Index: lib/Target/ARM/ARMISelLowering.cpp
===================================================================
--- lib/Target/ARM/ARMISelLowering.cpp
+++ lib/Target/ARM/ARMISelLowering.cpp
@@ -567,6 +567,7 @@
     setTargetDAGCombine(ISD::FP_TO_SINT);
     setTargetDAGCombine(ISD::FP_TO_UINT);
     setTargetDAGCombine(ISD::FDIV);
+    setTargetDAGCombine(ISD::LOAD);
 
     // It is legal to extload from v4i8 to v4i16 or v4i32.
     MVT Tys[6] = {MVT::v8i8, MVT::v4i8, MVT::v2i8,
@@ -8868,15 +8869,18 @@
                               DAG.getUNDEF(VT), NewMask.data());
 }
 
-/// CombineBaseUpdate - Target-specific DAG combine function for VLDDUP and
-/// NEON load/store intrinsics to merge base address updates.
+/// CombineBaseUpdate - Target-specific DAG combine function for VLDDUP,
+/// NEON load/store intrinsics, and generic vector load/stores, to merge
+/// base address updates.
+/// For generic load/stores, the memory type is assumed to be a vector.
 /// The caller is assumed to have checked legality.
 static SDValue CombineBaseUpdate(SDNode *N,
                                  TargetLowering::DAGCombinerInfo &DCI) {
   SelectionDAG &DAG = DCI.DAG;
   bool isIntrinsic = (N->getOpcode() == ISD::INTRINSIC_VOID ||
                       N->getOpcode() == ISD::INTRINSIC_W_CHAIN);
-  unsigned AddrOpIdx = (isIntrinsic ? 2 : 1);
+  bool isStore = N->getOpcode() == ISD::STORE;
+  unsigned AddrOpIdx = ((isIntrinsic || isStore) ? 2 : 1);
   SDValue Addr = N->getOperand(AddrOpIdx);
 
   // Search for a use of the address operand that is an increment.
@@ -8937,6 +8941,10 @@
       case ARMISD::VLD2DUP: NewOpc = ARMISD::VLD2DUP_UPD; NumVecs = 2; break;
       case ARMISD::VLD3DUP: NewOpc = ARMISD::VLD3DUP_UPD; NumVecs = 3; break;
       case ARMISD::VLD4DUP: NewOpc = ARMISD::VLD4DUP_UPD; NumVecs = 4; break;
+      case ISD::LOAD:       NewOpc = ARMISD::VLD1_UPD;
+        NumVecs = 1; isLaneOp = false; break;
+      case ISD::STORE:      NewOpc = ARMISD::VST1_UPD;
+        NumVecs = 1; isLoad = false; isLaneOp = false; break;
       }
     }
 
@@ -8944,8 +8952,11 @@
     EVT VecTy;
     if (isLoad)
       VecTy = N->getValueType(0);
-    else
+    else if (isIntrinsic)
       VecTy = N->getOperand(AddrOpIdx+1).getValueType();
+    else
+      VecTy = N->getOperand(1).getValueType();
+
     unsigned NumBytes = NumVecs * VecTy.getSizeInBits() / 8;
     if (isLaneOp)
       NumBytes /= VecTy.getVectorNumElements();
@@ -8978,8 +8989,13 @@
     Ops.push_back(N->getOperand(0)); // incoming chain
     Ops.push_back(N->getOperand(AddrOpIdx));
     Ops.push_back(Inc);
-    for (unsigned i = AddrOpIdx + 1; i < N->getNumOperands(); ++i) {
-      Ops.push_back(N->getOperand(i));
+    if (StoreSDNode *StN = dyn_cast<StoreSDNode>(N)) {
+      // Try to match the intrinsic's signature
+      Ops.push_back(StN->getValue());
+      Ops.push_back(DAG.getConstant(StN->getAlignment(), MVT::i32));
+    } else {
+      for (unsigned i = AddrOpIdx + 1; i < N->getNumOperands(); ++i)
+        Ops.push_back(N->getOperand(i));
     }
     MemSDNode *MemInt = cast<MemSDNode>(N);
     SDValue UpdN = DAG.getMemIntrinsicNode(NewOpc, SDLoc(N), SDTys,
@@ -9121,6 +9137,17 @@
   return DCI.DAG.getNode(ISD::BITCAST, SDLoc(N), VT, Op);
 }
 
+static SDValue PerformLOADCombine(SDNode *N,
+                                  TargetLowering::DAGCombinerInfo &DCI) {
+  EVT VT = N->getValueType(0);
+
+  // If this is a legal vector load, try to combine it into a VLD1_UPD.
