diff --git a/lib/Target/ARM/ARM.h b/lib/Target/ARM/ARM.h
index 83c8333..4679f74 100644
--- a/lib/Target/ARM/ARM.h
+++ b/lib/Target/ARM/ARM.h
@@ -49,6 +49,7 @@
 FunctionPass *createARMGlobalMergePass(const TargetLowering* tli);
 FunctionPass *createARMConstantIslandPass();
 FunctionPass *createNEONMoveFixPass();
+FunctionPass *createMLxExpansionPass();
 FunctionPass *createThumb2ITBlockPass();
 FunctionPass *createThumb2SizeReductionPass();
 
diff --git a/lib/Target/ARM/ARM.td b/lib/Target/ARM/ARM.td
index a99dbfb..35d3d1e 100644
--- a/lib/Target/ARM/ARM.td
+++ b/lib/Target/ARM/ARM.td
@@ -46,14 +46,11 @@
 def FeatureVFPOnlySP : SubtargetFeature<"fp-only-sp", "FPOnlySP", "true",
                           "Floating point unit supports single precision only">;
 
-// Some processors have multiply-accumulate instructions that don't
-// play nicely with other VFP instructions, and it's generally better
+// Some processors have FP multiply-accumulate instructions that don't
+// play nicely with other VFP / NEON instructions, and it's generally better
 // to just not use them.
-// FIXME: Currently, this is only flagged for Cortex-A8. It may be true for
-// others as well. We should do more benchmarking and confirm one way or
-// the other.
-def FeatureHasSlowVMLx : SubtargetFeature<"vmlx", "SlowVMLx", "true",
-                                          "Disable VFP MAC instructions">;
+def FeatureHasSlowFPVMLx : SubtargetFeature<"slowfpvmlx", "SlowFPVMLx", "true",
+                                         "Disable VFP / NEON MAC instructions">;
 // Some processors benefit from using NEON instructions for scalar
 // single-precision FP operations.
 def FeatureNEONForFP : SubtargetFeature<"neonfp", "UseNEONForSinglePrecisionFP",
@@ -150,26 +147,29 @@
 // V6 Processors.
 def : Processor<"arm1136j-s",       ARMV6Itineraries, [ArchV6]>;
 def : Processor<"arm1136jf-s",      ARMV6Itineraries, [ArchV6, FeatureVFP2,
-                                                       FeatureHasSlowVMLx]>;
+                                                       FeatureHasSlowFPVMLx]>;
 def : Processor<"arm1176jz-s",      ARMV6Itineraries, [ArchV6]>;
-def : Processor<"arm1176jzf-s",     ARMV6Itineraries, [ArchV6, FeatureVFP2]>;
+def : Processor<"arm1176jzf-s",     ARMV6Itineraries, [ArchV6, FeatureVFP2,
+                                                       FeatureHasSlowFPVMLx]>;
 def : Processor<"mpcorenovfp",      ARMV6Itineraries, [ArchV6]>;
-def : Processor<"mpcore",           ARMV6Itineraries, [ArchV6, FeatureVFP2]>;
+def : Processor<"mpcore",           ARMV6Itineraries, [ArchV6, FeatureVFP2,
+                                                       FeatureHasSlowFPVMLx]>;
 
 // V6M Processors.
 def : Processor<"cortex-m0",        ARMV6Itineraries, [ArchV6M]>;
 
 // V6T2 Processors.
 def : Processor<"arm1156t2-s",      ARMV6Itineraries, [ArchV6T2]>;
-def : Processor<"arm1156t2f-s",     ARMV6Itineraries, [ArchV6T2, FeatureVFP2]>;
+def : Processor<"arm1156t2f-s",     ARMV6Itineraries, [ArchV6T2, FeatureVFP2,
+                                                       FeatureHasSlowFPVMLx]>;
 
 // V7 Processors.
 def : Processor<"cortex-a8",        CortexA8Itineraries,
                                     [ArchV7A, ProcA8,
-                                     FeatureHasSlowVMLx, FeatureT2XtPk]>;
+                                     FeatureHasSlowFPVMLx, FeatureT2XtPk]>;
 def : Processor<"cortex-a9",        CortexA9Itineraries,
                                     [ArchV7A, ProcA9,
-                                     FeatureHasSlowVMLx, FeatureT2XtPk]>;
+                                     FeatureHasSlowFPVMLx, FeatureT2XtPk]>;
 
 // V7M Processors.
 def : ProcNoItin<"cortex-m3",       [ArchV7M]>;
diff --git a/lib/Target/ARM/ARMBaseInstrInfo.cpp b/lib/Target/ARM/ARMBaseInstrInfo.cpp
index 4838b7d..afec5c2 100644
--- a/lib/Target/ARM/ARMBaseInstrInfo.cpp
+++ b/lib/Target/ARM/ARMBaseInstrInfo.cpp
@@ -15,6 +15,7 @@
 #include "ARM.h"
 #include "ARMAddressingModes.h"
 #include "ARMConstantPoolValue.h"
+#include "ARMHazardRecognizer.h"
 #include "ARMMachineFunctionInfo.h"
 #include "ARMRegisterInfo.h"
 #include "ARMGenInstrInfo.inc"
@@ -40,9 +41,58 @@
 EnableARM3Addr("enable-arm-3-addr-conv", cl::Hidden,
                cl::desc("Enable ARM 2-addr to 3-addr conv"));
 
+
+/// ARM_MLxEntry - Record information about MLA / MLS instructions.
+struct ARM_MLxEntry {
+  unsigned MLxOpc;     // MLA / MLS opcode
+  unsigned MulOpc;     // Expanded multiplication opcode
+  unsigned AddSubOpc;  // Expanded add / sub opcode
+  bool NegAcc;         // True if the acc is negated before the add / sub.
+  bool HasLane;        // True if instruction has an extra "lane" operand.
+};
+
+static const ARM_MLxEntry ARM_MLxTable[] = {
+  // MLxOpc,          MulOpc,           AddSubOpc,       NegAcc, HasLane
+  // fp scalar ops
+  { ARM::VMLAS,       ARM::VMULS,       ARM::VADDS,      false,  false },
+  { ARM::VMLSS,       ARM::VMULS,       ARM::VSUBS,      false,  false },
+  { ARM::VMLAD,       ARM::VMULD,       ARM::VADDD,      false,  false },
+  { ARM::VMLSD,       ARM::VMULD,       ARM::VSUBD,      false,  false },
+  { ARM::VMLAfd_sfp,  ARM::VMULfd_sfp,  ARM::VADDfd_sfp, false,  false },
+  { ARM::VMLSfd_sfp,  ARM::VMULfd_sfp,  ARM::VSUBfd_sfp, false,  false },
+  { ARM::VNMLAS,      ARM::VNMULS,      ARM::VSUBS,      true,   false },
+  { ARM::VNMLSS,      ARM::VMULS,       ARM::VSUBS,      true,   false },
+  { ARM::VNMLAD,      ARM::VNMULD,      ARM::VSUBD,      true,   false },
+  { ARM::VNMLSD,      ARM::VMULD,       ARM::VSUBD,      true,   false },
+
+  // fp SIMD ops
+  { ARM::VMLAfd,      ARM::VMULfd,      ARM::VADDfd,     false,  false },
+  { ARM::VMLSfd,      ARM::VMULfd,      ARM::VSUBfd,     false,  false },
+  { ARM::VMLAfq,      ARM::VMULfq,      ARM::VADDfq,     false,  false },
+  { ARM::VMLSfq,      ARM::VMULfq,      ARM::VSUBfq,     false,  false },
+  { ARM::VMLAslfd,    ARM::VMULslfd,    ARM::VADDfd,     false,  true  },
+  { ARM::VMLSslfd,    ARM::VMULslfd,    ARM::VSUBfd,     false,  true  },
+  { ARM::VMLAslfq,    ARM::VMULslfq,    ARM::VADDfq,     false,  true  },
+  { ARM::VMLSslfq,    ARM::VMULslfq,    ARM::VSUBfq,     false,  true  },
+};
+
 ARMBaseInstrInfo::ARMBaseInstrInfo(const ARMSubtarget& STI)
   : TargetInstrInfoImpl(ARMInsts, array_lengthof(ARMInsts)),
     Subtarget(STI) {
+  for (unsigned i = 0, e = array_lengthof(ARM_MLxTable); i != e; ++i) {
+    if (!MLxEntryMap.insert(std::make_pair(ARM_MLxTable[i].MLxOpc, i)).second)
+      assert(false && "Duplicated entries?");
+    MLxHazardOpcodes.insert(ARM_MLxTable[i].AddSubOpc);
+    MLxHazardOpcodes.insert(ARM_MLxTable[i].MulOpc);
+  }
+}
+
+ScheduleHazardRecognizer *ARMBaseInstrInfo::
+CreateTargetPostRAHazardRecognizer(const InstrItineraryData *II) const {
+  if (Subtarget.isThumb2() || Subtarget.hasVFP2())
+    return (ScheduleHazardRecognizer *)
+      new ARMHazardRecognizer(II, *this, getRegisterInfo(), Subtarget);
+  return TargetInstrInfoImpl::CreateTargetPostRAHazardRecognizer(II);
 }
 
