summaryrefslogtreecommitdiffstats
path: root/llvm
diff options
context:
space:
mode:
Diffstat (limited to 'llvm')
-rw-r--r--llvm/lib/Target/ARM/ARMISelDAGToDAG.cpp16
-rw-r--r--llvm/lib/Target/ARM/ARMISelLowering.cpp131
-rw-r--r--llvm/test/CodeGen/ARM/alloc-no-stack-realign.ll17
-rw-r--r--llvm/test/CodeGen/ARM/memcpy-inline.ll15
-rw-r--r--llvm/test/CodeGen/ARM/vector-load.ll253
-rw-r--r--llvm/test/CodeGen/ARM/vector-store.ll258
-rw-r--r--llvm/test/Transforms/LoopStrengthReduce/ARM/ivchain-ARM.ll4
7 files changed, 654 insertions, 40 deletions
diff --git a/llvm/lib/Target/ARM/ARMISelDAGToDAG.cpp b/llvm/lib/Target/ARM/ARMISelDAGToDAG.cpp
index 0cbfe488ac4..6410b338238 100644
--- a/llvm/lib/Target/ARM/ARMISelDAGToDAG.cpp
+++ b/llvm/lib/Target/ARM/ARMISelDAGToDAG.cpp
@@ -992,18 +992,24 @@ bool ARMDAGToDAGISel::SelectAddrMode6(SDNode *Parent, SDValue N, SDValue &Addr,
Addr = N;
unsigned Alignment = 0;
- if (LSBaseSDNode *LSN = dyn_cast<LSBaseSDNode>(Parent)) {
+
+ MemSDNode *MemN = cast<MemSDNode>(Parent);
+
+ if (isa<LSBaseSDNode>(MemN) ||
+ ((MemN->getOpcode() == ARMISD::VST1_UPD ||
+ MemN->getOpcode() == ARMISD::VLD1_UPD) &&
+ MemN->getConstantOperandVal(MemN->getNumOperands() - 1) == 1)) {
// This case occurs only for VLD1-lane/dup and VST1-lane instructions.
// The maximum alignment is equal to the memory size being referenced.
- unsigned LSNAlign = LSN->getAlignment();
- unsigned MemSize = LSN->getMemoryVT().getSizeInBits() / 8;
- if (LSNAlign >= MemSize && MemSize > 1)
+ unsigned MMOAlign = MemN->getAlignment();
+ unsigned MemSize = MemN->getMemoryVT().getSizeInBits() / 8;
+ if (MMOAlign >= MemSize && MemSize > 1)
Alignment = MemSize;
} else {
// All other uses of addrmode6 are for intrinsics. For now just record
// the raw alignment value; it will be refined later based on the legal
// alignment operands for the intrinsic.
- Alignment = cast<MemIntrinsicSDNode>(Parent)->getAlignment();
+ Alignment = MemN->getAlignment();
}
Align = CurDAG->getTargetConstant(Alignment, MVT::i32);
diff --git a/llvm/lib/Target/ARM/ARMISelLowering.cpp b/llvm/lib/Target/ARM/ARMISelLowering.cpp
index f07af201e6e..4f9bdc0ab76 100644
--- a/llvm/lib/Target/ARM/ARMISelLowering.cpp
+++ b/llvm/lib/Target/ARM/ARMISelLowering.cpp
@@ -565,6 +565,7 @@ 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,
@@ -8872,17 +8873,18 @@ static SDValue PerformVECTOR_SHUFFLECombine(SDNode *N, SelectionDAG &DAG) {
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) {
- if (DCI.isBeforeLegalize() || DCI.isCalledByLegalizer())
- return SDValue();
-
SelectionDAG &DAG = DCI.DAG;
const bool isIntrinsic = (N->getOpcode() == ISD::INTRINSIC_VOID ||
N->getOpcode() == ISD::INTRINSIC_W_CHAIN);
- const unsigned AddrOpIdx = (isIntrinsic ? 2 : 1);
+ const bool isStore = N->getOpcode() == ISD::STORE;
+ const unsigned AddrOpIdx = ((isIntrinsic || isStore) ? 2 : 1);
SDValue Addr = N->getOperand(AddrOpIdx);
MemSDNode *MemN = cast<MemSDNode>(N);
@@ -8944,15 +8946,24 @@ 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; isLaneOp = false; isLoadOp = false; break;
}
}
// Find the size of memory referenced by the load/store.