+  if (VT.isVector() && DCI.DAG.getTargetLoweringInfo().isTypeLegal(VT))
+    return CombineBaseUpdate(N, DCI);
+
+  return SDValue();
+}
+
 /// PerformSTORECombine - Target-specific dag combine xforms for
 /// ISD::STORE.
 static SDValue PerformSTORECombine(SDNode *N,
@@ -9261,6 +9288,10 @@
                         St->getAAInfo());
   }
 
+  // If this is a legal vector store, try to combine it into a VST1_UPD.
+  if (VT.isVector() && DCI.DAG.getTargetLoweringInfo().isTypeLegal(VT))
+    return CombineBaseUpdate(N, DCI);
+
   return SDValue();
 }
 
@@ -9852,6 +9883,7 @@
   case ISD::ANY_EXTEND: return PerformExtendCombine(N, DCI.DAG, Subtarget);
   case ISD::SELECT_CC:  return PerformSELECT_CCCombine(N, DCI.DAG, Subtarget);
   case ARMISD::CMOV: return PerformCMOVCombine(N, DCI.DAG);
+  case ISD::LOAD:       return PerformLOADCombine(N, DCI);
   case ARMISD::VLD2DUP:
   case ARMISD::VLD3DUP:
   case ARMISD::VLD4DUP:
Index: test/CodeGen/ARM/alloc-no-stack-realign.ll
===================================================================
--- test/CodeGen/ARM/alloc-no-stack-realign.ll
+++ test/CodeGen/ARM/alloc-no-stack-realign.ll
@@ -9,8 +9,8 @@
 define void @test1(<16 x float>* noalias sret %agg.result) nounwind ssp "no-realign-stack" {
 entry:
 ; NO-REALIGN-LABEL: test1
-; NO-REALIGN: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1:[0-9]+]]:128]
-; NO-REALIGN: add r[[R2:[0-9]+]], r[[R1]], #16
+; NO-REALIGN: mov r[[R2:[0-9]+]], r[[R1:[0-9]+]]
+; NO-REALIGN: vld1.32 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]!
 ; NO-REALIGN: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
 ; NO-REALIGN: add r[[R2:[0-9]+]], r[[R1]], #32
 ; NO-REALIGN: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
@@ -21,16 +21,14 @@
 ; NO-REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
 ; NO-REALIGN: add r[[R2:[0-9]+]], r[[R1]], #32
 ; NO-REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
-; NO-REALIGN: add r[[R2:[0-9]+]], r[[R1]], #16
-; NO-REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
+; NO-REALIGN: vst1.32 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]!
 ; NO-REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]
 
 ; NO-REALIGN: add r[[R2:[0-9]+]], r[[R0:0]], #48
 ; NO-REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
 ; NO-REALIGN: add r[[R2:[0-9]+]], r[[R0]], #32
 ; NO-REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
-; NO-REALIGN: add r[[R2:[0-9]+]], r[[R1]], #16
-; NO-REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
+; NO-REALIGN: vst1.32 {{{d[0-9]+, d[0-9]+}}}, [r[[R0]]:128]!
 ; NO-REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R0]]:128]
  %retval = alloca <16 x float>, align 16
  %0 = load <16 x float>* @T3_retval, align 16
@@ -44,8 +42,8 @@
 entry:
 ; REALIGN-LABEL: test2
 ; REALIGN: bic sp, sp, #63
-; REALIGN: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1:[0-9]+]]:128]
-; REALIGN: add r[[R2:[0-9]+]], r[[R1]], #16
+; REALIGN: mov r[[R2:[0-9]+]], r[[R1:[0-9]+]]
+; REALIGN: vld1.32 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]!
