Index: llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
===================================================================
--- llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -467,7 +467,8 @@
                                     unsigned Alignment, unsigned AddressSpace) {
   std::pair<int, MVT> LT = TLI->getTypeLegalizationCost(DL, Src);
 
-  if (Opcode == Instruction::Store && Src->isVectorTy() && Alignment != 16 &&
+  if (ST->isMisaligned128StoreSlow() && Opcode == Instruction::Store &&
+      Src->isVectorTy() && Alignment != 16 &&
       Src->getVectorElementType()->isIntegerTy(64)) {
     // Unaligned stores are extremely inefficient. We don't split
     // unaligned v2i64 stores because the negative impact that has shown in
Index: llvm/trunk/test/Analysis/CostModel/AArch64/store.ll
===================================================================
--- llvm/trunk/test/Analysis/CostModel/AArch64/store.ll
+++ llvm/trunk/test/Analysis/CostModel/AArch64/store.ll
@@ -1,10 +1,16 @@
-; RUN: opt < %s  -cost-model -analyze -mtriple=arm64-apple-ios -mcpu=cyclone | FileCheck %s
+; RUN: opt < %s  -cost-model -analyze -mtriple=aarch64-apple-ios | FileCheck %s
+; RUN: opt < %s  -cost-model -analyze -mtriple=aarch64-apple-ios -mattr=slow-misaligned-128store | FileCheck %s --check-prefix=SLOW_MISALIGNED_128_STORE
+
 target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:32:64-v128:32:128-a0:0:32-n32-S32"
-; CHECK-LABEL: store
-define void @store() {
-    ; Stores of <2 x i64> should be expensive because we don't split them and
-    ; and unaligned 16b stores have bad performance.
-    ; CHECK: cost of 12 {{.*}} store
+; CHECK-LABEL: getMemoryOpCost
+; SLOW_MISALIGNED_128_STORE-LABEL: getMemoryOpCost
+define void @getMemoryOpCost() {
+    ; If FeatureSlowMisaligned128Store is set, we penalize <2 x i64> stores. On
+    ; Cyclone, for example, such stores should be expensive because we don't
+    ; split them and misaligned 16b stores have bad performance.
+    ;
+    ; CHECK: cost of 1 {{.*}} store
+    ; SLOW_MISALIGNED_128_STORE: cost of 12 {{.*}} store
     store <2 x i64> undef, <2 x i64> * undef
 
     ; We scalarize the loads/stores because there is no vector register name for