 MachineInstr *
@@ -197,7 +247,6 @@
   return NewMIs[0];
 }
 
-
 // Branch analysis.
 bool
 ARMBaseInstrInfo::AnalyzeBranch(MachineBasicBlock &MBB,MachineBasicBlock *&TBB,
@@ -2196,3 +2245,19 @@
   }
   return false;
 }
+
+bool
+ARMBaseInstrInfo::isFpMLxInstruction(unsigned Opcode, unsigned &MulOpc,
+                                     unsigned &AddSubOpc,
+                                     bool &NegAcc, bool &HasLane) const {
+  DenseMap<unsigned, unsigned>::const_iterator I = MLxEntryMap.find(Opcode);
+  if (I == MLxEntryMap.end())
+    return false;
+
+  const ARM_MLxEntry &Entry = ARM_MLxTable[I->second];
+  MulOpc = Entry.MulOpc;
+  AddSubOpc = Entry.AddSubOpc;
+  NegAcc = Entry.NegAcc;
+  HasLane = Entry.HasLane;
+  return true;
+}
diff --git a/lib/Target/ARM/ARMBaseInstrInfo.h b/lib/Target/ARM/ARMBaseInstrInfo.h
index 776be4d..ca8b9a0 100644
--- a/lib/Target/ARM/ARMBaseInstrInfo.h
+++ b/lib/Target/ARM/ARMBaseInstrInfo.h
@@ -17,6 +17,8 @@
 #include "ARM.h"
 #include "llvm/CodeGen/MachineInstrBuilder.h"
 #include "llvm/Target/TargetInstrInfo.h"
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/SmallSet.h"
 
 namespace llvm {
   class ARMSubtarget;
@@ -191,9 +193,11 @@
 
 class ARMBaseInstrInfo : public TargetInstrInfoImpl {
   const ARMSubtarget &Subtarget;
+
 protected:
   // Can be only subclassed.
   explicit ARMBaseInstrInfo(const ARMSubtarget &STI);
+
 public:
   // Return the non-pre/post incrementing version of 'Opc'. Return 0
   // if there is not such an opcode.
@@ -206,7 +210,9 @@
   virtual const ARMBaseRegisterInfo &getRegisterInfo() const =0;
   const ARMSubtarget &getSubtarget() const { return Subtarget; }
 
-public:
+  ScheduleHazardRecognizer *
+  CreateTargetPostRAHazardRecognizer(const InstrItineraryData *II) const;
+
   // Branch analysis.
   virtual bool AnalyzeBranch(MachineBasicBlock &MBB, MachineBasicBlock *&TBB,
                              MachineBasicBlock *&FBB,
@@ -393,6 +399,38 @@
                              const MachineInstr *UseMI, unsigned UseIdx) const;
   bool hasLowDefLatency(const InstrItineraryData *ItinData,
                         const MachineInstr *DefMI, unsigned DefIdx) const;
+
+private:
+  /// Modeling special VFP / NEON fp MLA / MLS hazards.
+
+  /// MLxEntryMap - Map fp MLA / MLS to the corresponding entry in the internal
+  /// MLx table.
+  DenseMap<unsigned, unsigned> MLxEntryMap;
+
+  /// MLxHazardOpcodes - Set of add / sub and multiply opcodes that would cause
+  /// stalls when scheduled together with fp MLA / MLS opcodes.
+  SmallSet<unsigned, 16> MLxHazardOpcodes;
+
+public:
+  /// isFpMLxInstruction - Return true if the specified opcode is a fp MLA / MLS
+  /// instruction.
+  bool isFpMLxInstruction(unsigned Opcode) const {
+    return MLxEntryMap.count(Opcode);
+  }
+
+  /// isFpMLxInstruction - This version also returns the multiply opcode and the
+  /// addition / subtraction opcode to expand to. Return true for 'HasLane' for
+  /// the MLX instructions with an extra lane operand.
+  bool isFpMLxInstruction(unsigned Opcode, unsigned &MulOpc,
+                          unsigned &AddSubOpc, bool &NegAcc,
+                          bool &HasLane) const;
+
+  /// canCauseFpMLxStall - Return true if an instruction of the specified opcode
+  /// will cause stalls when scheduled after (within 4-cycle window) a fp
+  /// MLA / MLS instruction.
+  bool canCauseFpMLxStall(unsigned Opcode) const {
+    return MLxHazardOpcodes.count(Opcode);
+  }
 };
 
 static inline
diff --git a/lib/Target/ARM/ARMHazardRecognizer.cpp b/lib/Target/ARM/ARMHazardRecognizer.cpp
new file mode 100644
index 0000000..317934f
--- /dev/null
+++ b/lib/Target/ARM/ARMHazardRecognizer.cpp
@@ -0,0 +1,114 @@
+//===-- ARMHazardRecognizer.cpp - ARM postra hazard recognizer ------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "ARMHazardRecognizer.h"
+#include "ARMBaseInstrInfo.h"
+#include "ARMSubtarget.h"
+#include "llvm/CodeGen/MachineInstr.h"
+#include "llvm/CodeGen/ScheduleDAG.h"
+#include "llvm/Target/TargetRegisterInfo.h"
+using namespace llvm;
+
+static bool hasRAWHazard(MachineInstr *DefMI, MachineInstr *MI,
+                         const TargetRegisterInfo &TRI) {
+  // FIXME: Detect integer instructions properly.
+  const TargetInstrDesc &TID = MI->getDesc();
+  unsigned Domain = TID.TSFlags & ARMII::DomainMask;
+  if (Domain == ARMII::DomainVFP) {
+    unsigned Opcode = MI->getOpcode();
+    if (Opcode == ARM::VSTRS || Opcode == ARM::VSTRD ||
+        Opcode == ARM::VMOVRS || Opcode == ARM::VMOVRRD)
+      return false;
+  } else if (Domain == ARMII::DomainNEON) {
+    if (MI->getDesc().mayStore() || MI->getDesc().mayLoad())
+      return false;
+  } else
+    return false;
+  return MI->readsRegister(DefMI->getOperand(0).getReg(), &TRI);
+}
+
+ScheduleHazardRecognizer::HazardType
+ARMHazardRecognizer::getHazardType(SUnit *SU) {
+  MachineInstr *MI = SU->getInstr();
+
+  if (!MI->isDebugValue()) {
+    if (ITBlockSize && MI != ITBlockMIs[ITBlockSize-1])
+      return Hazard;
+
+    // Look for special VMLA / VMLS hazards. A VMUL / VADD / VSUB following
+    // a VMLA / VMLS will cause 4 cycle stall.
+    const TargetInstrDesc &TID = MI->getDesc();
+    if (LastMI && (TID.TSFlags & ARMII::DomainMask) != ARMII::DomainGeneral) {
+      MachineInstr *DefMI = LastMI;
+      const TargetInstrDesc &LastTID = LastMI->getDesc();
+      // Skip over one non-VFP / NEON instruction.
+      if (!LastTID.isBarrier() &&
+          (LastTID.TSFlags & ARMII::DomainMask) == ARMII::DomainGeneral) {
+        MachineBasicBlock::iterator I = LastMI;
+        if (I != LastMI->getParent()->begin()) {
+          I = llvm::prior(I);
+          DefMI = &*I;
+        }
+      }
+
+      if (TII.isFpMLxInstruction(DefMI->getOpcode()) &&
+          (TII.canCauseFpMLxStall(MI->getOpcode()) ||
+           hasRAWHazard(DefMI, MI, TRI))) {
+        // Try to schedule another instruction for the next 4 cycles.
+        if (Stalls == 0)
+          Stalls = 4;
+        return Hazard;
+      }
+    }
+  }
+
+  return PostRAHazardRecognizer::getHazardType(SU);
+}
+
+void ARMHazardRecognizer::Reset() {
+  LastMI = 0;
+  Stalls = 0;
+  ITBlockSize = 0;
+  PostRAHazardRecognizer::Reset();
+}
+
+void ARMHazardRecognizer::EmitInstruction(SUnit *SU) {
+  MachineInstr *MI = SU->getInstr();
+  unsigned Opcode = MI->getOpcode();
+  if (ITBlockSize) {
+    --ITBlockSize;
+  } else if (Opcode == ARM::t2IT) {
+    unsigned Mask = MI->getOperand(1).getImm();
+    unsigned NumTZ = CountTrailingZeros_32(Mask);
+    assert(NumTZ <= 3 && "Invalid IT mask!");
+    ITBlockSize = 4 - NumTZ;
+    MachineBasicBlock::iterator I = MI;
+    for (unsigned i = 0; i < ITBlockSize; ++i) {
+      // Advance to the next instruction, skipping any dbg_value instructions.
+      do {
+        ++I;
+      } while (I->isDebugValue());
+      ITBlockMIs[ITBlockSize-1-i] = &*I;
+    }
+  }
+
+  if (!MI->isDebugValue()) {
+    LastMI = MI;
+    Stalls = 0;
+  }
+
+  PostRAHazardRecognizer::EmitInstruction(SU);
+}
+
+void ARMHazardRecognizer::AdvanceCycle() {
+  if (Stalls && --Stalls == 0)
+    // Stalled for 4 cycles but still can't schedule any other instructions.
+    LastMI = 0;
+  PostRAHazardRecognizer::AdvanceCycle();
+}
diff --git a/lib/Target/ARM/ARMHazardRecognizer.h b/lib/Target/ARM/ARMHazardRecognizer.h
new file mode 100644
index 0000000..d1919d8
--- /dev/null
+++ b/lib/Target/ARM/ARMHazardRecognizer.h
@@ -0,0 +1,53 @@
+//===-- ARMHazardRecognizer.h - ARM Hazard Recognizers ----------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file defines hazard recognizers for scheduling ARM functions.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef ARMHAZARDRECOGNIZER_H
+#define ARMHAZARDRECOGNIZER_H
+
+#include "llvm/CodeGen/PostRAHazardRecognizer.h"
+
+namespace llvm {
+
+class ARMBaseInstrInfo;
+class ARMBaseRegisterInfo;
+class ARMSubtarget;
+class MachineInstr;
+
+class ARMHazardRecognizer : public PostRAHazardRecognizer {
+  const ARMBaseInstrInfo &TII;
+  const ARMBaseRegisterInfo &TRI;
+  const ARMSubtarget &STI;
+
+  MachineInstr *LastMI;
+  unsigned Stalls;
+  unsigned ITBlockSize;  // No. of MIs in current IT block yet to be scheduled.
+  MachineInstr *ITBlockMIs[4];
+
+public:
+  ARMHazardRecognizer(const InstrItineraryData *ItinData,
+                      const ARMBaseInstrInfo &tii,
+                      const ARMBaseRegisterInfo &tri,
+                      const ARMSubtarget &sti) :
+    PostRAHazardRecognizer(ItinData), TII(tii), TRI(tri), STI(sti),
+    LastMI(0), ITBlockSize(0) {}
+
+  virtual HazardType getHazardType(SUnit *SU);
+  virtual void Reset();
+  virtual void EmitInstruction(SUnit *SU);
+  virtual void AdvanceCycle();
+};
+
+
+} // end namespace llvm
+
+#endif // ARMHAZARDRECOGNIZER_H
diff --git a/lib/Target/ARM/ARMISelDAGToDAG.cpp b/lib/Target/ARM/ARMISelDAGToDAG.cpp
index 96bdf48..bfba114 100644
--- a/lib/Target/ARM/ARMISelDAGToDAG.cpp
+++ b/lib/Target/ARM/ARMISelDAGToDAG.cpp
@@ -13,6 +13,7 @@
 