 ; REALIGN: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
 ; REALIGN: add r[[R2:[0-9]+]], r[[R1]], #32
 ; REALIGN: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
@@ -65,8 +63,7 @@
 ; REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]
 ; REALIGN: add r[[R1:[0-9]+]], r[[R0]], #32
 ; REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]
-; REALIGN: add r[[R1:[0-9]+]], r[[R0]], #16
-; REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]
+; REALIGN: vst1.32 {{{d[0-9]+, d[0-9]+}}}, [r[[R0]]:128]!
 ; REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R0]]:128]
  %retval = alloca <16 x float>, align 16
  %0 = load <16 x float>* @T3_retval, align 16
Index: test/CodeGen/ARM/memcpy-inline.ll
===================================================================
--- test/CodeGen/ARM/memcpy-inline.ll
+++ test/CodeGen/ARM/memcpy-inline.ll
@@ -46,10 +46,8 @@
 ; CHECK: movw [[REG2:r[0-9]+]], #16716
 ; CHECK: movt [[REG2:r[0-9]+]], #72
 ; CHECK: str [[REG2]], [r0, #32]
-; CHECK: vld1.8 {d{{[0-9]+}}, d{{[0-9]+}}}, [r1]
-; CHECK: vst1.8 {d{{[0-9]+}}, d{{[0-9]+}}}, [r0]
-; CHECK: adds r0, #16
-; CHECK: adds r1, #16
+; CHECK: vld1.64 {d{{[0-9]+}}, d{{[0-9]+}}}, [r1]!
+; CHECK: vst1.64 {d{{[0-9]+}}, d{{[0-9]+}}}, [r0]!
 ; CHECK: vld1.8 {d{{[0-9]+}}, d{{[0-9]+}}}, [r1]
 ; CHECK: vst1.8 {d{{[0-9]+}}, d{{[0-9]+}}}, [r0]
   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %C, i8* getelementptr inbounds ([36 x i8]* @.str2, i64 0, i64 0), i64 36, i32 1, i1 false)
@@ -59,10 +57,8 @@
 define void @t3(i8* nocapture %C) nounwind {
 entry:
 ; CHECK-LABEL: t3:
-; CHECK: vld1.8 {d{{[0-9]+}}, d{{[0-9]+}}}, [r1]
-; CHECK: vst1.8 {d{{[0-9]+}}, d{{[0-9]+}}}, [r0]
-; CHECK: adds r0, #16
-; CHECK: adds r1, #16
+; CHECK: vld1.64 {d{{[0-9]+}}, d{{[0-9]+}}}, [r1]!
+; CHECK: vst1.64 {d{{[0-9]+}}, d{{[0-9]+}}}, [r0]!
 ; CHECK: vld1.8 {d{{[0-9]+}}}, [r1]
 ; CHECK: vst1.8 {d{{[0-9]+}}}, [r0]
   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %C, i8* getelementptr inbounds ([24 x i8]* @.str3, i64 0, i64 0), i64 24, i32 1, i1 false)
@@ -73,7 +69,8 @@
 entry:
 ; CHECK-LABEL: t4:
 ; CHECK: vld1.8 {[[REG3:d[0-9]+]], [[REG4:d[0-9]+]]}, [r1]
-; CHECK: vst1.8 {[[REG3]], [[REG4]]}, [r0]
+; CHECK: vst1.64 {[[REG3]], [[REG4]]}, [r0]!
+; CHECK: strh [[REG5:r[0-9]+]], [r0]
   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %C, i8* getelementptr inbounds ([18 x i8]* @.str4, i64 0, i64 0), i64 18, i32 1, i1 false)
   ret void
 }
Index: test/CodeGen/ARM/vector-load.ll
===================================================================
--- /dev/null
+++ test/CodeGen/ARM/vector-load.ll
@@ -0,0 +1,184 @@
+; RUN: llc < %s | FileCheck %s
+
+target datalayout = "e-m:o-p:32:32-i1:8:32-i8:8:32-i16:16:32-f64:32:64-v64:32:64-v128:32:128-a:0:32-n32-S32"
+target triple = "thumbv7s-apple-ios8.0.0"
+
+define <8 x i8> @load_v8i8(<8 x i8>** %ptr) {
+;CHECK-LABEL: load_v8i8:
+;CHECK: vld1.8 {{{d[0-9]+}}}, [{{r[0-9]+}}]
+	%A = load <8 x i8>** %ptr
+	%lA = load <8 x i8>* %A, align 1
+	ret <8 x i8> %lA
+}
+
+define <8 x i8> @load_v8i8_update(<8 x i8>** %ptr) {
+;CHECK-LABEL: load_v8i8_update:
+;CHECK: vld1.8 {{{d[0-9]+}}}, [{{r[0-9]+}}]!
