Index: llvm/trunk/lib/Transforms/InstCombine/InstCombineCasts.cpp
===================================================================
--- llvm/trunk/lib/Transforms/InstCombine/InstCombineCasts.cpp
+++ llvm/trunk/lib/Transforms/InstCombine/InstCombineCasts.cpp
@@ -1715,6 +1715,40 @@
   return Result;
 }
 
+/// Given a bitcasted vector fed into an extract element instruction and then
+/// bitcasted again, eliminate at least one bitcast by changing the vector type
+/// of the extractelement instruction.
+/// Example:
+///   bitcast (extractelement (bitcast <2 x float> %X to <2 x i32>), 1) to float
+///    --->
+///   extractelement <2 x float> %X, i32 1
+static Instruction *foldBitCastExtElt(BitCastInst &BitCast, InstCombiner &IC,
+                                      const DataLayout &DL) {
+  // TODO: Create and use a pattern matcher for ExtractElementInst.
+  auto *ExtElt = dyn_cast<ExtractElementInst>(BitCast.getOperand(0));
+  if (!ExtElt || !ExtElt->hasOneUse())
+    return nullptr;
+
+  Value *InnerBitCast = nullptr;
+  if (!match(ExtElt->getOperand(0), m_BitCast(m_Value(InnerBitCast))))
+    return nullptr;
+
+  VectorType *VecType = cast<VectorType>(InnerBitCast->getType());
+  Type *DestType = BitCast.getType();
+
+  // If the element type of the vector doesn't match the result type,
+  // bitcast it to a vector type that we can extract from.
+  if (VecType->getElementType() != DestType) {
+    unsigned VecWidth = VecType->getPrimitiveSizeInBits();
+    unsigned DestWidth = DestType->getPrimitiveSizeInBits();
+    unsigned NumElts = VecWidth / DestWidth;
+    VecType = VectorType::get(DestType, NumElts);
+    InnerBitCast = IC.Builder->CreateBitCast(InnerBitCast, VecType, "bc");
+  }
+
+  return ExtractElementInst::Create(InnerBitCast, ExtElt->getOperand(1));
+}
+
 static Instruction *foldVecTruncToExtElt(Value *VecInput, Type *DestTy,
                                          unsigned ShiftAmt, InstCombiner &IC,
                                          const DataLayout &DL) {
@@ -1886,6 +1920,9 @@
     }
   }
 
+  if (Instruction *I = foldBitCastExtElt(CI, *this, DL))
+    return I;
+
   if (SrcTy->isPointerTy())
     return commonPointerCastTransforms(CI);
   return commonCastTransforms(CI);
Index: llvm/trunk/test/Transforms/InstCombine/bitcast.ll
===================================================================
--- llvm/trunk/test/Transforms/InstCombine/bitcast.ll
+++ llvm/trunk/test/Transforms/InstCombine/bitcast.ll
@@ -64,7 +64,7 @@
 ; CHECK-NEXT:  ret float %add
 }
 
-; TODO: Both bitcasts are unnecessary; change the extractelement.
+; Both bitcasts are unnecessary; change the extractelement.
 
 define float @bitcast_extelt1(<2 x float> %A) {
   %bc1 = bitcast <2 x float> %A to <2 x i32>
@@ -73,13 +73,11 @@
   ret float %bc2
 
 ; CHECK-LABEL: @bitcast_extelt1(
-; CHECK-NEXT:  %bc1 = bitcast <2 x float> %A to <2 x i32>
-; CHECK-NEXT:  %ext = extractelement <2 x i32> %bc1, i32 0
-; CHECK-NEXT:  %bc2 = bitcast i32 %ext to float
+; CHECK-NEXT:  %bc2 = extractelement <2 x float> %A, i32 0
 ; CHECK-NEXT:  ret float %bc2
 }
 
-; TODO: Second bitcast can be folded into the first.
+; Second bitcast can be folded into the first.
 
 define i64 @bitcast_extelt2(<4 x float> %A) {
   %bc1 = bitcast <4 x float> %A to <2 x double>
@@ -88,9 +86,8 @@
   ret i64 %bc2
 
 ; CHECK-LABEL: @bitcast_extelt2(
-; CHECK-NEXT:  %bc1 = bitcast <4 x float> %A to <2 x double>
-; CHECK-NEXT:  %ext = extractelement <2 x double> %bc1, i32 1
-; CHECK-NEXT:  %bc2 = bitcast double %ext to i64
+; CHECK-NEXT:  %bc = bitcast <4 x float> %A to <2 x i64>
+; CHECK-NEXT:  %bc2 = extractelement <2 x i64> %bc, i32 1
 ; CHECK-NEXT:  ret i64 %bc2
 }