+  %inc9 = add nsw i64 %i.03, 1
+  %exitcond5 = icmp ne i64 %inc9, 10
+  br i1 %exitcond5, label %for.cond1.preheader, label %for.end10
+
+for.end10:                                        ; preds = %for.inc8
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 20; i++)
+;;    for (long int j = 0; j < 20; j++) {
+;;      A[30*i + 500*j] = ...
+;;      ... = A[i - 500*j + 11];
+
+define void @banerjee9(i64* %A, i64* %B, i64 %m, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %entry, %for.inc8
+  %B.addr.04 = phi i64* [ %B, %entry ], [ %scevgep, %for.inc8 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc9, %for.inc8 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.cond1.preheader, %for.body3
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i64* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %mul = mul nsw i64 %i.03, 30
+  %mul4 = mul nsw i64 %j.02, 500
+  %add = add nsw i64 %mul, %mul4
+  %arrayidx = getelementptr inbounds i64* %A, i64 %add
+  store i64 0, i64* %arrayidx, align 8
+  %0 = mul i64 %j.02, -500
+  %sub = add i64 %i.03, %0
+  %add6 = add nsw i64 %sub, 11
+  %arrayidx7 = getelementptr inbounds i64* %A, i64 %add6
+  %1 = load i64* %arrayidx7, align 8
+; CHECK: da analyze - flow [<= =|<]!
+  %incdec.ptr = getelementptr inbounds i64* %B.addr.11, i64 1
+  store i64 %1, i64* %B.addr.11, align 8
+  %inc = add nsw i64 %j.02, 1
+  %exitcond = icmp ne i64 %inc, 20
+  br i1 %exitcond, label %for.body3, label %for.inc8
+
+for.inc8:                                         ; preds = %for.body3
+  %scevgep = getelementptr i64* %B.addr.04, i64 20
+  %inc9 = add nsw i64 %i.03, 1
+  %exitcond5 = icmp ne i64 %inc9, 20
+  br i1 %exitcond5, label %for.cond1.preheader, label %for.end10
+
+for.end10:                                        ; preds = %for.inc8
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 20; i++)
+;;    for (long int j = 0; j < 20; j++) {
+;;      A[i + 500*j] = ...
+;;      ... = A[i - 500*j + 11];
+
+define void @banerjee10(i64* %A, i64* %B, i64 %m, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %entry, %for.inc7
+  %B.addr.04 = phi i64* [ %B, %entry ], [ %scevgep, %for.inc7 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc8, %for.inc7 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.cond1.preheader, %for.body3
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i64* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %mul = mul nsw i64 %j.02, 500
+  %add = add nsw i64 %i.03, %mul
+  %arrayidx = getelementptr inbounds i64* %A, i64 %add
+  store i64 0, i64* %arrayidx, align 8
+  %0 = mul i64 %j.02, -500
+  %sub = add i64 %i.03, %0
+  %add5 = add nsw i64 %sub, 11
+  %arrayidx6 = getelementptr inbounds i64* %A, i64 %add5
+  %1 = load i64* %arrayidx6, align 8
+; CHECK: da analyze - flow [<> =]!
+  %incdec.ptr = getelementptr inbounds i64* %B.addr.11, i64 1
+  store i64 %1, i64* %B.addr.11, align 8
+  %inc = add nsw i64 %j.02, 1
+  %exitcond = icmp ne i64 %inc, 20
+  br i1 %exitcond, label %for.body3, label %for.inc7
+
+for.inc7:                                         ; preds = %for.body3
+  %scevgep = getelementptr i64* %B.addr.04, i64 20
+  %inc8 = add nsw i64 %i.03, 1
+  %exitcond5 = icmp ne i64 %inc8, 20
+  br i1 %exitcond5, label %for.cond1.preheader, label %for.end9
+
+for.end9:                                         ; preds = %for.inc7
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 20; i++)
+;;    for (long int j = 0; j < 20; j++) {
+;;      A[300*i + j] = ...
+;;      ... = A[250*i - j + 11];
+
+define void @banerjee11(i64* %A, i64* %B, i64 %m, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %entry, %for.inc7
+  %B.addr.04 = phi i64* [ %B, %entry ], [ %scevgep, %for.inc7 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc8, %for.inc7 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.cond1.preheader, %for.body3
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i64* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %mul = mul nsw i64 %i.03, 300
+  %add = add nsw i64 %mul, %j.02
+  %arrayidx = getelementptr inbounds i64* %A, i64 %add
+  store i64 0, i64* %arrayidx, align 8
+  %mul4 = mul nsw i64 %i.03, 250
+  %sub = sub nsw i64 %mul4, %j.02
+  %add5 = add nsw i64 %sub, 11
+  %arrayidx6 = getelementptr inbounds i64* %A, i64 %add5
+  %0 = load i64* %arrayidx6, align 8
+; CHECK: da analyze - flow [<= <>]!
+  %incdec.ptr = getelementptr inbounds i64* %B.addr.11, i64 1
+  store i64 %0, i64* %B.addr.11, align 8
+  %inc = add nsw i64 %j.02, 1
+  %exitcond = icmp ne i64 %inc, 20
+  br i1 %exitcond, label %for.body3, label %for.inc7
+
+for.inc7:                                         ; preds = %for.body3
+  %scevgep = getelementptr i64* %B.addr.04, i64 20
+  %inc8 = add nsw i64 %i.03, 1
+  %exitcond5 = icmp ne i64 %inc8, 20
+  br i1 %exitcond5, label %for.cond1.preheader, label %for.end9
+
+for.end9:                                         ; preds = %for.inc7
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 20; i++)
+;;    for (long int j = 0; j < 20; j++) {
+;;      A[100*i + j] = ...
+;;      ... = A[100*i - j + 11];
+
+define void @banerjee12(i64* %A, i64* %B, i64 %m, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %entry, %for.inc7
+  %B.addr.04 = phi i64* [ %B, %entry ], [ %scevgep, %for.inc7 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc8, %for.inc7 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.cond1.preheader, %for.body3
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i64* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %mul = mul nsw i64 %i.03, 100
+  %add = add nsw i64 %mul, %j.02
+  %arrayidx = getelementptr inbounds i64* %A, i64 %add
+  store i64 0, i64* %arrayidx, align 8
+  %mul4 = mul nsw i64 %i.03, 100
+  %sub = sub nsw i64 %mul4, %j.02
+  %add5 = add nsw i64 %sub, 11
+  %arrayidx6 = getelementptr inbounds i64* %A, i64 %add5
+  %0 = load i64* %arrayidx6, align 8
+; CHECK: da analyze - flow [= <>]!
+  %incdec.ptr = getelementptr inbounds i64* %B.addr.11, i64 1
+  store i64 %0, i64* %B.addr.11, align 8
+  %inc = add nsw i64 %j.02, 1
+  %exitcond = icmp ne i64 %inc, 20
+  br i1 %exitcond, label %for.body3, label %for.inc7
+
+for.inc7:                                         ; preds = %for.body3
+  %scevgep = getelementptr i64* %B.addr.04, i64 20
+  %inc8 = add nsw i64 %i.03, 1
+  %exitcond5 = icmp ne i64 %inc8, 20
+  br i1 %exitcond5, label %for.cond1.preheader, label %for.end9
+
+for.end9:                                         ; preds = %for.inc7
+  ret void
+}

test/Analysis/DependenceAnalysis/Coupled.ll

@@ -0,0 +1,509 @@
+; RUN: opt < %s -analyze -basicaa -da | FileCheck %s
+
+; ModuleID = 'Coupled.bc'
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.6.0"
+
+
+;; for (long int i = 0; i < 50; i++)
+;;   A[i][i] = ...
+;;   ... = A[i + 10][i + 9]
+
+define void @couple0([100 x i32]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %arrayidx1 = getelementptr inbounds [100 x i32]* %A, i64 %i.02, i64 %i.02
+  store i32 %conv, i32* %arrayidx1, align 4
+  %add = add nsw i64 %i.02, 9
+  %add2 = add nsw i64 %i.02, 10
+  %arrayidx4 = getelementptr inbounds [100 x i32]* %A, i64 %add2, i64 %add
+  %0 = load i32* %arrayidx4, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add nsw i64 %i.02, 1
+  %cmp = icmp slt i64 %inc, 50
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;; for (long int i = 0; i < 50; i++)
+;;   A[i][i] = ...
+;;   ... = A[i + 9][i + 9]
+
+define void @couple1([100 x i32]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %arrayidx1 = getelementptr inbounds [100 x i32]* %A, i64 %i.02, i64 %i.02
+  store i32 %conv, i32* %arrayidx1, align 4
+  %add = add nsw i64 %i.02, 9
+  %add2 = add nsw i64 %i.02, 9
+  %arrayidx4 = getelementptr inbounds [100 x i32]* %A, i64 %add2, i64 %add
+  %0 = load i32* %arrayidx4, align 4
+; CHECK: da analyze - consistent flow [-9]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add nsw i64 %i.02, 1
+  %cmp = icmp slt i64 %inc, 50
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;; for (long int i = 0; i < 50; i++)
+;;   A[3*i - 6][3*i - 6] = ...
+;;   ... = A[i][i]
+
+define void @couple2([100 x i32]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = mul nsw i64 %i.02, 3
+  %sub = add nsw i64 %mul, -6
+  %mul1 = mul nsw i64 %i.02, 3
+  %sub2 = add nsw i64 %mul1, -6
+  %arrayidx3 = getelementptr inbounds [100 x i32]* %A, i64 %sub2, i64 %sub
+  store i32 %conv, i32* %arrayidx3, align 4
+  %arrayidx5 = getelementptr inbounds [100 x i32]* %A, i64 %i.02, i64 %i.02
+  %0 = load i32* %arrayidx5, align 4
+; CHECK: da analyze - flow [*|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add nsw i64 %i.02, 1
+  %cmp = icmp slt i64 %inc, 50
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;; for (long int i = 0; i < 50; i++)
+;;   A[3*i - 6][3*i - 5] = ...
+;;   ... = A[i][i]
+
+define void @couple3([100 x i32]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = mul nsw i64 %i.02, 3
+  %sub = add nsw i64 %mul, -5
+  %mul1 = mul nsw i64 %i.02, 3
+  %sub2 = add nsw i64 %mul1, -6
+  %arrayidx3 = getelementptr inbounds [100 x i32]* %A, i64 %sub2, i64 %sub
+  store i32 %conv, i32* %arrayidx3, align 4
+  %arrayidx5 = getelementptr inbounds [100 x i32]* %A, i64 %i.02, i64 %i.02
+  %0 = load i32* %arrayidx5, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add nsw i64 %i.02, 1
+  %cmp = icmp slt i64 %inc, 50
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;; for (long int i = 0; i < 50; i++)
+;;   A[3*i - 6][3*i - n] = ...
+;;   ... = A[i][i]
+
+define void @couple4([100 x i32]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = mul nsw i64 %i.02, 3
+  %conv1 = sext i32 %n to i64
+  %sub = sub nsw i64 %mul, %conv1
+  %mul2 = mul nsw i64 %i.02, 3
+  %sub3 = add nsw i64 %mul2, -6
+  %arrayidx4 = getelementptr inbounds [100 x i32]* %A, i64 %sub3, i64 %sub
+  store i32 %conv, i32* %arrayidx4, align 4
+  %arrayidx6 = getelementptr inbounds [100 x i32]* %A, i64 %i.02, i64 %i.02
+  %0 = load i32* %arrayidx6, align 4
+; CHECK: da analyze - flow [*|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add nsw i64 %i.02, 1
+  %cmp = icmp slt i64 %inc, 50
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;; for (long int i = 0; i < 50; i++)
+;;   A[3*i - n + 1][3*i - n] = ...
+;;   ... = A[i][i]
+
+define void @couple5([100 x i32]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = mul nsw i64 %i.02, 3
+  %conv1 = sext i32 %n to i64
+  %sub = sub nsw i64 %mul, %conv1
+  %mul2 = mul nsw i64 %i.02, 3
+  %conv3 = sext i32 %n to i64
+  %sub4 = sub nsw i64 %mul2, %conv3
+  %add = add nsw i64 %sub4, 1
+  %arrayidx5 = getelementptr inbounds [100 x i32]* %A, i64 %add, i64 %sub
+  store i32 %conv, i32* %arrayidx5, align 4
+  %arrayidx7 = getelementptr inbounds [100 x i32]* %A, i64 %i.02, i64 %i.02
+  %0 = load i32* %arrayidx7, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add nsw i64 %i.02, 1
+  %cmp = icmp slt i64 %inc, 50
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;; for (long int i = 0; i < 50; i++)
+;;   A[i][3*i - 6] = ...
+;;   ... = A[i][i]
+
+define void @couple6([100 x i32]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = mul nsw i64 %i.02, 3
+  %sub = add nsw i64 %mul, -6
+  %arrayidx1 = getelementptr inbounds [100 x i32]* %A, i64 %i.02, i64 %sub
+  store i32 %conv, i32* %arrayidx1, align 4
+  %arrayidx3 = getelementptr inbounds [100 x i32]* %A, i64 %i.02, i64 %i.02
+  %0 = load i32* %arrayidx3, align 4
+; CHECK: da analyze - flow [=|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add nsw i64 %i.02, 1
+  %cmp = icmp slt i64 %inc, 50
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;; for (long int i = 0; i < 50; i++)
+;;   A[i][3*i - 5] = ...
+;;   ... = A[i][i]
+
+define void @couple7([100 x i32]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = mul nsw i64 %i.02, 3
+  %sub = add nsw i64 %mul, -5
+  %arrayidx1 = getelementptr inbounds [100 x i32]* %A, i64 %i.02, i64 %sub
+  store i32 %conv, i32* %arrayidx1, align 4
+  %arrayidx3 = getelementptr inbounds [100 x i32]* %A, i64 %i.02, i64 %i.02
+  %0 = load i32* %arrayidx3, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add nsw i64 %i.02, 1
+  %cmp = icmp slt i64 %inc, 50
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;; for (long int i = 0; i <= 15; i++)
+;;   A[3*i - 18][3 - i] = ...
+;;   ... = A[i][i]
+
+define void @couple8([100 x i32]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %sub = sub nsw i64 3, %i.02
+  %mul = mul nsw i64 %i.02, 3
+  %sub1 = add nsw i64 %mul, -18
+  %arrayidx2 = getelementptr inbounds [100 x i32]* %A, i64 %sub1, i64 %sub
+  store i32 %conv, i32* %arrayidx2, align 4
+  %arrayidx4 = getelementptr inbounds [100 x i32]* %A, i64 %i.02, i64 %i.02
+  %0 = load i32* %arrayidx4, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add nsw i64 %i.02, 1
+  %cmp = icmp slt i64 %inc, 16
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;; for (long int i = 0; i <= 15; i++)
+;;   A[3*i - 18][2 - i] = ...
+;;   ... = A[i][i]
+
+define void @couple9([100 x i32]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %sub = sub nsw i64 2, %i.02
+  %mul = mul nsw i64 %i.02, 3
+  %sub1 = add nsw i64 %mul, -18
+  %arrayidx2 = getelementptr inbounds [100 x i32]* %A, i64 %sub1, i64 %sub
+  store i32 %conv, i32* %arrayidx2, align 4
+  %arrayidx4 = getelementptr inbounds [100 x i32]* %A, i64 %i.02, i64 %i.02
+  %0 = load i32* %arrayidx4, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add nsw i64 %i.02, 1
+  %cmp = icmp slt i64 %inc, 16
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;; for (long int i = 0; i <= 15; i++)
+;;   A[3*i - 18][6 - i] = ...
+;;   ... = A[i][i]
+
+define void @couple10([100 x i32]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %sub = sub nsw i64 6, %i.02
+  %mul = mul nsw i64 %i.02, 3
+  %sub1 = add nsw i64 %mul, -18
+  %arrayidx2 = getelementptr inbounds [100 x i32]* %A, i64 %sub1, i64 %sub
+  store i32 %conv, i32* %arrayidx2, align 4
+  %arrayidx4 = getelementptr inbounds [100 x i32]* %A, i64 %i.02, i64 %i.02
+  %0 = load i32* %arrayidx4, align 4
+; CHECK: da analyze - flow [>] splitable!
+; CHECK: da analyze - split level = 1, iteration = 3!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add nsw i64 %i.02, 1
+  %cmp = icmp slt i64 %inc, 16
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;; for (long int i = 0; i <= 15; i++)
+;;   A[3*i - 18][18 - i] = ...
+;;   ... = A[i][i]
+
+define void @couple11([100 x i32]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %sub = sub nsw i64 18, %i.02
+  %mul = mul nsw i64 %i.02, 3
+  %sub1 = add nsw i64 %mul, -18
+  %arrayidx2 = getelementptr inbounds [100 x i32]* %A, i64 %sub1, i64 %sub
+  store i32 %conv, i32* %arrayidx2, align 4
+  %arrayidx4 = getelementptr inbounds [100 x i32]* %A, i64 %i.02, i64 %i.02
+  %0 = load i32* %arrayidx4, align 4
+; CHECK: da analyze - flow [=|<] splitable!
+; CHECK: da analyze - split level = 1, iteration = 9!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add nsw i64 %i.02, 1
+  %cmp = icmp slt i64 %inc, 16
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;; for (long int i = 0; i <= 12; i++)
+;;   A[3*i - 18][22 - i] = ...
+;;   ... = A[i][i]
+
+define void @couple12([100 x i32]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %sub = sub nsw i64 22, %i.02
+  %mul = mul nsw i64 %i.02, 3
+  %sub1 = add nsw i64 %mul, -18
+  %arrayidx2 = getelementptr inbounds [100 x i32]* %A, i64 %sub1, i64 %sub
+  store i32 %conv, i32* %arrayidx2, align 4
+  %arrayidx4 = getelementptr inbounds [100 x i32]* %A, i64 %i.02, i64 %i.02
+  %0 = load i32* %arrayidx4, align 4
+; CHECK: da analyze - flow [<] splitable!
+; CHECK: da analyze - split level = 1, iteration = 11!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add nsw i64 %i.02, 1
+  %cmp = icmp slt i64 %inc, 13
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;; for (long int i = 0; i < 12; i++)
+;;   A[3*i - 18][22 - i] = ...
+;;   ... = A[i][i]
+
+define void @couple13([100 x i32]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %sub = sub nsw i64 22, %i.02
+  %mul = mul nsw i64 %i.02, 3
+  %sub1 = add nsw i64 %mul, -18
+  %arrayidx2 = getelementptr inbounds [100 x i32]* %A, i64 %sub1, i64 %sub
+  store i32 %conv, i32* %arrayidx2, align 4
+  %arrayidx4 = getelementptr inbounds [100 x i32]* %A, i64 %i.02, i64 %i.02
+  %0 = load i32* %arrayidx4, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add nsw i64 %i.02, 1
+  %cmp = icmp slt i64 %inc, 12
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;; for (long int i = 0; i < 100; i++)
+;;   A[3*i - 18][18 - i][i] = ...
+;;   ... = A[i][i][i]
+
+define void @couple14([100 x [100 x i32]]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %sub = sub nsw i64 18, %i.02
+  %mul = mul nsw i64 %i.02, 3
+  %sub1 = add nsw i64 %mul, -18
+  %arrayidx3 = getelementptr inbounds [100 x [100 x i32]]* %A, i64 %sub1, i64 %sub, i64 %i.02
+  store i32 %conv, i32* %arrayidx3, align 4
+  %arrayidx6 = getelementptr inbounds [100 x [100 x i32]]* %A, i64 %i.02, i64 %i.02, i64 %i.02
+  %0 = load i32* %arrayidx6, align 4
+; CHECK: da analyze - flow [=|<] splitable!
+; CHECK: da analyze - split level = 1, iteration = 9!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add nsw i64 %i.02, 1
+  %cmp = icmp slt i64 %inc, 100
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;; for (long int i = 0; i < 100; i++)
+;;   A[3*i - 18][22 - i][i] = ...
+;;   ... = A[i][i][i]
+
+define void @couple15([100 x [100 x i32]]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %sub = sub nsw i64 22, %i.02
+  %mul = mul nsw i64 %i.02, 3
+  %sub1 = add nsw i64 %mul, -18
+  %arrayidx3 = getelementptr inbounds [100 x [100 x i32]]* %A, i64 %sub1, i64 %sub, i64 %i.02
+  store i32 %conv, i32* %arrayidx3, align 4
+  %arrayidx6 = getelementptr inbounds [100 x [100 x i32]]* %A, i64 %i.02, i64 %i.02, i64 %i.02
+  %0 = load i32* %arrayidx6, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add nsw i64 %i.02, 1
+  %cmp = icmp slt i64 %inc, 100
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}

