Index: lib/CodeGen/SelectionDAG/DAGCombiner.cpp
===================================================================
--- lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -414,6 +414,7 @@
                                    SDValue N2, SDValue N3, ISD::CondCode CC);
     SDValue foldLogicOfSetCCs(bool IsAnd, SDValue N0, SDValue N1,
                               const SDLoc &DL);
+    SDValue unfoldMaskedMerge(SDNode *N);
     SDValue SimplifySetCC(EVT VT, SDValue N0, SDValue N1, ISD::CondCode Cond,
                           const SDLoc &DL, bool foldBooleans);
     SDValue rebuildSetCC(SDValue N);
@@ -5361,6 +5362,91 @@
   return NeedsBswap ? DAG.getNode(ISD::BSWAP, SDLoc(N), VT, NewLoad) : NewLoad;
 }
 
+// If the target has andn, bsl, or a similar bit-select instruction,
+// we want to unfold masked merge, with canonical pattern of:
+//   |        A  |  |B|
+//   ((x ^ y) & m) ^ y
+//    |  D  |
+// Into:
+//   (x & m) | (y & ~m)
+SDValue DAGCombiner::unfoldMaskedMerge(SDNode *N) {
+  assert(N->getOpcode() == ISD::XOR);
+
+  EVT VT = N->getValueType(0);
+
+  // FIXME
+  if (VT.isVector())
+    return SDValue();
+
+  auto matchD = [](SDValue D, SDValue Y) -> llvm::Optional<SDValue> /*X*/ {
+    if (D.getOpcode() != ISD::XOR)
+      return llvm::None;
+    SDValue D0 = D->getOperand(0);
+    SDValue D1 = D->getOperand(1);
+    if (D1 == Y)
+      return D0;
+    else if (D0 == Y)
+      return D1;
+    return llvm::None;
+  };
+
+  SDValue A, D, X, Y, M;
+
+  auto matchA = [matchD, &D, &X, &Y, &M](SDValue A, SDValue B) -> bool {
+    if (A.getOpcode() != ISD::AND)
+      return false;
+    SDValue A0 = A.getOperand(0);
+    SDValue A1 = A.getOperand(1);
+    if (auto X_ = matchD(A0, B)) {
+      X = *X_;
+      D = A0;
+      M = A1;
+      Y = B;
+      return true;
+    } else if (auto X_ = matchD(A1, B)) {
+      X = *X_;
+      D = A1;
+      M = A0;
+      Y = B;
+      return true;
+    }
+    return false;
+  };
+
+  if (matchA(N->getOperand(0), N->getOperand(1)))
+    A = N->getOperand(0);
+  else if (matchA(N->getOperand(1), N->getOperand(0)))
+    A = N->getOperand(1);
+  else
+    return SDValue();
+
+  assert(A.getOpcode() == ISD::AND);
+  assert(D.getOpcode() == ISD::XOR);
+
+  // 'A' and 'D' part will be replaced completely.
+  // Don't proceed they can't be dropped.
+  if (!(A.hasOneUse() && D.hasOneUse()))
+    return SDValue();
+
+  // Don't do anything if the mask is constant. This should not be reachable.
+  // InstCombine should have already unfolded this pattern, and DAGCombiner
+  // probably shouldn't produce it, too.
+  if (isa<ConstantSDNode>(M.getNode()))
+    return SDValue();
+
+  // We can transform if the target has AndNot
+  if (!TLI.hasAndNot(M))
+    return SDValue();
+
+  SDLoc DL(N);
+
+  SDValue LHS = DAG.getNode(ISD::AND, DL, VT, X, M);
+  SDValue NotM = DAG.getNOT(DL, M, VT);
+  SDValue RHS = DAG.getNode(ISD::AND, DL, VT, Y, NotM);
+
+  return DAG.getNode(ISD::OR, DL, VT, LHS, RHS);
+}
+
 SDValue DAGCombiner::visitXOR(SDNode *N) {
   SDValue N0 = N->getOperand(0);
   SDValue N1 = N->getOperand(1);
@@ -5516,6 +5602,10 @@
     if (SDValue Tmp = SimplifyBinOpWithSameOpcodeHands(N))
       return Tmp;
 
+  // Unfold  ((x ^ y) & m) ^ y  into  (x & m) | (y & ~m)  if profitable
+  if (SDValue MM = unfoldMaskedMerge(N))
+    return MM;
+
   // Simplify the expression using non-local knowledge.
