5 files changed, 88 insertions, 3 deletions
diff --git a/lib/Analysis/TargetTransformInfo.cpp b/lib/Analysis/TargetTransformInfo.cpp
index 02af2d34c5..3ef74eb2d6 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::getRegisterBitWidth(bool Vector) const {
+  return PrevTTI->getRegisterBitWidth(Vector);
+}
+
 unsigned TargetTransformInfo::getMaximumUnrollFactor() const {
   return PrevTTI->getMaximumUnrollFactor();
 }
@@ -220,6 +224,10 @@ struct NoTTI : ImmutablePass, TargetTransformInfo {
     return 8;
   }
 
+  unsigned  getRegisterBitWidth(bool Vector) const {
+    return 32;
+  }
+
   unsigned getMaximumUnrollFactor() const {
     return 1;
   }
diff --git a/lib/CodeGen/BasicTargetTransformInfo.cpp b/lib/CodeGen/BasicTargetTransformInfo.cpp
index 2f3ac9a901..3892cc4dd5 100644
--- a/lib/CodeGen/BasicTargetTransformInfo.cpp
+++ b/lib/CodeGen/BasicTargetTransformInfo.cpp
@@ -84,6 +84,7 @@ public:
 
   virtual unsigned getNumberOfRegisters(bool Vector) const;
   virtual unsigned getMaximumUnrollFactor() const;
+  virtual unsigned getRegisterBitWidth(bool Vector) const;
   virtual unsigned getArithmeticInstrCost(unsigned Opcode, Type *Ty) const;
   virtual unsigned getShuffleCost(ShuffleKind Kind, Type *Tp,
                                   int Index, Type *SubTp) const;
@@ -183,6 +184,10 @@ unsigned BasicTTI::getNumberOfRegisters(bool Vector) const {
   return 1;
 }
 
+unsigned BasicTTI::getRegisterBitWidth(bool Vector) const {
+  return 32;
+}
+
 unsigned BasicTTI::getMaximumUnrollFactor() const {
   return 1;
 }
diff --git a/lib/Target/ARM/ARMTargetTransformInfo.cpp b/lib/Target/ARM/ARMTargetTransformInfo.cpp
index 634004acb4..404a6fff11 100644
--- a/lib/Target/ARM/ARMTargetTransformInfo.cpp
+++ b/lib/Target/ARM/ARMTargetTransformInfo.cpp
@@ -94,6 +94,16 @@ public:
     return 16;
   }
 
+  unsigned getRegisterBitWidth(bool Vector) const {
+    if (Vector) {
+      if (ST->hasNEON())
+        return 128;
+      return 0;
+    }
+
+    return 32;
+  }
+
   unsigned getMaximumUnrollFactor() const {
     // These are out of order CPUs:
     if (ST->isCortexA15() || ST->isSwift())
diff --git a/lib/Target/X86/X86TargetTransformInfo.cpp b/lib/Target/X86/X86TargetTransformInfo.cpp
index 6ab08cbd12..675c896d70 100644
--- a/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -83,6 +83,7 @@ public:
   /// @{
 
   virtual unsigned getNumberOfRegisters(bool Vector) const;
+  virtual unsigned getRegisterBitWidth(bool Vector) const;
   virtual unsigned getMaximumUnrollFactor() const;
   virtual unsigned getArithmeticInstrCost(unsigned Opcode, Type *Ty) const;
   virtual unsigned getShuffleCost(ShuffleKind Kind, Type *Tp,
@@ -165,11 +166,27 @@ X86TTI::PopcntSupportKind X86TTI::getPopcntSupport(unsigned TyWidth) const {
 }
 
 unsigned X86TTI::getNumberOfRegisters(bool Vector) const {
+  if (Vector && !ST->hasSSE1())
+    return 0;
+
   if (ST->is64Bit())
     return 16;
   return 8;
 }
 