+	%A = load <8 x i8>** %ptr
+	%lA = load <8 x i8>* %A, align 1
+	%inc = getelementptr <8 x i8>* %A, i38 1
+        store <8 x i8>* %inc, <8 x i8>** %ptr
+	ret <8 x i8> %lA
+}
+
+define <4 x i16> @load_v4i16(<4 x i16>** %ptr) {
+;CHECK-LABEL: load_v4i16:
+;CHECK: vld1.8 {{{d[0-9]+}}}, [{{r[0-9]+}}]
+	%A = load <4 x i16>** %ptr
+	%lA = load <4 x i16>* %A, align 1
+	ret <4 x i16> %lA
+}
+
+define <4 x i16> @load_v4i16_update(<4 x i16>** %ptr) {
+;CHECK-LABEL: load_v4i16_update:
+;CHECK: vld1.16 {{{d[0-9]+}}}, [{{r[0-9]+}}]!
+	%A = load <4 x i16>** %ptr
+	%lA = load <4 x i16>* %A, align 1
+	%inc = getelementptr <4 x i16>* %A, i34 1
+        store <4 x i16>* %inc, <4 x i16>** %ptr
+	ret <4 x i16> %lA
+}
+
+define <2 x i32> @load_v2i32(<2 x i32>** %ptr) {
+;CHECK-LABEL: load_v2i32:
+;CHECK: vld1.8 {{{d[0-9]+}}}, [{{r[0-9]+}}]
+	%A = load <2 x i32>** %ptr
+	%lA = load <2 x i32>* %A, align 1
+	ret <2 x i32> %lA
+}
+
+define <2 x i32> @load_v2i32_update(<2 x i32>** %ptr) {
+;CHECK-LABEL: load_v2i32_update:
+;CHECK: vld1.32 {{{d[0-9]+}}}, [{{r[0-9]+}}]!
+	%A = load <2 x i32>** %ptr
+	%lA = load <2 x i32>* %A, align 1
+	%inc = getelementptr <2 x i32>* %A, i32 1
+        store <2 x i32>* %inc, <2 x i32>** %ptr
+	ret <2 x i32> %lA
+}
+
+define <2 x float> @load_v2f32(<2 x float>** %ptr) {
+;CHECK-LABEL: load_v2f32:
+;CHECK: vld1.8 {{{d[0-9]+}}}, [{{r[0-9]+}}]
+	%A = load <2 x float>** %ptr
+	%lA = load <2 x float>* %A, align 1
+	ret <2 x float> %lA
+}
+
+define <2 x float> @load_v2f32_update(<2 x float>** %ptr) {
+;CHECK-LABEL: load_v2f32_update:
+;CHECK: vld1.32 {{{d[0-9]+}}}, [{{r[0-9]+}}]!
+	%A = load <2 x float>** %ptr
+	%lA = load <2 x float>* %A, align 1
+	%inc = getelementptr <2 x float>* %A, i32 1
+        store <2 x float>* %inc, <2 x float>** %ptr
+	ret <2 x float> %lA
+}
+
+define <1 x i64> @load_v1i64(<1 x i64>** %ptr) {
+;CHECK-LABEL: load_v1i64:
+;CHECK: vld1.8 {{{d[0-9]+}}}, [{{r[0-9]+}}]
+	%A = load <1 x i64>** %ptr
+	%lA = load <1 x i64>* %A, align 1
+	ret <1 x i64> %lA
+}
+
+define <1 x i64> @load_v1i64_update(<1 x i64>** %ptr) {
+;CHECK-LABEL: load_v1i64_update:
+;CHECK: vld1.64 {{{d[0-9]+}}}, [{{r[0-9]+}}]!
