Index: include/llvm/Target/TargetInstrInfo.h
===================================================================
--- include/llvm/Target/TargetInstrInfo.h
+++ include/llvm/Target/TargetInstrInfo.h
@@ -1192,6 +1192,23 @@
     return nullptr;
   }
 
+  // areMemAccessesTriviallyDiff - Sometimes, it is possible for the target to
+  // tell, even without aliasing information, that two MIs access different
+  // memory addresses. This function returns true if two MIs access different
+  // memory addresses, and false otherwise.
+  virtual bool areMemAccessesTriviallyDiff(MachineInstr *MIa,
+                                           MachineInstr *MIb) const {
+    return false;
+  }
+
+  /// For instructions with a base and offset, return the position of the
+  /// base register and offset operands.
+  virtual bool getBaseAndOffsetPosition(const MachineInstr *MI,
+                                        unsigned &BasePos,
+                                        unsigned &OffsetPos) const {
+    return false;
+  }
+
 private:
   int CallFrameSetupOpcode, CallFrameDestroyOpcode;
 };
Index: lib/CodeGen/ScheduleDAGInstrs.cpp
===================================================================
--- lib/CodeGen/ScheduleDAGInstrs.cpp
+++ lib/CodeGen/ScheduleDAGInstrs.cpp
@@ -511,10 +511,16 @@
 static bool MIsNeedChainEdge(AliasAnalysis *AA, const MachineFrameInfo *MFI,
                              MachineInstr *MIa,
                              MachineInstr *MIb) {
+  const MachineFunction *MF = MIa->getParent()->getParent();
+  const TargetInstrInfo *TII = MF->getSubtarget().getInstrInfo();
+
   // Cover a trivial case - no edge is need to itself.
   if (MIa == MIb)
     return false;
 
+  if (TII->areMemAccessesTriviallyDiff(MIa, MIb))
+    return false;
+
   // FIXME: Need to handle multiple memory operands to support all targets.
   if (!MIa->hasOneMemOperand() || !MIb->hasOneMemOperand())
     return true;
Index: lib/Target/AArch64/AArch64InstrInfo.h
===================================================================
--- lib/Target/AArch64/AArch64InstrInfo.h
+++ lib/Target/AArch64/AArch64InstrInfo.h
@@ -52,6 +52,9 @@
   bool isCoalescableExtInstr(const MachineInstr &MI, unsigned &SrcReg,
                              unsigned &DstReg, unsigned &SubIdx) const override;
 
+  bool areMemAccessesTriviallyDiff(MachineInstr *MIa,
+                                   MachineInstr *MIb) const override;
+
   unsigned isLoadFromStackSlot(const MachineInstr *MI,
                                int &FrameIndex) const override;
   unsigned isStoreToStackSlot(const MachineInstr *MI,
@@ -90,6 +93,10 @@
                             unsigned &Offset,
                             const TargetRegisterInfo *TRI) const override;
 
+  bool getLdStBaseRegImmOfsWidth(MachineInstr *LdSt, unsigned &BaseReg,
+                                 int &Offset, int &Width,
+                                 const TargetRegisterInfo *TRI) const;
+
   bool enableClusterLoads() const override { return true; }
 
   bool shouldClusterLoads(MachineInstr *FirstLdSt, MachineInstr *SecondLdSt,
Index: lib/Target/AArch64/AArch64InstrInfo.cpp
===================================================================
--- lib/Target/AArch64/AArch64InstrInfo.cpp
+++ lib/Target/AArch64/AArch64InstrInfo.cpp
@@ -607,6 +607,37 @@
   }
 }
 
+bool AArch64InstrInfo::areMemAccessesTriviallyDiff(MachineInstr *MIa,
+                                                   MachineInstr *MIb) const {
+  const TargetRegisterInfo *TRI = &getRegisterInfo();
+  unsigned BaseRegA = 0, BaseRegB = 0;
+  int OffsetA = 0, OffsetB = 0;
+  int WidthA = 0, WidthB = 0;
+
+  if (!MIa->mayStore() && !MIa->mayLoad())
+    return false;
+  if (!MIb->mayStore() && !MIb->mayLoad())
+    return false;
+
+  // Retrieve the base register, offset from the base register and width. Width
+  // is the size of memory that is being loaded/stored (e.g. 1, 2, 4, 8).  If
+  // base registers are identical, and the offset of a lower memory access +
+  // the width doesn't overlap the offset of a higher memory access,
+  // then the memory access are different.
+  if (getLdStBaseRegImmOfsWidth(MIa, BaseRegA, OffsetA, WidthA, TRI) &&
+      getLdStBaseRegImmOfsWidth(MIb, BaseRegB, OffsetB, WidthB, TRI)) {
+    if (BaseRegA == BaseRegB) {
+      int LowOffset = OffsetA < OffsetB ? OffsetA : OffsetB;
+      int HighOffset = (LowOffset == OffsetA) ? OffsetB : OffsetA;
+      int LowWidth = (LowOffset == OffsetA) ? WidthA : WidthB;
+      if (LowOffset + LowWidth <= HighOffset)
+        return true;
+    }
+  }
+  return false;
+}
+
+
 /// analyzeCompare - For a comparison instruction, return the source registers
 /// in SrcReg and SrcReg2, and the value it compares against in CmpValue.
 /// Return true if the comparison instruction can be analyzed.
@@ -1270,6 +1301,101 @@
   };
 }
 