EVT VecTy;
- if (isLoadOp)
+ if (isLoadOp) {
VecTy = N->getValueType(0);
- else
+ } else if (isIntrinsic) {
VecTy = N->getOperand(AddrOpIdx+1).getValueType();
+ } else {
+ assert(isStore && "Node has to be a load, a store, or an intrinsic!");
+ VecTy = N->getOperand(1).getValueType();
+ }
+
unsigned NumBytes = NumVecs * VecTy.getSizeInBits() / 8;
if (isLaneOp)
NumBytes /= VecTy.getVectorNumElements();
@@ -8969,13 +8980,53 @@ static SDValue CombineBaseUpdate(SDNode *N,
continue;
}
+ // OK, we found an ADD we can fold into the base update.
+ // Now, create a _UPD node, taking care of not breaking alignment.
+
+ EVT AlignedVecTy = VecTy;
+ unsigned Alignment = MemN->getAlignment();
+
+ // If this is a less-than-standard-aligned load/store, change the type to
+ // match the standard alignment.
+ // The alignment is overlooked when selecting _UPD variants; and it's
+ // easier to introduce bitcasts here than fix that.
+ // There are 3 ways to get to this base-update combine:
+ // - intrinsics: they are assumed to be properly aligned (to the standard
+ // alignment of the memory type), so we don't need to do anything.
+ // - ARMISD::VLDx nodes: they are only generated from the aforementioned
+ // intrinsics, so, likewise, there's nothing to do.
+ // - generic load/store instructions: the alignment is specified as an
+ // explicit operand, rather than implicitly as the standard alignment
+ // of the memory type (like the intrisics). We need to change the
+ // memory type to match the explicit alignment. That way, we don't
+ // generate non-standard-aligned ARMISD::VLDx nodes.
+ if (isa<LSBaseSDNode>(N)) {
+ if (Alignment == 0)
+ Alignment = 1;
+ if (Alignment < VecTy.getScalarSizeInBits() / 8) {
+ MVT EltTy = MVT::getIntegerVT(Alignment * 8);
+ assert(NumVecs == 1 && "Unexpected multi-element generic load/store.");
+ assert(!isLaneOp && "Unexpected generic load/store lane.");
+ unsigned NumElts = NumBytes / (EltTy.getSizeInBits() / 8);
+ AlignedVecTy = MVT::getVectorVT(EltTy, NumElts);
+ }
+ // Don't set an explicit alignment on regular load/stores that we want
+ // to transform to VLD/VST 1_UPD nodes.
+ // This matches the behavior of regular load/stores, which only get an
+ // explicit alignment if the MMO alignment is larger than the standard
+ // alignment of the memory type.
+ // Intrinsics, however, always get an explicit alignment, set to the
+ // alignment of the MMO.
+ Alignment = 1;
+ }
+
// Create the new updating load/store node.
// First, create an SDVTList for the new updating node's results.
EVT Tys[6];
unsigned NumResultVecs = (isLoadOp ? NumVecs : 0);
unsigned n;
for (n = 0; n < NumResultVecs; ++n)
- Tys[n] = VecTy;
+ Tys[n] = AlignedVecTy;
Tys[n++] = MVT::i32;
Tys[n] = MVT::Other;
SDVTList SDTys = DAG.getVTList(makeArrayRef(Tys, NumResultVecs+2));
@@ -8985,17 +9036,43 @@ 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)
- 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());
+ } else {
+ // Loads (and of course intrinsics) match the intrinsics' signature,
+ // so just add all but the alignment operand.
+ for (unsigned i = AddrOpIdx + 1; i < N->getNumOperands() - 1; ++i)
+ Ops.push_back(N->getOperand(i));
+ }
+
+ // For all node types, the alignment operand is always the last one.
+ Ops.push_back(DAG.getConstant(Alignment, MVT::i32));
+
+ // If this is a non-standard-aligned STORE, the penultimate operand is the
+ // stored value. Bitcast it to the aligned type.
+ if (AlignedVecTy != VecTy && N->getOpcode() == ISD::STORE) {
+ SDValue &StVal = Ops[Ops.size()-2];
+ StVal = DAG.getNode(ISD::BITCAST, SDLoc(N), AlignedVecTy, StVal);
+ }
SDValue UpdN = DAG.getMemIntrinsicNode(NewOpc, SDLoc(N), SDTys,
- Ops, MemN->getMemoryVT(),
+ Ops, AlignedVecTy,
MemN->getMemOperand());
// Update the uses.