+	%A = load <1 x i64>** %ptr
+	%lA = load <1 x i64>* %A, align 1
+	%inc = getelementptr <1 x i64>* %A, i31 1
+        store <1 x i64>* %inc, <1 x i64>** %ptr
+	ret <1 x i64> %lA
+}
+
+define <16 x i8> @load_v16i8(<16 x i8>** %ptr) {
+;CHECK-LABEL: load_v16i8:
+;CHECK: vld1.8 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]
+	%A = load <16 x i8>** %ptr
+	%lA = load <16 x i8>* %A, align 1
+	ret <16 x i8> %lA
+}
+
+define <16 x i8> @load_v16i8_update(<16 x i8>** %ptr) {
+;CHECK-LABEL: load_v16i8_update:
+;CHECK: vld1.8 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]!
+	%A = load <16 x i8>** %ptr
+	%lA = load <16 x i8>* %A, align 1
+	%inc = getelementptr <16 x i8>* %A, i316 1
+        store <16 x i8>* %inc, <16 x i8>** %ptr
+	ret <16 x i8> %lA
+}
+
+define <8 x i16> @load_v8i16(<8 x i16>** %ptr) {
+;CHECK-LABEL: load_v8i16:
+;CHECK: vld1.8 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]
+	%A = load <8 x i16>** %ptr
+	%lA = load <8 x i16>* %A, align 1
+	ret <8 x i16> %lA
+}
+
+define <8 x i16> @load_v8i16_update(<8 x i16>** %ptr) {
+;CHECK-LABEL: load_v8i16_update:
+;CHECK: vld1.16 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]!
+	%A = load <8 x i16>** %ptr
+	%lA = load <8 x i16>* %A, align 1
+	%inc = getelementptr <8 x i16>* %A, i38 1
+        store <8 x i16>* %inc, <8 x i16>** %ptr
+	ret <8 x i16> %lA
+}
+
+define <4 x i32> @load_v4i32(<4 x i32>** %ptr) {
+;CHECK-LABEL: load_v4i32:
+;CHECK: vld1.8 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]
+	%A = load <4 x i32>** %ptr
+	%lA = load <4 x i32>* %A, align 1
+	ret <4 x i32> %lA
+}
+
+define <4 x i32> @load_v4i32_update(<4 x i32>** %ptr) {
+;CHECK-LABEL: load_v4i32_update:
+;CHECK: vld1.32 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]!
+	%A = load <4 x i32>** %ptr
+	%lA = load <4 x i32>* %A, align 1
+	%inc = getelementptr <4 x i32>* %A, i34 1
+        store <4 x i32>* %inc, <4 x i32>** %ptr
+	ret <4 x i32> %lA
+}
+
+define <4 x float> @load_v4f32(<4 x float>** %ptr) {
+;CHECK-LABEL: load_v4f32:
+;CHECK: vld1.8 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]
+	%A = load <4 x float>** %ptr
+	%lA = load <4 x float>* %A, align 1
+	ret <4 x float> %lA
+}
+
+define <4 x float> @load_v4f32_update(<4 x float>** %ptr) {
+;CHECK-LABEL: load_v4f32_update:
+;CHECK: vld1.32 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]!
+	%A = load <4 x float>** %ptr
+	%lA = load <4 x float>* %A, align 1
+	%inc = getelementptr <4 x float>* %A, i34 1
+        store <4 x float>* %inc, <4 x float>** %ptr
+	ret <4 x float> %lA
+}
+
+define <2 x i64> @load_v2i64(<2 x i64>** %ptr) {
+;CHECK-LABEL: load_v2i64:
+;CHECK: vld1.8 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]
+	%A = load <2 x i64>** %ptr
+	%lA = load <2 x i64>* %A, align 1
+	ret <2 x i64> %lA
+}
+
+define <2 x i64> @load_v2i64_update(<2 x i64>** %ptr) {
+;CHECK-LABEL: load_v2i64_update:
+;CHECK: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]!