+
+bool
+AArch64InstrInfo::getLdStBaseRegImmOfsWidth(MachineInstr *LdSt,
+                              unsigned &BaseReg, int &Offset,
+                              int &Width, const TargetRegisterInfo *TRI) const {
+  // Offset is calculated as the immediate operand multiplied by the scaling factor.
+  // Unscaled instructions have scaling factor set to 1.
+  int Scale = 0;
+  switch (LdSt->getOpcode()) {
+  default:
+    return false;
+  case AArch64::LDURQi:
+  case AArch64::STURQi:
+    Width = 16;
+    Scale = 1;
+    break;
+  case AArch64::LDURXi:
+  case AArch64::LDURDi:
+  case AArch64::STURXi:
+  case AArch64::STURDi:
+    Width = 8;
+    Scale = 1;
+    break;
+  case AArch64::LDURWi:
+  case AArch64::LDURSi:
+  case AArch64::LDURSWi:
+  case AArch64::STURWi:
+  case AArch64::STURSi:
+    Width = 4;
+    Scale = 1;
+    break;
+  case AArch64::LDURHi:
+  case AArch64::LDURHHi:
+  case AArch64::LDURSHXi:
+  case AArch64::LDURSHWi:
+  case AArch64::STURHi:
+  case AArch64::STURHHi:
+    Width = 2;
+    Scale = 1;
+    break;
+  case AArch64::LDURBi:
+  case AArch64::LDURBBi:
+  case AArch64::LDURSBXi:
+  case AArch64::LDURSBWi:
+  case AArch64::STURBi:
+  case AArch64::STURBBi:
+    Width = 1;
+    Scale = 1;
+    break;
+  case AArch64::LDRXui:
+  case AArch64::STRXui:
+    Scale = Width = 8;
+    break;
+  case AArch64::LDRWui:
+  case AArch64::STRWui:
+    Scale = Width = 4;
+    break;
+  case AArch64::LDRBui:
+  case AArch64::STRBui:
+    Scale = Width = 1;
+    break;
+  case AArch64::LDRHui:
+  case AArch64::STRHui:
+    Scale = Width = 2;
+    break;
+  case AArch64::LDRSui:
+  case AArch64::STRSui:
+    Scale = Width = 4;
+    break;
+  case AArch64::LDRDui:
+  case AArch64::STRDui:
+    Scale = Width = 8;
+    break;
+  case AArch64::LDRQui:
+  case AArch64::STRQui:
+    Scale = Width = 16;
+    break;
+  case AArch64::LDRBBui:
+  case AArch64::STRBBui:
+    Scale = Width = 1;
+    break;
+  case AArch64::LDRHHui:
+  case AArch64::STRHHui:
+    Scale = Width = 2;
+    break;
+  };
+
+  if (!LdSt->getOperand(1).isReg() || !LdSt->getOperand(2).isImm())
+     return false;
+
+  BaseReg = LdSt->getOperand(1).getReg();
+  Offset = LdSt->getOperand(2).getImm() * Scale;
+  return true;
+}
+
 /// Detect opportunities for ldp/stp formation.
 ///
 /// Only called for LdSt for which getLdStBaseRegImmOfs returns true.
Index: lib/Target/AArch64/AArch64Subtarget.h
===================================================================
--- lib/Target/AArch64/AArch64Subtarget.h
+++ lib/Target/AArch64/AArch64Subtarget.h
@@ -111,6 +111,8 @@
   bool isCortexA57() const { return CPUString == "cortex-a57"; }
   bool isCortexA53() const { return CPUString == "cortex-a53"; }
 
+  bool useAA() const override { return true; }
+
   /// getMaxInlineSizeThreshold - Returns the maximum memset / memcpy size
   /// that still makes it profitable to inline the call.
   unsigned getMaxInlineSizeThreshold() const { return 64; }