SmallVector<SDValue, 5> NewResults;
for (unsigned i = 0; i < NumResultVecs; ++i)
NewResults.push_back(SDValue(UpdN.getNode(), i));
+
+ // If this is an non-standard-aligned LOAD, the first result is the loaded
+ // value. Bitcast it to the expected result type.
+ if (AlignedVecTy != VecTy && N->getOpcode() == ISD::LOAD) {
+ SDValue &LdVal = NewResults[0];
+ LdVal = DAG.getNode(ISD::BITCAST, SDLoc(N), VecTy, LdVal);
+ }
+
NewResults.push_back(SDValue(UpdN.getNode(), NumResultVecs+1)); // chain
DCI.CombineTo(N, NewResults);
DCI.CombineTo(User, SDValue(UpdN.getNode(), NumResultVecs));
@@ -9005,6 +9082,14 @@ static SDValue CombineBaseUpdate(SDNode *N,
return SDValue();
}
+static SDValue PerformVLDCombine(SDNode *N,
+ TargetLowering::DAGCombinerInfo &DCI) {
+ if (DCI.isBeforeLegalize() || DCI.isCalledByLegalizer())
+ return SDValue();
+
+ return CombineBaseUpdate(N, DCI);
+}
+
/// CombineVLDDUP - For a VDUPLANE node N, check if its source operand is a
/// vldN-lane (N > 1) intrinsic, and if all the other uses of that intrinsic
/// are also VDUPLANEs. If so, combine them to a vldN-dup operation and
@@ -9118,6 +9203,18 @@ 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 (ISD::isNormalLoad(N) && 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,
@@ -9256,6 +9353,11 @@ static SDValue PerformSTORECombine(SDNode *N,
St->getAAInfo());
}
+ // If this is a legal vector store, try to combine it into a VST1_UPD.
+ if (ISD::isNormalStore(N) && VT.isVector() &&
+ DCI.DAG.getTargetLoweringInfo().isTypeLegal(VT))
+ return CombineBaseUpdate(N, DCI);
+
return SDValue();
}
@@ -9849,10 +9951,11 @@ 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:
- return CombineBaseUpdate(N, DCI);
+ return PerformVLDCombine(N, DCI);
case ARMISD::BUILD_VECTOR:
return PerformARMBUILD_VECTORCombine(N, DCI);
case ISD::INTRINSIC_VOID:
@@ -9872,7 +9975,7 @@ SDValue ARMTargetLowering::PerformDAGCombine(SDNode *N,
case Intrinsic::arm_neon_vst2lane:
case Intrinsic::arm_neon_vst3lane:
case Intrinsic::arm_neon_vst4lane:
- return CombineBaseUpdate(N, DCI);
+ return PerformVLDCombine(N, DCI);
default: break;
}
break;
diff --git a/llvm/test/CodeGen/ARM/alloc-no-stack-realign.ll b/llvm/test/CodeGen/ARM/alloc-no-stack-realign.ll
index 24c28baff88..5ad87191efe 100644
--- a/llvm/test/CodeGen/ARM/alloc-no-stack-realign.ll
+++ b/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: 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 @@ 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: vst1.64 {{{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 @@ define void @test2(<16 x float>* noalias sret %agg.result) nounwind ssp {
entry:
; REALIGN-LABEL: test2
; REALIGN: bfc sp, #0, #6
-; 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 @@ 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: vst1.64 {{{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
diff --git a/llvm/test/CodeGen/ARM/memcpy-inline.ll b/llvm/test/CodeGen/ARM/memcpy-inline.ll
index 84ce4a7f0e7..33ac4e12563 100644
--- a/llvm/test/CodeGen/ARM/memcpy-inline.ll
+++ b/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: vst1.8 {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]!
; 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: vst1.8 {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]!
; 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: vst1.8 {[[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
}
diff --git a/llvm/test/CodeGen/ARM/vector-load.ll b/llvm/test/CodeGen/ARM/vector-load.ll
new file mode 100644
index 00000000000..c177a55d7a1
--- /dev/null
+++ b/llvm/test/CodeGen/ARM/vector-load.ll
@@ -0,0 +1,253 @@
+; 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: vld1.8 {{{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: vld1.8 {{{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: vld1.8 {{{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: vld1.8 {{{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: vld1.8 {{{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: vld1.8 {{{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: vld1.8 {{{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: vld1.8 {{{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
+}
+
+; Make sure we change the type to match alignment if necessary.
