5 files changed, 53 insertions, 5 deletions
diff --git a/lib/Analysis/TargetTransformInfo.cpp b/lib/Analysis/TargetTransformInfo.cpp
index 63f495a430..02af2d34c5 100644
--- a/lib/Analysis/TargetTransformInfo.cpp
+++ b/lib/Analysis/TargetTransformInfo.cpp
@@ -92,6 +92,10 @@ unsigned TargetTransformInfo::getNumberOfRegisters(bool Vector) const {
   return PrevTTI->getNumberOfRegisters(Vector);
 }
 
+unsigned TargetTransformInfo::getMaximumUnrollFactor() const {
+  return PrevTTI->getMaximumUnrollFactor();
+}
+
 unsigned TargetTransformInfo::getArithmeticInstrCost(unsigned Opcode,
                                                      Type *Ty) const {
   return PrevTTI->getArithmeticInstrCost(Opcode, Ty);
@@ -216,6 +220,10 @@ struct NoTTI : ImmutablePass, TargetTransformInfo {
     return 8;
   }
 
+  unsigned getMaximumUnrollFactor() const {
+    return 1;
+  }
+
   unsigned getArithmeticInstrCost(unsigned Opcode, Type *Ty) const {
     return 1;
   }
diff --git a/lib/CodeGen/BasicTargetTransformInfo.cpp b/lib/CodeGen/BasicTargetTransformInfo.cpp
index c27e081a5e..2f3ac9a901 100644
--- a/lib/CodeGen/BasicTargetTransformInfo.cpp
+++ b/lib/CodeGen/BasicTargetTransformInfo.cpp
@@ -83,6 +83,7 @@ public:
   /// @{
 
   virtual unsigned getNumberOfRegisters(bool Vector) const;
+  virtual unsigned getMaximumUnrollFactor() const;
   virtual unsigned getArithmeticInstrCost(unsigned Opcode, Type *Ty) const;
   virtual unsigned getShuffleCost(ShuffleKind Kind, Type *Tp,
                                   int Index, Type *SubTp) const;
@@ -182,6 +183,10 @@ unsigned BasicTTI::getNumberOfRegisters(bool Vector) const {
   return 1;
 }
 
+unsigned BasicTTI::getMaximumUnrollFactor() const {
+  return 1;
+}
+
 unsigned BasicTTI::getArithmeticInstrCost(unsigned Opcode, Type *Ty) const {
   // Check if any of the operands are vector operands.
   int ISD = TLI->InstructionOpcodeToISD(Opcode);
diff --git a/lib/Target/ARM/ARMTargetTransformInfo.cpp b/lib/Target/ARM/ARMTargetTransformInfo.cpp
index 03a23be0a6..634004acb4 100644
--- a/lib/Target/ARM/ARMTargetTransformInfo.cpp
+++ b/lib/Target/ARM/ARMTargetTransformInfo.cpp
@@ -77,6 +77,31 @@ public:
   virtual unsigned getIntImmCost(const APInt &Imm, Type *Ty) const;
 
   /// @}
+
+
+  /// \name Vector TTI Implementations
+  /// @{
+
+  unsigned getNumberOfRegisters(bool Vector) const {
+    if (Vector) {
+      if (ST->hasNEON())
+        return 16;
+      return 0;
+    }
+
+    if (ST->isThumb1Only())
+      return 8;
+    return 16;
+  }
+
+  unsigned getMaximumUnrollFactor() const {
+    // These are out of order CPUs:
+    if (ST->isCortexA15() || ST->isSwift())
+      return 2;
+    return 1;
+  }
+
+  /// @}
 };
 
 } // end anonymous namespace
diff --git a/lib/Target/X86/X86TargetTransformInfo.cpp b/lib/Target/X86/X86TargetTransformInfo.cpp
index 9cc1b180e9..6ab08cbd12 100644
--- a/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -75,7 +75,6 @@ public:
 
   /// \name Scalar TTI Implementations
   /// @{
-
   virtual PopcntSupportKind getPopcntSupport(unsigned TyWidth) const;
 
   /// @}
@@ -84,6 +83,7 @@ public:
   /// @{
 
   virtual unsigned getNumberOfRegisters(bool Vector) const;
+  virtual unsigned getMaximumUnrollFactor() const;
   virtual unsigned getArithmeticInstrCost(unsigned Opcode, Type *Ty) const;
   virtual unsigned getShuffleCost(ShuffleKind Kind, Type *Tp,
                                   int Index, Type *SubTp) const;
@@ -156,7 +156,6 @@ FindInConvertTable(const X86TypeConversionCostTblEntry *Tbl, unsigned len,
   return -1;
 }
 
-
 X86TTI::PopcntSupportKind X86TTI::getPopcntSupport(unsigned TyWidth) const {
   assert(isPowerOf2_32(TyWidth) && "Ty width must be power of 2");
   // TODO: Currently the __builtin_popcount() implementation using SSE3
@@ -171,6 +170,18 @@ unsigned X86TTI::getNumberOfRegisters(bool Vector) const {
   return 8;
 }
 
+unsigned X86TTI::getMaximumUnrollFactor() const {
+  if (ST->isAtom())
+    return 1;
+
+  // Sandybridge and Haswell have multiple execution ports and pipelined
+  // vector units.
+  if (ST->hasAVX())
+    return 4;
+
+  return 2;
+}
+
 unsigned X86TTI::getArithmeticInstrCost(unsigned Opcode, Type *Ty) const {
   // Legalize the type.
   std::pair<unsigned, MVT> LT = TLI->getTypeLegalizationCost(Ty);
diff --git a/lib/Transforms/Vectorize/LoopVectorize.cpp b/lib/Transforms/Vectorize/LoopVectorize.cpp
index 9c82cb8dca..c29f416be7 100644
--- a/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -116,9 +116,6 @@ static const unsigned RuntimeMemoryCheckThreshold = 4;
 /// This is the highest vector width that we try to generate.
 static const unsigned MaxVectorSize = 8;
 
-/// This is the highest Unroll Factor.
-static const unsigned MaxUnrollSize = 4;
-
 namespace {
 
 // Forward declarations.
@@ -2715,6 +2712,8 @@ LoopVectorizationCostModel::selectUnrollFactor(bool OptForSize,
   UF = std::min(UF, (MaxLoopSizeThreshold / R.NumInstructions));
 
   // Clamp the unroll factor ranges to reasonable factors.
+  unsigned MaxUnrollSize = TTI.getMaximumUnrollFactor();
+  
   if (UF > MaxUnrollSize)
     UF = MaxUnrollSize;
   else if (UF < 1)