1 files changed, 40 insertions, 3 deletions

diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index c44a34fe667..955134077bb 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -585,6 +585,11 @@ protected:
   /// Returns (and creates if needed) the trip count of the widened loop.
   Value *getOrCreateVectorTripCount(Loop *NewLoop);
 
+  /// Returns a bitcasted value to the requested vector type.
+  /// Also handles bitcasts of vector<float> <-> vector<pointer> types.
+  Value *createBitOrPointerCast(Value *V, VectorType *DstVTy,
+                                const DataLayout &DL);
+
   /// Emit a bypass check to see if the vector trip count is zero, including if
   /// it overflows.
   void emitMinimumIterationCountCheck(Loop *L, BasicBlock *Bypass);
@@ -2866,6 +2871,7 @@ void InnerLoopVectorizer::vectorizeInterleaveGroup(Instruction *Instr) {
   if (Instr != Group->getInsertPos())
     return;
 
+  const DataLayout &DL = Instr->getModule()->getDataLayout();
   Value *Ptr = getPointerOperand(Instr);
 
   // Prepare for the vector type of the interleaved load/store.
@@ -2940,7 +2946,7 @@ void InnerLoopVectorizer::vectorizeInterleaveGroup(Instruction *Instr) {
         // If this member has different type, cast the result type.
         if (Member->getType() != ScalarTy) {
           VectorType *OtherVTy = VectorType::get(Member->getType(), VF);
-          StridedVec = Builder.CreateBitOrPointerCast(StridedVec, OtherVTy);
+          StridedVec = createBitOrPointerCast(StridedVec, OtherVTy, DL);
         }
 
         if (Group->isReverse())
@@ -2969,9 +2975,10 @@ void InnerLoopVectorizer::vectorizeInterleaveGroup(Instruction *Instr) {
       if (Group->isReverse())
         StoredVec = reverseVector(StoredVec);
 
-      // If this member has different type, cast it to an unified type.
+      // If this member has different type, cast it to a unified type.
+
       if (StoredVec->getType() != SubVT)
-        StoredVec = Builder.CreateBitOrPointerCast(StoredVec, SubVT);
+        StoredVec = createBitOrPointerCast(StoredVec, SubVT, DL);
 
       StoredVecs.push_back(StoredVec);
     }
@@ -3272,6 +3279,36 @@ Value *InnerLoopVectorizer::getOrCreateVectorTripCount(Loop *L) {
   return VectorTripCount;
 }
 
+Value *InnerLoopVectorizer::createBitOrPointerCast(Value *V, VectorType *DstVTy,
+                                                   const DataLayout &DL) {
+  // Verify that V is a vector type with same number of elements as DstVTy.
+  unsigned VF = DstVTy->getNumElements();
+  VectorType *SrcVecTy = cast<VectorType>(V->getType());
+  assert((VF == SrcVecTy->getNumElements()) && "Vector dimensions do not match");
+  Type *SrcElemTy = SrcVecTy->getElementType();
+  Type *DstElemTy = DstVTy->getElementType();
+  assert((DL.getTypeSizeInBits(SrcElemTy) == DL.getTypeSizeInBits(DstElemTy)) &&
+         "Vector elements must have same size");
+
+  // Do a direct cast if element types are castable.
+  if (CastInst::isBitOrNoopPointerCastable(SrcElemTy, DstElemTy, DL)) {
+    return Builder.CreateBitOrPointerCast(V, DstVTy);
+  }
+  // V cannot be directly casted to desired vector type.
+  // May happen when V is a floating point vector but DstVTy is a vector of
+  // pointers or vice-versa. Handle this using a two-step bitcast using an
+  // intermediate Integer type for the bitcast i.e. Ptr <-> Int <-> Float.
+  assert((DstElemTy->isPointerTy() != SrcElemTy->isPointerTy()) &&
+         "Only one type should be a pointer type");
+  assert((DstElemTy->isFloatingPointTy() != SrcElemTy->isFloatingPointTy()) &&
+         "Only one type should be a floating point type");
+  Type *IntTy =
+      IntegerType::getIntNTy(V->getContext(), DL.getTypeSizeInBits(SrcElemTy));
+  VectorType *VecIntTy = VectorType::get(IntTy, VF);
+  Value *CastVal = Builder.CreateBitOrPointerCast(V, VecIntTy);
+  return Builder.CreateBitOrPointerCast(CastVal, DstVTy);
+}
+
 void InnerLoopVectorizer::emitMinimumIterationCountCheck(Loop *L,
                                                          BasicBlock *Bypass) {
   Value *Count = getOrCreateTripCount(L);