+	%A = load <2 x i64>** %ptr
+	%lA = load <2 x i64>* %A, align 1
+	%inc = getelementptr <2 x i64>* %A, i32 1
+        store <2 x i64>* %inc, <2 x i64>** %ptr
+	ret <2 x i64> %lA
+}
Index: test/CodeGen/ARM/vector-store.ll
===================================================================
--- /dev/null
+++ test/CodeGen/ARM/vector-store.ll
@@ -0,0 +1,184 @@
+; RUN: llc < %s | FileCheck %s
+
+target datalayout = "e-m:o-p:32:32-i1:8:32-i8:8:32-i16:16:32-f64:32:64-v64:32:64-v128:32:128-a:0:32-n32-S32"
+target triple = "thumbv7s-apple-ios8.0.0"
+
+define void @store_v8i8(<8 x i8>** %ptr, <8 x i8> %val) {
+;CHECK-LABEL: store_v8i8:
+;CHECK: str r1, [r0]
+	%A = load <8 x i8>** %ptr
+	store  <8 x i8> %val, <8 x i8>* %A, align 1
+	ret void
+}
+
+define void @store_v8i8_update(<8 x i8>** %ptr, <8 x i8> %val) {
+;CHECK-LABEL: store_v8i8_update:
+;CHECK: vst1.8 {{{d[0-9]+}}}, [{{r[0-9]+}}]!
+	%A = load <8 x i8>** %ptr
+	store  <8 x i8> %val, <8 x i8>* %A, align 1
+	%inc = getelementptr <8 x i8>* %A, i38 1
+        store <8 x i8>* %inc, <8 x i8>** %ptr
+	ret void
+}
+
+define void @store_v4i16(<4 x i16>** %ptr, <4 x i16> %val) {
+;CHECK-LABEL: store_v4i16:
+;CHECK: str r1, [r0]
+	%A = load <4 x i16>** %ptr
+	store  <4 x i16> %val, <4 x i16>* %A, align 1
+	ret void
+}
+
+define void @store_v4i16_update(<4 x i16>** %ptr, <4 x i16> %val) {
+;CHECK-LABEL: store_v4i16_update:
+;CHECK: vst1.16 {{{d[0-9]+}}}, [{{r[0-9]+}}]!
+	%A = load <4 x i16>** %ptr
+	store  <4 x i16> %val, <4 x i16>* %A, align 1
+	%inc = getelementptr <4 x i16>* %A, i34 1
+        store <4 x i16>* %inc, <4 x i16>** %ptr
+	ret void
+}
+
+define void @store_v2i32(<2 x i32>** %ptr, <2 x i32> %val) {
+;CHECK-LABEL: store_v2i32:
+;CHECK: str r1, [r0]
+	%A = load <2 x i32>** %ptr
+	store  <2 x i32> %val, <2 x i32>* %A, align 1
+	ret void
+}
+
+define void @store_v2i32_update(<2 x i32>** %ptr, <2 x i32> %val) {
+;CHECK-LABEL: store_v2i32_update:
+;CHECK: vst1.32 {{{d[0-9]+}}}, [{{r[0-9]+}}]!
+	%A = load <2 x i32>** %ptr
+	store  <2 x i32> %val, <2 x i32>* %A, align 1
+	%inc = getelementptr <2 x i32>* %A, i32 1
+        store <2 x i32>* %inc, <2 x i32>** %ptr
+	ret void
+}
+
+define void @store_v2f32(<2 x float>** %ptr, <2 x float> %val) {
+;CHECK-LABEL: store_v2f32:
+;CHECK: str r1, [r0]
+	%A = load <2 x float>** %ptr
+	store  <2 x float> %val, <2 x float>* %A, align 1
+	ret void
+}
+
+define void @store_v2f32_update(<2 x float>** %ptr, <2 x float> %val) {
+;CHECK-LABEL: store_v2f32_update:
+;CHECK: vst1.32 {{{d[0-9]+}}}, [{{r[0-9]+}}]!
+	%A = load <2 x float>** %ptr
+	store  <2 x float> %val, <2 x float>* %A, align 1
+	%inc = getelementptr <2 x float>* %A, i32 1
+        store <2 x float>* %inc, <2 x float>** %ptr
+	ret void
+}
+
+define void @store_v1i64(<1 x i64>** %ptr, <1 x i64> %val) {
+;CHECK-LABEL: store_v1i64:
+;CHECK: str r1, [r0]
+	%A = load <1 x i64>** %ptr
+	store  <1 x i64> %val, <1 x i64>* %A, align 1
+	ret void
+}
+
+define void @store_v1i64_update(<1 x i64>** %ptr, <1 x i64> %val) {
+;CHECK-LABEL: store_v1i64_update:
+;CHECK: vst1.64 {{{d[0-9]+}}}, [{{r[0-9]+}}]!
