Index: lib/Target/ARM/ARMTargetTransformInfo.cpp
===================================================================
--- lib/Target/ARM/ARMTargetTransformInfo.cpp
+++ lib/Target/ARM/ARMTargetTransformInfo.cpp
@@ -394,6 +394,28 @@
     TTI::OperandValueProperties Opd2PropInfo) {
 
   int ISDOpcode = TLI->InstructionOpcodeToISD(Opcode);
+  assert(ISDOpcode && "Invalid opcode");
+
+  if (ISDOpcode == ISD::SDIV &&
+      Op2Info == TargetTransformInfo::OK_UniformConstantValue &&
+      Opd2PropInfo == TargetTransformInfo::OP_PowerOf2) {
+    // On ARM, scalar signed division by constants power-of-two are
+    // normally expanded to the sequence SRA + SRL + ADD + SRA.
+    // The OperandValue properties many not be same as that of previous
+    // operation;conservatively assume OP_None.
+    int Cost = 2 * getArithmeticInstrCost(Instruction::AShr, Ty, Op1Info,
+                                          Op2Info, TargetTransformInfo::OP_None,
+                                          TargetTransformInfo::OP_None);
+    Cost += getArithmeticInstrCost(Instruction::LShr, Ty, Op1Info, Op2Info,
+                                   TargetTransformInfo::OP_None,
+                                   TargetTransformInfo::OP_None);
+    Cost += getArithmeticInstrCost(Instruction::Add, Ty, Op1Info, Op2Info,
+                                   TargetTransformInfo::OP_None,
+                                   TargetTransformInfo::OP_None);
+
+    return Cost;
+  }
+
   std::pair<int, MVT> LT = TLI->getTypeLegalizationCost(DL, Ty);
 
   const unsigned FunctionCallDivCost = 20;
Index: test/Transforms/LoopVectorize/ARM/powof2sdiv.ll
===================================================================
--- /dev/null
+++ test/Transforms/LoopVectorize/ARM/powof2sdiv.ll
@@ -0,0 +1,29 @@
+; RUN: opt < %s  -loop-vectorize -mtriple=thumbv7-unknown-linux-gnu -S | FileCheck %s
+
+%struct.anon = type { [100 x i32], i32, [100 x i32] }
+
+@Foo = common global %struct.anon zeroinitializer, align 4
+
+; CHECK-LABEL: @foo(
+; CHECK: load <4 x i32>, <4 x i32>*
+; CHECK: sdiv <4 x i32>
+; CHECK: store <4 x i32>
+
+define void @foo(){
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds %struct.anon, %struct.anon* @Foo, i64 0, i32 2, i64 %indvars.iv
+  %0 = load i32, i32* %arrayidx, align 4
+  %div = sdiv i32 %0, 2
+  %arrayidx2 = getelementptr inbounds %struct.anon, %struct.anon* @Foo, i64 0, i32 0, i64 %indvars.iv
+  store i32 %div, i32* %arrayidx2, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 100
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
Index: test/Transforms/SLPVectorizer/ARM/sdiv-pow2.ll
===================================================================
--- /dev/null
+++ test/Transforms/SLPVectorizer/ARM/sdiv-pow2.ll
@@ -0,0 +1,40 @@
+; RUN: opt < %s -basicaa -slp-vectorizer -S -mtriple=thumbv7-unknown-linux-gnu | FileCheck %s
+
+; CHECK-LABEL: @test1
+; CHECK: load <4 x i32>
+; CHECK: add nsw <4 x i32>
+; CHECK: sdiv <4 x i32>
+
+define void @test1(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32* noalias nocapture readonly %c) {
+entry:
+  %0 = load i32, i32* %b, align 4
+  %1 = load i32, i32* %c, align 4
+  %add = add nsw i32 %1, %0
+  %div = sdiv i32 %add, 2
+  store i32 %div, i32* %a, align 4
+  %arrayidx3 = getelementptr inbounds i32, i32* %b, i64 1
+  %2 = load i32, i32* %arrayidx3, align 4
+  %arrayidx4 = getelementptr inbounds i32, i32* %c, i64 1
+  %3 = load i32, i32* %arrayidx4, align 4
+  %add5 = add nsw i32 %3, %2
+  %div6 = sdiv i32 %add5, 2
+  %arrayidx7 = getelementptr inbounds i32, i32* %a, i64 1
+  store i32 %div6, i32* %arrayidx7, align 4
+  %arrayidx8 = getelementptr inbounds i32, i32* %b, i64 2
+  %4 = load i32, i32* %arrayidx8, align 4
+  %arrayidx9 = getelementptr inbounds i32, i32* %c, i64 2
+  %5 = load i32, i32* %arrayidx9, align 4
+  %add10 = add nsw i32 %5, %4
+  %div11 = sdiv i32 %add10, 2
+  %arrayidx12 = getelementptr inbounds i32, i32* %a, i64 2
+  store i32 %div11, i32* %arrayidx12, align 4
+  %arrayidx13 = getelementptr inbounds i32, i32* %b, i64 3
+  %6 = load i32, i32* %arrayidx13, align 4
+  %arrayidx14 = getelementptr inbounds i32, i32* %c, i64 3
+  %7 = load i32, i32* %arrayidx14, align 4
+  %add15 = add nsw i32 %7, %6
+  %div16 = sdiv i32 %add15, 2
+  %arrayidx17 = getelementptr inbounds i32, i32* %a, i64 3
+  store i32 %div16, i32* %arrayidx17, align 4
+  ret void
+}