 #define DEBUG_TYPE "arm-isel"
 #include "ARM.h"
+#include "ARMBaseInstrInfo.h"
 #include "ARMAddressingModes.h"
 #include "ARMTargetMachine.h"
 #include "llvm/CallingConv.h"
@@ -41,6 +42,11 @@
   cl::desc("Disable isel of shifter-op"),
   cl::init(false));
 
+static cl::opt<bool>
+CheckVMLxHazard("check-vmlx-hazard", cl::Hidden,
+  cl::desc("Check fp vmla / vmls hazard at isel time"),
+  cl::init(false));
+
 //===--------------------------------------------------------------------===//
 /// ARMDAGToDAGISel - ARM specific code to select ARM machine
 /// instructions for SelectionDAG operations.
@@ -54,6 +60,7 @@
 
 class ARMDAGToDAGISel : public SelectionDAGISel {
   ARMBaseTargetMachine &TM;
+  const ARMBaseInstrInfo *TII;
 
   /// Subtarget - Keep a pointer to the ARMSubtarget around so that we can
   /// make the right decision when generating code for different targets.
@@ -63,7 +70,8 @@
   explicit ARMDAGToDAGISel(ARMBaseTargetMachine &tm,
                            CodeGenOpt::Level OptLevel)
     : SelectionDAGISel(tm, OptLevel), TM(tm),
-    Subtarget(&TM.getSubtarget<ARMSubtarget>()) {
+      TII(static_cast<const ARMBaseInstrInfo*>(TM.getInstrInfo())),
+      Subtarget(&TM.getSubtarget<ARMSubtarget>()) {
   }
 
   virtual const char *getPassName() const {
@@ -78,6 +86,8 @@
 
   SDNode *Select(SDNode *N);
 
+
+  bool hasNoVMLxHazardUse(SDNode *N) const;
   bool isShifterOpProfitable(const SDValue &Shift,
                              ARM_AM::ShiftOpc ShOpcVal, unsigned ShAmt);
   bool SelectShifterOperandReg(SDValue N, SDValue &A,
@@ -272,6 +282,50 @@
          isInt32Immediate(N->getOperand(1).getNode(), Imm);
 }
 
+/// hasNoVMLxHazardUse - Return true if it's desirable to select a FP MLA / MLS
+/// node. VFP / NEON fp VMLA / VMLS instructions have special RAW hazards (at
+/// least on current ARM implementations) which should be avoidded.
+bool ARMDAGToDAGISel::hasNoVMLxHazardUse(SDNode *N) const {
+  if (OptLevel == CodeGenOpt::None)
+    return true;
+
+  if (!CheckVMLxHazard)
+    return true;
+
+  if (!Subtarget->isCortexA8() && !Subtarget->isCortexA9())
+    return true;
+
+  if (!N->hasOneUse())
+    return false;
+
+  SDNode *Use = *N->use_begin();
+  if (Use->getOpcode() == ISD::CopyToReg)
+    return true;
+  if (Use->isMachineOpcode()) {
+    const TargetInstrDesc &TID = TII->get(Use->getMachineOpcode());
+    if (TID.mayStore())
+      return true;
+    unsigned Opcode = TID.getOpcode();
+    if (Opcode == ARM::VMOVRS || Opcode == ARM::VMOVRRD)
+      return true;
+    // vmlx feeding into another vmlx. We actually want to unfold
+    // the use later in the MLxExpansion pass. e.g.
+    // vmla
+    // vmla (stall 8 cycles)
+    //
+    // vmul (5 cycles)
+    // vadd (5 cycles)
+    // vmla
+    // This adds up to about 18 - 19 cycles.
+    //
+    // vmla
+    // vmul (stall 4 cycles)
+    // vadd adds up to about 14 cycles.
+    return TII->isFpMLxInstruction(Opcode);
+  }
+
+  return false;
+}
 
 bool ARMDAGToDAGISel::isShifterOpProfitable(const SDValue &Shift,
                                             ARM_AM::ShiftOpc ShOpcVal,
diff --git a/lib/Target/ARM/ARMInstrInfo.td b/lib/Target/ARM/ARMInstrInfo.td
index 9ca36d8..8a59ff5 100644
--- a/lib/Target/ARM/ARMInstrInfo.td
+++ b/lib/Target/ARM/ARMInstrInfo.td
@@ -175,7 +175,7 @@
 // FIXME: Eventually this will be just "hasV6T2Ops".
 def UseMovt          : Predicate<"Subtarget->useMovt()">;
 def DontUseMovt      : Predicate<"!Subtarget->useMovt()">;
-def UseVMLx          : Predicate<"Subtarget->useVMLx()">;
+def UseFPVMLx        : Predicate<"Subtarget->useFPVMLx()">;
 
 //===----------------------------------------------------------------------===//
 // ARM Flag Definitions.
@@ -279,6 +279,21 @@
   return N->hasOneUse();
 }]>;
 
