Index: lib/CodeGen/SelectionDAG/DAGCombiner.cpp
===================================================================
--- lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -1734,7 +1734,7 @@
     return SDValue(N, 0);
 
   // fold (a+b) -> (a|b) iff a and b share no bits.
-  if ((!LegalOperations || TLI.isOperationLegal(ISD::OR, VT)) &&
+  if ((!LegalOperations || TLI.isOperationLegalOrCustom(ISD::OR, VT)) &&
       VT.isInteger() && !VT.isVector() && DAG.haveNoCommonBitsSet(N0, N1))
     return DAG.getNode(ISD::OR, SDLoc(N), VT, N0, N1);
 
@@ -6373,7 +6373,7 @@
       isa<LoadSDNode>(N0.getOperand(0)) &&
       N0.getOperand(1).getOpcode() == ISD::Constant &&
       TLI.isLoadExtLegal(ISD::ZEXTLOAD, VT, N0.getValueType()) &&
-      (!LegalOperations && TLI.isOperationLegal(N0.getOpcode(), VT))) {
+      (!LegalOperations && TLI.isOperationLegalOrCustom(N0.getOpcode(), VT))) {
     LoadSDNode *LN0 = cast<LoadSDNode>(N0.getOperand(0));
     if (LN0->getExtensionType() != ISD::SEXTLOAD && LN0->isUnindexed()) {
       bool DoXform = true;
Index: lib/Target/AArch64/AArch64ISelLowering.h
===================================================================
--- lib/Target/AArch64/AArch64ISelLowering.h
+++ lib/Target/AArch64/AArch64ISelLowering.h
@@ -488,6 +488,8 @@
   SDValue LowerCTPOP(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerF128Call(SDValue Op, SelectionDAG &DAG,
                         RTLIB::Libcall Call) const;
+  SDValue LowerAND(SDValue Op, SelectionDAG &DAG) const;
+  SDValue LowerOR(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerFCOPYSIGN(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerFP_EXTEND(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerFP_ROUND(SDValue Op, SelectionDAG &DAG) const;
Index: lib/Target/AArch64/AArch64ISelLowering.cpp
===================================================================
--- lib/Target/AArch64/AArch64ISelLowering.cpp
+++ lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -144,6 +144,16 @@
   setOperationAction(ISD::XOR, MVT::i32, Custom);
   setOperationAction(ISD::XOR, MVT::i64, Custom);
 
+  // Custom lowering hooks are needed for OR
+  // to fold it into CCMP.
+  setOperationAction(ISD::OR, MVT::i32, Custom);
+  setOperationAction(ISD::OR, MVT::i64, Custom);
+
+  // Custom lowering hooks are needed for AND
+  // to fold it into CCMP.
+  setOperationAction(ISD::AND, MVT::i32, Custom);
+  setOperationAction(ISD::AND, MVT::i64, Custom);
+
   // Virtually no operation on f128 is legal, but LLVM can't expand them when
   // there's a valid register class, so we need custom operations in most cases.
   setOperationAction(ISD::FABS, MVT::f128, Expand);
@@ -1662,6 +1672,60 @@
   return makeLibCall(DAG, Call, MVT::f128, Ops, false, SDLoc(Op)).first;
 }
 
+SDValue AArch64TargetLowering::LowerAND(SDValue Op, SelectionDAG &DAG) const {
+
+  EVT VT = Op.getValueType();
+  if (VT.isVector())
+    return LowerVectorAND(Op, DAG);
+
+  if (!Op->hasOneUse())
+    return Op;
+
+  SDNode *N = cast<SDNode>(Op.getNode());
+  SDValue Chain;
+  if (!(isUsedByReturnOnly(N, Chain)))
+    return Op;
+
+  SDLoc DL(Op);
+  SDValue LHS = Op.getOperand(0);
+  SDValue RHS = Op.getOperand(1);
+  if ((LHS.getOpcode() != ISD::SETCC) || (RHS.getOpcode() != ISD::SETCC))
+    return Op;
+
+  SDValue TVal = DAG.getConstant(1, DL, VT);
+  SDValue FVal = DAG.getConstant(0, DL, VT);
+  SDValue CCVal;
+  SDValue Cmp = getAArch64Cmp(Op, FVal, ISD::SETEQ, CCVal, DAG, DL);
+  return DAG.getNode(AArch64ISD::CSEL, DL, VT, FVal, TVal, CCVal, Cmp);
+}
+
+SDValue AArch64TargetLowering::LowerOR(SDValue Op, SelectionDAG &DAG) const {
+
+  EVT VT = Op.getValueType();
+  if (VT.isVector())
+      return LowerVectorOR(Op, DAG);
+
+  if (!Op->hasOneUse())
+    return Op;
+
+  SDNode *N = cast<SDNode>(Op.getNode());
+  SDValue Chain;
+  if (!(isUsedByReturnOnly(N, Chain)))
+    return Op;
+
+  SDLoc DL(Op);
+  SDValue LHS = Op.getOperand(0);
+  SDValue RHS = Op.getOperand(1);
+  if ((LHS.getOpcode() != ISD::SETCC) || (RHS.getOpcode() != ISD::SETCC))
+    return Op;
+
+  SDValue TVal = DAG.getConstant(1, DL, VT);
+  SDValue FVal = DAG.getConstant(0, DL, VT);
+  SDValue CCVal;
+  SDValue Cmp = getAArch64Cmp(Op, FVal, ISD::SETEQ, CCVal, DAG, DL);
+  return DAG.getNode(AArch64ISD::CSEL, DL, VT, FVal, TVal, CCVal, Cmp);
+}
+
 static SDValue LowerXOR(SDValue Op, SelectionDAG &DAG) {
   SDValue Sel = Op.getOperand(0);
   SDValue Other = Op.getOperand(1);
@@ -2316,9 +2380,9 @@
   case ISD::FCOPYSIGN:
     return LowerFCOPYSIGN(Op, DAG);
   case ISD::AND:
-    return LowerVectorAND(Op, DAG);
+    return LowerAND(Op, DAG);
   case ISD::OR:
-    return LowerVectorOR(Op, DAG);
+    return LowerOR(Op, DAG);
   case ISD::XOR:
     return LowerXOR(Op, DAG);
   case ISD::PREFETCH:
Index: test/CodeGen/AArch64/arm64-ccmp.ll
===================================================================
--- test/CodeGen/AArch64/arm64-ccmp.ll
+++ test/CodeGen/AArch64/arm64-ccmp.ll
@@ -389,6 +389,19 @@
   ret i32 %sel
 }
 
+; CHECK-LABEL: single_noselect
+define i32 @single_noselect(i32 %A, i32 %B) #0 {
+; CHECK: cmp w1, #1
+; CHECK-NEXT: ccmp w0, #1, #8, ge
+; CHECK-NEXT: cset w0, lt
+; CHECK-NEXT: ret
+  %notlhs = icmp slt i32 %A, 1
+  %notrhs = icmp slt i32 %B, 1
+  %lnot = or i1 %notlhs, %notrhs
+  %conv = zext i1 %lnot to i32
+  ret i32 %conv
+}
+
 ; CHECK-LABEL: select_noccmp1
 define i64 @select_noccmp1(i64 %v1, i64 %v2, i64 %v3, i64 %r) {
 ; CHECK: cmp x0, #0