   if (SimplifyDemandedBits(SDValue(N, 0)))
     return SDValue(N, 0);
Index: test/CodeGen/AArch64/unfold-masked-merge-scalar.ll
===================================================================
--- test/CodeGen/AArch64/unfold-masked-merge-scalar.ll
+++ test/CodeGen/AArch64/unfold-masked-merge-scalar.ll
@@ -128,9 +128,9 @@
 define i8 @in8(i8 %x, i8 %y, i8 %mask) {
 ; CHECK-LABEL: in8:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    eor w8, w0, w1
-; CHECK-NEXT:    and w8, w8, w2
-; CHECK-NEXT:    eor w0, w8, w1
+; CHECK-NEXT:    and w8, w0, w2
+; CHECK-NEXT:    bic w9, w1, w2
+; CHECK-NEXT:    orr w0, w8, w9
 ; CHECK-NEXT:    ret
   %n0 = xor i8 %x, %y
   %n1 = and i8 %n0, %mask
@@ -156,9 +156,9 @@
 define i16 @in16(i16 %x, i16 %y, i16 %mask) {
 ; CHECK-LABEL: in16:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    eor w8, w0, w1
-; CHECK-NEXT:    and w8, w8, w2
-; CHECK-NEXT:    eor w0, w8, w1
+; CHECK-NEXT:    and w8, w0, w2
+; CHECK-NEXT:    bic w9, w1, w2
+; CHECK-NEXT:    orr w0, w8, w9
 ; CHECK-NEXT:    ret
   %n0 = xor i16 %x, %y
   %n1 = and i16 %n0, %mask
@@ -184,9 +184,9 @@
 define i32 @in32(i32 %x, i32 %y, i32 %mask) {
 ; CHECK-LABEL: in32:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    eor w8, w0, w1
-; CHECK-NEXT:    and w8, w8, w2
-; CHECK-NEXT:    eor w0, w8, w1
+; CHECK-NEXT:    bic w8, w1, w2
+; CHECK-NEXT:    and w9, w0, w2
+; CHECK-NEXT:    orr w0, w9, w8
 ; CHECK-NEXT:    ret
   %n0 = xor i32 %x, %y
   %n1 = and i32 %n0, %mask
@@ -212,9 +212,9 @@
 define i64 @in64(i64 %x, i64 %y, i64 %mask) {
 ; CHECK-LABEL: in64:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    eor x8, x0, x1
-; CHECK-NEXT:    and x8, x8, x2
-; CHECK-NEXT:    eor x0, x8, x1
+; CHECK-NEXT:    bic x8, x1, x2
+; CHECK-NEXT:    and x9, x0, x2
+; CHECK-NEXT:    orr x0, x9, x8
 ; CHECK-NEXT:    ret
   %n0 = xor i64 %x, %y
   %n1 = and i64 %n0, %mask
@@ -242,9 +242,9 @@
 define i32 @in_commutativity_0_0_1(i32 %x, i32 %y, i32 %mask) {
 ; CHECK-LABEL: in_commutativity_0_0_1:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    eor w8, w0, w1
-; CHECK-NEXT:    and w8, w2, w8
-; CHECK-NEXT:    eor w0, w8, w1
+; CHECK-NEXT:    bic w8, w1, w2
+; CHECK-NEXT:    and w9, w0, w2
+; CHECK-NEXT:    orr w0, w9, w8
 ; CHECK-NEXT:    ret
   %n0 = xor i32 %x, %y
   %n1 = and i32 %mask, %n0 ; swapped
@@ -255,9 +255,9 @@
 define i32 @in_commutativity_0_1_0(i32 %x, i32 %y, i32 %mask) {
 ; CHECK-LABEL: in_commutativity_0_1_0:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    eor w8, w0, w1
-; CHECK-NEXT:    and w8, w8, w2
-; CHECK-NEXT:    eor w0, w1, w8
+; CHECK-NEXT:    bic w8, w1, w2
+; CHECK-NEXT:    and w9, w0, w2
+; CHECK-NEXT:    orr w0, w9, w8
 ; CHECK-NEXT:    ret
   %n0 = xor i32 %x, %y
   %n1 = and i32 %n0, %mask
@@ -268,9 +268,9 @@
 define i32 @in_commutativity_0_1_1(i32 %x, i32 %y, i32 %mask) {