test/Analysis/DependenceAnalysis/ExactRDIV.ll

@@ -0,0 +1,508 @@
+; RUN: opt < %s -analyze -basicaa -da | FileCheck %s
+
+; ModuleID = 'ExactRDIV.bc'
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.6.0"
+
+
+;;  for (long int i = 0; i < 10; i++)
+;;    A[4*i + 10] = ...
+;;  for (long int j = 0; j < 10; j++)
+;;    ... = A[2*j + 1];
+
+define void @rdiv0(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = shl nsw i64 %i.03, 2
+  %add = add nsw i64 %mul, 10
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %inc = add nsw i64 %i.03, 1
+  %cmp = icmp slt i64 %inc, 10
+  br i1 %cmp, label %for.body, label %for.body4
+
+for.body4:                                        ; preds = %for.body4, %for.body
+  %j.02 = phi i64 [ %inc9, %for.body4 ], [ 0, %for.body ]
+  %B.addr.01 = phi i32* [ %incdec.ptr, %for.body4 ], [ %B, %for.body ]
+  %mul5 = shl nsw i64 %j.02, 1
+  %add64 = or i64 %mul5, 1
+  %arrayidx7 = getelementptr inbounds i32* %A, i64 %add64
+  %0 = load i32* %arrayidx7, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc9 = add nsw i64 %j.02, 1
+  %cmp2 = icmp slt i64 %inc9, 10
+  br i1 %cmp2, label %for.body4, label %for.end10
+
+for.end10:                                        ; preds = %for.body4
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 5; i++)
+;;    A[11*i - 45] = ...
+;;  for (long int j = 0; j < 10; j++)
+;;    ... = A[j];
+
+define void @rdiv1(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = mul nsw i64 %i.03, 11
+  %sub = add nsw i64 %mul, -45
+  %arrayidx = getelementptr inbounds i32* %A, i64 %sub
+  store i32 %conv, i32* %arrayidx, align 4
+  %inc = add nsw i64 %i.03, 1
+  %cmp = icmp slt i64 %inc, 5
+  br i1 %cmp, label %for.body, label %for.body4
+
+for.body4:                                        ; preds = %for.body4, %for.body
+  %j.02 = phi i64 [ %inc7, %for.body4 ], [ 0, %for.body ]
+  %B.addr.01 = phi i32* [ %incdec.ptr, %for.body4 ], [ %B, %for.body ]
+  %arrayidx5 = getelementptr inbounds i32* %A, i64 %j.02
+  %0 = load i32* %arrayidx5, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc7 = add nsw i64 %j.02, 1
+  %cmp2 = icmp slt i64 %inc7, 10
+  br i1 %cmp2, label %for.body4, label %for.end8
+
+for.end8:                                         ; preds = %for.body4
+  ret void
+}
+
+
+;;  for (long int i = 0; i <= 5; i++)
+;;    A[11*i - 45] = ...
+;;  for (long int j = 0; j < 10; j++)
+;;    ... = A[j];
+
+define void @rdiv2(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = mul nsw i64 %i.03, 11
+  %sub = add nsw i64 %mul, -45
+  %arrayidx = getelementptr inbounds i32* %A, i64 %sub
+  store i32 %conv, i32* %arrayidx, align 4
+  %inc = add nsw i64 %i.03, 1
+  %cmp = icmp slt i64 %inc, 6
+  br i1 %cmp, label %for.body, label %for.body4
+
+for.body4:                                        ; preds = %for.body4, %for.body
+  %j.02 = phi i64 [ %inc7, %for.body4 ], [ 0, %for.body ]
+  %B.addr.01 = phi i32* [ %incdec.ptr, %for.body4 ], [ %B, %for.body ]
+  %arrayidx5 = getelementptr inbounds i32* %A, i64 %j.02
+  %0 = load i32* %arrayidx5, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc7 = add nsw i64 %j.02, 1
+  %cmp2 = icmp slt i64 %inc7, 10
+  br i1 %cmp2, label %for.body4, label %for.end8
+
+for.end8:                                         ; preds = %for.body4
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 5; i++)
+;;    A[11*i - 45] = ...
+;;  for (long int j = 0; j <= 10; j++)
+;;    ... = A[j];
+
+define void @rdiv3(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = mul nsw i64 %i.03, 11
+  %sub = add nsw i64 %mul, -45
+  %arrayidx = getelementptr inbounds i32* %A, i64 %sub
+  store i32 %conv, i32* %arrayidx, align 4
+  %inc = add nsw i64 %i.03, 1
+  %cmp = icmp slt i64 %inc, 5
+  br i1 %cmp, label %for.body, label %for.body4
+
+for.body4:                                        ; preds = %for.body4, %for.body
+  %j.02 = phi i64 [ %inc7, %for.body4 ], [ 0, %for.body ]
+  %B.addr.01 = phi i32* [ %incdec.ptr, %for.body4 ], [ %B, %for.body ]
+  %arrayidx5 = getelementptr inbounds i32* %A, i64 %j.02
+  %0 = load i32* %arrayidx5, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc7 = add nsw i64 %j.02, 1
+  %cmp2 = icmp slt i64 %inc7, 11
+  br i1 %cmp2, label %for.body4, label %for.end8
+
+for.end8:                                         ; preds = %for.body4
+  ret void
+}
+
+
+;;  for (long int i = 0; i <= 5; i++)
+;;    A[11*i - 45] = ...
+;;  for (long int j = 0; j <= 10; j++)
+;;    ... = A[j];
+
+define void @rdiv4(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = mul nsw i64 %i.03, 11
+  %sub = add nsw i64 %mul, -45
+  %arrayidx = getelementptr inbounds i32* %A, i64 %sub
+  store i32 %conv, i32* %arrayidx, align 4
+  %inc = add nsw i64 %i.03, 1
+  %cmp = icmp slt i64 %inc, 6
+  br i1 %cmp, label %for.body, label %for.body4
+
+for.body4:                                        ; preds = %for.body4, %for.body
+  %j.02 = phi i64 [ %inc7, %for.body4 ], [ 0, %for.body ]
+  %B.addr.01 = phi i32* [ %incdec.ptr, %for.body4 ], [ %B, %for.body ]
+  %arrayidx5 = getelementptr inbounds i32* %A, i64 %j.02
+  %0 = load i32* %arrayidx5, align 4
+; CHECK: da analyze - flow!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc7 = add nsw i64 %j.02, 1
+  %cmp2 = icmp slt i64 %inc7, 11
+  br i1 %cmp2, label %for.body4, label %for.end8
+
+for.end8:                                         ; preds = %for.body4
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 5; i++)
+;;    A[-11*i + 45] = ...
+;;  for (long int j = 0; j < 10; j++)
+;;    ... = A[-j];
+
+define void @rdiv5(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = mul nsw i64 %i.03, -11
+  %add = add nsw i64 %mul, 45
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %inc = add nsw i64 %i.03, 1
+  %cmp = icmp slt i64 %inc, 5
+  br i1 %cmp, label %for.body, label %for.body4
+
+for.body4:                                        ; preds = %for.body4, %for.body
+  %j.02 = phi i64 [ %inc7, %for.body4 ], [ 0, %for.body ]
+  %B.addr.01 = phi i32* [ %incdec.ptr, %for.body4 ], [ %B, %for.body ]
+  %sub = sub nsw i64 0, %j.02
+  %arrayidx5 = getelementptr inbounds i32* %A, i64 %sub
+  %0 = load i32* %arrayidx5, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc7 = add nsw i64 %j.02, 1
+  %cmp2 = icmp slt i64 %inc7, 10
+  br i1 %cmp2, label %for.body4, label %for.end8
+
+for.end8:                                         ; preds = %for.body4
+  ret void
+}
+
+
+;;  for (long int i = 0; i <= 5; i++)
+;;    A[-11*i + 45] = ...
+;;  for (long int j = 0; j < 10; j++)
+;;    ... = A[-j];
+
+define void @rdiv6(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = mul nsw i64 %i.03, -11
+  %add = add nsw i64 %mul, 45
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %inc = add nsw i64 %i.03, 1
+  %cmp = icmp slt i64 %inc, 6
+  br i1 %cmp, label %for.body, label %for.body4
+
+for.body4:                                        ; preds = %for.body4, %for.body
+  %j.02 = phi i64 [ %inc7, %for.body4 ], [ 0, %for.body ]
+  %B.addr.01 = phi i32* [ %incdec.ptr, %for.body4 ], [ %B, %for.body ]
+  %sub = sub nsw i64 0, %j.02
+  %arrayidx5 = getelementptr inbounds i32* %A, i64 %sub
+  %0 = load i32* %arrayidx5, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc7 = add nsw i64 %j.02, 1
+  %cmp2 = icmp slt i64 %inc7, 10
+  br i1 %cmp2, label %for.body4, label %for.end8
+
+for.end8:                                         ; preds = %for.body4
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 5; i++)
+;;    A[-11*i + 45] = ...
+;;  for (long int j = 0; j <= 10; j++)
+;;    ... = A[-j];
+
+define void @rdiv7(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = mul nsw i64 %i.03, -11
+  %add = add nsw i64 %mul, 45
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %inc = add nsw i64 %i.03, 1
+  %cmp = icmp slt i64 %inc, 5
+  br i1 %cmp, label %for.body, label %for.body4
+
+for.body4:                                        ; preds = %for.body4, %for.body
+  %j.02 = phi i64 [ %inc7, %for.body4 ], [ 0, %for.body ]
+  %B.addr.01 = phi i32* [ %incdec.ptr, %for.body4 ], [ %B, %for.body ]
+  %sub = sub nsw i64 0, %j.02
+  %arrayidx5 = getelementptr inbounds i32* %A, i64 %sub
+  %0 = load i32* %arrayidx5, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc7 = add nsw i64 %j.02, 1
+  %cmp2 = icmp slt i64 %inc7, 11
+  br i1 %cmp2, label %for.body4, label %for.end8
+
+for.end8:                                         ; preds = %for.body4
+  ret void
+}
+
+
+;;  for (long int i = 0; i <= 5; i++)
+;;    A[-11*i + 45] = ...
+;;  for (long int j = 0; j <= 10; j++)
+;;    ... = A[-j];
+
+define void @rdiv8(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = mul nsw i64 %i.03, -11
+  %add = add nsw i64 %mul, 45
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %inc = add nsw i64 %i.03, 1
+  %cmp = icmp slt i64 %inc, 6
+  br i1 %cmp, label %for.body, label %for.body4
+
+for.body4:                                        ; preds = %for.body4, %for.body
+  %j.02 = phi i64 [ %inc7, %for.body4 ], [ 0, %for.body ]
+  %B.addr.01 = phi i32* [ %incdec.ptr, %for.body4 ], [ %B, %for.body ]
+  %sub = sub nsw i64 0, %j.02
+  %arrayidx5 = getelementptr inbounds i32* %A, i64 %sub
+  %0 = load i32* %arrayidx5, align 4
+; CHECK: da analyze - flow!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc7 = add nsw i64 %j.02, 1
+  %cmp2 = icmp slt i64 %inc7, 11
+  br i1 %cmp2, label %for.body4, label %for.end8
+
+for.end8:                                         ; preds = %for.body4
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 5; i++)
+;;    for (long int j = 0; j < 10; j++)
+;;      A[11*i - j] = ...
+;;      ... = A[45];
+
+define void @rdiv9(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %for.inc5, %entry
+  %B.addr.04 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.inc5 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc6, %for.inc5 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.body3, %for.cond1.preheader
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i32* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = mul nsw i64 %i.03, 11
+  %sub = sub nsw i64 %mul, %j.02
+  %arrayidx = getelementptr inbounds i32* %A, i64 %sub
+  store i32 %conv, i32* %arrayidx, align 4
+  %arrayidx4 = getelementptr inbounds i32* %A, i64 45
+  %0 = load i32* %arrayidx4, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.11, i64 1
+  store i32 %0, i32* %B.addr.11, align 4
+  %inc = add nsw i64 %j.02, 1
+  %cmp2 = icmp slt i64 %inc, 10
+  br i1 %cmp2, label %for.body3, label %for.inc5
+
+for.inc5:                                         ; preds = %for.body3
+  %inc6 = add nsw i64 %i.03, 1
+  %cmp = icmp slt i64 %inc6, 5
+  br i1 %cmp, label %for.cond1.preheader, label %for.end7
+
+for.end7:                                         ; preds = %for.inc5
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 5; i++)
+;;    for (long int j = 0; j <= 10; j++)
+;;      A[11*i - j] = ...
+;;      ... = A[45];
+
+define void @rdiv10(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %for.inc5, %entry
+  %B.addr.04 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.inc5 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc6, %for.inc5 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.body3, %for.cond1.preheader
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i32* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = mul nsw i64 %i.03, 11
+  %sub = sub nsw i64 %mul, %j.02
+  %arrayidx = getelementptr inbounds i32* %A, i64 %sub
+  store i32 %conv, i32* %arrayidx, align 4
+  %arrayidx4 = getelementptr inbounds i32* %A, i64 45
+  %0 = load i32* %arrayidx4, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.11, i64 1
+  store i32 %0, i32* %B.addr.11, align 4
+  %inc = add nsw i64 %j.02, 1
+  %cmp2 = icmp slt i64 %inc, 10
+  br i1 %cmp2, label %for.body3, label %for.inc5
+
+for.inc5:                                         ; preds = %for.body3
+  %inc6 = add nsw i64 %i.03, 1
+  %cmp = icmp slt i64 %inc6, 6
+  br i1 %cmp, label %for.cond1.preheader, label %for.end7
+
+for.end7:                                         ; preds = %for.inc5
+  ret void
+}
+
+
+;;  for (long int i = 0; i <= 5; i++)
+;;    for (long int j = 0; j <= 10; j++)
+;;      A[11*i - j] = ...
+;;      ... = A[45];
+
+define void @rdiv11(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %for.inc5, %entry
+  %B.addr.04 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.inc5 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc6, %for.inc5 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.body3, %for.cond1.preheader
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i32* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = mul nsw i64 %i.03, 11
+  %sub = sub nsw i64 %mul, %j.02
+  %arrayidx = getelementptr inbounds i32* %A, i64 %sub
+  store i32 %conv, i32* %arrayidx, align 4
+  %arrayidx4 = getelementptr inbounds i32* %A, i64 45
+  %0 = load i32* %arrayidx4, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.11, i64 1
+  store i32 %0, i32* %B.addr.11, align 4
+  %inc = add nsw i64 %j.02, 1
+  %cmp2 = icmp slt i64 %inc, 11
+  br i1 %cmp2, label %for.body3, label %for.inc5
+
+for.inc5:                                         ; preds = %for.body3
+  %inc6 = add nsw i64 %i.03, 1
+  %cmp = icmp slt i64 %inc6, 5
+  br i1 %cmp, label %for.cond1.preheader, label %for.end7
+
+for.end7:                                         ; preds = %for.inc5
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 5; i++)
+;;    for (long int j = 0; j < 10; j++)
+;;      A[11*i - j] = ...
+;;      ... = A[45];
+
+define void @rdiv12(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %for.inc5, %entry
+  %B.addr.04 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.inc5 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc6, %for.inc5 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.body3, %for.cond1.preheader
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i32* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = mul nsw i64 %i.03, 11
+  %sub = sub nsw i64 %mul, %j.02
+  %arrayidx = getelementptr inbounds i32* %A, i64 %sub
+  store i32 %conv, i32* %arrayidx, align 4
+  %arrayidx4 = getelementptr inbounds i32* %A, i64 45
+  %0 = load i32* %arrayidx4, align 4
+; CHECK: da analyze - flow [* *|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.11, i64 1
+  store i32 %0, i32* %B.addr.11, align 4
+  %inc = add nsw i64 %j.02, 1
+  %cmp2 = icmp slt i64 %inc, 11
+  br i1 %cmp2, label %for.body3, label %for.inc5
+
+for.inc5:                                         ; preds = %for.body3
+  %inc6 = add nsw i64 %i.03, 1
+  %cmp = icmp slt i64 %inc6, 6
+  br i1 %cmp, label %for.cond1.preheader, label %for.end7
+
+for.end7:                                         ; preds = %for.inc5
+  ret void
+}

test/Analysis/DependenceAnalysis/ExactSIV.ll

@@ -0,0 +1,428 @@
+; RUN: opt < %s -analyze -basicaa -da | FileCheck %s
+
+; ModuleID = 'ExactSIV.bc'
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.6.0"
+
+
+;;  for (long unsigned i = 0; i < 10; i++) {
+;;    A[i + 10] = ...
+;;    ... = A[2*i + 1];
+
+define void @exact0(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %add = add i64 %i.02, 10
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul = shl i64 %i.02, 1
+  %add13 = or i64 %mul, 1
+  %arrayidx2 = getelementptr inbounds i32* %A, i64 %add13
+  %0 = load i32* %arrayidx2, align 4
+; CHECK: da analyze - flow [<=|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 10
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < 10; i++) {
+;;    A[4*i + 10] = ...
+;;    ... = A[2*i + 1];
+
+define void @exact1(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = shl i64 %i.02, 2
+  %add = add i64 %mul, 10
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul1 = shl i64 %i.02, 1
+  %add23 = or i64 %mul1, 1
+  %arrayidx3 = getelementptr inbounds i32* %A, i64 %add23
+  %0 = load i32* %arrayidx3, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 10
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < 10; i++) {
+;;    A[6*i] = ...
+;;    ... = A[i + 60];
+
+define void @exact2(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = mul i64 %i.02, 6
+  %arrayidx = getelementptr inbounds i32* %A, i64 %mul
+  store i32 %conv, i32* %arrayidx, align 4
+  %add = add i64 %i.02, 60
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 %add
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 10
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i <= 10; i++) {
+;;    A[6*i] = ...
+;;    ... = A[i + 60];
+
+define void @exact3(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = mul i64 %i.02, 6
+  %arrayidx = getelementptr inbounds i32* %A, i64 %mul
+  store i32 %conv, i32* %arrayidx, align 4
+  %add = add i64 %i.02, 60
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 %add
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - flow [>]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 11
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < 12; i++) {
+;;    A[6*i] = ...
+;;    ... = A[i + 60];
+
+define void @exact4(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = mul i64 %i.02, 6
+  %arrayidx = getelementptr inbounds i32* %A, i64 %mul
+  store i32 %conv, i32* %arrayidx, align 4
+  %add = add i64 %i.02, 60
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 %add
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - flow [>]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 12
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i <= 12; i++) {
+;;    A[6*i] = ...
+;;    ... = A[i + 60];
+
+define void @exact5(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = mul i64 %i.02, 6
+  %arrayidx = getelementptr inbounds i32* %A, i64 %mul
+  store i32 %conv, i32* %arrayidx, align 4
+  %add = add i64 %i.02, 60
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 %add
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - flow [=>|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 13
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < 18; i++) {
+;;    A[6*i] = ...
+;;    ... = A[i + 60];
+
+define void @exact6(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = mul i64 %i.02, 6
+  %arrayidx = getelementptr inbounds i32* %A, i64 %mul
+  store i32 %conv, i32* %arrayidx, align 4
+  %add = add i64 %i.02, 60
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 %add
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - flow [=>|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 18
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i <= 18; i++) {
+;;    A[6*i] = ...
+;;    ... = A[i + 60];
+
+define void @exact7(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = mul i64 %i.02, 6
+  %arrayidx = getelementptr inbounds i32* %A, i64 %mul
+  store i32 %conv, i32* %arrayidx, align 4
+  %add = add i64 %i.02, 60
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 %add
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - flow [*|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 19
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < 10; i++) {
+;;    A[-6*i] = ...
+;;    ... = A[-i - 60];
+
+define void @exact8(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = mul i64 %i.02, -6
+  %arrayidx = getelementptr inbounds i32* %A, i64 %mul
+  store i32 %conv, i32* %arrayidx, align 4
+  %sub1 = sub i64 -60, %i.02
+  %arrayidx2 = getelementptr inbounds i32* %A, i64 %sub1
+  %0 = load i32* %arrayidx2, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 10
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i <= 10; i++) {
+;;    A[-6*i] = ...
+;;    ... = A[-i - 60];
+
+define void @exact9(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = mul i64 %i.02, -6
+  %arrayidx = getelementptr inbounds i32* %A, i64 %mul
+  store i32 %conv, i32* %arrayidx, align 4
+  %sub1 = sub i64 -60, %i.02
+  %arrayidx2 = getelementptr inbounds i32* %A, i64 %sub1
+  %0 = load i32* %arrayidx2, align 4
+; CHECK: da analyze - flow [>]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 11
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < 12; i++) {
+;;    A[-6*i] = ...
+;;    ... = A[-i - 60];
+
+define void @exact10(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = mul i64 %i.02, -6
+  %arrayidx = getelementptr inbounds i32* %A, i64 %mul
+  store i32 %conv, i32* %arrayidx, align 4
+  %sub1 = sub i64 -60, %i.02
+  %arrayidx2 = getelementptr inbounds i32* %A, i64 %sub1
+  %0 = load i32* %arrayidx2, align 4
+; CHECK: da analyze - flow [>]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 12
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i <= 12; i++) {
+;;    A[-6*i] = ...
+;;    ... = A[-i - 60];
+
+define void @exact11(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = mul i64 %i.02, -6
+  %arrayidx = getelementptr inbounds i32* %A, i64 %mul
+  store i32 %conv, i32* %arrayidx, align 4
+  %sub1 = sub i64 -60, %i.02
+  %arrayidx2 = getelementptr inbounds i32* %A, i64 %sub1
+  %0 = load i32* %arrayidx2, align 4
+; CHECK: da analyze - flow [=>|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 13
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < 18; i++) {
+;;    A[-6*i] = ...
+;;    ... = A[-i - 60];
+
+define void @exact12(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = mul i64 %i.02, -6
+  %arrayidx = getelementptr inbounds i32* %A, i64 %mul
+  store i32 %conv, i32* %arrayidx, align 4
+  %sub1 = sub i64 -60, %i.02
+  %arrayidx2 = getelementptr inbounds i32* %A, i64 %sub1
+  %0 = load i32* %arrayidx2, align 4
+; CHECK: da analyze - flow [=>|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 18
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i <= 18; i++) {
+;;    A[-6*i] = ...
+;;    ... = A[-i - 60];
+
+define void @exact13(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = mul i64 %i.02, -6
+  %arrayidx = getelementptr inbounds i32* %A, i64 %mul
+  store i32 %conv, i32* %arrayidx, align 4
+  %sub1 = sub i64 -60, %i.02
+  %arrayidx2 = getelementptr inbounds i32* %A, i64 %sub1
+  %0 = load i32* %arrayidx2, align 4
+; CHECK: da analyze - flow [*|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 19
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}