+define <2 x i64> @load_v2i64_update_aligned2(<2 x i64>** %ptr) {
+;CHECK-LABEL: load_v2i64_update_aligned2:
+;CHECK: vld1.16 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]!
+ %A = load <2 x i64>** %ptr
+ %lA = load <2 x i64>* %A, align 2
+ %inc = getelementptr <2 x i64>* %A, i32 1
+ store <2 x i64>* %inc, <2 x i64>** %ptr
+ ret <2 x i64> %lA
+}
+
+define <2 x i64> @load_v2i64_update_aligned4(<2 x i64>** %ptr) {
+;CHECK-LABEL: load_v2i64_update_aligned4:
+;CHECK: vld1.32 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}]!
+ %A = load <2 x i64>** %ptr
+ %lA = load <2 x i64>* %A, align 4
+ %inc = getelementptr <2 x i64>* %A, i32 1
+ store <2 x i64>* %inc, <2 x i64>** %ptr
+ ret <2 x i64> %lA
+}
+
+define <2 x i64> @load_v2i64_update_aligned8(<2 x i64>** %ptr) {
+;CHECK-LABEL: load_v2i64_update_aligned8:
+;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 8
+ %inc = getelementptr <2 x i64>* %A, i32 1
+ store <2 x i64>* %inc, <2 x i64>** %ptr
+ ret <2 x i64> %lA
+}
+
+define <2 x i64> @load_v2i64_update_aligned16(<2 x i64>** %ptr) {
+;CHECK-LABEL: load_v2i64_update_aligned16:
+;CHECK: vld1.64 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}:128]!
+ %A = load <2 x i64>** %ptr
+ %lA = load <2 x i64>* %A, align 16
+ %inc = getelementptr <2 x i64>* %A, i32 1
+ store <2 x i64>* %inc, <2 x i64>** %ptr
+ ret <2 x i64> %lA
+}
+
+; Make sure we don't break smaller-than-dreg extloads.
+define <4 x i32> @zextload_v8i8tov8i32(<4 x i8>** %ptr) {
+;CHECK-LABEL: zextload_v8i8tov8i32:
+;CHECK: vld1.32 {{{d[0-9]+}}[0]}, [{{r[0-9]+}}:32]
+;CHECK: vmovl.u8 {{q[0-9]+}}, {{d[0-9]+}}
+;CHECK: vmovl.u16 {{q[0-9]+}}, {{d[0-9]+}}
+ %A = load <4 x i8>** %ptr
+ %lA = load <4 x i8>* %A, align 4
+ %zlA = zext <4 x i8> %lA to <4 x i32>
+ ret <4 x i32> %zlA
+}
+
+define <4 x i32> @zextload_v8i8tov8i32_fake_update(<4 x i8>** %ptr) {
+;CHECK-LABEL: zextload_v8i8tov8i32_fake_update:
+;CHECK: ldr.w r[[PTRREG:[0-9]+]], [r0]
+;CHECK: vld1.32 {{{d[0-9]+}}[0]}, [r[[PTRREG]]:32]
+;CHECK: add.w r[[INCREG:[0-9]+]], r[[PTRREG]], #16
+;CHECK: str.w r[[INCREG]], [r0]
+;CHECK: vmovl.u8 {{q[0-9]+}}, {{d[0-9]+}}
+;CHECK: vmovl.u16 {{q[0-9]+}}, {{d[0-9]+}}
+ %A = load <4 x i8>** %ptr
+ %lA = load <4 x i8>* %A, align 4
+ %inc = getelementptr <4 x i8>* %A, i38 4
+ store <4 x i8>* %inc, <4 x i8>** %ptr
+ %zlA = zext <4 x i8> %lA to <4 x i32>
+ ret <4 x i32> %zlA
+}
diff --git a/llvm/test/CodeGen/ARM/vector-store.ll b/llvm/test/CodeGen/ARM/vector-store.ll
new file mode 100644
index 00000000000..55cb8f26658
--- /dev/null
+++ b/llvm/test/CodeGen/ARM/vector-store.ll
@@ -0,0 +1,258 @@
+; 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: vst1.8 {{{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: vst1.8 {{{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: vst1.8 {{{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: vst1.8 {{{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: vst1.8 {{{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
+ %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: vst1.8 {{{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