 ; CHECK-LABEL: in_commutativity_0_1_1:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    eor w8, w0, w1
-; CHECK-NEXT:    and w8, w2, w8
-; CHECK-NEXT:    eor w0, w1, w8
+; CHECK-NEXT:    bic w8, w1, w2
+; CHECK-NEXT:    and w9, w0, w2
+; CHECK-NEXT:    orr w0, w9, w8
 ; CHECK-NEXT:    ret
   %n0 = xor i32 %x, %y
   %n1 = and i32 %mask, %n0 ; swapped
@@ -281,9 +281,9 @@
 define i32 @in_commutativity_1_0_0(i32 %x, i32 %y, i32 %mask) {
 ; CHECK-LABEL: in_commutativity_1_0_0:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    eor w8, w0, w1
-; CHECK-NEXT:    and w8, w8, w2
-; CHECK-NEXT:    eor w0, w8, w0
+; CHECK-NEXT:    bic w8, w0, w2
+; CHECK-NEXT:    and w9, w1, w2
+; CHECK-NEXT:    orr w0, w9, w8
 ; CHECK-NEXT:    ret
   %n0 = xor i32 %x, %y
   %n1 = and i32 %n0, %mask
@@ -294,9 +294,9 @@
 define i32 @in_commutativity_1_0_1(i32 %x, i32 %y, i32 %mask) {
 ; CHECK-LABEL: in_commutativity_1_0_1:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    eor w8, w0, w1
-; CHECK-NEXT:    and w8, w2, w8
-; CHECK-NEXT:    eor w0, w8, w0
+; CHECK-NEXT:    bic w8, w0, w2
+; CHECK-NEXT:    and w9, w1, w2
+; CHECK-NEXT:    orr w0, w9, w8
 ; CHECK-NEXT:    ret
   %n0 = xor i32 %x, %y
   %n1 = and i32 %mask, %n0 ; swapped
@@ -307,9 +307,9 @@
 define i32 @in_commutativity_1_1_0(i32 %x, i32 %y, i32 %mask) {
 ; CHECK-LABEL: in_commutativity_1_1_0:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    eor w8, w0, w1
-; CHECK-NEXT:    and w8, w8, w2
-; CHECK-NEXT:    eor w0, w0, w8
+; CHECK-NEXT:    bic w8, w0, w2
+; CHECK-NEXT:    and w9, w1, w2
+; CHECK-NEXT:    orr w0, w9, w8
 ; CHECK-NEXT:    ret
   %n0 = xor i32 %x, %y
   %n1 = and i32 %n0, %mask
@@ -320,9 +320,9 @@
 define i32 @in_commutativity_1_1_1(i32 %x, i32 %y, i32 %mask) {
 ; CHECK-LABEL: in_commutativity_1_1_1:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    eor w8, w0, w1
-; CHECK-NEXT:    and w8, w2, w8
-; CHECK-NEXT:    eor w0, w0, w8
+; CHECK-NEXT:    bic w8, w0, w2
+; CHECK-NEXT:    and w9, w1, w2
+; CHECK-NEXT:    orr w0, w9, w8
 ; CHECK-NEXT:    ret
   %n0 = xor i32 %x, %y
   %n1 = and i32 %mask, %n0 ; swapped
@@ -381,9 +381,9 @@
 ; CHECK-LABEL: in_complex_y0:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    and w8, w1, w2
-; CHECK-NEXT:    eor w9, w0, w8
-; CHECK-NEXT:    and w9, w9, w3
-; CHECK-NEXT:    eor w0, w9, w8
+; CHECK-NEXT:    and w9, w0, w3
+; CHECK-NEXT:    bic w8, w8, w3
+; CHECK-NEXT:    orr w0, w9, w8
 ; CHECK-NEXT:    ret
   %y = and i32 %y_hi, %y_low
   %n0 = xor i32 %x, %y
@@ -396,9 +396,9 @@
 ; CHECK-LABEL: in_complex_y1:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    and w8, w1, w2
-; CHECK-NEXT:    eor w9, w0, w8
-; CHECK-NEXT:    and w9, w9, w3
-; CHECK-NEXT:    eor w0, w8, w9
+; CHECK-NEXT:    and w9, w0, w3
+; CHECK-NEXT:    bic w8, w8, w3
+; CHECK-NEXT:    orr w0, w9, w8
 ; CHECK-NEXT:    ret
   %y = and i32 %y_hi, %y_low
   %n0 = xor i32 %x, %y
@@ -445,9 +445,9 @@