test/Analysis/DependenceAnalysis/GCD.ll

@@ -0,0 +1,597 @@
+; RUN: opt < %s -analyze -basicaa -da | FileCheck %s
+
+; ModuleID = 'GCD.bc'
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.6.0"
+
+
+;;  for (long int i = 0; i < 100; i++)
+;;    for (long int j = 0; j < 100; j++)
+;;      A[2*i - 4*j] = ...
+;;      ... = A[6*i + 8*j];
+
+define void @gcd0(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %entry, %for.inc8
+  %B.addr.04 = phi i32* [ %B, %entry ], [ %scevgep, %for.inc8 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc9, %for.inc8 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.cond1.preheader, %for.body3
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i32* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = shl nsw i64 %i.03, 1
+  %mul4 = shl nsw i64 %j.02, 2
+  %sub = sub nsw i64 %mul, %mul4
+  %arrayidx = getelementptr inbounds i32* %A, i64 %sub
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul5 = mul nsw i64 %i.03, 6
+  %mul6 = shl nsw i64 %j.02, 3
+  %add = add nsw i64 %mul5, %mul6
+  %arrayidx7 = getelementptr inbounds i32* %A, i64 %add
+  %0 = load i32* %arrayidx7, align 4
+; CHECK: da analyze - flow [=> *|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.11, i64 1
+  store i32 %0, i32* %B.addr.11, align 4
+  %inc = add nsw i64 %j.02, 1
+  %exitcond = icmp ne i64 %inc, 100
+  br i1 %exitcond, label %for.body3, label %for.inc8
+
+for.inc8:                                         ; preds = %for.body3
+  %scevgep = getelementptr i32* %B.addr.04, i64 100
+  %inc9 = add nsw i64 %i.03, 1
+  %exitcond5 = icmp ne i64 %inc9, 100
+  br i1 %exitcond5, label %for.cond1.preheader, label %for.end10
+
+for.end10:                                        ; preds = %for.inc8
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 100; i++)
+;;    for (long int j = 0; j < 100; j++)
+;;      A[2*i - 4*j] = ...
+;;      ... = A[6*i + 8*j + 1];
+
+define void @gcd1(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %entry, %for.inc9
+  %B.addr.04 = phi i32* [ %B, %entry ], [ %scevgep, %for.inc9 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc10, %for.inc9 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.cond1.preheader, %for.body3
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i32* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = shl nsw i64 %i.03, 1
+  %mul4 = shl nsw i64 %j.02, 2
+  %sub = sub nsw i64 %mul, %mul4
+  %arrayidx = getelementptr inbounds i32* %A, i64 %sub
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul5 = mul nsw i64 %i.03, 6
+  %mul6 = shl nsw i64 %j.02, 3
+  %add = add nsw i64 %mul5, %mul6
+  %add7 = or i64 %add, 1
+  %arrayidx8 = getelementptr inbounds i32* %A, i64 %add7
+  %0 = load i32* %arrayidx8, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.11, i64 1
+  store i32 %0, i32* %B.addr.11, align 4
+  %inc = add nsw i64 %j.02, 1
+  %exitcond = icmp ne i64 %inc, 100
+  br i1 %exitcond, label %for.body3, label %for.inc9
+
+for.inc9:                                         ; preds = %for.body3
+  %scevgep = getelementptr i32* %B.addr.04, i64 100
+  %inc10 = add nsw i64 %i.03, 1
+  %exitcond5 = icmp ne i64 %inc10, 100
+  br i1 %exitcond5, label %for.cond1.preheader, label %for.end11
+
+for.end11:                                        ; preds = %for.inc9
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 100; i++)
+;;    for (long int j = 0; j < 100; j++)
+;;      A[2*i - 4*j + 1] = ...
+;;      ... = A[6*i + 8*j];
+
+define void @gcd2(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %entry, %for.inc9
+  %B.addr.04 = phi i32* [ %B, %entry ], [ %scevgep, %for.inc9 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc10, %for.inc9 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.cond1.preheader, %for.body3
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i32* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = shl nsw i64 %i.03, 1
+  %mul4 = shl nsw i64 %j.02, 2
+  %sub = sub nsw i64 %mul, %mul4
+  %add5 = or i64 %sub, 1
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add5
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul5 = mul nsw i64 %i.03, 6
+  %mul6 = shl nsw i64 %j.02, 3
+  %add7 = add nsw i64 %mul5, %mul6
+  %arrayidx8 = getelementptr inbounds i32* %A, i64 %add7
+  %0 = load i32* %arrayidx8, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.11, i64 1
+  store i32 %0, i32* %B.addr.11, align 4
+  %inc = add nsw i64 %j.02, 1
+  %exitcond = icmp ne i64 %inc, 100
+  br i1 %exitcond, label %for.body3, label %for.inc9
+
+for.inc9:                                         ; preds = %for.body3
+  %scevgep = getelementptr i32* %B.addr.04, i64 100
+  %inc10 = add nsw i64 %i.03, 1
+  %exitcond6 = icmp ne i64 %inc10, 100
+  br i1 %exitcond6, label %for.cond1.preheader, label %for.end11
+
+for.end11:                                        ; preds = %for.inc9
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 100; i++)
+;;    for (long int j = 0; j < 100; j++)
+;;      A[i + 2*j] = ...
+;;      ... = A[i + 2*j - 1];
+
+define void @gcd3(i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %entry, %for.inc7
+  %B.addr.04 = phi i32* [ %B, %entry ], [ %scevgep, %for.inc7 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc8, %for.inc7 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.cond1.preheader, %for.body3
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i32* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = shl nsw i64 %j.02, 1
+  %add = add nsw i64 %i.03, %mul
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul4 = shl nsw i64 %j.02, 1
+  %add5 = add nsw i64 %i.03, %mul4
+  %sub = add nsw i64 %add5, -1
+  %arrayidx6 = getelementptr inbounds i32* %A, i64 %sub
+  %0 = load i32* %arrayidx6, align 4
+; CHECK: da analyze - flow [<> *]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.11, i64 1
+  store i32 %0, i32* %B.addr.11, align 4
+  %inc = add nsw i64 %j.02, 1
+  %exitcond = icmp ne i64 %inc, 100
+  br i1 %exitcond, label %for.body3, label %for.inc7
+
+for.inc7:                                         ; preds = %for.body3
+  %scevgep = getelementptr i32* %B.addr.04, i64 100
+  %inc8 = add nsw i64 %i.03, 1
+  %exitcond5 = icmp ne i64 %inc8, 100
+  br i1 %exitcond5, label %for.cond1.preheader, label %for.end9
+
+for.end9:                                         ; preds = %for.inc7
+  ret void
+}
+
+
+;;  void gcd4(int *A, int *B, long int M, long int N) {
+;;    for (long int i = 0; i < 100; i++)
+;;      for (long int j = 0; j < 100; j++) {
+;;        A[5*i + 10*j*M + 9*M*N] = i;
+;;        *B++ = A[15*i + 20*j*M - 21*N*M + 4];
+
+define void @gcd4(i32* %A, i32* %B, i64 %M, i64 %N) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %entry, %for.inc17
+  %B.addr.04 = phi i32* [ %B, %entry ], [ %scevgep, %for.inc17 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc18, %for.inc17 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.cond1.preheader, %for.body3
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i32* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = mul nsw i64 %i.03, 5
+  %mul4 = mul nsw i64 %j.02, 10
+  %mul5 = mul nsw i64 %mul4, %M
+  %add = add nsw i64 %mul, %mul5
+  %mul6 = mul nsw i64 %M, 9
+  %mul7 = mul nsw i64 %mul6, %N
+  %add8 = add nsw i64 %add, %mul7
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add8
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul9 = mul nsw i64 %i.03, 15
+  %mul10 = mul nsw i64 %j.02, 20
+  %mul11 = mul nsw i64 %mul10, %M
+  %add12 = add nsw i64 %mul9, %mul11
+  %mul13 = mul nsw i64 %N, 21
+  %mul14 = mul nsw i64 %mul13, %M
+  %sub = sub nsw i64 %add12, %mul14
+  %add15 = add nsw i64 %sub, 4
+  %arrayidx16 = getelementptr inbounds i32* %A, i64 %add15
+  %0 = load i32* %arrayidx16, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.11, i64 1
+  store i32 %0, i32* %B.addr.11, align 4
+  %inc = add nsw i64 %j.02, 1
+  %exitcond = icmp ne i64 %inc, 100
+  br i1 %exitcond, label %for.body3, label %for.inc17
+
+for.inc17:                                        ; preds = %for.body3
+  %scevgep = getelementptr i32* %B.addr.04, i64 100
+  %inc18 = add nsw i64 %i.03, 1
+  %exitcond5 = icmp ne i64 %inc18, 100
+  br i1 %exitcond5, label %for.cond1.preheader, label %for.end19
+
+for.end19:                                        ; preds = %for.inc17
+  ret void
+}
+
+
+;;  void gcd5(int *A, int *B, long int M, long int N) {
+;;    for (long int i = 0; i < 100; i++)
+;;      for (long int j = 0; j < 100; j++) {
+;;        A[5*i + 10*j*M + 9*M*N] = i;
+;;        *B++ = A[15*i + 20*j*M - 21*N*M + 5];
+
+define void @gcd5(i32* %A, i32* %B, i64 %M, i64 %N) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %entry, %for.inc17
+  %B.addr.04 = phi i32* [ %B, %entry ], [ %scevgep, %for.inc17 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc18, %for.inc17 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.cond1.preheader, %for.body3
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i32* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = mul nsw i64 %i.03, 5
+  %mul4 = mul nsw i64 %j.02, 10
+  %mul5 = mul nsw i64 %mul4, %M
+  %add = add nsw i64 %mul, %mul5
+  %mul6 = mul nsw i64 %M, 9
+  %mul7 = mul nsw i64 %mul6, %N
+  %add8 = add nsw i64 %add, %mul7
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add8
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul9 = mul nsw i64 %i.03, 15
+  %mul10 = mul nsw i64 %j.02, 20
+  %mul11 = mul nsw i64 %mul10, %M
+  %add12 = add nsw i64 %mul9, %mul11
+  %mul13 = mul nsw i64 %N, 21
+  %mul14 = mul nsw i64 %mul13, %M
+  %sub = sub nsw i64 %add12, %mul14
+  %add15 = add nsw i64 %sub, 5
+  %arrayidx16 = getelementptr inbounds i32* %A, i64 %add15
+  %0 = load i32* %arrayidx16, align 4
+; CHECK: da analyze - flow [<> *]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.11, i64 1
+  store i32 %0, i32* %B.addr.11, align 4
+  %inc = add nsw i64 %j.02, 1
+  %exitcond = icmp ne i64 %inc, 100
+  br i1 %exitcond, label %for.body3, label %for.inc17
+
+for.inc17:                                        ; preds = %for.body3
+  %scevgep = getelementptr i32* %B.addr.04, i64 100
+  %inc18 = add nsw i64 %i.03, 1
+  %exitcond5 = icmp ne i64 %inc18, 100
+  br i1 %exitcond5, label %for.cond1.preheader, label %for.end19
+
+for.end19:                                        ; preds = %for.inc17
+  ret void
+}
+
+
+;;  void gcd6(long int n, int A[][n], int *B) {
+;;    for (long int i = 0; i < n; i++)
+;;      for (long int j = 0; j < n; j++) {
+;;        A[2*i][4*j] = i;
+;;        *B++ = A[8*i][6*j + 1];
+
+define void @gcd6(i64 %n, i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  %cmp4 = icmp sgt i64 %n, 0
+  br i1 %cmp4, label %for.cond1.preheader.preheader, label %for.end12
+
+for.cond1.preheader.preheader:                    ; preds = %entry
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %for.cond1.preheader.preheader, %for.inc10
+  %i.06 = phi i64 [ %inc11, %for.inc10 ], [ 0, %for.cond1.preheader.preheader ]
+  %B.addr.05 = phi i32* [ %B.addr.1.lcssa, %for.inc10 ], [ %B, %for.cond1.preheader.preheader ]
+  %cmp21 = icmp sgt i64 %n, 0
+  br i1 %cmp21, label %for.body3.preheader, label %for.inc10
+
+for.body3.preheader:                              ; preds = %for.cond1.preheader
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.body3.preheader, %for.body3
+  %j.03 = phi i64 [ %inc, %for.body3 ], [ 0, %for.body3.preheader ]
+  %B.addr.12 = phi i32* [ %incdec.ptr, %for.body3 ], [ %B.addr.05, %for.body3.preheader ]
+  %conv = trunc i64 %i.06 to i32
+  %mul = shl nsw i64 %j.03, 2
+  %mul4 = shl nsw i64 %i.06, 1
+  %0 = mul nsw i64 %mul4, %n
+  %arrayidx.sum = add i64 %0, %mul
+  %arrayidx5 = getelementptr inbounds i32* %A, i64 %arrayidx.sum
+  store i32 %conv, i32* %arrayidx5, align 4
+  %mul6 = mul nsw i64 %j.03, 6
+  %add7 = or i64 %mul6, 1
+  %mul7 = shl nsw i64 %i.06, 3
+  %1 = mul nsw i64 %mul7, %n
+  %arrayidx8.sum = add i64 %1, %add7
+  %arrayidx9 = getelementptr inbounds i32* %A, i64 %arrayidx8.sum
+  %2 = load i32* %arrayidx9, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.12, i64 1
+  store i32 %2, i32* %B.addr.12, align 4
+  %inc = add nsw i64 %j.03, 1
+  %exitcond = icmp ne i64 %inc, %n
+  br i1 %exitcond, label %for.body3, label %for.inc10.loopexit
+
+for.inc10.loopexit:                               ; preds = %for.body3
+  %scevgep = getelementptr i32* %B.addr.05, i64 %n
+  br label %for.inc10
+
+for.inc10:                                        ; preds = %for.inc10.loopexit, %for.cond1.preheader
+  %B.addr.1.lcssa = phi i32* [ %B.addr.05, %for.cond1.preheader ], [ %scevgep, %for.inc10.loopexit ]
+  %inc11 = add nsw i64 %i.06, 1
+  %exitcond8 = icmp ne i64 %inc11, %n
+  br i1 %exitcond8, label %for.cond1.preheader, label %for.end12.loopexit
+
+for.end12.loopexit:                               ; preds = %for.inc10
+  br label %for.end12
+
+for.end12:                                        ; preds = %for.end12.loopexit, %entry
+  ret void
+}
+
+
+;;  void gcd7(int n, int A[][n], int *B) {
+;;    for (int i = 0; i < n; i++)
+;;      for (int j = 0; j < n; j++) {
+;;        A[2*i][4*j] = i;
+;;        *B++ = A[8*i][6*j + 1];
+
+define void @gcd7(i32 %n, i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  %0 = zext i32 %n to i64
+  %cmp4 = icmp sgt i32 %n, 0
+  br i1 %cmp4, label %for.cond1.preheader.preheader, label %for.end15
+
+for.cond1.preheader.preheader:                    ; preds = %entry
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %for.cond1.preheader.preheader, %for.inc13
+  %indvars.iv8 = phi i64 [ 0, %for.cond1.preheader.preheader ], [ %indvars.iv.next9, %for.inc13 ]
+  %B.addr.05 = phi i32* [ %B.addr.1.lcssa, %for.inc13 ], [ %B, %for.cond1.preheader.preheader ]
+  %1 = add i32 %n, -1
+  %2 = zext i32 %1 to i64
+  %3 = add i64 %2, 1
+  %cmp21 = icmp sgt i32 %n, 0
+  br i1 %cmp21, label %for.body3.preheader, label %for.inc13
+
+for.body3.preheader:                              ; preds = %for.cond1.preheader
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.body3.preheader, %for.body3
+  %indvars.iv = phi i64 [ 0, %for.body3.preheader ], [ %indvars.iv.next, %for.body3 ]
+  %B.addr.12 = phi i32* [ %incdec.ptr, %for.body3 ], [ %B.addr.05, %for.body3.preheader ]
+  %4 = trunc i64 %indvars.iv to i32
+  %mul = shl nsw i32 %4, 2
+  %idxprom = sext i32 %mul to i64
+  %5 = trunc i64 %indvars.iv8 to i32
+  %mul4 = shl nsw i32 %5, 1
+  %idxprom5 = sext i32 %mul4 to i64
+  %6 = mul nsw i64 %idxprom5, %0
+  %arrayidx.sum = add i64 %6, %idxprom
+  %arrayidx6 = getelementptr inbounds i32* %A, i64 %arrayidx.sum
+  %7 = trunc i64 %indvars.iv8 to i32
+  store i32 %7, i32* %arrayidx6, align 4
+  %8 = trunc i64 %indvars.iv to i32
+  %mul7 = mul nsw i32 %8, 6
+  %add7 = or i32 %mul7, 1
+  %idxprom8 = sext i32 %add7 to i64
+  %9 = trunc i64 %indvars.iv8 to i32
+  %mul9 = shl nsw i32 %9, 3
+  %idxprom10 = sext i32 %mul9 to i64
+  %10 = mul nsw i64 %idxprom10, %0
+  %arrayidx11.sum = add i64 %10, %idxprom8
+  %arrayidx12 = getelementptr inbounds i32* %A, i64 %arrayidx11.sum
+  %11 = load i32* %arrayidx12, align 4
+; CHECK: da analyze - flow [* *|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.12, i64 1
+  store i32 %11, i32* %B.addr.12, align 4
+  %indvars.iv.next = add i64 %indvars.iv, 1
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+  %exitcond = icmp ne i32 %lftr.wideiv, %n
+  br i1 %exitcond, label %for.body3, label %for.inc13.loopexit
+
+for.inc13.loopexit:                               ; preds = %for.body3
+  %scevgep = getelementptr i32* %B.addr.05, i64 %3
+  br label %for.inc13
+
+for.inc13:                                        ; preds = %for.inc13.loopexit, %for.cond1.preheader
+  %B.addr.1.lcssa = phi i32* [ %B.addr.05, %for.cond1.preheader ], [ %scevgep, %for.inc13.loopexit ]
+  %indvars.iv.next9 = add i64 %indvars.iv8, 1
+  %lftr.wideiv10 = trunc i64 %indvars.iv.next9 to i32
+  %exitcond11 = icmp ne i32 %lftr.wideiv10, %n
+  br i1 %exitcond11, label %for.cond1.preheader, label %for.end15.loopexit
+
+for.end15.loopexit:                               ; preds = %for.inc13
+  br label %for.end15
+
+for.end15:                                        ; preds = %for.end15.loopexit, %entry
+  ret void
+}
+
+
+;;  void gcd8(int n, int *A, int *B) {
+;;    for (int i = 0; i < n; i++)
+;;      for (int j = 0; j < n; j++) {
+;;        A[n*2*i + 4*j] = i;
+;;        *B++ = A[n*8*i + 6*j + 1];
+
+define void @gcd8(i32 %n, i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  %cmp4 = icmp sgt i32 %n, 0
+  br i1 %cmp4, label %for.cond1.preheader.preheader, label %for.end15
+
+for.cond1.preheader.preheader:                    ; preds = %entry
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %for.cond1.preheader.preheader, %for.inc13
+  %i.06 = phi i32 [ %inc14, %for.inc13 ], [ 0, %for.cond1.preheader.preheader ]
+  %B.addr.05 = phi i32* [ %B.addr.1.lcssa, %for.inc13 ], [ %B, %for.cond1.preheader.preheader ]
+  %0 = add i32 %n, -1
+  %1 = zext i32 %0 to i64
+  %2 = add i64 %1, 1
+  %cmp21 = icmp sgt i32 %n, 0
+  br i1 %cmp21, label %for.body3.preheader, label %for.inc13
+
+for.body3.preheader:                              ; preds = %for.cond1.preheader
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.body3.preheader, %for.body3
+  %indvars.iv = phi i64 [ 0, %for.body3.preheader ], [ %indvars.iv.next, %for.body3 ]
+  %B.addr.12 = phi i32* [ %incdec.ptr, %for.body3 ], [ %B.addr.05, %for.body3.preheader ]
+  %mul = shl nsw i32 %n, 1
+  %mul4 = mul nsw i32 %mul, %i.06
+  %3 = trunc i64 %indvars.iv to i32
+  %mul5 = shl nsw i32 %3, 2
+  %add = add nsw i32 %mul4, %mul5
+  %idxprom = sext i32 %add to i64
+  %arrayidx = getelementptr inbounds i32* %A, i64 %idxprom
+  store i32 %i.06, i32* %arrayidx, align 4
+  %mul6 = shl nsw i32 %n, 3
+  %mul7 = mul nsw i32 %mul6, %i.06
+  %4 = trunc i64 %indvars.iv to i32
+  %mul8 = mul nsw i32 %4, 6
+  %add9 = add nsw i32 %mul7, %mul8
+  %add10 = or i32 %add9, 1
+  %idxprom11 = sext i32 %add10 to i64
+  %arrayidx12 = getelementptr inbounds i32* %A, i64 %idxprom11
+  %5 = load i32* %arrayidx12, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.12, i64 1
+  store i32 %5, i32* %B.addr.12, align 4
+  %indvars.iv.next = add i64 %indvars.iv, 1
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+  %exitcond = icmp ne i32 %lftr.wideiv, %n
+  br i1 %exitcond, label %for.body3, label %for.inc13.loopexit
+
+for.inc13.loopexit:                               ; preds = %for.body3
+  %scevgep = getelementptr i32* %B.addr.05, i64 %2
+  br label %for.inc13
+
+for.inc13:                                        ; preds = %for.inc13.loopexit, %for.cond1.preheader
+  %B.addr.1.lcssa = phi i32* [ %B.addr.05, %for.cond1.preheader ], [ %scevgep, %for.inc13.loopexit ]
+  %inc14 = add nsw i32 %i.06, 1
+  %exitcond7 = icmp ne i32 %inc14, %n
+  br i1 %exitcond7, label %for.cond1.preheader, label %for.end15.loopexit
+
+for.end15.loopexit:                               ; preds = %for.inc13
+  br label %for.end15
+
+for.end15:                                        ; preds = %for.end15.loopexit, %entry
+  ret void
+}
+
+
+;;  void gcd9(unsigned n, int A[][n], int *B) {
+;;    for (unsigned i = 0; i < n; i++)
+;;      for (unsigned j = 0; j < n; j++) {
+;;        A[2*i][4*j] = i;
+;;        *B++ = A[8*i][6*j + 1];
+
+define void @gcd9(i32 %n, i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  %0 = zext i32 %n to i64
+  %cmp4 = icmp eq i32 %n, 0
+  br i1 %cmp4, label %for.end15, label %for.cond1.preheader.preheader
+
+for.cond1.preheader.preheader:                    ; preds = %entry
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %for.cond1.preheader.preheader, %for.inc13
+  %indvars.iv8 = phi i64 [ 0, %for.cond1.preheader.preheader ], [ %indvars.iv.next9, %for.inc13 ]
+  %B.addr.05 = phi i32* [ %B.addr.1.lcssa, %for.inc13 ], [ %B, %for.cond1.preheader.preheader ]
+  %1 = add i32 %n, -1
+  %2 = zext i32 %1 to i64
+  %3 = add i64 %2, 1
+  %cmp21 = icmp eq i32 %n, 0
+  br i1 %cmp21, label %for.inc13, label %for.body3.preheader
+
+for.body3.preheader:                              ; preds = %for.cond1.preheader
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.body3.preheader, %for.body3
+  %indvars.iv = phi i64 [ 0, %for.body3.preheader ], [ %indvars.iv.next, %for.body3 ]
+  %B.addr.12 = phi i32* [ %incdec.ptr, %for.body3 ], [ %B.addr.05, %for.body3.preheader ]
+  %4 = trunc i64 %indvars.iv to i32
+  %mul = shl i32 %4, 2
+  %idxprom = zext i32 %mul to i64
+  %5 = trunc i64 %indvars.iv8 to i32
+  %mul4 = shl i32 %5, 1
+  %idxprom5 = zext i32 %mul4 to i64
+  %6 = mul nsw i64 %idxprom5, %0
+  %arrayidx.sum = add i64 %6, %idxprom
+  %arrayidx6 = getelementptr inbounds i32* %A, i64 %arrayidx.sum
+  %7 = trunc i64 %indvars.iv8 to i32
+  store i32 %7, i32* %arrayidx6, align 4
+  %8 = trunc i64 %indvars.iv to i32
+  %mul7 = mul i32 %8, 6
+  %add7 = or i32 %mul7, 1
+  %idxprom8 = zext i32 %add7 to i64
+  %9 = trunc i64 %indvars.iv8 to i32
+  %mul9 = shl i32 %9, 3
+  %idxprom10 = zext i32 %mul9 to i64
+  %10 = mul nsw i64 %idxprom10, %0
+  %arrayidx11.sum = add i64 %10, %idxprom8
+  %arrayidx12 = getelementptr inbounds i32* %A, i64 %arrayidx11.sum
+  %11 = load i32* %arrayidx12, align 4
+; CHECK: da analyze - flow [* *|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.12, i64 1
+  store i32 %11, i32* %B.addr.12, align 4
+  %indvars.iv.next = add i64 %indvars.iv, 1
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+  %exitcond = icmp ne i32 %lftr.wideiv, %n
+  br i1 %exitcond, label %for.body3, label %for.inc13.loopexit
+
+for.inc13.loopexit:                               ; preds = %for.body3
+  %scevgep = getelementptr i32* %B.addr.05, i64 %3
+  br label %for.inc13
+
+for.inc13:                                        ; preds = %for.inc13.loopexit, %for.cond1.preheader
+  %B.addr.1.lcssa = phi i32* [ %B.addr.05, %for.cond1.preheader ], [ %scevgep, %for.inc13.loopexit ]
+  %indvars.iv.next9 = add i64 %indvars.iv8, 1
+  %lftr.wideiv10 = trunc i64 %indvars.iv.next9 to i32
+  %exitcond11 = icmp ne i32 %lftr.wideiv10, %n
+  br i1 %exitcond11, label %for.cond1.preheader, label %for.end15.loopexit
+
+for.end15.loopexit:                               ; preds = %for.inc13
+  br label %for.end15
+
+for.end15:                                        ; preds = %for.end15.loopexit, %entry
+  ret void
+}

