Index: lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp
===================================================================
--- lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp
+++ lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp
@@ -305,24 +305,20 @@
   return visitAllocSite(AI);
 }
 
-/// \brief Helper to combine a load to a new type.
+/// \brief Helper to combine a load to a new value.
 ///
-/// This just does the work of combining a load to a new type. It handles
+/// This just does the work of combining a load to a new value. It handles
 /// metadata, etc., and returns the new instruction. The \c NewTy should be the
-/// loaded *value* type. This will convert it to a pointer, cast the operand to
-/// that pointer type, load it, etc.
+/// loaded *value* type.
 ///
 /// Note that this will create all of the instructions with whatever insert
 /// point the \c InstCombiner currently is using.
-static LoadInst *combineLoadToNewType(InstCombiner &IC, LoadInst &LI, Type *NewTy) {
-  Value *Ptr = LI.getPointerOperand();
-  unsigned AS = LI.getPointerAddressSpace();
+static LoadInst *combineLoadToNewValue(InstCombiner &IC, LoadInst &LI, Value *V, Type *NewTy) {
   SmallVector<std::pair<unsigned, MDNode *>, 8> MD;
   LI.getAllMetadata(MD);
 
   LoadInst *NewLoad = IC.Builder->CreateAlignedLoad(
-      IC.Builder->CreateBitCast(Ptr, NewTy->getPointerTo(AS)),
-      LI.getAlignment(), LI.getName());
+      V, LI.getAlignment(), LI.getName());
   MDBuilder MDB(NewLoad->getContext());
   for (const auto &MDPair : MD) {
     unsigned ID = MDPair.first;
@@ -358,6 +354,7 @@
       // If it's integral now, translate it to !range metadata.
       if (NewTy->isIntegerTy()) {
         auto *ITy = cast<IntegerType>(NewTy);
+        Value *Ptr = LI.getPointerOperand();
         auto *NullInt = ConstantExpr::getPtrToInt(
             ConstantPointerNull::get(cast<PointerType>(Ptr->getType())), ITy);
         auto *NonNullInt =
@@ -377,6 +374,23 @@
   return NewLoad;
 }
 
+/// \brief Helper to combine a load to a new type.
+///
+/// This just does the work of combining a load to a new type. It handles
+/// metadata, etc., and returns the new instruction. The \c NewTy should be the
+/// loaded *value* type. This will convert it to a pointer, cast the operand to
+/// that pointer type, load it, etc.
+///
+/// Note that this will create all of the instructions with whatever insert
+/// point the \c InstCombiner currently is using.
+static LoadInst *combineLoadToNewType(InstCombiner &IC, LoadInst &LI, Type *NewTy) {
+  Value *Ptr = LI.getPointerOperand();
+  unsigned AS = LI.getPointerAddressSpace();
+  
+  Value *V = IC.Builder->CreateBitCast(Ptr, NewTy->getPointerTo(AS));
+  return combineLoadToNewValue(IC, LI, V, NewTy);
+}
+
 /// \brief Combine a store to a new type.
 ///
 /// Returns the newly created store instruction.
@@ -495,6 +509,34 @@
   return nullptr;
 }
 
+static Instruction *unpackLoadToAggregate(InstCombiner &IC, LoadInst &LI) {
+  // FIXME: We could probably with some care handle both volatile and atomic
+  // stores here but it isn't clear that this is important.
+  if (!LI.isSimple())
+    return nullptr;
+
+  Value *Ptr = LI.getPointerOperand();
+  Type *T = cast<PointerType>(Ptr->getType())->getElementType();
+
+  if (!T->isAggregateType())
+    return nullptr;
+
+  if (StructType *ST = dyn_cast<StructType>(T)) {
+    // If the struct only have one element, we unpack.
+    if (ST->getNumElements() == 1) {
+      Ptr = IC.Builder->CreateStructGEP(Ptr, 0);
+      LoadInst *NewLoad = combineLoadToNewValue(IC, LI, Ptr, T);
+
+      Instruction *V = InsertValueInst::Create(UndefValue::get(T), NewLoad, 0);
+
+      LI.replaceAllUsesWith(V);
+      return V;
+    }
+  }
+
+  return nullptr;
+}
+
 // If we can determine that all possible objects pointed to by the provided
 // pointer value are, not only dereferenceable, but also definitively less than
 // or equal to the provided maximum size, then return true. Otherwise, return
@@ -689,6 +731,9 @@
   else if (LoadAlign == 0)
     LI.setAlignment(EffectiveLoadAlign);
 
+  if (Instruction *Res = unpackLoadToAggregate(*this, LI))
+    return Res;
+
   // Replace GEP indices if possible.
   if (Instruction *NewGEPI = replaceGEPIdxWithZero(*this, Op, LI)) {
       Worklist.Add(NewGEPI);
Index: test/Transforms/InstCombine/unpack-fca.ll
===================================================================
--- test/Transforms/InstCombine/unpack-fca.ll
+++ test/Transforms/InstCombine/unpack-fca.ll
@@ -12,7 +12,7 @@
 
 declare i8* @allocmemory(i64)
 
-define void @structA() {
+define void @storeA() {
 body:
   %0 = tail call i8* @allocmemory(i64 32)
   %1 = bitcast i8* %0 to %A*
@@ -21,7 +21,7 @@
   ret void
 }
 
-define void @structOfA() {
+define void @storeStructOfA() {
 body:
   %0 = tail call i8* @allocmemory(i64 32)
   %1 = bitcast i8* %0 to { %A }*
@@ -29,3 +29,35 @@
   store { %A } { %A { %A__vtbl* @A__vtblZ } }, { %A }* %1, align 8
   ret void
 }
+
+define %A @loadA() {
+body:
+  %0 = tail call i8* @allocmemory(i64 32)
+  %1 = bitcast i8* %0 to %A*
+; CHECK: load %A__vtbl*,
+; CHECK: insertvalue %A undef, %A__vtbl* {{.*}}, 0
+  %2 = load %A, %A* %1, align 8
+  ret %A %2
+}
+
+define { %A } @loadStructOfA() {
+body:
+  %0 = tail call i8* @allocmemory(i64 32)
+  %1 = bitcast i8* %0 to { %A }*
+; CHECK: load %A__vtbl*,
+; CHECK: insertvalue %A undef, %A__vtbl* {{.*}}, 0
+; CHECK: insertvalue { %A } undef, %A {{.*}}, 0
+  %2 = load { %A }, { %A }* %1, align 8
+  ret { %A } %2
+}
+
+define { %A } @structOfA() {
+body:
+  %0 = tail call i8* @allocmemory(i64 32)
+  %1 = bitcast i8* %0 to { %A }*
+; CHECK: store %A__vtbl* @A__vtblZ
+  store { %A } { %A { %A__vtbl* @A__vtblZ } }, { %A }* %1, align 8
+  %2 = load { %A }, { %A }* %1, align 8
+; CHECK: ret { %A } { %A { %A__vtbl* @A__vtblZ } }
+  ret { %A } %2
+}