 ; CHECK-LABEL: in_complex_m0:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    eor w8, w2, w3
-; CHECK-NEXT:    eor w9, w0, w1
-; CHECK-NEXT:    and w8, w9, w8
-; CHECK-NEXT:    eor w0, w8, w1
+; CHECK-NEXT:    bic w9, w1, w8
+; CHECK-NEXT:    and w8, w0, w8
+; CHECK-NEXT:    orr w0, w8, w9
 ; CHECK-NEXT:    ret
   %mask = xor i32 %m_a, %m_b
   %n0 = xor i32 %x, %y
@@ -460,9 +460,9 @@
 ; CHECK-LABEL: in_complex_m1:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    eor w8, w2, w3
-; CHECK-NEXT:    eor w9, w0, w1
-; CHECK-NEXT:    and w8, w8, w9
-; CHECK-NEXT:    eor w0, w8, w1
+; CHECK-NEXT:    bic w9, w1, w8
+; CHECK-NEXT:    and w8, w0, w8
+; CHECK-NEXT:    orr w0, w8, w9
 ; CHECK-NEXT:    ret
   %mask = xor i32 %m_a, %m_b
   %n0 = xor i32 %x, %y
@@ -480,9 +480,9 @@
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    and w8, w1, w2
 ; CHECK-NEXT:    eor w9, w3, w4
-; CHECK-NEXT:    eor w10, w0, w8
-; CHECK-NEXT:    and w9, w10, w9
-; CHECK-NEXT:    eor w0, w9, w8
+; CHECK-NEXT:    bic w8, w8, w9
+; CHECK-NEXT:    and w9, w0, w9
+; CHECK-NEXT:    orr w0, w9, w8
 ; CHECK-NEXT:    ret
   %y = and i32 %y_hi, %y_low
   %mask = xor i32 %m_a, %m_b
@@ -497,9 +497,9 @@
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    and w8, w1, w2
 ; CHECK-NEXT:    eor w9, w3, w4
-; CHECK-NEXT:    eor w10, w0, w8
-; CHECK-NEXT:    and w9, w10, w9
-; CHECK-NEXT:    eor w0, w8, w9
+; CHECK-NEXT:    bic w8, w8, w9
+; CHECK-NEXT:    and w9, w0, w9
+; CHECK-NEXT:    orr w0, w9, w8
 ; CHECK-NEXT:    ret
   %y = and i32 %y_hi, %y_low
   %mask = xor i32 %m_a, %m_b
@@ -514,9 +514,9 @@
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    and w8, w1, w2
 ; CHECK-NEXT:    eor w9, w3, w4
-; CHECK-NEXT:    eor w10, w0, w8
-; CHECK-NEXT:    and w9, w9, w10
-; CHECK-NEXT:    eor w0, w9, w8
+; CHECK-NEXT:    bic w8, w8, w9
+; CHECK-NEXT:    and w9, w0, w9
+; CHECK-NEXT:    orr w0, w9, w8
 ; CHECK-NEXT:    ret
   %y = and i32 %y_hi, %y_low
   %mask = xor i32 %m_a, %m_b
@@ -531,9 +531,9 @@
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    and w8, w1, w2
 ; CHECK-NEXT:    eor w9, w3, w4
-; CHECK-NEXT:    eor w10, w0, w8
-; CHECK-NEXT:    and w9, w9, w10
-; CHECK-NEXT:    eor w0, w8, w9
+; CHECK-NEXT:    bic w8, w8, w9
+; CHECK-NEXT:    and w9, w0, w9
+; CHECK-NEXT:    orr w0, w9, w8
 ; CHECK-NEXT:    ret
   %y = and i32 %y_hi, %y_low
   %mask = xor i32 %m_a, %m_b
Index: test/CodeGen/X86/unfold-masked-merge-scalar.ll
===================================================================
--- test/CodeGen/X86/unfold-masked-merge-scalar.ll
+++ test/CodeGen/X86/unfold-masked-merge-scalar.ll
@@ -220,10 +220,10 @@
 ;
 ; CHECK-BMI-LABEL: in8:
 ; CHECK-BMI:       # %bb.0:
-; CHECK-BMI-NEXT:    xorl %esi, %edi
+; CHECK-BMI-NEXT:    andnl %esi, %edx, %eax
 ; CHECK-BMI-NEXT:    andl %edx, %edi
-; CHECK-BMI-NEXT:    xorl %esi, %edi
-; CHECK-BMI-NEXT:    movl %edi, %eax