test/Analysis/DependenceAnalysis/Preliminary.ll

@@ -0,0 +1,469 @@
+; RUN: opt < %s -analyze -basicaa -indvars -da | FileCheck %s
+
+; This series of tests is more interesting when debugging is enabled.
+
+; ModuleID = 'Preliminary.bc'
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.6.0"
+
+
+;; may alias
+;; int p0(int n, int *A, int *B) {
+;;  A[0] = n;
+;;  return B[1];
+
+define i32 @p0(i32 %n, i32* %A, i32* %B) nounwind uwtable ssp {
+entry:
+  store i32 %n, i32* %A, align 4
+  %arrayidx1 = getelementptr inbounds i32* %B, i64 1
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - confused!
+  ret i32 %0
+}
+
+
+;; no alias
+;; int p1(int n, int *restrict A, int *restrict B) {
+;;  A[0] = n;
+;;  return B[1];
+
+define i32 @p1(i32 %n, i32* noalias %A, i32* noalias %B) nounwind uwtable ssp {
+entry:
+  store i32 %n, i32* %A, align 4
+  %arrayidx1 = getelementptr inbounds i32* %B, i64 1
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - none!
+  ret i32 %0
+}
+
+;; check loop nesting levels
+;;  for (long int i = 0; i < n; i++)
+;;    for (long int j = 0; j < n; j++)
+;;      for (long int k = 0; k < n; k++)
+;;        A[i][j][k] = ...
+;;      for (long int k = 0; k < n; k++)
+;;        ... = A[i + 3][j + 2][k + 1];
+
+define void @p2(i64 %n, [100 x [100 x i64]]* %A, i64* %B) nounwind uwtable ssp {
+entry:
+  %cmp10 = icmp sgt i64 %n, 0
+  br i1 %cmp10, label %for.cond1.preheader, label %for.end26
+
+for.cond1.preheader:                              ; preds = %for.inc24, %entry
+  %B.addr.012 = phi i64* [ %B.addr.1.lcssa, %for.inc24 ], [ %B, %entry ]
+  %i.011 = phi i64 [ %inc25, %for.inc24 ], [ 0, %entry ]
+  %cmp26 = icmp sgt i64 %n, 0
+  br i1 %cmp26, label %for.cond4.preheader, label %for.inc24
+
+for.cond4.preheader:                              ; preds = %for.inc21, %for.cond1.preheader
+  %B.addr.18 = phi i64* [ %B.addr.2.lcssa, %for.inc21 ], [ %B.addr.012, %for.cond1.preheader ]
+  %j.07 = phi i64 [ %inc22, %for.inc21 ], [ 0, %for.cond1.preheader ]
+  %cmp51 = icmp sgt i64 %n, 0
+  br i1 %cmp51, label %for.body6, label %for.cond10.loopexit
+
+for.body6:                                        ; preds = %for.body6, %for.cond4.preheader
+  %k.02 = phi i64 [ %inc, %for.body6 ], [ 0, %for.cond4.preheader ]
+  %arrayidx8 = getelementptr inbounds [100 x [100 x i64]]* %A, i64 %i.011, i64 %j.07, i64 %k.02
+  store i64 %i.011, i64* %arrayidx8, align 8
+  %inc = add nsw i64 %k.02, 1
+  %cmp5 = icmp slt i64 %inc, %n
+  br i1 %cmp5, label %for.body6, label %for.cond10.loopexit
+
+for.cond10.loopexit:                              ; preds = %for.body6, %for.cond4.preheader
+  %cmp113 = icmp sgt i64 %n, 0
+  br i1 %cmp113, label %for.body12, label %for.inc21
+
+for.body12:                                       ; preds = %for.body12, %for.cond10.loopexit
+  %k9.05 = phi i64 [ %inc19, %for.body12 ], [ 0, %for.cond10.loopexit ]
+  %B.addr.24 = phi i64* [ %incdec.ptr, %for.body12 ], [ %B.addr.18, %for.cond10.loopexit ]
+  %add = add nsw i64 %k9.05, 1
+  %add13 = add nsw i64 %j.07, 2
+  %add14 = add nsw i64 %i.011, 3
+  %arrayidx17 = getelementptr inbounds [100 x [100 x i64]]* %A, i64 %add14, i64 %add13, i64 %add
+  %0 = load i64* %arrayidx17, align 8
+; CHECK: da analyze - flow [-3 -2]!
+  %incdec.ptr = getelementptr inbounds i64* %B.addr.24, i64 1
+  store i64 %0, i64* %B.addr.24, align 8
+  %inc19 = add nsw i64 %k9.05, 1
+  %cmp11 = icmp slt i64 %inc19, %n
+  br i1 %cmp11, label %for.body12, label %for.inc21
+
+for.inc21:                                        ; preds = %for.body12, %for.cond10.loopexit
+  %B.addr.2.lcssa = phi i64* [ %B.addr.18, %for.cond10.loopexit ], [ %incdec.ptr, %for.body12 ]
+  %inc22 = add nsw i64 %j.07, 1
+  %cmp2 = icmp slt i64 %inc22, %n
+  br i1 %cmp2, label %for.cond4.preheader, label %for.inc24
+
+for.inc24:                                        ; preds = %for.inc21, %for.cond1.preheader
+  %B.addr.1.lcssa = phi i64* [ %B.addr.012, %for.cond1.preheader ], [ %B.addr.2.lcssa, %for.inc21 ]
+  %inc25 = add nsw i64 %i.011, 1
+  %cmp = icmp slt i64 %inc25, %n
+  br i1 %cmp, label %for.cond1.preheader, label %for.end26
+
+for.end26:                                        ; preds = %for.inc24, %entry
+  ret void
+}
+
+
+;; classify subscripts
+;;  for (long int i = 0; i < n; i++)
+;;  for (long int j = 0; j < n; j++)
+;;  for (long int k = 0; k < n; k++)
+;;  for (long int l = 0; l < n; l++)
+;;  for (long int m = 0; m < n; m++)
+;;  for (long int o = 0; o < n; o++)
+;;  for (long int p = 0; p < n; p++)
+;;  for (long int q = 0; q < n; q++)
+;;  for (long int r = 0; r < n; r++)
+;;  for (long int s = 0; s < n; s++)
+;;  for (long int u = 0; u < n; u++)
+;;  for (long int t = 0; t < n; t++) {
+;;          A[i - 3] [j] [2] [k-1] [2*l + 1] [m] [p + q] [r + s] = ...
+;;    ... = A[i + 3] [2] [u] [1-k] [3*l - 1] [o] [1 + n] [t + 2];
+
+define void @p3(i64 %n, [100 x [100 x [100 x [100 x [100 x [100 x [100 x i64]]]]]]]* %A, i64* %B) nounwind uwtable ssp {
+entry:
+  %cmp44 = icmp sgt i64 %n, 0
+  br i1 %cmp44, label %for.cond1.preheader, label %for.end90
+
+for.cond1.preheader:                              ; preds = %for.inc88, %entry
+  %B.addr.046 = phi i64* [ %B.addr.1.lcssa, %for.inc88 ], [ %B, %entry ]
+  %i.045 = phi i64 [ %inc89, %for.inc88 ], [ 0, %entry ]
+  %cmp240 = icmp sgt i64 %n, 0
+  br i1 %cmp240, label %for.cond4.preheader, label %for.inc88
+
+for.cond4.preheader:                              ; preds = %for.inc85, %for.cond1.preheader
+  %B.addr.142 = phi i64* [ %B.addr.2.lcssa, %for.inc85 ], [ %B.addr.046, %for.cond1.preheader ]
+  %j.041 = phi i64 [ %inc86, %for.inc85 ], [ 0, %for.cond1.preheader ]
+  %cmp536 = icmp sgt i64 %n, 0
+  br i1 %cmp536, label %for.cond7.preheader, label %for.inc85
+
+for.cond7.preheader:                              ; preds = %for.inc82, %for.cond4.preheader
+  %B.addr.238 = phi i64* [ %B.addr.3.lcssa, %for.inc82 ], [ %B.addr.142, %for.cond4.preheader ]
+  %k.037 = phi i64 [ %inc83, %for.inc82 ], [ 0, %for.cond4.preheader ]
+  %cmp832 = icmp sgt i64 %n, 0
+  br i1 %cmp832, label %for.cond10.preheader, label %for.inc82
+
+for.cond10.preheader:                             ; preds = %for.inc79, %for.cond7.preheader
+  %B.addr.334 = phi i64* [ %B.addr.4.lcssa, %for.inc79 ], [ %B.addr.238, %for.cond7.preheader ]
+  %l.033 = phi i64 [ %inc80, %for.inc79 ], [ 0, %for.cond7.preheader ]
+  %cmp1128 = icmp sgt i64 %n, 0
+  br i1 %cmp1128, label %for.cond13.preheader, label %for.inc79
+
+for.cond13.preheader:                             ; preds = %for.inc76, %for.cond10.preheader
+  %B.addr.430 = phi i64* [ %B.addr.5.lcssa, %for.inc76 ], [ %B.addr.334, %for.cond10.preheader ]
+  %m.029 = phi i64 [ %inc77, %for.inc76 ], [ 0, %for.cond10.preheader ]
+  %cmp1424 = icmp sgt i64 %n, 0
+  br i1 %cmp1424, label %for.cond16.preheader, label %for.inc76
+
+for.cond16.preheader:                             ; preds = %for.inc73, %for.cond13.preheader
+  %B.addr.526 = phi i64* [ %B.addr.6.lcssa, %for.inc73 ], [ %B.addr.430, %for.cond13.preheader ]
+  %o.025 = phi i64 [ %inc74, %for.inc73 ], [ 0, %for.cond13.preheader ]
+  %cmp1720 = icmp sgt i64 %n, 0
+  br i1 %cmp1720, label %for.cond19.preheader, label %for.inc73
+
+for.cond19.preheader:                             ; preds = %for.inc70, %for.cond16.preheader
+  %B.addr.622 = phi i64* [ %B.addr.7.lcssa, %for.inc70 ], [ %B.addr.526, %for.cond16.preheader ]
+  %p.021 = phi i64 [ %inc71, %for.inc70 ], [ 0, %for.cond16.preheader ]
+  %cmp2016 = icmp sgt i64 %n, 0
+  br i1 %cmp2016, label %for.cond22.preheader, label %for.inc70
+
+for.cond22.preheader:                             ; preds = %for.inc67, %for.cond19.preheader
+  %B.addr.718 = phi i64* [ %B.addr.8.lcssa, %for.inc67 ], [ %B.addr.622, %for.cond19.preheader ]
+  %q.017 = phi i64 [ %inc68, %for.inc67 ], [ 0, %for.cond19.preheader ]
+  %cmp2312 = icmp sgt i64 %n, 0
+  br i1 %cmp2312, label %for.cond25.preheader, label %for.inc67
+
+for.cond25.preheader:                             ; preds = %for.inc64, %for.cond22.preheader
+  %B.addr.814 = phi i64* [ %B.addr.9.lcssa, %for.inc64 ], [ %B.addr.718, %for.cond22.preheader ]
+  %r.013 = phi i64 [ %inc65, %for.inc64 ], [ 0, %for.cond22.preheader ]
+  %cmp268 = icmp sgt i64 %n, 0
+  br i1 %cmp268, label %for.cond28.preheader, label %for.inc64
+
+for.cond28.preheader:                             ; preds = %for.inc61, %for.cond25.preheader
+  %B.addr.910 = phi i64* [ %B.addr.10.lcssa, %for.inc61 ], [ %B.addr.814, %for.cond25.preheader ]
+  %s.09 = phi i64 [ %inc62, %for.inc61 ], [ 0, %for.cond25.preheader ]
+  %cmp294 = icmp sgt i64 %n, 0
+  br i1 %cmp294, label %for.cond31.preheader, label %for.inc61
+
+for.cond31.preheader:                             ; preds = %for.inc58, %for.cond28.preheader
+  %u.06 = phi i64 [ %inc59, %for.inc58 ], [ 0, %for.cond28.preheader ]
+  %B.addr.105 = phi i64* [ %B.addr.11.lcssa, %for.inc58 ], [ %B.addr.910, %for.cond28.preheader ]
+  %cmp321 = icmp sgt i64 %n, 0
+  br i1 %cmp321, label %for.body33, label %for.inc58
+
+for.body33:                                       ; preds = %for.body33, %for.cond31.preheader
+  %t.03 = phi i64 [ %inc, %for.body33 ], [ 0, %for.cond31.preheader ]
+  %B.addr.112 = phi i64* [ %incdec.ptr, %for.body33 ], [ %B.addr.105, %for.cond31.preheader ]
+  %add = add nsw i64 %r.013, %s.09
+  %add34 = add nsw i64 %p.021, %q.017
+  %mul = shl nsw i64 %l.033, 1
+  %add3547 = or i64 %mul, 1
+  %sub = add nsw i64 %k.037, -1
+  %sub36 = add nsw i64 %i.045, -3
+  %arrayidx43 = getelementptr inbounds [100 x [100 x [100 x [100 x [100 x [100 x [100 x i64]]]]]]]* %A, i64 %sub36, i64 %j.041, i64 2, i64 %sub, i64 %add3547, i64 %m.029, i64 %add34, i64 %add
+  store i64 %i.045, i64* %arrayidx43, align 8
+  %add44 = add nsw i64 %t.03, 2
+  %add45 = add nsw i64 %n, 1
+  %mul46 = mul nsw i64 %l.033, 3
+  %sub47 = add nsw i64 %mul46, -1
+  %sub48 = sub nsw i64 1, %k.037
+  %add49 = add nsw i64 %i.045, 3
+  %arrayidx57 = getelementptr inbounds [100 x [100 x [100 x [100 x [100 x [100 x [100 x i64]]]]]]]* %A, i64 %add49, i64 2, i64 %u.06, i64 %sub48, i64 %sub47, i64 %o.025, i64 %add45, i64 %add44
+  %0 = load i64* %arrayidx57, align 8
+; CHECK: da analyze - flow [-6 * * => * * * * * * * *] splitable!
+; CHECK: da analyze - split level = 3, iteration = 1!
+  %incdec.ptr = getelementptr inbounds i64* %B.addr.112, i64 1
+  store i64 %0, i64* %B.addr.112, align 8
+  %inc = add nsw i64 %t.03, 1
+  %cmp32 = icmp slt i64 %inc, %n
+  br i1 %cmp32, label %for.body33, label %for.inc58
+
+for.inc58:                                        ; preds = %for.body33, %for.cond31.preheader
+  %B.addr.11.lcssa = phi i64* [ %B.addr.105, %for.cond31.preheader ], [ %incdec.ptr, %for.body33 ]
+  %inc59 = add nsw i64 %u.06, 1
+  %cmp29 = icmp slt i64 %inc59, %n
+  br i1 %cmp29, label %for.cond31.preheader, label %for.inc61
+
+for.inc61:                                        ; preds = %for.inc58, %for.cond28.preheader
+  %B.addr.10.lcssa = phi i64* [ %B.addr.910, %for.cond28.preheader ], [ %B.addr.11.lcssa, %for.inc58 ]
+  %inc62 = add nsw i64 %s.09, 1
+  %cmp26 = icmp slt i64 %inc62, %n
+  br i1 %cmp26, label %for.cond28.preheader, label %for.inc64
+
+for.inc64:                                        ; preds = %for.inc61, %for.cond25.preheader
+  %B.addr.9.lcssa = phi i64* [ %B.addr.814, %for.cond25.preheader ], [ %B.addr.10.lcssa, %for.inc61 ]
+  %inc65 = add nsw i64 %r.013, 1
+  %cmp23 = icmp slt i64 %inc65, %n
+  br i1 %cmp23, label %for.cond25.preheader, label %for.inc67
+
+for.inc67:                                        ; preds = %for.inc64, %for.cond22.preheader
+  %B.addr.8.lcssa = phi i64* [ %B.addr.718, %for.cond22.preheader ], [ %B.addr.9.lcssa, %for.inc64 ]
+  %inc68 = add nsw i64 %q.017, 1
+  %cmp20 = icmp slt i64 %inc68, %n
+  br i1 %cmp20, label %for.cond22.preheader, label %for.inc70
+
+for.inc70:                                        ; preds = %for.inc67, %for.cond19.preheader
+  %B.addr.7.lcssa = phi i64* [ %B.addr.622, %for.cond19.preheader ], [ %B.addr.8.lcssa, %for.inc67 ]
+  %inc71 = add nsw i64 %p.021, 1
+  %cmp17 = icmp slt i64 %inc71, %n
+  br i1 %cmp17, label %for.cond19.preheader, label %for.inc73
+
+for.inc73:                                        ; preds = %for.inc70, %for.cond16.preheader
+  %B.addr.6.lcssa = phi i64* [ %B.addr.526, %for.cond16.preheader ], [ %B.addr.7.lcssa, %for.inc70 ]
+  %inc74 = add nsw i64 %o.025, 1
+  %cmp14 = icmp slt i64 %inc74, %n
+  br i1 %cmp14, label %for.cond16.preheader, label %for.inc76
+
+for.inc76:                                        ; preds = %for.inc73, %for.cond13.preheader
+  %B.addr.5.lcssa = phi i64* [ %B.addr.430, %for.cond13.preheader ], [ %B.addr.6.lcssa, %for.inc73 ]
+  %inc77 = add nsw i64 %m.029, 1
+  %cmp11 = icmp slt i64 %inc77, %n
+  br i1 %cmp11, label %for.cond13.preheader, label %for.inc79
+
+for.inc79:                                        ; preds = %for.inc76, %for.cond10.preheader
+  %B.addr.4.lcssa = phi i64* [ %B.addr.334, %for.cond10.preheader ], [ %B.addr.5.lcssa, %for.inc76 ]
+  %inc80 = add nsw i64 %l.033, 1
+  %cmp8 = icmp slt i64 %inc80, %n
+  br i1 %cmp8, label %for.cond10.preheader, label %for.inc82
+
+for.inc82:                                        ; preds = %for.inc79, %for.cond7.preheader
+  %B.addr.3.lcssa = phi i64* [ %B.addr.238, %for.cond7.preheader ], [ %B.addr.4.lcssa, %for.inc79 ]
+  %inc83 = add nsw i64 %k.037, 1
+  %cmp5 = icmp slt i64 %inc83, %n
+  br i1 %cmp5, label %for.cond7.preheader, label %for.inc85
+
+for.inc85:                                        ; preds = %for.inc82, %for.cond4.preheader
+  %B.addr.2.lcssa = phi i64* [ %B.addr.142, %for.cond4.preheader ], [ %B.addr.3.lcssa, %for.inc82 ]
+  %inc86 = add nsw i64 %j.041, 1
+  %cmp2 = icmp slt i64 %inc86, %n
+  br i1 %cmp2, label %for.cond4.preheader, label %for.inc88
+
+for.inc88:                                        ; preds = %for.inc85, %for.cond1.preheader
+  %B.addr.1.lcssa = phi i64* [ %B.addr.046, %for.cond1.preheader ], [ %B.addr.2.lcssa, %for.inc85 ]
+  %inc89 = add nsw i64 %i.045, 1
+  %cmp = icmp slt i64 %inc89, %n
+  br i1 %cmp, label %for.cond1.preheader, label %for.end90
+
+for.end90:                                        ; preds = %for.inc88, %entry
+  ret void
+}
+
+
+;; cleanup around chars, shorts, ints
+;;void p4(int *A, int *B, long int n)
+;;  for (char i = 0; i < n; i++)
+;;    A[i + 2] = ...
+;;    ... = A[i];
+
+define void @p4(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  %cmp1 = icmp sgt i64 %n, 0
+  br i1 %cmp1, label %for.body, label %for.end
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i8 [ %inc, %for.body ], [ 0, %entry ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %entry ]
+  %conv2 = sext i8 %i.03 to i32
+  %conv3 = sext i8 %i.03 to i64
+  %add = add i64 %conv3, 2
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv2, i32* %arrayidx, align 4
+  %idxprom4 = sext i8 %i.03 to i64
+  %arrayidx5 = getelementptr inbounds i32* %A, i64 %idxprom4
+  %0 = load i32* %arrayidx5, align 4
+; CHECK: da analyze - flow [*|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc = add i8 %i.03, 1
+  %conv = sext i8 %inc to i64
+  %cmp = icmp slt i64 %conv, %n
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+
+;;void p5(int *A, int *B, long int n)
+;;  for (short i = 0; i < n; i++)
+;;    A[i + 2] = ...
+;;    ... = A[i];
+
+define void @p5(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  %cmp1 = icmp sgt i64 %n, 0
+  br i1 %cmp1, label %for.body, label %for.end
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i16 [ %inc, %for.body ], [ 0, %entry ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %entry ]
+  %conv2 = sext i16 %i.03 to i32
+  %conv3 = sext i16 %i.03 to i64
+  %add = add i64 %conv3, 2
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv2, i32* %arrayidx, align 4
+  %idxprom4 = sext i16 %i.03 to i64
+  %arrayidx5 = getelementptr inbounds i32* %A, i64 %idxprom4
+  %0 = load i32* %arrayidx5, align 4
+; CHECK: da analyze - flow [*|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc = add i16 %i.03, 1
+  %conv = sext i16 %inc to i64
+  %cmp = icmp slt i64 %conv, %n
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+
+;;void p6(int *A, int *B, long int n)
+;;  for (int i = 0; i < n; i++)
+;;    A[i + 2] = ...
+;;    ... = A[i];
+
+define void @p6(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  %cmp1 = icmp sgt i64 %n, 0
+  br i1 %cmp1, label %for.body, label %for.end
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %entry ]
+  %add = add nsw i32 %i.03, 2
+  %idxprom = sext i32 %add to i64
+  %arrayidx = getelementptr inbounds i32* %A, i64 %idxprom
+  store i32 %i.03, i32* %arrayidx, align 4
+  %idxprom2 = sext i32 %i.03 to i64
+  %arrayidx3 = getelementptr inbounds i32* %A, i64 %idxprom2
+  %0 = load i32* %arrayidx3, align 4
+; CHECK: da analyze - consistent flow [2]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc = add nsw i32 %i.03, 1
+  %conv = sext i32 %inc to i64
+  %cmp = icmp slt i64 %conv, %n
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+
+;;void p7(unsigned *A, unsigned *B,  char n)
+;;  A[n] = ...
+;;  ... = A[n + 1];
+
+define void @p7(i32* %A, i32* %B, i8 signext %n) nounwind uwtable ssp {
+entry:
+  %idxprom = sext i8 %n to i64
+  %arrayidx = getelementptr inbounds i32* %A, i64 %idxprom
+  store i32 0, i32* %arrayidx, align 4
+  %conv = sext i8 %n to i64
+  %add = add i64 %conv, 1
+  %arrayidx2 = getelementptr inbounds i32* %A, i64 %add
+  %0 = load i32* %arrayidx2, align 4
+; CHECK: da analyze - none!
+  store i32 %0, i32* %B, align 4
+  ret void
+}
+
+
+
+;;void p8(unsigned *A, unsigned *B,  short n)
+;;  A[n] = ...
+;;  ... = A[n + 1];
+
+define void @p8(i32* %A, i32* %B, i16 signext %n) nounwind uwtable ssp {
+entry:
+  %idxprom = sext i16 %n to i64
+  %arrayidx = getelementptr inbounds i32* %A, i64 %idxprom
+  store i32 0, i32* %arrayidx, align 4
+  %conv = sext i16 %n to i64
+  %add = add i64 %conv, 1
+  %arrayidx2 = getelementptr inbounds i32* %A, i64 %add
+  %0 = load i32* %arrayidx2, align 4
+; CHECK: da analyze - none!
+  store i32 %0, i32* %B, align 4
+  ret void
+}
+
+
+;;void p9(unsigned *A, unsigned *B,  int n)
+;;  A[n] = ...
+;;  ... = A[n + 1];
+
+define void @p9(i32* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  %idxprom = sext i32 %n to i64
+  %arrayidx = getelementptr inbounds i32* %A, i64 %idxprom
+  store i32 0, i32* %arrayidx, align 4
+  %add = add nsw i32 %n, 1
+  %idxprom1 = sext i32 %add to i64
+  %arrayidx2 = getelementptr inbounds i32* %A, i64 %idxprom1
+  %0 = load i32* %arrayidx2, align 4
+; CHECK: da analyze - none!
+  store i32 %0, i32* %B, align 4
+  ret void
+}
+
+
+;;void p10(unsigned *A, unsigned *B,  unsigned n)
+;;  A[n] = ...
+;;  ... = A[n + 1];
+
+define void @p10(i32* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  %idxprom = zext i32 %n to i64
+  %arrayidx = getelementptr inbounds i32* %A, i64 %idxprom
+  store i32 0, i32* %arrayidx, align 4
+  %add = add i32 %n, 1
+  %idxprom1 = zext i32 %add to i64
+  %arrayidx2 = getelementptr inbounds i32* %A, i64 %idxprom1
+  %0 = load i32* %arrayidx2, align 4
+; CHECK: da analyze - none!
+  store i32 %0, i32* %B, align 4
+  ret void
+}

