Index: lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp
===================================================================
--- lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp
+++ lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp
@@ -800,6 +800,30 @@
   return false;
 }
 
+static bool unpackStoreToAggregate(InstCombiner &IC, StoreInst &SI) {
+  // FIXME: We could probably with some care handle both volatile and atomic
+  // stores here but it isn't clear that this is important.
+  if (!SI.isSimple())
+    return false;
+
+  Value *V = SI.getValueOperand();
+  Type *T = V->getType();
+
+  if (!T->isAggregateType())
+    return false;
+
+  if (StructType* ST = dyn_cast<StructType>(T)) {
+    // If the struct only have one element, we unpack.
+    if (ST->getNumElements() == 1) {
+      V = IC.Builder->CreateExtractValue(V, 0);
+      combineStoreToNewValue(IC, SI, V);
+      return true;
+    }
+  }
+
+  return false;
+}
+
 /// equivalentAddressValues - Test if A and B will obviously have the same
 /// value. This includes recognizing that %t0 and %t1 will have the same
 /// value in code like this:
@@ -849,6 +873,10 @@
   else if (StoreAlign == 0)
     SI.setAlignment(EffectiveStoreAlign);
 
+  // Try to canonicalize the stored type.
+  if (unpackStoreToAggregate(*this, SI))
+    return EraseInstFromFunction(SI);
+
   // Replace GEP indices if possible.
   if (Instruction *NewGEPI = replaceGEPIdxWithZero(*this, Ptr, SI)) {
       Worklist.Add(NewGEPI);
Index: test/Transforms/InstCombine/unpack-fca.ll
===================================================================
--- /dev/null
+++ test/Transforms/InstCombine/unpack-fca.ll
@@ -0,0 +1,31 @@
+; RUN: opt -instcombine -S < %s | FileCheck %s
+
+target datalayout = "e-i64:64-f80:128-n8:16:32:64"
+target triple = "x86_64-unknown-linux-gnu"
+
+%A__vtbl = type { i8*, i32 (%A*)* }
+%A = type { %A__vtbl* }
+
+@A__vtblZ = constant %A__vtbl { i8* null, i32 (%A*)* @A.foo }
+
+declare i32 @A.foo(%A* nocapture %this)
+
+declare i8* @allocmemory(i64)
+
+define void @structA() {
+body:
+  %0 = tail call i8* @allocmemory(i64 32)
+  %1 = bitcast i8* %0 to %A*
+; CHECK: store %A__vtbl* @A__vtblZ
+  store %A { %A__vtbl* @A__vtblZ }, %A* %1, align 8
+  ret void
+}
+
+define void @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
+  ret void
+}