+ %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: vst1.8 {{{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
+ %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: vst1.8 {{{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
+ %inc = getelementptr <2 x i64>* %A, i32 1
+ store <2 x i64>* %inc, <2 x i64>** %ptr
+ ret void
+}
+
+define void @store_v2i64_update_aligned2(<2 x i64>** %ptr, <2 x i64> %val) {
+;CHECK-LABEL: store_v2i64_update_aligned2:
+;CHECK: vst1.16 {{{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 2
+ %inc = getelementptr <2 x i64>* %A, i32 1
+ store <2 x i64>* %inc, <2 x i64>** %ptr
+ ret void
+}
+
+define void @store_v2i64_update_aligned4(<2 x i64>** %ptr, <2 x i64> %val) {
+;CHECK-LABEL: store_v2i64_update_aligned4:
+;CHECK: vst1.32 {{{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 4
+ %inc = getelementptr <2 x i64>* %A, i32 1
+ store <2 x i64>* %inc, <2 x i64>** %ptr
+ ret void
+}
+
+define void @store_v2i64_update_aligned8(<2 x i64>** %ptr, <2 x i64> %val) {
+;CHECK-LABEL: store_v2i64_update_aligned8:
+;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 8
+ %inc = getelementptr <2 x i64>* %A, i32 1
+ store <2 x i64>* %inc, <2 x i64>** %ptr
+ ret void
+}
+
+define void @store_v2i64_update_aligned16(<2 x i64>** %ptr, <2 x i64> %val) {
+;CHECK-LABEL: store_v2i64_update_aligned16:
+;CHECK: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [{{r[0-9]+}}:128]!
+ %A = load <2 x i64>** %ptr
+ store <2 x i64> %val, <2 x i64>* %A, align 16
+ %inc = getelementptr <2 x i64>* %A, i32 1
+ store <2 x i64>* %inc, <2 x i64>** %ptr
+ ret void
+}
+
+define void @truncstore_v4i32tov4i8(<4 x i8>** %ptr, <4 x i32> %val) {
+;CHECK-LABEL: truncstore_v4i32tov4i8:
+;CHECK: ldr.w r9, [sp]
+;CHECK: vmov {{d[0-9]+}}, r3, r9
+;CHECK: vmov {{d[0-9]+}}, r1, r2
+;CHECK: vmovn.i32 [[VECLO:d[0-9]+]], {{q[0-9]+}}
+;CHECK: vuzp.8 [[VECLO]], {{d[0-9]+}}
+;CHECK: ldr r[[PTRREG:[0-9]+]], [r0]
+;CHECK: vst1.32 {[[VECLO]][0]}, [r[[PTRREG]]:32]
+ %A = load <4 x i8>** %ptr
+ %trunc = trunc <4 x i32> %val to <4 x i8>
+ store <4 x i8> %trunc, <4 x i8>* %A, align 4
+ ret void
+}
+
+define void @truncstore_v4i32tov4i8_fake_update(<4 x i8>** %ptr, <4 x i32> %val) {
+;CHECK-LABEL: truncstore_v4i32tov4i8_fake_update:
+;CHECK: ldr.w r9, [sp]
+;CHECK: vmov {{d[0-9]+}}, r3, r9
+;CHECK: vmov {{d[0-9]+}}, r1, r2
+;CHECK: movs [[IMM16:r[0-9]+]], #16
+;CHECK: vmovn.i32 [[VECLO:d[0-9]+]], {{q[0-9]+}}
+;CHECK: vuzp.8 [[VECLO]], {{d[0-9]+}}
+;CHECK: ldr r[[PTRREG:[0-9]+]], [r0]
+;CHECK: vst1.32 {[[VECLO]][0]}, [r[[PTRREG]]:32], [[IMM16]]
+;CHECK: str r[[PTRREG]], [r0]
+ %A = load <4 x i8>** %ptr
+ %trunc = trunc <4 x i32> %val to <4 x i8>
+ store <4 x i8> %trunc, <4 x i8>* %A, align 4
+ %inc = getelementptr <4 x i8>* %A, i38 4
+ store <4 x i8>* %inc, <4 x i8>** %ptr
+ ret void
+}
diff --git a/llvm/test/Transforms/LoopStrengthReduce/ARM/ivchain-ARM.ll b/llvm/test/Transforms/LoopStrengthReduce/ARM/ivchain-ARM.ll
index f4edf092641..26b294042d4 100644
--- a/llvm/test/Transforms/LoopStrengthReduce/ARM/ivchain-ARM.ll
+++ b/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}}
OpenPOWER on IntegriCloud