test/Analysis/DependenceAnalysis/Propagating.ll

@@ -0,0 +1,467 @@
+; RUN: opt < %s -analyze -basicaa -da | FileCheck %s
+
+; ModuleID = 'Propagating.bc'
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.6.0"
+
+
+;;  for (long int i = 0; i < 100; i++)
+;;    for (long int j = 0; j < 100; j++)
+;;      A[i + 1][i + j] = i;
+;;      *B++ = A[i][i + j];
+
+define void @prop0([100 x i32]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %for.inc9, %entry
+  %B.addr.04 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.inc9 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc10, %for.inc9 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.body3, %for.cond1.preheader
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i32* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %conv = trunc i64 %i.03 to i32
+  %add = add nsw i64 %i.03, %j.02
+  %add4 = add nsw i64 %i.03, 1
+  %arrayidx5 = getelementptr inbounds [100 x i32]* %A, i64 %add4, i64 %add
+  store i32 %conv, i32* %arrayidx5, align 4
+  %add6 = add nsw i64 %i.03, %j.02
+  %arrayidx8 = getelementptr inbounds [100 x i32]* %A, i64 %i.03, i64 %add6
+  %0 = load i32* %arrayidx8, align 4
+; CHECK: da analyze - consistent flow [1 -1]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.11, i64 1
+  store i32 %0, i32* %B.addr.11, align 4
+  %inc = add nsw i64 %j.02, 1
+  %cmp2 = icmp slt i64 %inc, 100
+  br i1 %cmp2, label %for.body3, label %for.inc9
+
+for.inc9:                                         ; preds = %for.body3
+  %inc10 = add nsw i64 %i.03, 1
+  %cmp = icmp slt i64 %inc10, 100
+  br i1 %cmp, label %for.cond1.preheader, label %for.end11
+
+for.end11:                                        ; preds = %for.inc9
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 100; i++)
+;;    for (long int j = 0; j < 100; j++)
+;;      for (long int k = 0; k < 100; k++)
+;;        A[j - i][i + 1][j + k] = ...
+;;        ... = A[j - i][i][j + k];
+
+define void @prop1([100 x [100 x i32]]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %for.inc18, %entry
+  %B.addr.06 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.inc18 ]
+  %i.05 = phi i64 [ 0, %entry ], [ %inc19, %for.inc18 ]
+  br label %for.cond4.preheader
+
+for.cond4.preheader:                              ; preds = %for.inc15, %for.cond1.preheader
+  %B.addr.14 = phi i32* [ %B.addr.06, %for.cond1.preheader ], [ %incdec.ptr, %for.inc15 ]
+  %j.03 = phi i64 [ 0, %for.cond1.preheader ], [ %inc16, %for.inc15 ]
+  br label %for.body6
+
+for.body6:                                        ; preds = %for.body6, %for.cond4.preheader
+  %k.02 = phi i64 [ 0, %for.cond4.preheader ], [ %inc, %for.body6 ]
+  %B.addr.21 = phi i32* [ %B.addr.14, %for.cond4.preheader ], [ %incdec.ptr, %for.body6 ]
+  %conv = trunc i64 %i.05 to i32
+  %add = add nsw i64 %j.03, %k.02
+  %add7 = add nsw i64 %i.05, 1
+  %sub = sub nsw i64 %j.03, %i.05
+  %arrayidx9 = getelementptr inbounds [100 x [100 x i32]]* %A, i64 %sub, i64 %add7, i64 %add
+  store i32 %conv, i32* %arrayidx9, align 4
+  %add10 = add nsw i64 %j.03, %k.02
+  %sub11 = sub nsw i64 %j.03, %i.05
+  %arrayidx14 = getelementptr inbounds [100 x [100 x i32]]* %A, i64 %sub11, i64 %i.05, i64 %add10
+  %0 = load i32* %arrayidx14, align 4
+; CHECK: da analyze - consistent flow [1 1 -1]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.21, i64 1
+  store i32 %0, i32* %B.addr.21, align 4
+  %inc = add nsw i64 %k.02, 1
+  %cmp5 = icmp slt i64 %inc, 100
+  br i1 %cmp5, label %for.body6, label %for.inc15
+
+for.inc15:                                        ; preds = %for.body6
+  %inc16 = add nsw i64 %j.03, 1
+  %cmp2 = icmp slt i64 %inc16, 100
+  br i1 %cmp2, label %for.cond4.preheader, label %for.inc18
+
+for.inc18:                                        ; preds = %for.inc15
+  %inc19 = add nsw i64 %i.05, 1
+  %cmp = icmp slt i64 %inc19, 100
+  br i1 %cmp, label %for.cond1.preheader, label %for.end20
+
+for.end20:                                        ; preds = %for.inc18
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 100; i++)
+;;    for (long int j = 0; j < 100; j++)
+;;      A[i - 1][2*i] = ...
+;;      ... = A[i][i + j + 110];
+
+define void @prop2([100 x i32]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %for.inc8, %entry
+  %B.addr.04 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.inc8 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc9, %for.inc8 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.body3, %for.cond1.preheader
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i32* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = shl nsw i64 %i.03, 1
+  %sub = add nsw i64 %i.03, -1
+  %arrayidx4 = getelementptr inbounds [100 x i32]* %A, i64 %sub, i64 %mul
+  store i32 %conv, i32* %arrayidx4, align 4
+  %add = add nsw i64 %i.03, %j.02
+  %add5 = add nsw i64 %add, 110
+  %arrayidx7 = getelementptr inbounds [100 x i32]* %A, i64 %i.03, i64 %add5
+  %0 = load i32* %arrayidx7, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.11, i64 1
+  store i32 %0, i32* %B.addr.11, align 4
+  %inc = add nsw i64 %j.02, 1
+  %cmp2 = icmp slt i64 %inc, 100
+  br i1 %cmp2, label %for.body3, label %for.inc8
+
+for.inc8:                                         ; preds = %for.body3
+  %inc9 = add nsw i64 %i.03, 1
+  %cmp = icmp slt i64 %inc9, 100
+  br i1 %cmp, label %for.cond1.preheader, label %for.end10
+
+for.end10:                                        ; preds = %for.inc8
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 100; i++)
+;;    for (long int j = 0; j < 100; j++)
+;;      A[i][2*j + i] = ...
+;;      ... = A[i][2*j - i + 5];
+
+define void @prop3([100 x i32]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %for.inc9, %entry
+  %B.addr.04 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.inc9 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc10, %for.inc9 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.body3, %for.cond1.preheader
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i32* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = shl nsw i64 %j.02, 1
+  %add = add nsw i64 %mul, %i.03
+  %arrayidx4 = getelementptr inbounds [100 x i32]* %A, i64 %i.03, i64 %add
+  store i32 %conv, i32* %arrayidx4, align 4
+  %mul5 = shl nsw i64 %j.02, 1
+  %sub = sub nsw i64 %mul5, %i.03
+  %add6 = add nsw i64 %sub, 5
+  %arrayidx8 = getelementptr inbounds [100 x i32]* %A, i64 %i.03, i64 %add6
+  %0 = load i32* %arrayidx8, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.11, i64 1
+  store i32 %0, i32* %B.addr.11, align 4
+  %inc = add nsw i64 %j.02, 1
+  %cmp2 = icmp slt i64 %inc, 100
+  br i1 %cmp2, label %for.body3, label %for.inc9
+
+for.inc9:                                         ; preds = %for.body3
+  %inc10 = add nsw i64 %i.03, 1
+  %cmp = icmp slt i64 %inc10, 100
+  br i1 %cmp, label %for.cond1.preheader, label %for.end11
+
+for.end11:                                        ; preds = %for.inc9
+  ret void
+}
+
+
+;; propagate Distance
+;;  for (long int i = 0; i < 100; i++)
+;;    for (long int j = 0; j < 100; j++)
+;;      A[i + 2][2*i + j + 1] = ...
+;;      ... = A[i][2*i + j];
+
+define void @prop4([100 x i32]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %for.inc11, %entry
+  %B.addr.04 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.inc11 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc12, %for.inc11 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.body3, %for.cond1.preheader
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i32* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = shl nsw i64 %i.03, 1
+  %add = add nsw i64 %mul, %j.02
+  %add4 = add nsw i64 %add, 1
+  %add5 = add nsw i64 %i.03, 2
+  %arrayidx6 = getelementptr inbounds [100 x i32]* %A, i64 %add5, i64 %add4
+  store i32 %conv, i32* %arrayidx6, align 4
+  %mul7 = shl nsw i64 %i.03, 1
+  %add8 = add nsw i64 %mul7, %j.02
+  %arrayidx10 = getelementptr inbounds [100 x i32]* %A, i64 %i.03, i64 %add8
+  %0 = load i32* %arrayidx10, align 4
+; CHECK: da analyze - consistent flow [2 -3]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.11, i64 1
+  store i32 %0, i32* %B.addr.11, align 4
+  %inc = add nsw i64 %j.02, 1
+  %cmp2 = icmp slt i64 %inc, 100
+  br i1 %cmp2, label %for.body3, label %for.inc11
+
+for.inc11:                                        ; preds = %for.body3
+  %inc12 = add nsw i64 %i.03, 1
+  %cmp = icmp slt i64 %inc12, 100
+  br i1 %cmp, label %for.cond1.preheader, label %for.end13
+
+for.end13:                                        ; preds = %for.inc11
+  ret void
+}
+
+
+;; propagate Point
+;;  for (long int i = 0; i < 100; i++)
+;;    for (long int j = 0; j < 100; j++)
+;;      A[3*i - 18][22 - i][2*i + j] = ...
+;;      ... = A[i][i][3*i + j];
+
+define void @prop5([100 x [100 x i32]]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %for.inc13, %entry
+  %B.addr.04 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.inc13 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc14, %for.inc13 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.body3, %for.cond1.preheader
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i32* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = shl nsw i64 %i.03, 1
+  %add = add nsw i64 %mul, %j.02
+  %sub = sub nsw i64 22, %i.03
+  %mul4 = mul nsw i64 %i.03, 3
+  %sub5 = add nsw i64 %mul4, -18
+  %arrayidx7 = getelementptr inbounds [100 x [100 x i32]]* %A, i64 %sub5, i64 %sub, i64 %add
+  store i32 %conv, i32* %arrayidx7, align 4
+  %mul8 = mul nsw i64 %i.03, 3
+  %add9 = add nsw i64 %mul8, %j.02
+  %arrayidx12 = getelementptr inbounds [100 x [100 x i32]]* %A, i64 %i.03, i64 %i.03, i64 %add9
+  %0 = load i32* %arrayidx12, align 4
+; CHECK: da analyze - flow [< -16] splitable!
+; CHECK: da analyze - split level = 1, iteration = 11!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.11, i64 1
+  store i32 %0, i32* %B.addr.11, align 4
+  %inc = add nsw i64 %j.02, 1
+  %cmp2 = icmp slt i64 %inc, 100
+  br i1 %cmp2, label %for.body3, label %for.inc13
+
+for.inc13:                                        ; preds = %for.body3
+  %inc14 = add nsw i64 %i.03, 1
+  %cmp = icmp slt i64 %inc14, 100
+  br i1 %cmp, label %for.cond1.preheader, label %for.end15
+
+for.end15:                                        ; preds = %for.inc13
+  ret void
+}
+
+
+;; propagate Line
+;;  for (long int i = 0; i < 100; i++)
+;;    for (long int j = 0; j < 100; j++)
+;;      A[i + 1][4*i + j + 2] = ...
+;;      ... = A[2*i][8*i + j];
+
+define void @prop6([100 x i32]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %for.inc12, %entry
+  %B.addr.04 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.inc12 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc13, %for.inc12 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.body3, %for.cond1.preheader
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i32* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = shl nsw i64 %i.03, 2
+  %add = add nsw i64 %mul, %j.02
+  %add4 = add nsw i64 %add, 2
+  %add5 = add nsw i64 %i.03, 1
+  %arrayidx6 = getelementptr inbounds [100 x i32]* %A, i64 %add5, i64 %add4
+  store i32 %conv, i32* %arrayidx6, align 4
+  %mul7 = shl nsw i64 %i.03, 3
+  %add8 = add nsw i64 %mul7, %j.02
+  %mul9 = shl nsw i64 %i.03, 1
+  %arrayidx11 = getelementptr inbounds [100 x i32]* %A, i64 %mul9, i64 %add8
+  %0 = load i32* %arrayidx11, align 4
+; CHECK: da analyze - flow [=> -2]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.11, i64 1
+  store i32 %0, i32* %B.addr.11, align 4
+  %inc = add nsw i64 %j.02, 1
+  %cmp2 = icmp slt i64 %inc, 100
+  br i1 %cmp2, label %for.body3, label %for.inc12
+
+for.inc12:                                        ; preds = %for.body3
+  %inc13 = add nsw i64 %i.03, 1
+  %cmp = icmp slt i64 %inc13, 100
+  br i1 %cmp, label %for.cond1.preheader, label %for.end14
+
+for.end14:                                        ; preds = %for.inc12
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 100; i++)
+;;    for (long int j = 0; j < 100; j++)
+;;      A[2*i + 4][-5*i + j + 2] = ...
+;;      ... = A[-2*i + 20][5*i + j];
+
+define void @prop7([100 x i32]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %for.inc14, %entry
+  %B.addr.04 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.inc14 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc15, %for.inc14 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.body3, %for.cond1.preheader
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i32* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = mul nsw i64 %i.03, -5
+  %add = add nsw i64 %mul, %j.02
+  %add4 = add nsw i64 %add, 2
+  %mul5 = shl nsw i64 %i.03, 1
+  %add6 = add nsw i64 %mul5, 4
+  %arrayidx7 = getelementptr inbounds [100 x i32]* %A, i64 %add6, i64 %add4
+  store i32 %conv, i32* %arrayidx7, align 4
+  %mul8 = mul nsw i64 %i.03, 5
+  %add9 = add nsw i64 %mul8, %j.02
+  %mul10 = mul nsw i64 %i.03, -2
+  %add11 = add nsw i64 %mul10, 20
+  %arrayidx13 = getelementptr inbounds [100 x i32]* %A, i64 %add11, i64 %add9
+  %0 = load i32* %arrayidx13, align 4
+; CHECK: da analyze - flow [* -38] splitable!
+; CHECK: da analyze - split level = 1, iteration = 4!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.11, i64 1
+  store i32 %0, i32* %B.addr.11, align 4
+  %inc = add nsw i64 %j.02, 1
+  %cmp2 = icmp slt i64 %inc, 100
+  br i1 %cmp2, label %for.body3, label %for.inc14
+
+for.inc14:                                        ; preds = %for.body3
+  %inc15 = add nsw i64 %i.03, 1
+  %cmp = icmp slt i64 %inc15, 100
+  br i1 %cmp, label %for.cond1.preheader, label %for.end16
+
+for.end16:                                        ; preds = %for.inc14
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 100; i++)
+;;    for (long int j = 0; j < 100; j++)
+;;      A[4][j + 2] = ...
+;;      ... = A[-2*i + 4][5*i + j];
+
+define void @prop8([100 x i32]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %for.inc10, %entry
+  %B.addr.04 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.inc10 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc11, %for.inc10 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.body3, %for.cond1.preheader
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i32* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %conv = trunc i64 %i.03 to i32
+  %add = add nsw i64 %j.02, 2
+  %arrayidx4 = getelementptr inbounds [100 x i32]* %A, i64 4, i64 %add
+  store i32 %conv, i32* %arrayidx4, align 4
+  %mul = mul nsw i64 %i.03, 5
+  %add5 = add nsw i64 %mul, %j.02
+  %mul6 = mul nsw i64 %i.03, -2
+  %add7 = add nsw i64 %mul6, 4
+  %arrayidx9 = getelementptr inbounds [100 x i32]* %A, i64 %add7, i64 %add5
+  %0 = load i32* %arrayidx9, align 4
+; CHECK: da analyze - flow [p<= 2]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.11, i64 1
+  store i32 %0, i32* %B.addr.11, align 4
+  %inc = add nsw i64 %j.02, 1
+  %cmp2 = icmp slt i64 %inc, 100
+  br i1 %cmp2, label %for.body3, label %for.inc10
+
+for.inc10:                                        ; preds = %for.body3
+  %inc11 = add nsw i64 %i.03, 1
+  %cmp = icmp slt i64 %inc11, 100
+  br i1 %cmp, label %for.cond1.preheader, label %for.end12
+
+for.end12:                                        ; preds = %for.inc10
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 100; i++)
+;;    for (long int j = 0; j < 100; j++)
+;;      A[2*i + 4][5*i + j + 2] = ...
+;;      ... = A[4][j];
+
+define void @prop9([100 x i32]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %for.inc10, %entry
+  %B.addr.04 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.inc10 ]
+  %i.03 = phi i64 [ 0, %entry ], [ %inc11, %for.inc10 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.body3, %for.cond1.preheader
+  %j.02 = phi i64 [ 0, %for.cond1.preheader ], [ %inc, %for.body3 ]
+  %B.addr.11 = phi i32* [ %B.addr.04, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = mul nsw i64 %i.03, 5
+  %add = add nsw i64 %mul, %j.02
+  %add4 = add nsw i64 %add, 2
+  %mul5 = shl nsw i64 %i.03, 1
+  %add6 = add nsw i64 %mul5, 4
+  %arrayidx7 = getelementptr inbounds [100 x i32]* %A, i64 %add6, i64 %add4
+  store i32 %conv, i32* %arrayidx7, align 4
+  %arrayidx9 = getelementptr inbounds [100 x i32]* %A, i64 4, i64 %j.02
+  %0 = load i32* %arrayidx9, align 4
+; CHECK: da analyze - flow [p<= 2]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.11, i64 1
+  store i32 %0, i32* %B.addr.11, align 4
+  %inc = add nsw i64 %j.02, 1
+  %cmp2 = icmp slt i64 %inc, 100
+  br i1 %cmp2, label %for.body3, label %for.inc10
+
+for.inc10:                                        ; preds = %for.body3
+  %inc11 = add nsw i64 %i.03, 1
+  %cmp = icmp slt i64 %inc11, 100
+  br i1 %cmp, label %for.cond1.preheader, label %for.end12
+
+for.end12:                                        ; preds = %for.inc10
+  ret void
+}