+// An 'fmul' node with a single use.
+def fmul_su : PatFrag<(ops node:$lhs, node:$rhs), (fmul node:$lhs, node:$rhs),[{
+  return N->hasOneUse();
+}]>;
+
+// An 'fadd' node which checks for single non-hazardous use.
+def fadd_mlx : PatFrag<(ops node:$lhs, node:$rhs),(fadd node:$lhs, node:$rhs),[{
+  return hasNoVMLxHazardUse(N);
+}]>;
+
+// An 'fsub' node which checks for single non-hazardous use.
+def fsub_mlx : PatFrag<(ops node:$lhs, node:$rhs),(fsub node:$lhs, node:$rhs),[{
+  return hasNoVMLxHazardUse(N);
+}]>;
+
 //===----------------------------------------------------------------------===//
 // Operand Definitions.
 //
diff --git a/lib/Target/ARM/ARMInstrNEON.td b/lib/Target/ARM/ARMInstrNEON.td
index f5b30c3..bc45d78 100644
--- a/lib/Target/ARM/ARMInstrNEON.td
+++ b/lib/Target/ARM/ARMInstrNEON.td
@@ -1907,7 +1907,7 @@
 // Multiply-Add/Sub operations: single-, double- and quad-register.
 class N3VSMulOp<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
                 InstrItinClass itin, string OpcodeStr, string Dt,
-                ValueType Ty, SDNode MulOp, SDNode OpNode>
+                ValueType Ty, SDPatternOperator MulOp, SDNode OpNode>
   : N3V<op24, op23, op21_20, op11_8, 0, op4,
         (outs DPR_VFP2:$Vd),
         (ins DPR_VFP2:$src1, DPR_VFP2:$Vn, DPR_VFP2:$Vm), N3RegFrm, itin,
@@ -1915,7 +1915,7 @@
 
 class N3VDMulOp<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
                 InstrItinClass itin, string OpcodeStr, string Dt,
-                ValueType Ty, SDNode MulOp, SDNode OpNode>
+                ValueType Ty, SDPatternOperator MulOp, SDPatternOperator OpNode>
   : N3V<op24, op23, op21_20, op11_8, 0, op4,
         (outs DPR:$Vd), (ins DPR:$src1, DPR:$Vn, DPR:$Vm), N3RegFrm, itin,
         OpcodeStr, Dt, "$Vd, $Vn, $Vm", "$src1 = $Vd",
@@ -1924,7 +1924,7 @@
 
 class N3VDMulOpSL<bits<2> op21_20, bits<4> op11_8, InstrItinClass itin,
                   string OpcodeStr, string Dt,
-                  ValueType Ty, SDNode MulOp, SDNode ShOp>
+                  ValueType Ty, SDPatternOperator MulOp, SDPatternOperator ShOp>
   : N3V<0, 1, op21_20, op11_8, 1, 0,
         (outs DPR:$Vd),
         (ins DPR:$src1, DPR:$Vn, DPR_VFP2:$Vm, nohash_imm:$lane),
@@ -1951,7 +1951,7 @@
 
 class N3VQMulOp<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
                 InstrItinClass itin, string OpcodeStr, string Dt, ValueType Ty,
-                SDNode MulOp, SDNode OpNode>
+                SDPatternOperator MulOp, SDPatternOperator OpNode>
   : N3V<op24, op23, op21_20, op11_8, 1, op4,
         (outs QPR:$Vd), (ins QPR:$src1, QPR:$Vn, QPR:$Vm), N3RegFrm, itin,
         OpcodeStr, Dt, "$Vd, $Vn, $Vm", "$src1 = $Vd",
@@ -1959,7 +1959,7 @@
                              (Ty (MulOp QPR:$Vn, QPR:$Vm)))))]>;
 class N3VQMulOpSL<bits<2> op21_20, bits<4> op11_8, InstrItinClass itin,
                   string OpcodeStr, string Dt, ValueType ResTy, ValueType OpTy,
-                  SDNode MulOp, SDNode ShOp>
+                  SDPatternOperator MulOp, SDPatternOperator ShOp>
   : N3V<1, 1, op21_20, op11_8, 1, 0,
         (outs QPR:$Vd),
         (ins QPR:$src1, QPR:$Vn, DPR_VFP2:$Vm, nohash_imm:$lane),
@@ -3282,15 +3282,19 @@
 defm VMLA     : N3VMulOp_QHS<0, 0, 0b1001, 0, IIC_VMACi16D, IIC_VMACi32D,
                              IIC_VMACi16Q, IIC_VMACi32Q, "vmla", "i", add>;
 def  VMLAfd   : N3VDMulOp<0, 0, 0b00, 0b1101, 1, IIC_VMACD, "vmla", "f32",
-                          v2f32, fmul, fadd>;
+                          v2f32, fmul_su, fadd_mlx>,
+                Requires<[HasNEON, UseFPVMLx]>;
 def  VMLAfq   : N3VQMulOp<0, 0, 0b00, 0b1101, 1, IIC_VMACQ, "vmla", "f32",
-                          v4f32, fmul, fadd>;
+                          v4f32, fmul_su, fadd_mlx>,
+                Requires<[HasNEON, UseFPVMLx]>;
 defm VMLAsl   : N3VMulOpSL_HS<0b0000, IIC_VMACi16D, IIC_VMACi32D,
                               IIC_VMACi16Q, IIC_VMACi32Q, "vmla", "i", add>;
 def  VMLAslfd : N3VDMulOpSL<0b10, 0b0001, IIC_VMACD, "vmla", "f32",
-                            v2f32, fmul, fadd>;
+                            v2f32, fmul_su, fadd_mlx>,
+                Requires<[HasNEON, UseFPVMLx]>;
 def  VMLAslfq : N3VQMulOpSL<0b10, 0b0001, IIC_VMACQ, "vmla", "f32",
-                            v4f32, v2f32, fmul, fadd>;
+                            v4f32, v2f32, fmul_su, fadd_mlx>,
+                Requires<[HasNEON, UseFPVMLx]>;
 
 def : Pat<(v8i16 (add (v8i16 QPR:$src1),
                   (mul (v8i16 QPR:$src2),
@@ -3308,14 +3312,15 @@
                                       (DSubReg_i32_reg imm:$lane))),
                               (SubReg_i32_lane imm:$lane)))>;
 
-def : Pat<(v4f32 (fadd (v4f32 QPR:$src1),
-                  (fmul (v4f32 QPR:$src2),
+def : Pat<(v4f32 (fadd_mlx (v4f32 QPR:$src1),
+                  (fmul_su (v4f32 QPR:$src2),
                         (v4f32 (NEONvduplane (v4f32 QPR:$src3), imm:$lane))))),
           (v4f32 (VMLAslfq (v4f32 QPR:$src1),
                            (v4f32 QPR:$src2),
                            (v2f32 (EXTRACT_SUBREG QPR:$src3,
                                    (DSubReg_i32_reg imm:$lane))),
-                           (SubReg_i32_lane imm:$lane)))>;
+                           (SubReg_i32_lane imm:$lane)))>,
+          Requires<[HasNEON, UseFPVMLx]>;
 
 //   VMLAL    : Vector Multiply Accumulate Long (Q += D * D)
 defm VMLALs   : N3VLMulOp_QHS<0,1,0b1000,0, IIC_VMACi16D, IIC_VMACi32D,
@@ -3335,15 +3340,19 @@
 defm VMLS     : N3VMulOp_QHS<1, 0, 0b1001, 0, IIC_VMACi16D, IIC_VMACi32D,
                              IIC_VMACi16Q, IIC_VMACi32Q, "vmls", "i", sub>;
 def  VMLSfd   : N3VDMulOp<0, 0, 0b10, 0b1101, 1, IIC_VMACD, "vmls", "f32",
-                          v2f32, fmul, fsub>;
+                          v2f32, fmul_su, fsub_mlx>,
+                Requires<[HasNEON, UseFPVMLx]>;
 def  VMLSfq   : N3VQMulOp<0, 0, 0b10, 0b1101, 1, IIC_VMACQ, "vmls", "f32",
-                          v4f32, fmul, fsub>;
+                          v4f32, fmul_su, fsub_mlx>,
+                Requires<[HasNEON, UseFPVMLx]>;
 defm VMLSsl   : N3VMulOpSL_HS<0b0100, IIC_VMACi16D, IIC_VMACi32D,
                               IIC_VMACi16Q, IIC_VMACi32Q, "vmls", "i", sub>;
 def  VMLSslfd : N3VDMulOpSL<0b10, 0b0101, IIC_VMACD, "vmls", "f32",
-                            v2f32, fmul, fsub>;
+                            v2f32, fmul_su, fsub_mlx>,
+                Requires<[HasNEON, UseFPVMLx]>;
 def  VMLSslfq : N3VQMulOpSL<0b10, 0b0101, IIC_VMACQ, "vmls", "f32",
-                            v4f32, v2f32, fmul, fsub>;
+                            v4f32, v2f32, fmul_su, fsub_mlx>,
+                Requires<[HasNEON, UseFPVMLx]>;
 
 def : Pat<(v8i16 (sub (v8i16 QPR:$src1),
                   (mul (v8i16 QPR:$src2),
@@ -3361,13 +3370,14 @@
                                       (DSubReg_i32_reg imm:$lane))),
                               (SubReg_i32_lane imm:$lane)))>;
 
-def : Pat<(v4f32 (fsub (v4f32 QPR:$src1),
-                  (fmul (v4f32 QPR:$src2),
+def : Pat<(v4f32 (fsub_mlx (v4f32 QPR:$src1),
+                  (fmul_su (v4f32 QPR:$src2),
                         (v4f32 (NEONvduplane (v4f32 QPR:$src3), imm:$lane))))),
           (v4f32 (VMLSslfq (v4f32 QPR:$src1), (v4f32 QPR:$src2),
                            (v2f32 (EXTRACT_SUBREG QPR:$src3,
                                    (DSubReg_i32_reg imm:$lane))),
-                           (SubReg_i32_lane imm:$lane)))>;
+                           (SubReg_i32_lane imm:$lane)))>,
+          Requires<[HasNEON, UseFPVMLx]>;
 
 //   VMLSL    : Vector Multiply Subtract Long (Q -= D * D)
 defm VMLSLs   : N3VLMulOp_QHS<0,1,0b1010,0, IIC_VMACi16D, IIC_VMACi32D,
@@ -4706,15 +4716,17 @@
 // vml[as].f32 can cause 4-8 cycle stalls in following ASIMD instructions, so
 // we want to avoid them for now. e.g., alternating vmla/vadd instructions.
 
