[ARM] Combine base-updating/post-incrementing vector load/stores.

We used to only combine intrinsics, and turn them into VLD1_UPD/VST1_UPD
when the base pointer is incremented after the load/store.

We can do the same thing for generic load/stores.

Note that we can only combine the first load/store+adds pair in
a sequence (as might be generated for a v16f32 load for instance),
because other combines turn the base pointer addition chain (each
computing the address of the next load, from the address of the last
load) into independent additions (common base pointer + this load's
offset).

Differential Revision: http://reviews.llvm.org/D6585

llvm-svn: 223862

llvm/lib/Target/ARM/ARMISelLowering.cpp

@@ -567,6 +567,7 @@ ARMTargetLowering::ARMTargetLowering(const TargetMachine &TM)
     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 @@ static SDValue PerformVECTOR_SHUFFLECombine(SDNode *N, SelectionDAG &DAG) {
                               DAG.getUNDEF(VT), NewMask.data());
 }
 
-/// CombineBaseUpdate - Target-specific DAG combine function for VLDDUP and
+/// CombineBaseUpdate - Target-specific DAG combine function for VLDDUP,
-/// NEON load/store intrinsics to merge base address updates.
+/// 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 @@ static SDValue CombineBaseUpdate(SDNode *N,
       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 @@ static SDValue CombineBaseUpdate(SDNode *N,
     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 @@ static SDValue CombineBaseUpdate(SDNode *N,
     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) {
+    if (StoreSDNode *StN = dyn_cast<StoreSDNode>(N)) {
-      Ops.push_back(N->getOperand(i));
+      // 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 @@ static SDValue PerformVDUPLANECombine(SDNode *N,
   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 @@ static SDValue PerformSTORECombine(SDNode *N,
                         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 @@ SDValue ARMTargetLowering::PerformDAGCombine(SDNode *N,
   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:

llvm/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: mov r[[R2:[0-9]+]], r[[R1:[0-9]+]]
-; NO-REALIGN: add r[[R2:[0-9]+]], r[[R1]], #16
+; 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 @@ entry:
 ; 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: vst1.32 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]!
-; NO-REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]: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: vst1.32 {{{d[0-9]+, d[0-9]+}}}, [r[[R0]]:128]!
-; NO-REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]: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 @@ define void @test2(<16 x float>* noalias sret %agg.result) nounwind ssp {
 entry:
 ; REALIGN-LABEL: test2
 ; REALIGN: bic sp, sp, #63
-; REALIGN: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1:[0-9]+]]:128]
+; REALIGN: mov r[[R2:[0-9]+]], r[[R1:[0-9]+]]
-; REALIGN: add r[[R2:[0-9]+]], r[[R1]], #16
+; 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 @@ entry:
 ; 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: vst1.32 {{{d[0-9]+, d[0-9]+}}}, [r[[R0]]:128]!
-; REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]: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

llvm/test/CodeGen/ARM/memcpy-inline.ll

@@ -46,10 +46,8 @@ entry:
 ; 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: vld1.64 {d{{[0-9]+}}, d{{[0-9]+}}}, [r1]!
-; CHECK: vst1.8 {d{{[0-9]+}}, d{{[0-9]+}}}, [r0]
+; CHECK: vst1.64 {d{{[0-9]+}}, d{{[0-9]+}}}, [r0]!
-; CHECK: adds r0, #16
-; CHECK: adds r1, #16
 ; 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 @@ entry:
 define void @t3(i8* nocapture %C) nounwind {
 entry:
 ; CHECK-LABEL: t3:
-; CHECK: vld1.8 {d{{[0-9]+}}, d{{[0-9]+}}}, [r1]
+; CHECK: vld1.64 {d{{[0-9]+}}, d{{[0-9]+}}}, [r1]!
-; CHECK: vst1.8 {d{{[0-9]+}}, d{{[0-9]+}}}, [r0]
+; CHECK: vst1.64 {d{{[0-9]+}}, d{{[0-9]+}}}, [r0]!
-; CHECK: adds r0, #16
-; CHECK: adds r1, #16
 ; 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 @@ define void @t4(i8* nocapture %C) nounwind {
 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
 }

llvm/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
+}

llvm/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
+}

llvm/test/Transforms/LoopStrengthReduce/ARM/ivchain-ARM.ll

@@ -201,7 +201,7 @@ for.end:                                          ; preds = %for.body
 ;
 ; Currently we have three extra add.w's that keep the store address
 ; live past the next increment because ISEL is unfortunately undoing
-; the store chain. ISEL also fails to convert the stores to
+; the store chain. ISEL also fails to convert all but one of the stores to
 ; post-increment addressing. However, the loads should use
 ; post-increment addressing, no add's or add.w's beyond the three
 ; mentioned. Most importantly, there should be no spills or reloads!
@@ -210,7 +210,7 @@ for.end:                                          ; preds = %for.body
 ; A9: %.lr.ph
 ; A9-NOT: lsl.w
 ; A9-NOT: {{ldr|str|adds|add r}}
-; A9: add.w r
+; A9: vst1.8 {{.*}} [r{{[0-9]+}}]!
 ; A9-NOT: {{ldr|str|adds|add r}}
 ; A9: add.w r
 ; A9-NOT: {{ldr|str|adds|add r}}