test/Analysis/DependenceAnalysis/Separability.ll

@@ -0,0 +1,267 @@
+; RUN: opt < %s -analyze -basicaa -da | FileCheck %s
+
+; ModuleID = 'Separability.bc'
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.6.0"
+
+
+;;  for (long int i = 0; i < 50; i++)
+;;    for (long int j = 0; j < 50; j++)
+;;      for (long int k = 0; k < 50; k++)
+;;        for (long int l = 0; l < 50; l++)
+;;          A[n][i][j + k] = ...
+;;          ... = A[10][i + 10][2*j - l];
+
+define void @sep0([100 x [100 x i32]]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %for.inc22, %entry
+  %B.addr.08 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.inc22 ]
+  %i.07 = phi i64 [ 0, %entry ], [ %inc23, %for.inc22 ]
+  br label %for.cond4.preheader
+
+for.cond4.preheader:                              ; preds = %for.inc19, %for.cond1.preheader
+  %B.addr.16 = phi i32* [ %B.addr.08, %for.cond1.preheader ], [ %incdec.ptr, %for.inc19 ]
+  %j.05 = phi i64 [ 0, %for.cond1.preheader ], [ %inc20, %for.inc19 ]
+  br label %for.cond7.preheader
+
+for.cond7.preheader:                              ; preds = %for.inc16, %for.cond4.preheader
+  %B.addr.24 = phi i32* [ %B.addr.16, %for.cond4.preheader ], [ %incdec.ptr, %for.inc16 ]
+  %k.03 = phi i64 [ 0, %for.cond4.preheader ], [ %inc17, %for.inc16 ]
+  br label %for.body9
+
+for.body9:                                        ; preds = %for.body9, %for.cond7.preheader
+  %l.02 = phi i64 [ 0, %for.cond7.preheader ], [ %inc, %for.body9 ]
+  %B.addr.31 = phi i32* [ %B.addr.24, %for.cond7.preheader ], [ %incdec.ptr, %for.body9 ]
+  %conv = trunc i64 %i.07 to i32
+  %add = add nsw i64 %j.05, %k.03
+  %idxprom = sext i32 %n to i64
+  %arrayidx11 = getelementptr inbounds [100 x [100 x i32]]* %A, i64 %idxprom, i64 %i.07, i64 %add
+  store i32 %conv, i32* %arrayidx11, align 4
+  %mul = shl nsw i64 %j.05, 1
+  %sub = sub nsw i64 %mul, %l.02
+  %add12 = add nsw i64 %i.07, 10
+  %arrayidx15 = getelementptr inbounds [100 x [100 x i32]]* %A, i64 10, i64 %add12, i64 %sub
+  %0 = load i32* %arrayidx15, align 4
+; CHECK: da analyze - flow [-10 * * *]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.31, i64 1
+  store i32 %0, i32* %B.addr.31, align 4
+  %inc = add nsw i64 %l.02, 1
+  %cmp8 = icmp slt i64 %inc, 50
+  br i1 %cmp8, label %for.body9, label %for.inc16
+
+for.inc16:                                        ; preds = %for.body9
+  %inc17 = add nsw i64 %k.03, 1
+  %cmp5 = icmp slt i64 %inc17, 50
+  br i1 %cmp5, label %for.cond7.preheader, label %for.inc19
+
+for.inc19:                                        ; preds = %for.inc16
+  %inc20 = add nsw i64 %j.05, 1
+  %cmp2 = icmp slt i64 %inc20, 50
+  br i1 %cmp2, label %for.cond4.preheader, label %for.inc22
+
+for.inc22:                                        ; preds = %for.inc19
+  %inc23 = add nsw i64 %i.07, 1
+  %cmp = icmp slt i64 %inc23, 50
+  br i1 %cmp, label %for.cond1.preheader, label %for.end24
+
+for.end24:                                        ; preds = %for.inc22
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 50; i++)
+;;    for (long int j = 0; j < 50; j++)
+;;      for (long int k = 0; k < 50; k++)
+;;        for (long int l = 0; l < 50; l++)
+;;          A[i][i][j + k] = ...
+;;          ... = A[10][i + 10][2*j - l];
+
+define void @sep1([100 x [100 x i32]]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %for.inc22, %entry
+  %B.addr.08 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.inc22 ]
+  %i.07 = phi i64 [ 0, %entry ], [ %inc23, %for.inc22 ]
+  br label %for.cond4.preheader
+
+for.cond4.preheader:                              ; preds = %for.inc19, %for.cond1.preheader
+  %B.addr.16 = phi i32* [ %B.addr.08, %for.cond1.preheader ], [ %incdec.ptr, %for.inc19 ]
+  %j.05 = phi i64 [ 0, %for.cond1.preheader ], [ %inc20, %for.inc19 ]
+  br label %for.cond7.preheader
+
+for.cond7.preheader:                              ; preds = %for.inc16, %for.cond4.preheader
+  %B.addr.24 = phi i32* [ %B.addr.16, %for.cond4.preheader ], [ %incdec.ptr, %for.inc16 ]
+  %k.03 = phi i64 [ 0, %for.cond4.preheader ], [ %inc17, %for.inc16 ]
+  br label %for.body9
+
+for.body9:                                        ; preds = %for.body9, %for.cond7.preheader
+  %l.02 = phi i64 [ 0, %for.cond7.preheader ], [ %inc, %for.body9 ]
+  %B.addr.31 = phi i32* [ %B.addr.24, %for.cond7.preheader ], [ %incdec.ptr, %for.body9 ]
+  %conv = trunc i64 %i.07 to i32
+  %add = add nsw i64 %j.05, %k.03
+  %arrayidx11 = getelementptr inbounds [100 x [100 x i32]]* %A, i64 %i.07, i64 %i.07, i64 %add
+  store i32 %conv, i32* %arrayidx11, align 4
+  %mul = shl nsw i64 %j.05, 1
+  %sub = sub nsw i64 %mul, %l.02
+  %add12 = add nsw i64 %i.07, 10
+  %arrayidx15 = getelementptr inbounds [100 x [100 x i32]]* %A, i64 10, i64 %add12, i64 %sub
+  %0 = load i32* %arrayidx15, align 4
+; CHECK: da analyze - flow [> * * *]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.31, i64 1
+  store i32 %0, i32* %B.addr.31, align 4
+  %inc = add nsw i64 %l.02, 1
+  %cmp8 = icmp slt i64 %inc, 50
+  br i1 %cmp8, label %for.body9, label %for.inc16
+
+for.inc16:                                        ; preds = %for.body9
+  %inc17 = add nsw i64 %k.03, 1
+  %cmp5 = icmp slt i64 %inc17, 50
+  br i1 %cmp5, label %for.cond7.preheader, label %for.inc19
+
+for.inc19:                                        ; preds = %for.inc16
+  %inc20 = add nsw i64 %j.05, 1
+  %cmp2 = icmp slt i64 %inc20, 50
+  br i1 %cmp2, label %for.cond4.preheader, label %for.inc22
+
+for.inc22:                                        ; preds = %for.inc19
+  %inc23 = add nsw i64 %i.07, 1
+  %cmp = icmp slt i64 %inc23, 50
+  br i1 %cmp, label %for.cond1.preheader, label %for.end24
+
+for.end24:                                        ; preds = %for.inc22
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 50; i++)
+;;    for (long int j = 0; j < 50; j++)
+;;      for (long int k = 0; k < 50; k++)
+;;        for (long int l = 0; l < 50; l++)
+;;          A[i][i][i + k][l] = ...
+;;          ... = A[10][i + 10][j + k][l + 10];
+
+define void @sep2([100 x [100 x [100 x i32]]]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %for.inc26, %entry
+  %B.addr.08 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.inc26 ]
+  %i.07 = phi i64 [ 0, %entry ], [ %inc27, %for.inc26 ]
+  br label %for.cond4.preheader
+
+for.cond4.preheader:                              ; preds = %for.inc23, %for.cond1.preheader
+  %B.addr.16 = phi i32* [ %B.addr.08, %for.cond1.preheader ], [ %incdec.ptr, %for.inc23 ]
+  %j.05 = phi i64 [ 0, %for.cond1.preheader ], [ %inc24, %for.inc23 ]
+  br label %for.cond7.preheader
+
+for.cond7.preheader:                              ; preds = %for.inc20, %for.cond4.preheader
+  %B.addr.24 = phi i32* [ %B.addr.16, %for.cond4.preheader ], [ %incdec.ptr, %for.inc20 ]
+  %k.03 = phi i64 [ 0, %for.cond4.preheader ], [ %inc21, %for.inc20 ]
+  br label %for.body9
+
+for.body9:                                        ; preds = %for.body9, %for.cond7.preheader
+  %l.02 = phi i64 [ 0, %for.cond7.preheader ], [ %inc, %for.body9 ]
+  %B.addr.31 = phi i32* [ %B.addr.24, %for.cond7.preheader ], [ %incdec.ptr, %for.body9 ]
+  %conv = trunc i64 %i.07 to i32
+  %add = add nsw i64 %i.07, %k.03
+  %arrayidx12 = getelementptr inbounds [100 x [100 x [100 x i32]]]* %A, i64 %i.07, i64 %i.07, i64 %add, i64 %l.02
+  store i32 %conv, i32* %arrayidx12, align 4
+  %add13 = add nsw i64 %l.02, 10
+  %add14 = add nsw i64 %j.05, %k.03
+  %add15 = add nsw i64 %i.07, 10
+  %arrayidx19 = getelementptr inbounds [100 x [100 x [100 x i32]]]* %A, i64 10, i64 %add15, i64 %add14, i64 %add13
+  %0 = load i32* %arrayidx19, align 4
+; CHECK: da analyze - flow [> * * -10]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.31, i64 1
+  store i32 %0, i32* %B.addr.31, align 4
+  %inc = add nsw i64 %l.02, 1
+  %cmp8 = icmp slt i64 %inc, 50
+  br i1 %cmp8, label %for.body9, label %for.inc20
+
+for.inc20:                                        ; preds = %for.body9
+  %inc21 = add nsw i64 %k.03, 1
+  %cmp5 = icmp slt i64 %inc21, 50
+  br i1 %cmp5, label %for.cond7.preheader, label %for.inc23
+
+for.inc23:                                        ; preds = %for.inc20
+  %inc24 = add nsw i64 %j.05, 1
+  %cmp2 = icmp slt i64 %inc24, 50
+  br i1 %cmp2, label %for.cond4.preheader, label %for.inc26
+
+for.inc26:                                        ; preds = %for.inc23
+  %inc27 = add nsw i64 %i.07, 1
+  %cmp = icmp slt i64 %inc27, 50
+  br i1 %cmp, label %for.cond1.preheader, label %for.end28
+
+for.end28:                                        ; preds = %for.inc26
+  ret void
+}
+
+
+;;  for (long int i = 0; i < 50; i++)
+;;    for (long int j = 0; j < 50; j++)
+;;      for (long int k = 0; k < 50; k++)
+;;        for (long int l = 0; l < 50; l++)
+;;          A[i][i][i + k][l + k] = ...
+;;          ... = A[10][i + 10][j + k][l + 10];
+
+define void @sep3([100 x [100 x [100 x i32]]]* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  br label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %for.inc27, %entry
+  %B.addr.08 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.inc27 ]
+  %i.07 = phi i64 [ 0, %entry ], [ %inc28, %for.inc27 ]
+  br label %for.cond4.preheader
+
+for.cond4.preheader:                              ; preds = %for.inc24, %for.cond1.preheader
+  %B.addr.16 = phi i32* [ %B.addr.08, %for.cond1.preheader ], [ %incdec.ptr, %for.inc24 ]
+  %j.05 = phi i64 [ 0, %for.cond1.preheader ], [ %inc25, %for.inc24 ]
+  br label %for.cond7.preheader
+
+for.cond7.preheader:                              ; preds = %for.inc21, %for.cond4.preheader
+  %B.addr.24 = phi i32* [ %B.addr.16, %for.cond4.preheader ], [ %incdec.ptr, %for.inc21 ]
+  %k.03 = phi i64 [ 0, %for.cond4.preheader ], [ %inc22, %for.inc21 ]
+  br label %for.body9
+
+for.body9:                                        ; preds = %for.body9, %for.cond7.preheader
+  %l.02 = phi i64 [ 0, %for.cond7.preheader ], [ %inc, %for.body9 ]
+  %B.addr.31 = phi i32* [ %B.addr.24, %for.cond7.preheader ], [ %incdec.ptr, %for.body9 ]
+  %conv = trunc i64 %i.07 to i32
+  %add = add nsw i64 %l.02, %k.03
+  %add10 = add nsw i64 %i.07, %k.03
+  %arrayidx13 = getelementptr inbounds [100 x [100 x [100 x i32]]]* %A, i64 %i.07, i64 %i.07, i64 %add10, i64 %add
+  store i32 %conv, i32* %arrayidx13, align 4
+  %add14 = add nsw i64 %l.02, 10
+  %add15 = add nsw i64 %j.05, %k.03
+  %add16 = add nsw i64 %i.07, 10
+  %arrayidx20 = getelementptr inbounds [100 x [100 x [100 x i32]]]* %A, i64 10, i64 %add16, i64 %add15, i64 %add14
+  %0 = load i32* %arrayidx20, align 4
+; CHECK: da analyze - flow [> * * *]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.31, i64 1
+  store i32 %0, i32* %B.addr.31, align 4
+  %inc = add nsw i64 %l.02, 1
+  %cmp8 = icmp slt i64 %inc, 50
+  br i1 %cmp8, label %for.body9, label %for.inc21
+
+for.inc21:                                        ; preds = %for.body9
+  %inc22 = add nsw i64 %k.03, 1
+  %cmp5 = icmp slt i64 %inc22, 50
+  br i1 %cmp5, label %for.cond7.preheader, label %for.inc24
+
+for.inc24:                                        ; preds = %for.inc21
+  %inc25 = add nsw i64 %j.05, 1
+  %cmp2 = icmp slt i64 %inc25, 50
+  br i1 %cmp2, label %for.cond4.preheader, label %for.inc27
+
+for.inc27:                                        ; preds = %for.inc24
+  %inc28 = add nsw i64 %i.07, 1
+  %cmp = icmp slt i64 %inc28, 50
+  br i1 %cmp, label %for.cond1.preheader, label %for.end29
+
+for.end29:                                        ; preds = %for.inc27
+  ret void
+}