-//let neverHasSideEffects = 1 in
-//def VMLAfd_sfp : N3VSMulOp<0,0,0b00,0b1101,1, IIC_VMACD, "vmla", "f32",
-//                           v2f32, fmul, fadd>;
-//def : N3VSMulOpPat<fmul, fadd, VMLAfd_sfp>;
+let neverHasSideEffects = 1 in
+def VMLAfd_sfp : N3VSMulOp<0,0,0b00,0b1101,1, IIC_VMACD, "vmla", "f32",
+                           v2f32, fmul_su, fadd>;
+def : N3VSMulOpPat<fmul, fadd, VMLAfd_sfp>,
+      Requires<[HasNEON, UseNEONForFP, UseFPVMLx]>;
 
-//let neverHasSideEffects = 1 in
-//def VMLSfd_sfp : N3VSMulOp<0,0,0b10,0b1101,1, IIC_VMACD, "vmls", "f32",
-//                           v2f32, fmul, fsub>;
-//def : N3VSMulOpPat<fmul, fsub, VMLSfd_sfp>;
+let neverHasSideEffects = 1 in
+def VMLSfd_sfp : N3VSMulOp<0,0,0b10,0b1101,1, IIC_VMACD, "vmls", "f32",
+                           v2f32, fmul_su, fsub>;
+def : N3VSMulOpPat<fmul, fsub, VMLSfd_sfp>,
+      Requires<[HasNEON, UseNEONForFP, UseFPVMLx]>;
 
 // Vector Absolute used for single-precision FP
 let neverHasSideEffects = 1 in
diff --git a/lib/Target/ARM/ARMInstrVFP.td b/lib/Target/ARM/ARMInstrVFP.td
index d622169..568c74a 100644
--- a/lib/Target/ARM/ARMInstrVFP.td
+++ b/lib/Target/ARM/ARMInstrVFP.td
@@ -751,93 +751,93 @@
 def VMLAD : ADbI<0b11100, 0b00, 0, 0,
                  (outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm),
                  IIC_fpMAC64, "vmla", ".f64\t$Dd, $Dn, $Dm",
-                 [(set DPR:$Dd, (fadd (fmul DPR:$Dn, DPR:$Dm),
-                                      (f64 DPR:$Ddin)))]>,
+                 [(set DPR:$Dd, (fadd_mlx (fmul_su DPR:$Dn, DPR:$Dm),
+                                          (f64 DPR:$Ddin)))]>,
               RegConstraint<"$Ddin = $Dd">,
-              Requires<[HasVFP2,UseVMLx]>;
+              Requires<[HasVFP2,UseFPVMLx]>;
 
 def VMLAS : ASbIn<0b11100, 0b00, 0, 0,
                   (outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm),
                   IIC_fpMAC32, "vmla", ".f32\t$Sd, $Sn, $Sm",
-                  [(set SPR:$Sd, (fadd (fmul SPR:$Sn, SPR:$Sm),
-                                       SPR:$Sdin))]>,
+                  [(set SPR:$Sd, (fadd_mlx (fmul_su SPR:$Sn, SPR:$Sm),
+                                           SPR:$Sdin))]>,
               RegConstraint<"$Sdin = $Sd">,
-              Requires<[HasVFP2,DontUseNEONForFP,UseVMLx]>;
+              Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]>;
 
-def : Pat<(fadd DPR:$dstin, (fmul DPR:$a, (f64 DPR:$b))),
+def : Pat<(fadd_mlx DPR:$dstin, (fmul_su DPR:$a, (f64 DPR:$b))),
           (VMLAD DPR:$dstin, DPR:$a, DPR:$b)>,
-          Requires<[HasVFP2,UseVMLx]>;
-def : Pat<(fadd SPR:$dstin, (fmul SPR:$a, SPR:$b)),
+          Requires<[HasVFP2,UseFPVMLx]>;
+def : Pat<(fadd_mlx SPR:$dstin, (fmul_su SPR:$a, SPR:$b)),
           (VMLAS SPR:$dstin, SPR:$a, SPR:$b)>,
-          Requires<[HasVFP2,DontUseNEONForFP, UseVMLx]>;
+          Requires<[HasVFP2,DontUseNEONForFP, UseFPVMLx]>;
 
 def VMLSD : ADbI<0b11100, 0b00, 1, 0,
                  (outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm),
                  IIC_fpMAC64, "vmls", ".f64\t$Dd, $Dn, $Dm",
-                 [(set DPR:$Dd, (fadd (fneg (fmul DPR:$Dn,DPR:$Dm)),
-                                            (f64 DPR:$Ddin)))]>,
+                 [(set DPR:$Dd, (fadd_mlx (fneg (fmul_su DPR:$Dn,DPR:$Dm)),
+                                          (f64 DPR:$Ddin)))]>,
               RegConstraint<"$Ddin = $Dd">,
-              Requires<[HasVFP2,UseVMLx]>;
+              Requires<[HasVFP2,UseFPVMLx]>;
 
 def VMLSS : ASbIn<0b11100, 0b00, 1, 0,
                   (outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm),
                   IIC_fpMAC32, "vmls", ".f32\t$Sd, $Sn, $Sm",
-                  [(set SPR:$Sd, (fadd (fneg (fmul SPR:$Sn, SPR:$Sm)),
-                                       SPR:$Sdin))]>,
+                  [(set SPR:$Sd, (fadd_mlx (fneg (fmul_su SPR:$Sn, SPR:$Sm)),
+                                           SPR:$Sdin))]>,
               RegConstraint<"$Sdin = $Sd">,
-              Requires<[HasVFP2,DontUseNEONForFP,UseVMLx]>;
+              Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]>;
 
-def : Pat<(fsub DPR:$dstin, (fmul DPR:$a, (f64 DPR:$b))),
+def : Pat<(fsub_mlx DPR:$dstin, (fmul_su DPR:$a, (f64 DPR:$b))),
           (VMLSD DPR:$dstin, DPR:$a, DPR:$b)>,
-          Requires<[HasVFP2,UseVMLx]>;
-def : Pat<(fsub SPR:$dstin, (fmul SPR:$a, SPR:$b)),
+          Requires<[HasVFP2,UseFPVMLx]>;
+def : Pat<(fsub_mlx SPR:$dstin, (fmul_su SPR:$a, SPR:$b)),
           (VMLSS SPR:$dstin, SPR:$a, SPR:$b)>,
-          Requires<[HasVFP2,DontUseNEONForFP,UseVMLx]>;
+          Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]>;
 
 def VNMLAD : ADbI<0b11100, 0b01, 1, 0,
                   (outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm),
                   IIC_fpMAC64, "vnmla", ".f64\t$Dd, $Dn, $Dm",
-                  [(set DPR:$Dd,(fsub (fneg (fmul DPR:$Dn,DPR:$Dm)),
-                                      (f64 DPR:$Ddin)))]>,
+                  [(set DPR:$Dd,(fsub_mlx (fneg (fmul_su DPR:$Dn,DPR:$Dm)),
+                                          (f64 DPR:$Ddin)))]>,
                 RegConstraint<"$Ddin = $Dd">,
-                Requires<[HasVFP2,UseVMLx]>;
+                Requires<[HasVFP2,UseFPVMLx]>;
 
 def VNMLAS : ASbI<0b11100, 0b01, 1, 0,
                   (outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm),
                   IIC_fpMAC32, "vnmla", ".f32\t$Sd, $Sn, $Sm",
-                  [(set SPR:$Sd, (fsub (fneg (fmul SPR:$Sn, SPR:$Sm)),
-                                       SPR:$Sdin))]>,
+                  [(set SPR:$Sd, (fsub_mlx (fneg (fmul_su SPR:$Sn, SPR:$Sm)),
+                                           SPR:$Sdin))]>,
                 RegConstraint<"$Sdin = $Sd">,
-                Requires<[HasVFP2,DontUseNEONForFP,UseVMLx]>;
+                Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]>;
 