+	%A = load <1 x i64>** %ptr
+	store  <1 x i64> %val, <1 x i64>* %A, align 1
+	%inc = getelementptr <1 x i64>* %A, i31 1
+        store <1 x i64>* %inc, <1 x i64>** %ptr
+	ret void
+}
+
+define void @store_v16i8(<16 x i8>** %ptr, <16 x i8> %val) {
+;CHECK-LABEL: store_v16i8:
+;CHECK: vst1.8 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]
+	%A = load <16 x i8>** %ptr
+	store  <16 x i8> %val, <16 x i8>* %A, align 1
+	ret void
+}
+
+define void @store_v16i8_update(<16 x i8>** %ptr, <16 x i8> %val) {
+;CHECK-LABEL: store_v16i8_update:
+;CHECK: vst1.8 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]!
+	%A = load <16 x i8>** %ptr
+	store  <16 x i8> %val, <16 x i8>* %A, align 1
+	%inc = getelementptr <16 x i8>* %A, i316 1
+        store <16 x i8>* %inc, <16 x i8>** %ptr
+	ret void
+}
+
+define void @store_v8i16(<8 x i16>** %ptr, <8 x i16> %val) {
+;CHECK-LABEL: store_v8i16:
+;CHECK: vst1.8 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]
+	%A = load <8 x i16>** %ptr
+	store  <8 x i16> %val, <8 x i16>* %A, align 1
+	ret void
+}
+
+define void @store_v8i16_update(<8 x i16>** %ptr, <8 x i16> %val) {
+;CHECK-LABEL: store_v8i16_update:
+;CHECK: vst1.16 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]!
+	%A = load <8 x i16>** %ptr
+	store  <8 x i16> %val, <8 x i16>* %A, align 1
+	%inc = getelementptr <8 x i16>* %A, i38 1
+        store <8 x i16>* %inc, <8 x i16>** %ptr
+	ret void
+}
+
+define void @store_v4i32(<4 x i32>** %ptr, <4 x i32> %val) {
+;CHECK-LABEL: store_v4i32:
+;CHECK: vst1.8 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]
+	%A = load <4 x i32>** %ptr
+	store  <4 x i32> %val, <4 x i32>* %A, align 1
+	ret void
+}
+
+define void @store_v4i32_update(<4 x i32>** %ptr, <4 x i32> %val) {
+;CHECK-LABEL: store_v4i32_update:
+;CHECK: vst1.32 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]!
+	%A = load <4 x i32>** %ptr
+	store  <4 x i32> %val, <4 x i32>* %A, align 1
+	%inc = getelementptr <4 x i32>* %A, i34 1
+        store <4 x i32>* %inc, <4 x i32>** %ptr
+	ret void
+}
+
+define void @store_v4f32(<4 x float>** %ptr, <4 x float> %val) {
+;CHECK-LABEL: store_v4f32:
+;CHECK: vst1.8 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]
+	%A = load <4 x float>** %ptr
+	store  <4 x float> %val, <4 x float>* %A, align 1
+	ret void
+}
+
+define void @store_v4f32_update(<4 x float>** %ptr, <4 x float> %val) {
+;CHECK-LABEL: store_v4f32_update:
+;CHECK: vst1.32 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]!
+	%A = load <4 x float>** %ptr
+	store  <4 x float> %val, <4 x float>* %A, align 1
+	%inc = getelementptr <4 x float>* %A, i34 1
+        store <4 x float>* %inc, <4 x float>** %ptr
+	ret void
+}
+
+define void @store_v2i64(<2 x i64>** %ptr, <2 x i64> %val) {
+;CHECK-LABEL: store_v2i64:
+;CHECK: vst1.8 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]
+	%A = load <2 x i64>** %ptr
+	store  <2 x i64> %val, <2 x i64>* %A, align 1
+	ret void
+}
+
+define void @store_v2i64_update(<2 x i64>** %ptr, <2 x i64> %val) {
+;CHECK-LABEL: store_v2i64_update:
+;CHECK: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]!
+	%A = load <2 x i64>** %ptr
+	store  <2 x i64> %val, <2 x i64>* %A, align 1
+	%inc = getelementptr <2 x i64>* %A, i32 1
+        store <2 x i64>* %inc, <2 x i64>** %ptr
+	ret void
+}