test/Analysis/DependenceAnalysis/StrongSIV.ll

@@ -0,0 +1,342 @@
+; RUN: opt < %s -analyze -basicaa -indvars -da | FileCheck %s
+
+; ModuleID = 'StrongSIV.bc'
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.6.0"
+
+
+;;  for (int i = 0; i < n; i++)
+;;    A[i + 2] = ...
+;;    ... = A[i];
+
+define void @strong0(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  %cmp1 = icmp sgt i64 %n, 0
+  br i1 %cmp1, label %for.body, label %for.end
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %entry ]
+  %add = add nsw i32 %i.03, 2
+  %idxprom = sext i32 %add to i64
+  %arrayidx = getelementptr inbounds i32* %A, i64 %idxprom
+  store i32 %i.03, i32* %arrayidx, align 4
+  %idxprom2 = sext i32 %i.03 to i64
+  %arrayidx3 = getelementptr inbounds i32* %A, i64 %idxprom2
+  %0 = load i32* %arrayidx3, align 4
+; CHECK: da analyze - consistent flow [2]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc = add nsw i32 %i.03, 1
+  %conv = sext i32 %inc to i64
+  %cmp = icmp slt i64 %conv, %n
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+
+;;  for (long int i = 0; i < n; i++)
+;;    A[i + 2] = ...
+;;    ... = A[i];
+
+define void @strong1(i32* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  %conv = sext i32 %n to i64
+  %cmp1 = icmp sgt i32 %n, 0
+  br i1 %cmp1, label %for.body, label %for.end
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %entry ]
+  %conv2 = trunc i64 %i.03 to i32
+  %add = add nsw i64 %i.03, 2
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv2, i32* %arrayidx, align 4
+  %arrayidx3 = getelementptr inbounds i32* %A, i64 %i.03
+  %0 = load i32* %arrayidx3, align 4
+; CHECK: da analyze - consistent flow [2]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc = add nsw i64 %i.03, 1
+  %cmp = icmp slt i64 %inc, %conv
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < n; i++)
+;;    A[i + 2] = ...
+;;    ... = A[i];
+
+define void @strong2(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  %cmp1 = icmp eq i64 %n, 0
+  br i1 %cmp1, label %for.end, label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %entry ]
+  %conv = trunc i64 %i.03 to i32
+  %add = add i64 %i.03, 2
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 %i.03
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - consistent flow [2]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc = add i64 %i.03, 1
+  %cmp = icmp ult i64 %inc, %n
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+
+;;  for (int i = 0; i < n; i++)
+;;    A[i + 2] = ...
+;;    ... = A[i];
+
+define void @strong3(i32* %A, i32* %B, i32 %n) nounwind uwtable ssp {
+entry:
+  %cmp1 = icmp sgt i32 %n, 0
+  br i1 %cmp1, label %for.body, label %for.end
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %entry ]
+  %add = add nsw i32 %i.03, 2
+  %idxprom = sext i32 %add to i64
+  %arrayidx = getelementptr inbounds i32* %A, i64 %idxprom
+  store i32 %i.03, i32* %arrayidx, align 4
+  %idxprom1 = sext i32 %i.03 to i64
+  %arrayidx2 = getelementptr inbounds i32* %A, i64 %idxprom1
+  %0 = load i32* %arrayidx2, align 4
+; CHECK: da analyze - consistent flow [2]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc = add nsw i32 %i.03, 1
+  %cmp = icmp slt i32 %inc, %n
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < 19; i++)
+;;    A[i + 19] = ...
+;;    ... = A[i];
+
+define void @strong4(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %add = add i64 %i.02, 19
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 %i.02
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 19
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < 20; i++)
+;;    A[i + 19] = ...
+;;    ... = A[i];
+
+define void @strong5(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %add = add i64 %i.02, 19
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 %i.02
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - consistent flow [19]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 20
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < 20; i++)
+;;    A[2*i + 6] = ...
+;;    ... = A[2*i];
+
+define void @strong6(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = shl i64 %i.02, 1
+  %add = add i64 %mul, 6
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul1 = shl i64 %i.02, 1
+  %arrayidx2 = getelementptr inbounds i32* %A, i64 %mul1
+  %0 = load i32* %arrayidx2, align 4
+; CHECK: da analyze - consistent flow [3]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 20
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < 20; i++)
+;;    A[2*i + 7] = ...
+;;    ... = A[2*i];
+
+define void @strong7(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = shl i64 %i.02, 1
+  %add = add i64 %mul, 7
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul1 = shl i64 %i.02, 1
+  %arrayidx2 = getelementptr inbounds i32* %A, i64 %mul1
+  %0 = load i32* %arrayidx2, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 20
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < 20; i++)
+;;    A[i + n] = ...
+;;    ... = A[i];
+
+define void @strong8(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %add = add i64 %i.02, %n
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 %i.02
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - consistent flow [%n|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 20
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < n; i++)
+;;    A[i + n] = ...
+;;    ... = A[i + 2*n];
+
+define void @strong9(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  %cmp1 = icmp eq i64 %n, 0
+  br i1 %cmp1, label %for.end, label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %entry ]
+  %conv = trunc i64 %i.03 to i32
+  %add = add i64 %i.03, %n
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul = shl i64 %n, 1
+  %add1 = add i64 %i.03, %mul
+  %arrayidx2 = getelementptr inbounds i32* %A, i64 %add1
+  %0 = load i32* %arrayidx2, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc = add i64 %i.03, 1
+  %cmp = icmp ult i64 %inc, %n
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < 1000; i++)
+;;    A[n*i + 5] = ...
+;;    ... = A[n*i + 5];
+
+define void @strong10(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = mul i64 %i.02, %n
+  %add = add i64 %mul, 5
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul1 = mul i64 %i.02, %n
+  %add2 = add i64 %mul1, 5
+  %arrayidx3 = getelementptr inbounds i32* %A, i64 %add2
+  %0 = load i32* %arrayidx3, align 4
+; CHECK: da analyze - consistent flow [0|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 1000
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}

test/Analysis/DependenceAnalysis/SymbolicRDIV.ll

@@ -0,0 +1,312 @@
+; RUN: opt < %s -analyze -basicaa -da | FileCheck %s
+
+; ModuleID = 'SymbolicRDIV.bc'
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.6.0"
+
+
+;;  for (long int i = 0; i < n1; i++)
+;;    A[2*i + n1] = ...
+;;  for (long int j = 0; j < n2; j++)
+;;    ... = A[3*j + 3*n1];
+
+define void @symbolicrdiv0(i32* %A, i32* %B, i64 %n1, i64 %n2) nounwind uwtable ssp {
+entry:
+  %cmp4 = icmp eq i64 %n1, 0
+  br i1 %cmp4, label %for.cond1.preheader, label %for.body
+
+for.cond1.preheader:                              ; preds = %for.body, %entry
+  %cmp21 = icmp eq i64 %n2, 0
+  br i1 %cmp21, label %for.end11, label %for.body4
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.05 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %conv = trunc i64 %i.05 to i32
+  %mul = shl nsw i64 %i.05, 1
+  %add = add i64 %mul, %n1
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %inc = add nsw i64 %i.05, 1
+  %cmp = icmp ult i64 %inc, %n1
+  br i1 %cmp, label %for.body, label %for.cond1.preheader
+
+for.body4:                                        ; preds = %for.body4, %for.cond1.preheader
+  %j.03 = phi i64 [ %inc10, %for.body4 ], [ 0, %for.cond1.preheader ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body4 ], [ %B, %for.cond1.preheader ]
+  %mul56 = add i64 %j.03, %n1
+  %add7 = mul i64 %mul56, 3
+  %arrayidx8 = getelementptr inbounds i32* %A, i64 %add7
+  %0 = load i32* %arrayidx8, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc10 = add nsw i64 %j.03, 1
+  %cmp2 = icmp ult i64 %inc10, %n2
+  br i1 %cmp2, label %for.body4, label %for.end11
+
+for.end11:                                        ; preds = %for.body4, %for.cond1.preheader
+  ret void
+}
+
+
+;;  for (long int i = 0; i < n1; i++)
+;;    A[2*i + 5*n2] = ...
+;;  for (long int j = 0; j < n2; j++)
+;;    ... = A[3*j + 2*n2];
+
+define void @symbolicrdiv1(i32* %A, i32* %B, i64 %n1, i64 %n2) nounwind uwtable ssp {
+entry:
+  %cmp4 = icmp eq i64 %n1, 0
+  br i1 %cmp4, label %for.cond2.preheader, label %for.body
+
+for.cond2.preheader:                              ; preds = %for.body, %entry
+  %cmp31 = icmp eq i64 %n2, 0
+  br i1 %cmp31, label %for.end12, label %for.body5
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.05 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %conv = trunc i64 %i.05 to i32
+  %mul = shl nsw i64 %i.05, 1
+  %mul1 = mul i64 %n2, 5
+  %add = add i64 %mul, %mul1
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %inc = add nsw i64 %i.05, 1
+  %cmp = icmp ult i64 %inc, %n1
+  br i1 %cmp, label %for.body, label %for.cond2.preheader
+
+for.body5:                                        ; preds = %for.body5, %for.cond2.preheader
+  %j.03 = phi i64 [ %inc11, %for.body5 ], [ 0, %for.cond2.preheader ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body5 ], [ %B, %for.cond2.preheader ]
+  %mul6 = mul nsw i64 %j.03, 3
+  %mul7 = shl i64 %n2, 1
+  %add8 = add i64 %mul6, %mul7
+  %arrayidx9 = getelementptr inbounds i32* %A, i64 %add8
+  %0 = load i32* %arrayidx9, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc11 = add nsw i64 %j.03, 1
+  %cmp3 = icmp ult i64 %inc11, %n2
+  br i1 %cmp3, label %for.body5, label %for.end12
+
+for.end12:                                        ; preds = %for.body5, %for.cond2.preheader
+  ret void
+}
+
+
+;;  for (long int i = 0; i < n1; i++)
+;;    A[2*i - n2] = ...
+;;  for (long int j = 0; j < n2; j++)
+;;    ... = A[-j + 2*n1];
+
+define void @symbolicrdiv2(i32* %A, i32* %B, i64 %n1, i64 %n2) nounwind uwtable ssp {
+entry:
+  %cmp4 = icmp eq i64 %n1, 0
+  br i1 %cmp4, label %for.cond1.preheader, label %for.body
+
+for.cond1.preheader:                              ; preds = %for.body, %entry
+  %cmp21 = icmp eq i64 %n2, 0
+  br i1 %cmp21, label %for.end10, label %for.body4
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.05 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %conv = trunc i64 %i.05 to i32
+  %mul = shl nsw i64 %i.05, 1
+  %sub = sub i64 %mul, %n2
+  %arrayidx = getelementptr inbounds i32* %A, i64 %sub
+  store i32 %conv, i32* %arrayidx, align 4
+  %inc = add nsw i64 %i.05, 1
+  %cmp = icmp ult i64 %inc, %n1
+  br i1 %cmp, label %for.body, label %for.cond1.preheader
+
+for.body4:                                        ; preds = %for.body4, %for.cond1.preheader
+  %j.03 = phi i64 [ %inc9, %for.body4 ], [ 0, %for.cond1.preheader ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body4 ], [ %B, %for.cond1.preheader ]
+  %mul6 = shl i64 %n1, 1
+  %add = sub i64 %mul6, %j.03
+  %arrayidx7 = getelementptr inbounds i32* %A, i64 %add
+  %0 = load i32* %arrayidx7, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc9 = add nsw i64 %j.03, 1
+  %cmp2 = icmp ult i64 %inc9, %n2
+  br i1 %cmp2, label %for.body4, label %for.end10
+
+for.end10:                                        ; preds = %for.body4, %for.cond1.preheader
+  ret void
+}
+
+
+;;  for (long int i = 0; i < n1; i++)
+;;    A[-i + n2] = ...
+;;  for (long int j = 0; j < n2; j++)
+;;    ... = A[j - n1];
+
+define void @symbolicrdiv3(i32* %A, i32* %B, i64 %n1, i64 %n2) nounwind uwtable ssp {
+entry:
+  %cmp4 = icmp eq i64 %n1, 0
+  br i1 %cmp4, label %for.cond1.preheader, label %for.body
+
+for.cond1.preheader:                              ; preds = %for.body, %entry
+  %cmp21 = icmp eq i64 %n2, 0
+  br i1 %cmp21, label %for.end9, label %for.body4
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.05 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %conv = trunc i64 %i.05 to i32
+  %add = sub i64 %n2, %i.05
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %inc = add nsw i64 %i.05, 1
+  %cmp = icmp ult i64 %inc, %n1
+  br i1 %cmp, label %for.body, label %for.cond1.preheader
+
+for.body4:                                        ; preds = %for.body4, %for.cond1.preheader
+  %j.03 = phi i64 [ %inc8, %for.body4 ], [ 0, %for.cond1.preheader ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body4 ], [ %B, %for.cond1.preheader ]
+  %sub5 = sub i64 %j.03, %n1
+  %arrayidx6 = getelementptr inbounds i32* %A, i64 %sub5
+  %0 = load i32* %arrayidx6, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc8 = add nsw i64 %j.03, 1
+  %cmp2 = icmp ult i64 %inc8, %n2
+  br i1 %cmp2, label %for.body4, label %for.end9
+
+for.end9:                                         ; preds = %for.body4, %for.cond1.preheader
+  ret void
+}
+
+
+;;  for (long int i = 0; i < n1; i++)
+;;    A[-i + 2*n1] = ...
+;;  for (long int j = 0; j < n2; j++)
+;;    ... = A[-j + n1];
+
+define void @symbolicrdiv4(i32* %A, i32* %B, i64 %n1, i64 %n2) nounwind uwtable ssp {
+entry:
+  %cmp4 = icmp eq i64 %n1, 0
+  br i1 %cmp4, label %for.cond1.preheader, label %for.body
+
+for.cond1.preheader:                              ; preds = %for.body, %entry
+  %cmp21 = icmp eq i64 %n2, 0
+  br i1 %cmp21, label %for.end10, label %for.body4
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.05 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %conv = trunc i64 %i.05 to i32
+  %mul = shl i64 %n1, 1
+  %add = sub i64 %mul, %i.05
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %inc = add nsw i64 %i.05, 1
+  %cmp = icmp ult i64 %inc, %n1
+  br i1 %cmp, label %for.body, label %for.cond1.preheader
+
+for.body4:                                        ; preds = %for.body4, %for.cond1.preheader
+  %j.03 = phi i64 [ %inc9, %for.body4 ], [ 0, %for.cond1.preheader ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body4 ], [ %B, %for.cond1.preheader ]
+  %add6 = sub i64 %n1, %j.03
+  %arrayidx7 = getelementptr inbounds i32* %A, i64 %add6
+  %0 = load i32* %arrayidx7, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc9 = add nsw i64 %j.03, 1
+  %cmp2 = icmp ult i64 %inc9, %n2
+  br i1 %cmp2, label %for.body4, label %for.end10
+
+for.end10:                                        ; preds = %for.body4, %for.cond1.preheader
+  ret void
+}
+
+
+;;  for (long int i = 0; i < n1; i++)
+;;    A[-i + n2] = ...
+;;  for (long int j = 0; j < n2; j++)
+;;    ... = A[-j + 2*n2];
+
+define void @symbolicrdiv5(i32* %A, i32* %B, i64 %n1, i64 %n2) nounwind uwtable ssp {
+entry:
+  %cmp4 = icmp eq i64 %n1, 0
+  br i1 %cmp4, label %for.cond1.preheader, label %for.body
+
+for.cond1.preheader:                              ; preds = %for.body, %entry
+  %cmp21 = icmp eq i64 %n2, 0
+  br i1 %cmp21, label %for.end10, label %for.body4
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.05 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %conv = trunc i64 %i.05 to i32
+  %add = sub i64 %n2, %i.05
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %inc = add nsw i64 %i.05, 1
+  %cmp = icmp ult i64 %inc, %n1
+  br i1 %cmp, label %for.body, label %for.cond1.preheader
+
+for.body4:                                        ; preds = %for.body4, %for.cond1.preheader
+  %j.03 = phi i64 [ %inc9, %for.body4 ], [ 0, %for.cond1.preheader ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body4 ], [ %B, %for.cond1.preheader ]
+  %mul = shl i64 %n2, 1
+  %add6 = sub i64 %mul, %j.03
+  %arrayidx7 = getelementptr inbounds i32* %A, i64 %add6
+  %0 = load i32* %arrayidx7, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc9 = add nsw i64 %j.03, 1
+  %cmp2 = icmp ult i64 %inc9, %n2
+  br i1 %cmp2, label %for.body4, label %for.end10
+
+for.end10:                                        ; preds = %for.body4, %for.cond1.preheader
+  ret void
+}
+
+
+;;  for (long int i = 0; i < n1; i++)
+;;    for (long int j = 0; j < n2; j++)
+;;      A[j -i + n2] = ...
+;;      ... = A[2*n2];
+
+define void @symbolicrdiv6(i32* %A, i32* %B, i64 %n1, i64 %n2) nounwind uwtable ssp {
+entry:
+  %cmp4 = icmp eq i64 %n1, 0
+  br i1 %cmp4, label %for.end7, label %for.cond1.preheader
+
+for.cond1.preheader:                              ; preds = %for.inc5, %entry
+  %B.addr.06 = phi i32* [ %B.addr.1.lcssa, %for.inc5 ], [ %B, %entry ]
+  %i.05 = phi i64 [ %inc6, %for.inc5 ], [ 0, %entry ]
+  %cmp21 = icmp eq i64 %n2, 0
+  br i1 %cmp21, label %for.inc5, label %for.body3
+
+for.body3:                                        ; preds = %for.body3, %for.cond1.preheader
+  %j.03 = phi i64 [ %inc, %for.body3 ], [ 0, %for.cond1.preheader ]
+  %B.addr.12 = phi i32* [ %incdec.ptr, %for.body3 ], [ %B.addr.06, %for.cond1.preheader ]
+  %conv = trunc i64 %i.05 to i32
+  %sub = sub nsw i64 %j.03, %i.05
+  %add = add i64 %sub, %n2
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul = shl i64 %n2, 1
+  %arrayidx4 = getelementptr inbounds i32* %A, i64 %mul
+  %0 = load i32* %arrayidx4, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.12, i64 1
+  store i32 %0, i32* %B.addr.12, align 4
+  %inc = add nsw i64 %j.03, 1
+  %cmp2 = icmp ult i64 %inc, %n2
+  br i1 %cmp2, label %for.body3, label %for.inc5
+
+for.inc5:                                         ; preds = %for.body3, %for.cond1.preheader
+  %B.addr.1.lcssa = phi i32* [ %B.addr.06, %for.cond1.preheader ], [ %incdec.ptr, %for.body3 ]
+  %inc6 = add nsw i64 %i.05, 1
+  %cmp = icmp ult i64 %inc6, %n1
+  br i1 %cmp, label %for.cond1.preheader, label %for.end7
+
+for.end7:                                         ; preds = %for.inc5, %entry
+  ret void
+}