-def : Pat<(fsub (fneg (fmul DPR:$a, (f64 DPR:$b))), DPR:$dstin),
+def : Pat<(fsub_mlx (fneg (fmul_su DPR:$a, (f64 DPR:$b))), DPR:$dstin),
           (VNMLAD DPR:$dstin, DPR:$a, DPR:$b)>,
-          Requires<[HasVFP2,UseVMLx]>;
-def : Pat<(fsub (fneg (fmul SPR:$a, SPR:$b)), SPR:$dstin),
+          Requires<[HasVFP2,UseFPVMLx]>;
+def : Pat<(fsub_mlx (fneg (fmul_su SPR:$a, SPR:$b)), SPR:$dstin),
           (VNMLAS SPR:$dstin, SPR:$a, SPR:$b)>,
-          Requires<[HasVFP2,DontUseNEONForFP,UseVMLx]>;
+          Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]>;
 
 def VNMLSD : ADbI<0b11100, 0b01, 0, 0,
                   (outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm),
                   IIC_fpMAC64, "vnmls", ".f64\t$Dd, $Dn, $Dm",
-                  [(set DPR:$Dd, (fsub (fmul DPR:$Dn, DPR:$Dm),
-                                       (f64 DPR:$Ddin)))]>,
+                  [(set DPR:$Dd, (fsub_mlx (fmul_su DPR:$Dn, DPR:$Dm),
+                                           (f64 DPR:$Ddin)))]>,
                RegConstraint<"$Ddin = $Dd">,
-               Requires<[HasVFP2,UseVMLx]>;
+               Requires<[HasVFP2,UseFPVMLx]>;
 
 def VNMLSS : ASbI<0b11100, 0b01, 0, 0,
                   (outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm),
                   IIC_fpMAC32, "vnmls", ".f32\t$Sd, $Sn, $Sm",
-                  [(set SPR:$Sd, (fsub (fmul SPR:$Sn, SPR:$Sm), SPR:$Sdin))]>,
+             [(set SPR:$Sd, (fsub_mlx (fmul_su SPR:$Sn, SPR:$Sm), SPR:$Sdin))]>,
                          RegConstraint<"$Sdin = $Sd">,
-                  Requires<[HasVFP2,DontUseNEONForFP,UseVMLx]>;
+                  Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]>;
 
-def : Pat<(fsub (fmul DPR:$a, (f64 DPR:$b)), DPR:$dstin),
+def : Pat<(fsub_mlx (fmul_su DPR:$a, (f64 DPR:$b)), DPR:$dstin),
           (VNMLSD DPR:$dstin, DPR:$a, DPR:$b)>,
-          Requires<[HasVFP2,UseVMLx]>;
-def : Pat<(fsub (fmul SPR:$a, SPR:$b), SPR:$dstin),
+          Requires<[HasVFP2,UseFPVMLx]>;
+def : Pat<(fsub_mlx (fmul_su SPR:$a, SPR:$b), SPR:$dstin),
           (VNMLSS SPR:$dstin, SPR:$a, SPR:$b)>,
-          Requires<[HasVFP2,DontUseNEONForFP,UseVMLx]>;
+          Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]>;
 
 
 //===----------------------------------------------------------------------===//
diff --git a/lib/Target/ARM/ARMSubtarget.cpp b/lib/Target/ARM/ARMSubtarget.cpp
index e39c30e..5508dc8 100644
--- a/lib/Target/ARM/ARMSubtarget.cpp
+++ b/lib/Target/ARM/ARMSubtarget.cpp
@@ -37,7 +37,7 @@
   , ARMProcFamily(Others)
   , ARMFPUType(None)
   , UseNEONForSinglePrecisionFP(false)
-  , SlowVMLx(false)
+  , SlowFPVMLx(false)
   , SlowFPBrcc(false)
   , IsThumb(isT)
   , ThumbMode(Thumb1)
diff --git a/lib/Target/ARM/ARMSubtarget.h b/lib/Target/ARM/ARMSubtarget.h
index 551b2f9..240364f 100644
--- a/lib/Target/ARM/ARMSubtarget.h
+++ b/lib/Target/ARM/ARMSubtarget.h
@@ -57,9 +57,9 @@
   /// determine if NEON should actually be used.
   bool UseNEONForSinglePrecisionFP;
 
-  /// SlowVMLx - If the VFP2 instructions are available, indicates whether
-  /// the VML[AS] instructions are slow (if so, don't use them).
-  bool SlowVMLx;
+  /// SlowFPVMLx - If the VFP2 / NEON instructions are available, indicates
+  /// whether the FP VML[AS] instructions are slow (if so, don't use them).
+  bool SlowFPVMLx;
 
   /// SlowFPBrcc - True if floating point compare + branch is slow.
   bool SlowFPBrcc;
@@ -176,7 +176,7 @@
   bool hasDivide() const { return HasHardwareDivide; }
   bool hasT2ExtractPack() const { return HasT2ExtractPack; }
   bool hasDataBarrier() const { return HasDataBarrier; }
-  bool useVMLx() const {return hasVFP2() && !SlowVMLx; }
+  bool useFPVMLx() const { return !SlowFPVMLx; }
   bool isFPBrccSlow() const { return SlowFPBrcc; }
   bool isFPOnlySP() const { return FPOnlySP; }
   bool prefers32BitThumb() const { return Pref32BitThumb; }
diff --git a/lib/Target/ARM/ARMTargetMachine.cpp b/lib/Target/ARM/ARMTargetMachine.cpp
index 1c05ab5..89047f4 100644
--- a/lib/Target/ARM/ARMTargetMachine.cpp
+++ b/lib/Target/ARM/ARMTargetMachine.cpp
@@ -16,11 +16,14 @@
 #include "ARM.h"
 #include "llvm/PassManager.h"
 #include "llvm/CodeGen/Passes.h"
+#include "llvm/Support/CommandLine.h"
 #include "llvm/Support/FormattedStream.h"
 #include "llvm/Target/TargetOptions.h"
 #include "llvm/Target/TargetRegistry.h"
 using namespace llvm;
 
+static cl::opt<bool>ExpandMLx("expand-fp-mlx", cl::init(false), cl::Hidden);
+
 static MCAsmInfo *createMCAsmInfo(const Target &T, StringRef TT) {
   Triple TheTriple(TT);
   switch (TheTriple.getOS()) {
@@ -146,6 +149,9 @@
   // FIXME: temporarily disabling load / store optimization pass for Thumb1.
   if (OptLevel != CodeGenOpt::None && !Subtarget.isThumb1Only())
     PM.add(createARMLoadStoreOptimizationPass(true));
+  if (ExpandMLx &&
+      OptLevel != CodeGenOpt::None && Subtarget.hasVFP2())
+    PM.add(createMLxExpansionPass());
 