+unsigned X86TTI::getRegisterBitWidth(bool Vector) const {
+  if (Vector) {
+    if (ST->hasAVX()) return 256;
+    if (ST->hasSSE1()) return 128;
+    return 0;
+  }
+
+  if (ST->is64Bit())
+    return 64;
+  return 32;
+
+}
+
 unsigned X86TTI::getMaximumUnrollFactor() const {
   if (ST->isAtom())
     return 1;
diff --git a/lib/Transforms/Vectorize/LoopVectorize.cpp b/lib/Transforms/Vectorize/LoopVectorize.cpp
index c29f416be7..cde4bb889e 100644
--- a/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -113,9 +113,6 @@ static const unsigned MaxLoopSizeThreshold = 32;
 /// number of pointers. Notice that the check is quadratic!
 static const unsigned RuntimeMemoryCheckThreshold = 4;
 
-/// This is the highest vector width that we try to generate.
-static const unsigned MaxVectorSize = 8;
-
 namespace {
 
 // Forward declarations.
@@ -523,6 +520,10 @@ public:
   /// possible.
   unsigned selectVectorizationFactor(bool OptForSize, unsigned UserVF);
 
+  /// \returns The size (in bits) of the widest type in the code that
+  /// needs to be vectorized. We ignore values that remain scalar such as
+  /// 64 bit loop indices.
+  unsigned getWidestType();
 
   /// \return The most profitable unroll factor.
   /// If UserUF is non-zero then this method finds the best unroll-factor
@@ -2621,6 +2622,20 @@ LoopVectorizationCostModel::selectVectorizationFactor(bool OptForSize,
   unsigned TC = SE->getSmallConstantTripCount(TheLoop, TheLoop->getLoopLatch());
   DEBUG(dbgs() << "LV: Found trip count:"<<TC<<"\n");
 
+  unsigned WidestType = getWidestType();
+  unsigned WidestRegister = TTI.getRegisterBitWidth(true);
+  unsigned MaxVectorSize = WidestRegister / WidestType;
+  DEBUG(dbgs() << "LV: The Widest type: " << WidestType << " bits.\n");
+  DEBUG(dbgs() << "LV: The Widest register is:" << WidestRegister << "bits.\n");
+
+  if (MaxVectorSize == 0) {
+    DEBUG(dbgs() << "LV: The target has no vector registers.\n");
+    return 1;
+  }
+
+  assert(MaxVectorSize <= 32 && "Did not expect to pack so many elements"
+         " into one vector.");
+  
   unsigned VF = MaxVectorSize;
 
   // If we optimize the program for size, avoid creating the tail loop.
@@ -2672,6 +2687,36 @@ LoopVectorizationCostModel::selectVectorizationFactor(bool OptForSize,
   return Width;
 }
 
+unsigned LoopVectorizationCostModel::getWidestType() {
+  unsigned MaxWidth = 8;
+
+  // For each block.
+  for (Loop::block_iterator bb = TheLoop->block_begin(),
+       be = TheLoop->block_end(); bb != be; ++bb) {
+    BasicBlock *BB = *bb;
+
+    // For each instruction in the loop.
+    for (BasicBlock::iterator it = BB->begin(), e = BB->end(); it != e; ++it) {
+      if (Legal->isUniformAfterVectorization(it))
+        continue;
+
+      Type *T = it->getType();
+
+      if (StoreInst *ST = dyn_cast<StoreInst>(it))
+        T = ST->getValueOperand()->getType();
+
+      // PHINodes and pointers are difficult to analyze, but we catch all other
+      // uses of the types in other instructions.
+      if (isa<PHINode>(it) || T->isPointerTy() || T->isVoidTy())
+        continue;
+
+      MaxWidth = std::max(MaxWidth, T->getScalarSizeInBits());
+    }
+  }
+
+  return MaxWidth;
+}
+
 unsigned
 LoopVectorizationCostModel::selectUnrollFactor(bool OptForSize,
                                                unsigned UserUF) {