test/Analysis/DependenceAnalysis/SymbolicSIV.ll

@@ -0,0 +1,330 @@
+; RUN: opt < %s -analyze -basicaa -da | FileCheck %s
+
+; ModuleID = 'SymbolicSIV.bc'
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.6.0"
+
+
+;;  for (long int i = 0; i < n; i++)
+;;    A[2*i + n] = ...
+;;    ... = A[3*i + 3*n];
+
+define void @symbolicsiv0(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  %cmp1 = icmp eq i64 %n, 0
+  br i1 %cmp1, label %for.end, label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %entry ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = shl nsw i64 %i.03, 1
+  %add = add i64 %mul, %n
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul14 = add i64 %i.03, %n
+  %add3 = mul i64 %mul14, 3
+  %arrayidx4 = getelementptr inbounds i32* %A, i64 %add3
+  %0 = load i32* %arrayidx4, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc = add nsw i64 %i.03, 1
+  %cmp = icmp ult i64 %inc, %n
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+
+;;  for (long int i = 0; i < n; i++)
+;;    A[2*i + 5*n] = ...
+;;    ... = A[3*i + 2*n];
+
+define void @symbolicsiv1(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  %cmp1 = icmp eq i64 %n, 0
+  br i1 %cmp1, label %for.end, label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %entry ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = shl nsw i64 %i.03, 1
+  %mul1 = mul i64 %n, 5
+  %add = add i64 %mul, %mul1
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul2 = mul nsw i64 %i.03, 3
+  %mul3 = shl i64 %n, 1
+  %add4 = add i64 %mul2, %mul3
+  %arrayidx5 = getelementptr inbounds i32* %A, i64 %add4
+  %0 = load i32* %arrayidx5, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc = add nsw i64 %i.03, 1
+  %cmp = icmp ult i64 %inc, %n
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+
+;;  for (long int i = 0; i < n; i++)
+;;    A[2*i - n] = ...
+;;    ... = A[-i + 2*n];
+
+define void @symbolicsiv2(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  %cmp1 = icmp eq i64 %n, 0
+  br i1 %cmp1, label %for.end, label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %entry ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = shl nsw i64 %i.03, 1
+  %sub = sub i64 %mul, %n
+  %arrayidx = getelementptr inbounds i32* %A, i64 %sub
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul2 = shl i64 %n, 1
+  %add = sub i64 %mul2, %i.03
+  %arrayidx3 = getelementptr inbounds i32* %A, i64 %add
+  %0 = load i32* %arrayidx3, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc = add nsw i64 %i.03, 1
+  %cmp = icmp ult i64 %inc, %n
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+
+;;  for (long int i = 0; i < n; i++)
+;;    A[-2*i + n + 1] = ...
+;;    ... = A[i - 2*n];
+
+define void @symbolicsiv3(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  %cmp1 = icmp eq i64 %n, 0
+  br i1 %cmp1, label %for.end, label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %entry ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = mul nsw i64 %i.03, -2
+  %add = add i64 %mul, %n
+  %add1 = add i64 %add, 1
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add1
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul2 = shl i64 %n, 1
+  %sub = sub i64 %i.03, %mul2
+  %arrayidx3 = getelementptr inbounds i32* %A, i64 %sub
+  %0 = load i32* %arrayidx3, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc = add nsw i64 %i.03, 1
+  %cmp = icmp ult i64 %inc, %n
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+
+;;  for (long int i = 0; i < n; i++)
+;;    A[-2*i + 3*n] = ...
+;;    ... = A[-i + n];
+
+define void @symbolicsiv4(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  %cmp1 = icmp eq i64 %n, 0
+  br i1 %cmp1, label %for.end, label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %entry ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = mul nsw i64 %i.03, -2
+  %mul1 = mul i64 %n, 3
+  %add = add i64 %mul, %mul1
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %add2 = sub i64 %n, %i.03
+  %arrayidx3 = getelementptr inbounds i32* %A, i64 %add2
+  %0 = load i32* %arrayidx3, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc = add nsw i64 %i.03, 1
+  %cmp = icmp ult i64 %inc, %n
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+
+;;  for (long int i = 0; i < n; i++)
+;;    A[-2*i - 2*n] = ...
+;;    ... = A[-i - n];
+
+define void @symbolicsiv5(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  %cmp1 = icmp eq i64 %n, 0
+  br i1 %cmp1, label %for.end, label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %entry ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = mul nsw i64 %i.03, -2
+  %mul1 = shl i64 %n, 1
+  %sub = sub i64 %mul, %mul1
+  %arrayidx = getelementptr inbounds i32* %A, i64 %sub
+  store i32 %conv, i32* %arrayidx, align 4
+  %sub2 = sub nsw i64 0, %i.03
+  %sub3 = sub i64 %sub2, %n
+  %arrayidx4 = getelementptr inbounds i32* %A, i64 %sub3
+  %0 = load i32* %arrayidx4, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc = add nsw i64 %i.03, 1
+  %cmp = icmp ult i64 %inc, %n
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+
+;; why doesn't SCEV package understand that n >= 0?
+;;void weaktest(int *A, int *B, long unsigned n)
+;;  for (long unsigned i = 0; i < n; i++)
+;;    A[i + n + 1] = ...
+;;    ... = A[-i];
+
+define void @weaktest(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  %cmp1 = icmp eq i64 %n, 0
+  br i1 %cmp1, label %for.end, label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %entry ]
+  %conv = trunc i64 %i.03 to i32
+  %add = add i64 %i.03, %n
+  %add1 = add i64 %add, 1
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add1
+  store i32 %conv, i32* %arrayidx, align 4
+  %sub = sub i64 0, %i.03
+  %arrayidx2 = getelementptr inbounds i32* %A, i64 %sub
+  %0 = load i32* %arrayidx2, align 4
+; CHECK: da analyze - flow [*|<] splitable!
+; CHECK: da analyze - split level = 1, iteration = ((0 smax (-1 + (-1 * %n))) /u 2)!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc = add i64 %i.03, 1
+  %cmp = icmp ult i64 %inc, %n
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+
+;;  void symbolicsiv6(int *A, int *B, long unsigned n, long unsigned N, long unsigned M) {
+;;    for (long int i = 0; i < n; i++) {
+;;      A[4*N*i + M] = i;
+;;      *B++ = A[4*N*i + 3*M + 1];
+
+define void @symbolicsiv6(i32* %A, i32* %B, i64 %n, i64 %N, i64 %M) nounwind uwtable ssp {
+entry:
+  %cmp1 = icmp eq i64 %n, 0
+  br i1 %cmp1, label %for.end, label %for.body.preheader
+
+for.body.preheader:                               ; preds = %entry
+  br label %for.body
+
+for.body:                                         ; preds = %for.body.preheader, %for.body
+  %i.03 = phi i64 [ %inc, %for.body ], [ 0, %for.body.preheader ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %for.body.preheader ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = shl i64 %N, 2
+  %mul1 = mul i64 %mul, %i.03
+  %add = add i64 %mul1, %M
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul2 = shl i64 %N, 2
+  %mul3 = mul i64 %mul2, %i.03
+  %mul4 = mul i64 %M, 3
+  %add5 = add i64 %mul3, %mul4
+  %add6 = add i64 %add5, 1
+  %arrayidx7 = getelementptr inbounds i32* %A, i64 %add6
+  %0 = load i32* %arrayidx7, align 4
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+; CHECK: da analyze - none!
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc = add nsw i64 %i.03, 1
+  %exitcond = icmp ne i64 %inc, %n
+  br i1 %exitcond, label %for.body, label %for.end.loopexit
+
+for.end.loopexit:                                 ; preds = %for.body
+  br label %for.end
+
+for.end:                                          ; preds = %for.end.loopexit, %entry
+  ret void
+}
+
+
+;;  void symbolicsiv7(int *A, int *B, long unsigned n, long unsigned N, long unsigned M) {
+;;    for (long int i = 0; i < n; i++) {
+;;      A[2*N*i + M] = i;
+;;      *B++ = A[2*N*i - 3*M + 2];
+
+define void @symbolicsiv7(i32* %A, i32* %B, i64 %n, i64 %N, i64 %M) nounwind uwtable ssp {
+entry:
+  %cmp1 = icmp eq i64 %n, 0
+  br i1 %cmp1, label %for.end, label %for.body.preheader
+
+for.body.preheader:                               ; preds = %entry
+  br label %for.body
+
+for.body:                                         ; preds = %for.body.preheader, %for.body
+  %i.03 = phi i64 [ %inc, %for.body ], [ 0, %for.body.preheader ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %for.body.preheader ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = shl i64 %N, 1
+  %mul1 = mul i64 %mul, %i.03
+  %add = add i64 %mul1, %M
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul2 = shl i64 %N, 1
+  %mul3 = mul i64 %mul2, %i.03
+  %0 = mul i64 %M, -3
+  %sub = add i64 %mul3, %0
+  %add5 = add i64 %sub, 2
+  %arrayidx6 = getelementptr inbounds i32* %A, i64 %add5
+  %1 = load i32* %arrayidx6, align 4
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+; CHECK: da analyze - flow [<>]!
+  store i32 %1, i32* %B.addr.02, align 4
+  %inc = add nsw i64 %i.03, 1
+  %exitcond = icmp ne i64 %inc, %n
+  br i1 %exitcond, label %for.body, label %for.end.loopexit
+
+for.end.loopexit:                                 ; preds = %for.body
+  br label %for.end
+
+for.end:                                          ; preds = %for.end.loopexit, %entry
+  ret void
+}

test/Analysis/DependenceAnalysis/WeakCrossingSIV.ll

@@ -0,0 +1,220 @@
+; RUN: opt < %s -analyze -basicaa -da | FileCheck %s
+
+; ModuleID = 'WeakCrossingSIV.bc'
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.6.0"
+
+
+;;  for (long unsigned i = 0; i < n; i++)
+;;    A[1 + n*i] = ...
+;;    ... = A[1 - n*i];
+
+define void @weakcrossing0(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  %cmp1 = icmp eq i64 %n, 0
+  br i1 %cmp1, label %for.end, label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %entry ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = mul i64 %i.03, %n
+  %add = add i64 %mul, 1
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul1 = mul i64 %i.03, %n
+  %sub = sub i64 1, %mul1
+  %arrayidx2 = getelementptr inbounds i32* %A, i64 %sub
+  %0 = load i32* %arrayidx2, align 4
+; CHECK: da analyze - flow [0|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc = add i64 %i.03, 1
+  %cmp = icmp ult i64 %inc, %n
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < n; i++)
+;;    A[n + i] = ...
+;;    ... = A[1 + n - i];
+
+define void @weakcrossing1(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  %cmp1 = icmp eq i64 %n, 0
+  br i1 %cmp1, label %for.end, label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %entry ]
+  %conv = trunc i64 %i.03 to i32
+  %add = add i64 %i.03, %n
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %add1 = add i64 %n, 1
+  %sub = sub i64 %add1, %i.03
+  %arrayidx2 = getelementptr inbounds i32* %A, i64 %sub
+  %0 = load i32* %arrayidx2, align 4
+; CHECK: da analyze - flow [<>] splitable!
+; CHECK: da analyze - split level = 1, iteration = 0!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc = add i64 %i.03, 1
+  %cmp = icmp ult i64 %inc, %n
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < 3; i++)
+;;    A[i] = ...
+;;    ... = A[6 - i];
+
+define void @weakcrossing2(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %arrayidx = getelementptr inbounds i32* %A, i64 %i.02
+  store i32 %conv, i32* %arrayidx, align 4
+  %sub = sub i64 6, %i.02
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 %sub
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 3
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < 4; i++)
+;;    A[i] = ...
+;;    ... = A[6 - i];
+
+define void @weakcrossing3(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %arrayidx = getelementptr inbounds i32* %A, i64 %i.02
+  store i32 %conv, i32* %arrayidx, align 4
+  %sub = sub i64 6, %i.02
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 %sub
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - flow [0|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 4
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < 10; i++)
+;;    A[i] = ...
+;;    ... = A[-6 - i];
+
+define void @weakcrossing4(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %arrayidx = getelementptr inbounds i32* %A, i64 %i.02
+  store i32 %conv, i32* %arrayidx, align 4
+  %sub = sub i64 -6, %i.02
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 %sub
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 10
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < n; i++)
+;;    A[3*i] = ...
+;;    ... = A[5 - 3*i];
+
+define void @weakcrossing5(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  %cmp1 = icmp eq i64 %n, 0
+  br i1 %cmp1, label %for.end, label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %entry ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = mul i64 %i.03, 3
+  %arrayidx = getelementptr inbounds i32* %A, i64 %mul
+  store i32 %conv, i32* %arrayidx, align 4
+  %0 = mul i64 %i.03, -3
+  %sub = add i64 %0, 5
+  %arrayidx2 = getelementptr inbounds i32* %A, i64 %sub
+  %1 = load i32* %arrayidx2, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %1, i32* %B.addr.02, align 4
+  %inc = add i64 %i.03, 1
+  %cmp = icmp ult i64 %inc, %n
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < 4; i++)
+;;    A[i] = ...
+;;    ... = A[5 - i];
+
+define void @weakcrossing6(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %arrayidx = getelementptr inbounds i32* %A, i64 %i.02
+  store i32 %conv, i32* %arrayidx, align 4
+  %sub = sub i64 5, %i.02
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 %sub
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - flow [<>] splitable!
+; CHECK: da analyze - split level = 1, iteration = 2!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 4
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}

test/Analysis/DependenceAnalysis/WeakZeroDstSIV.ll

@@ -0,0 +1,212 @@
+; RUN: opt < %s -analyze -basicaa -da | FileCheck %s
+
+; ModuleID = 'WeakZeroDstSIV.bc'
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.6.0"
+
+
+;;  for (long unsigned i = 0; i < 30; i++)
+;;    A[2*i + 10] = ...
+;;    ... = A[10];
+
+define void @weakzerodst0(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = shl i64 %i.02, 1
+  %add = add i64 %mul, 10
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 10
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - flow [p<=|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 30
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < n; i++)
+;;    A[n*i + 10] = ...
+;;    ... = A[10];
+
+define void @weakzerodst1(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  %cmp1 = icmp eq i64 %n, 0
+  br i1 %cmp1, label %for.end, label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %entry ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = mul i64 %i.03, %n
+  %add = add i64 %mul, 10
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 %conv, i32* %arrayidx, align 4
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 10
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - flow [p<=|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc = add i64 %i.03, 1
+  %cmp = icmp ult i64 %inc, %n
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < 5; i++)
+;;    A[2*i] = ...
+;;    ... = A[10];
+
+define void @weakzerodst2(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = shl i64 %i.02, 1
+  %arrayidx = getelementptr inbounds i32* %A, i64 %mul
+  store i32 %conv, i32* %arrayidx, align 4
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 10
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 5
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < 6; i++)
+;;    A[2*i] = ...
+;;    ... = A[10];
+
+define void @weakzerodst3(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = shl i64 %i.02, 1
+  %arrayidx = getelementptr inbounds i32* %A, i64 %mul
+  store i32 %conv, i32* %arrayidx, align 4
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 10
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - flow [=>p|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 6
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < 7; i++)
+;;    A[2*i] = ...
+;;    ... = A[10];
+
+define void @weakzerodst4(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = shl i64 %i.02, 1
+  %arrayidx = getelementptr inbounds i32* %A, i64 %mul
+  store i32 %conv, i32* %arrayidx, align 4
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 10
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - flow [*|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 7
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < 7; i++)
+;;    A[2*i] = ...
+;;    ... = A[-10];
+
+define void @weakzerodst5(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %mul = shl i64 %i.02, 1
+  %arrayidx = getelementptr inbounds i32* %A, i64 %mul
+  store i32 %conv, i32* %arrayidx, align 4
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 -10
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 7
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < n; i++)
+;;    A[3*i] = ...
+;;    ... = A[10];
+
+define void @weakzerodst6(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  %cmp1 = icmp eq i64 %n, 0
+  br i1 %cmp1, label %for.end, label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %entry ]
+  %conv = trunc i64 %i.03 to i32
+  %mul = mul i64 %i.03, 3
+  %arrayidx = getelementptr inbounds i32* %A, i64 %mul
+  store i32 %conv, i32* %arrayidx, align 4
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 10
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc = add i64 %i.03, 1
+  %cmp = icmp ult i64 %inc, %n
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}

test/Analysis/DependenceAnalysis/WeakZeroSrcSIV.ll

@@ -0,0 +1,212 @@
+; RUN: opt < %s -analyze -basicaa -da | FileCheck %s
+
+; ModuleID = 'WeakZeroSrcSIV.bc'
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.6.0"
+
+
+;;  for (long unsigned i = 0; i < 30; i++)
+;;    A[10] = ...
+;;    ... = A[2*i + 10];
+
+define void @weakzerosrc0(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %arrayidx = getelementptr inbounds i32* %A, i64 10
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul = shl i64 %i.02, 1
+  %add = add i64 %mul, 10
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 %add
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - flow [p<=|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 30
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < n; i++)
+;;    A[10] = ...
+;;    ... = A[n*i + 10];
+
+define void @weakzerosrc1(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  %cmp1 = icmp eq i64 %n, 0
+  br i1 %cmp1, label %for.end, label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %entry ]
+  %conv = trunc i64 %i.03 to i32
+  %arrayidx = getelementptr inbounds i32* %A, i64 10
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul = mul i64 %i.03, %n
+  %add = add i64 %mul, 10
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 %add
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - flow [p<=|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc = add i64 %i.03, 1
+  %cmp = icmp ult i64 %inc, %n
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < 5; i++)
+;;    A[10] = ...
+;;    ... = A[2*i];
+
+define void @weakzerosrc2(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %arrayidx = getelementptr inbounds i32* %A, i64 10
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul = shl i64 %i.02, 1
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 %mul
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 5
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < 6; i++)
+;;    A[10] = ...
+;;    ... = A[2*i];
+
+define void @weakzerosrc3(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %arrayidx = getelementptr inbounds i32* %A, i64 10
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul = shl i64 %i.02, 1
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 %mul
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - flow [=>p|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 6
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < 7; i++)
+;;    A[10] = ...
+;;    ... = A[2*i];
+
+define void @weakzerosrc4(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %arrayidx = getelementptr inbounds i32* %A, i64 10
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul = shl i64 %i.02, 1
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 %mul
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - flow [*|<]!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 7
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < 7; i++)
+;;    A[-10] = ...
+;;    ... = A[2*i];
+
+define void @weakzerosrc5(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
+  %conv = trunc i64 %i.02 to i32
+  %arrayidx = getelementptr inbounds i32* %A, i64 -10
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul = shl i64 %i.02, 1
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 %mul
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
+  store i32 %0, i32* %B.addr.01, align 4
+  %inc = add i64 %i.02, 1
+  %cmp = icmp ult i64 %inc, 7
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+
+;;  for (long unsigned i = 0; i < n; i++)
+;;    A[10] = ...
+;;    ... = A[3*i];
+
+define void @weakzerosrc6(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  %cmp1 = icmp eq i64 %n, 0
+  br i1 %cmp1, label %for.end, label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.03 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %entry ]
+  %conv = trunc i64 %i.03 to i32
+  %arrayidx = getelementptr inbounds i32* %A, i64 10
+  store i32 %conv, i32* %arrayidx, align 4
+  %mul = mul i64 %i.03, 3
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 %mul
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - none!
+  %incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
+  store i32 %0, i32* %B.addr.02, align 4
+  %inc = add i64 %i.03, 1
+  %cmp = icmp ult i64 %inc, %n
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}

test/Analysis/DependenceAnalysis/ZIV.ll

@@ -0,0 +1,53 @@
+; RUN: opt < %s -analyze -basicaa -da | FileCheck %s
+
+; ModuleID = 'ZIV.bc'
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.6.0"
+
+
+;;  A[n + 1] = ...
+;;  ... = A[1 + n];
+
+define void @z0(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  %add = add i64 %n, 1
+  %arrayidx = getelementptr inbounds i32* %A, i64 %add
+  store i32 0, i32* %arrayidx, align 4
+  %add1 = add i64 %n, 1
+  %arrayidx2 = getelementptr inbounds i32* %A, i64 %add1
+  %0 = load i32* %arrayidx2, align 4
+; CHECK: da analyze - consistent flow!
+  store i32 %0, i32* %B, align 4
+  ret void
+}
+
+
+;;  A[n] = ...
+;;  ... = A[n + 1];
+
+define void @z1(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
+entry:
+  %arrayidx = getelementptr inbounds i32* %A, i64 %n
+  store i32 0, i32* %arrayidx, align 4
+  %add = add i64 %n, 1
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 %add
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - none!
+  store i32 %0, i32* %B, align 4
+  ret void
+}
+
+
+;;  A[n] = ...
+;;  ... = A[m];
+
+define void @z2(i32* %A, i32* %B, i64 %n, i64 %m) nounwind uwtable ssp {
+entry:
+  %arrayidx = getelementptr inbounds i32* %A, i64 %n
+  store i32 0, i32* %arrayidx, align 4
+  %arrayidx1 = getelementptr inbounds i32* %A, i64 %m
+  %0 = load i32* %arrayidx1, align 4
+; CHECK: da analyze - flow!
+  store i32 %0, i32* %B, align 4
+  ret void
+}

test/Analysis/DependenceAnalysis/lit.local.cfg

@@ -0,0 +1 @@
+config.suffixes = ['.ll']