   return true;
 }
diff --git a/lib/Target/ARM/CMakeLists.txt b/lib/Target/ARM/CMakeLists.txt
index 59a580a..632ab95 100644
--- a/lib/Target/ARM/CMakeLists.txt
+++ b/lib/Target/ARM/CMakeLists.txt
@@ -29,6 +29,7 @@
   ARMFastISel.cpp
   ARMFrameInfo.cpp
   ARMGlobalMerge.cpp
+  ARMHazardRecognizer.cpp
   ARMISelDAGToDAG.cpp
   ARMISelLowering.cpp
   ARMInstrInfo.cpp
@@ -46,7 +47,6 @@
   Thumb1InstrInfo.cpp
   Thumb1FrameInfo.cpp
   Thumb1RegisterInfo.cpp
-  Thumb2HazardRecognizer.cpp
   Thumb2ITBlockPass.cpp
   Thumb2InstrInfo.cpp
   Thumb2RegisterInfo.cpp
diff --git a/lib/Target/ARM/MLxExpansionPass.cpp b/lib/Target/ARM/MLxExpansionPass.cpp
new file mode 100644
index 0000000..ec7257b
--- /dev/null
+++ b/lib/Target/ARM/MLxExpansionPass.cpp
@@ -0,0 +1,324 @@
+//===-- MLxExpansionPass.cpp - Expand MLx instrs to avoid hazards ----------=//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// Expand VFP / NEON floating point MLA / MLS instructions (each to a pair of
+// multiple and add / sub instructions) when special VMLx hazards are detected.
+//
+//===----------------------------------------------------------------------===//
+
+#define DEBUG_TYPE "mlx-expansion"
+#include "ARM.h"
+#include "ARMBaseInstrInfo.h"
+#include "llvm/CodeGen/MachineInstr.h"
+#include "llvm/CodeGen/MachineInstrBuilder.h"
+#include "llvm/CodeGen/MachineFunctionPass.h"
+#include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "llvm/Target/TargetRegisterInfo.h"
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/SmallSet.h"
+#include "llvm/ADT/Statistic.h"
+#include "llvm/Support/CommandLine.h"
+#include "llvm/Support/Debug.h"
+#include "llvm/Support/raw_ostream.h"
+using namespace llvm;
+
+static cl::opt<bool>
+ForceExapnd("expand-all-fp-mlx", cl::init(false), cl::Hidden);
+static cl::opt<unsigned>
+ExpandLimit("expand-limit", cl::init(~0U), cl::Hidden);
+
+STATISTIC(NumExpand, "Number of fp MLA / MLS instructions expanded");
+
+namespace {
+  struct MLxExpansion : public MachineFunctionPass {
+    static char ID;
+    MLxExpansion() : MachineFunctionPass(ID) {}
+
+    virtual bool runOnMachineFunction(MachineFunction &Fn);
+
+    virtual const char *getPassName() const {
+      return "ARM MLA / MLS expansion pass";
+    }
+
+  private:
+    const ARMBaseInstrInfo *TII;
+    const TargetRegisterInfo *TRI;
+    MachineRegisterInfo *MRI;
+
+    unsigned HazardLimit;
+    unsigned MIIdx;
+    MachineInstr* LastMIs[4];
+
+    void clearStack();
+    void pushStack(MachineInstr *MI);
+    MachineInstr *getAccDefMI(MachineInstr *MI) const;
+    unsigned getDefReg(MachineInstr *MI) const;
+    bool hasRAWHazard(unsigned Reg, MachineInstr *MI) const;
+    bool FindMLxHazard(MachineInstr *MI) const;
+    void ExpandFPMLxInstruction(MachineBasicBlock &MBB, MachineInstr *MI,
+                                unsigned MulOpc, unsigned AddSubOpc,
+                                bool NegAcc, bool HasLane);
+    bool ExpandFPMLxInstructions(MachineBasicBlock &MBB);
+  };
+  char MLxExpansion::ID = 0;
+}
+
+void MLxExpansion::clearStack() {
+  std::fill(LastMIs, LastMIs + 4, (MachineInstr*)0);
+  MIIdx = 0;
+}
+
+void MLxExpansion::pushStack(MachineInstr *MI) {
+  LastMIs[MIIdx] = MI;
+  if (++MIIdx == 4)
+    MIIdx = 0;
+}
+
+MachineInstr *MLxExpansion::getAccDefMI(MachineInstr *MI) const {
+  // Look past COPY and INSERT_SUBREG instructions to find the
+  // real definition MI. This is important for _sfp instructions.
+  unsigned Reg = MI->getOperand(1).getReg();
+  if (TargetRegisterInfo::isPhysicalRegister(Reg))
+    return 0;
+
+  MachineBasicBlock *MBB = MI->getParent();
+  MachineInstr *DefMI = MRI->getVRegDef(Reg);
+  while (true) {
+    if (DefMI->getParent() != MBB)
+      break;
+    if (DefMI->isCopyLike()) {
+      Reg = DefMI->getOperand(1).getReg();
+      if (TargetRegisterInfo::isVirtualRegister(Reg)) {
+        DefMI = MRI->getVRegDef(Reg);
+        continue;
+      }
+    } else if (DefMI->isInsertSubreg()) {
+      Reg = DefMI->getOperand(2).getReg();
+      if (TargetRegisterInfo::isVirtualRegister(Reg)) {
+        DefMI = MRI->getVRegDef(Reg);
+        continue;
+      }
+    }
+    break;
+  }
+  return DefMI;
+}
+
+unsigned MLxExpansion::getDefReg(MachineInstr *MI) const {
+  unsigned Reg = MI->getOperand(0).getReg();
+  if (TargetRegisterInfo::isPhysicalRegister(Reg) ||
+      !MRI->hasOneNonDBGUse(Reg))
+    return Reg;
+
+  MachineBasicBlock *MBB = MI->getParent();
+  MachineInstr *UseMI = &*MRI->use_nodbg_begin(Reg);
+  if (UseMI->getParent() != MBB)
+    return Reg;
+
+  while (UseMI->isCopy() || UseMI->isInsertSubreg()) {
+    Reg = UseMI->getOperand(0).getReg();
+    if (TargetRegisterInfo::isPhysicalRegister(Reg) ||
+        !MRI->hasOneNonDBGUse(Reg))
+      return Reg;
+    UseMI = &*MRI->use_nodbg_begin(Reg);
+    if (UseMI->getParent() != MBB)
+      return Reg;
+  }
+
+  return Reg;
+}
+
+bool MLxExpansion::hasRAWHazard(unsigned Reg, MachineInstr *MI) const {
+  const TargetInstrDesc &TID = MI->getDesc();
+  // FIXME: Detect integer instructions properly.
+  unsigned Domain = TID.TSFlags & ARMII::DomainMask;
+  if (Domain == ARMII::DomainVFP) {
+    unsigned Opcode = TID.getOpcode();
+    if (Opcode == ARM::VSTRS || Opcode == ARM::VSTRD ||
+        Opcode == ARM::VMOVRS || Opcode == ARM::VMOVRRD)
+      return false;
+  } else if (Domain == ARMII::DomainNEON) {
+    if (TID.mayStore() || TID.mayLoad())
+      return false;
+  } else {
+    return false;
+  }
+
+  return MI->readsRegister(Reg, TRI);
+  return false;
+}
+
+
+bool MLxExpansion::FindMLxHazard(MachineInstr *MI) const {
+  if (NumExpand >= ExpandLimit)
+    return false;
+
+  if (ForceExapnd)
+    return true;
+
+  MachineInstr *DefMI = getAccDefMI(MI);
+  if (TII->isFpMLxInstruction(DefMI->getOpcode()))
+    // r0 = vmla
+    // r3 = vmla r0, r1, r2
+    // takes 16 - 17 cycles
+    //
+    // r0 = vmla
+    // r4 = vmul r1, r2
+    // r3 = vadd r0, r4
+    // takes about 14 - 15 cycles even with vmul stalling for 4 cycles.
+    return true;
+
+  // If a VMLA.F is followed by an VADD.F or VMUL.F with no RAW hazard, the
+  // VADD.F or VMUL.F will stall 4 cycles before issue. The 4 cycle stall
+  // preserves the in-order retirement of the instructions.
+  // Look at the next few instructions, if *most* of them can cause hazards,
+  // then the scheduler can't *fix* this, we'd better break up the VMLA.
+  for (unsigned i = 1; i <= 4; ++i) {
+    int Idx = ((int)MIIdx - i + 4) % 4;
+    MachineInstr *NextMI = LastMIs[Idx];
+    if (!NextMI)
+      continue;
+
+    if (TII->canCauseFpMLxStall(NextMI->getOpcode()))
+        return true;
+
+    // Look for VMLx RAW hazard.
+    if (hasRAWHazard(getDefReg(MI), NextMI))
+      return true;
+  }
+
+  return false;
+}
+
+/// ExpandFPMLxInstructions - Expand a MLA / MLS instruction into a pair
+/// of MUL + ADD / SUB instructions.
+void
+MLxExpansion::ExpandFPMLxInstruction(MachineBasicBlock &MBB, MachineInstr *MI,
+                                     unsigned MulOpc, unsigned AddSubOpc,
+                                     bool NegAcc, bool HasLane) {
+  unsigned DstReg = MI->getOperand(0).getReg();
+  bool DstDead = MI->getOperand(0).isDead();
+  unsigned AccReg = MI->getOperand(1).getReg();
+  unsigned Src1Reg = MI->getOperand(2).getReg();
+  unsigned Src2Reg = MI->getOperand(3).getReg();
+  bool Src1Kill = MI->getOperand(2).isKill();
+  bool Src2Kill = MI->getOperand(3).isKill();
+  unsigned LaneImm = HasLane ? MI->getOperand(4).getImm() : 0;
+  unsigned NextOp = HasLane ? 5 : 4;
+  ARMCC::CondCodes Pred = (ARMCC::CondCodes)MI->getOperand(NextOp).getImm();
+  unsigned PredReg = MI->getOperand(++NextOp).getReg();
+
+  const TargetInstrDesc &TID1 = TII->get(MulOpc);
+  const TargetInstrDesc &TID2 = TII->get(AddSubOpc);
+  unsigned TmpReg = MRI->createVirtualRegister(TID1.getRegClass(0, TRI));
+
+  MachineInstrBuilder MIB = BuildMI(MBB, *MI, MI->getDebugLoc(), TID1, TmpReg)
+    .addReg(Src1Reg, getKillRegState(Src1Kill))
+    .addReg(Src2Reg, getKillRegState(Src2Kill));
+  if (HasLane)
+    MIB.addImm(LaneImm);
+  MIB.addImm(Pred).addReg(PredReg);
+
+  MIB = BuildMI(MBB, *MI, MI->getDebugLoc(), TID2)
+    .addReg(DstReg, getDefRegState(true) | getDeadRegState(DstDead));
+
+  if (NegAcc) {
+    bool AccKill = MRI->hasOneNonDBGUse(AccReg);
+    MIB.addReg(TmpReg, getKillRegState(true))
+       .addReg(AccReg, getKillRegState(AccKill));
+  } else {
+    MIB.addReg(AccReg).addReg(TmpReg, getKillRegState(true));
+  }
+  MIB.addImm(Pred).addReg(PredReg);
+
+  DEBUG({
+      dbgs() << "Expanding: " << *MI;
+      dbgs() << "  to:\n";
+      MachineBasicBlock::iterator MII = MI;
+      MII = llvm::prior(MII);
+      MachineInstr &MI2 = *MII;
+      MII = llvm::prior(MII);
+      MachineInstr &MI1 = *MII;
+      dbgs() << "    " << MI1;
+      dbgs() << "    " << MI2;
+   });
+
+  MI->eraseFromParent();
+  ++NumExpand;
+}
+
+bool MLxExpansion::ExpandFPMLxInstructions(MachineBasicBlock &MBB) {
+  bool Changed = false;
+
+  clearStack();
+
+  unsigned Skip = 0;
+  MachineBasicBlock::reverse_iterator MII = MBB.rbegin(), E = MBB.rend();
+  while (MII != E) {
+    MachineInstr *MI = &*MII;
+
+    if (MI->isLabel() || MI->isImplicitDef() || MI->isCopy()) {
+      ++MII;
+      continue;
+    }
+
+    const TargetInstrDesc &TID = MI->getDesc();
+    if (TID.isBarrier()) {
+      clearStack();
+      Skip = 0;
+      ++MII;
+      continue;
+    }
+
+    unsigned Domain = TID.TSFlags & ARMII::DomainMask;
+    if (Domain == ARMII::DomainGeneral) {
+      if (++Skip == 2)
+        // Assume dual issues of non-VFP / NEON instructions.
+        pushStack(0);
+    } else {
+      Skip = 0;
+
+      unsigned MulOpc, AddSubOpc;
+      bool NegAcc, HasLane;
+      if (!TII->isFpMLxInstruction(TID.getOpcode(),
+                                   MulOpc, AddSubOpc, NegAcc, HasLane) ||
+          !FindMLxHazard(MI))
+        pushStack(MI);
+      else {
+        ExpandFPMLxInstruction(MBB, MI, MulOpc, AddSubOpc, NegAcc, HasLane);
+        E = MBB.rend(); // May have changed if MI was the 1st instruction.
+        Changed = true;
+        continue;
+      }
+    }
+
+    ++MII;
+  }
+
+  return Changed;
+}
+
+bool MLxExpansion::runOnMachineFunction(MachineFunction &Fn) {
+  TII = static_cast<const ARMBaseInstrInfo*>(Fn.getTarget().getInstrInfo());
+  TRI = Fn.getTarget().getRegisterInfo();
+  MRI = &Fn.getRegInfo();
+
+  bool Modified = false;
+  for (MachineFunction::iterator MFI = Fn.begin(), E = Fn.end(); MFI != E;
+       ++MFI) {
+    MachineBasicBlock &MBB = *MFI;
+    Modified |= ExpandFPMLxInstructions(MBB);
+  }
+
+  return Modified;
+}
+
+FunctionPass *llvm::createMLxExpansionPass() {
+  return new MLxExpansion();
+}
diff --git a/lib/Target/ARM/Thumb2HazardRecognizer.cpp b/lib/Target/ARM/Thumb2HazardRecognizer.cpp
deleted file mode 100644
index 172908d..0000000
--- a/lib/Target/ARM/Thumb2HazardRecognizer.cpp
+++ /dev/null
@@ -1,53 +0,0 @@
-//===-- Thumb2HazardRecognizer.cpp - Thumb2 postra hazard recognizer ------===//
-//
-//                     The LLVM Compiler Infrastructure
-//
-// This file is distributed under the University of Illinois Open Source
-// License. See LICENSE.TXT for details.
-//
-//===----------------------------------------------------------------------===//
-
-#include "ARM.h"
-#include "Thumb2HazardRecognizer.h"
-#include "llvm/CodeGen/MachineInstr.h"
-#include "llvm/CodeGen/ScheduleDAG.h"
-using namespace llvm;
-
-ScheduleHazardRecognizer::HazardType
-Thumb2HazardRecognizer::getHazardType(SUnit *SU) {
-  if (ITBlockSize) {
-    MachineInstr *MI = SU->getInstr();
-    if (!MI->isDebugValue() && MI != ITBlockMIs[ITBlockSize-1])
-      return Hazard;
-  }
-
-  return PostRAHazardRecognizer::getHazardType(SU);
-}
-
-void Thumb2HazardRecognizer::Reset() {
-  ITBlockSize = 0;
-  PostRAHazardRecognizer::Reset();
-}
-
-void Thumb2HazardRecognizer::EmitInstruction(SUnit *SU) {
-  MachineInstr *MI = SU->getInstr();
-  unsigned Opcode = MI->getOpcode();
-  if (ITBlockSize) {
-    --ITBlockSize;
-  } else if (Opcode == ARM::t2IT) {
-    unsigned Mask = MI->getOperand(1).getImm();
-    unsigned NumTZ = CountTrailingZeros_32(Mask);
-    assert(NumTZ <= 3 && "Invalid IT mask!");
-    ITBlockSize = 4 - NumTZ;
-    MachineBasicBlock::iterator I = MI;
-    for (unsigned i = 0; i < ITBlockSize; ++i) {
-      // Advance to the next instruction, skipping any dbg_value instructions.
-      do {
-        ++I;
-      } while (I->isDebugValue());
-      ITBlockMIs[ITBlockSize-1-i] = &*I;
-    }
-  }
-
-  PostRAHazardRecognizer::EmitInstruction(SU);
-}
diff --git a/lib/Target/ARM/Thumb2HazardRecognizer.h b/lib/Target/ARM/Thumb2HazardRecognizer.h
deleted file mode 100644
index aa4411f..0000000
--- a/lib/Target/ARM/Thumb2HazardRecognizer.h
+++ /dev/null
@@ -1,40 +0,0 @@
-//===-- Thumb2HazardRecognizer.h - Thumb2 Hazard Recognizers ----*- C++ -*-===//
-//
-//                     The LLVM Compiler Infrastructure
-//
-// This file is distributed under the University of Illinois Open Source
-// License. See LICENSE.TXT for details.
-//
-//===----------------------------------------------------------------------===//
-//
-// This file defines hazard recognizers for scheduling Thumb2 functions on
-// ARM processors.
-//
-//===----------------------------------------------------------------------===//
-
-#ifndef THUMB2HAZARDRECOGNIZER_H
-#define THUMB2HAZARDRECOGNIZER_H
-
-#include "llvm/CodeGen/PostRAHazardRecognizer.h"
-
-namespace llvm {
-
-class MachineInstr;
-
-class Thumb2HazardRecognizer : public PostRAHazardRecognizer {
-  unsigned ITBlockSize;  // No. of MIs in current IT block yet to be scheduled.
-  MachineInstr *ITBlockMIs[4];
-
-public:
-  Thumb2HazardRecognizer(const InstrItineraryData *ItinData) :
-    PostRAHazardRecognizer(ItinData) {}
-
-  virtual HazardType getHazardType(SUnit *SU);
-  virtual void Reset();
-  virtual void EmitInstruction(SUnit *SU);
-};
-
-
-} // end namespace llvm
-
-#endif // THUMB2HAZARDRECOGNIZER_H
diff --git a/lib/Target/ARM/Thumb2InstrInfo.cpp b/lib/Target/ARM/Thumb2InstrInfo.cpp
index 719b140..2f67257 100644
--- a/lib/Target/ARM/Thumb2InstrInfo.cpp
+++ b/lib/Target/ARM/Thumb2InstrInfo.cpp
@@ -17,7 +17,6 @@
 #include "ARMAddressingModes.h"
 #include "ARMGenInstrInfo.inc"
 #include "ARMMachineFunctionInfo.h"
-#include "Thumb2HazardRecognizer.h"
 #include "Thumb2InstrInfo.h"
 #include "llvm/CodeGen/MachineFrameInfo.h"
 #include "llvm/CodeGen/MachineInstrBuilder.h"
@@ -175,11 +174,6 @@
   ARMBaseInstrInfo::loadRegFromStackSlot(MBB, I, DestReg, FI, RC, TRI);
 }
 
-ScheduleHazardRecognizer *Thumb2InstrInfo::
-CreateTargetPostRAHazardRecognizer(const InstrItineraryData *II) const {
-  return (ScheduleHazardRecognizer *)new Thumb2HazardRecognizer(II);
-}
-
 void llvm::emitT2RegPlusImmediate(MachineBasicBlock &MBB,
                                MachineBasicBlock::iterator &MBBI, DebugLoc dl,
                                unsigned DestReg, unsigned BaseReg, int NumBytes,
diff --git a/lib/Target/ARM/Thumb2InstrInfo.h b/lib/Target/ARM/Thumb2InstrInfo.h
index 9ed7eea..f2637d7 100644
--- a/lib/Target/ARM/Thumb2InstrInfo.h
+++ b/lib/Target/ARM/Thumb2InstrInfo.h
@@ -65,9 +65,6 @@
   /// always be able to get register info as well (through this method).
   ///
   const Thumb2RegisterInfo &getRegisterInfo() const { return RI; }
-
-  ScheduleHazardRecognizer *
-  CreateTargetPostRAHazardRecognizer(const InstrItineraryData *II) const;
 };
 
 /// getITInstrPredicate - Valid only in Thumb2 mode. This function is identical