+; CHECK-BMI-NEXT:    orl %edi, %eax
+; CHECK-BMI-NEXT:    # kill: def $al killed $al killed $eax
 ; CHECK-BMI-NEXT:    retq
   %n0 = xor i8 %x, %y
   %n1 = and i8 %n0, %mask
@@ -266,10 +266,10 @@
 ;
 ; CHECK-BMI-LABEL: in16:
 ; CHECK-BMI:       # %bb.0:
-; CHECK-BMI-NEXT:    xorl %esi, %edi
+; CHECK-BMI-NEXT:    andnl %esi, %edx, %eax
 ; CHECK-BMI-NEXT:    andl %edx, %edi
-; CHECK-BMI-NEXT:    xorl %esi, %edi
-; CHECK-BMI-NEXT:    movl %edi, %eax
+; CHECK-BMI-NEXT:    orl %edi, %eax
+; CHECK-BMI-NEXT:    # kill: def $ax killed $ax killed $eax
 ; CHECK-BMI-NEXT:    retq
   %n0 = xor i16 %x, %y
   %n1 = and i16 %n0, %mask
@@ -312,10 +312,9 @@
 ;
 ; CHECK-BMI-LABEL: in32:
 ; CHECK-BMI:       # %bb.0:
-; CHECK-BMI-NEXT:    xorl %esi, %edi
+; CHECK-BMI-NEXT:    andnl %esi, %edx, %eax
 ; CHECK-BMI-NEXT:    andl %edx, %edi
-; CHECK-BMI-NEXT:    xorl %esi, %edi
-; CHECK-BMI-NEXT:    movl %edi, %eax
+; CHECK-BMI-NEXT:    orl %edi, %eax
 ; CHECK-BMI-NEXT:    retq
   %n0 = xor i32 %x, %y
   %n1 = and i32 %n0, %mask
@@ -358,10 +357,9 @@
 ;
 ; CHECK-BMI-LABEL: in64:
 ; CHECK-BMI:       # %bb.0:
-; CHECK-BMI-NEXT:    xorq %rsi, %rdi
+; CHECK-BMI-NEXT:    andnq %rsi, %rdx, %rax
 ; CHECK-BMI-NEXT:    andq %rdx, %rdi
-; CHECK-BMI-NEXT:    xorq %rsi, %rdi
-; CHECK-BMI-NEXT:    movq %rdi, %rax
+; CHECK-BMI-NEXT:    orq %rdi, %rax
 ; CHECK-BMI-NEXT:    retq
   %n0 = xor i64 %x, %y
   %n1 = and i64 %n0, %mask
@@ -406,10 +404,9 @@
 ;
 ; CHECK-BMI-LABEL: in_commutativity_0_0_1:
 ; CHECK-BMI:       # %bb.0:
-; CHECK-BMI-NEXT:    xorl %esi, %edi
+; CHECK-BMI-NEXT:    andnl %esi, %edx, %eax
 ; CHECK-BMI-NEXT:    andl %edx, %edi
-; CHECK-BMI-NEXT:    xorl %esi, %edi
-; CHECK-BMI-NEXT:    movl %edi, %eax
+; CHECK-BMI-NEXT:    orl %edi, %eax
 ; CHECK-BMI-NEXT:    retq
   %n0 = xor i32 %x, %y
   %n1 = and i32 %mask, %n0 ; swapped
@@ -428,10 +425,9 @@
 ;
 ; CHECK-BMI-LABEL: in_commutativity_0_1_0:
 ; CHECK-BMI:       # %bb.0:
-; CHECK-BMI-NEXT:    xorl %esi, %edi
+; CHECK-BMI-NEXT:    andnl %esi, %edx, %eax
 ; CHECK-BMI-NEXT:    andl %edx, %edi
-; CHECK-BMI-NEXT:    xorl %esi, %edi
-; CHECK-BMI-NEXT:    movl %edi, %eax
+; CHECK-BMI-NEXT:    orl %edi, %eax
 ; CHECK-BMI-NEXT:    retq
   %n0 = xor i32 %x, %y
   %n1 = and i32 %n0, %mask
@@ -450,10 +446,9 @@
 ;
 ; CHECK-BMI-LABEL: in_commutativity_0_1_1:
 ; CHECK-BMI:       # %bb.0:
-; CHECK-BMI-NEXT:    xorl %esi, %edi
+; CHECK-BMI-NEXT:    andnl %esi, %edx, %eax
 ; CHECK-BMI-NEXT:    andl %edx, %edi
-; CHECK-BMI-NEXT:    xorl %esi, %edi
-; CHECK-BMI-NEXT:    movl %edi, %eax
+; CHECK-BMI-NEXT:    orl %edi, %eax
 ; CHECK-BMI-NEXT:    retq
   %n0 = xor i32 %x, %y
   %n1 = and i32 %mask, %n0 ; swapped
@@ -472,10 +467,9 @@
 ;
 ; CHECK-BMI-LABEL: in_commutativity_1_0_0:
 ; CHECK-BMI:       # %bb.0:
-; CHECK-BMI-NEXT:    xorl %edi, %esi
+; CHECK-BMI-NEXT:    andnl %edi, %edx, %eax
 ; CHECK-BMI-NEXT:    andl %edx, %esi
-; CHECK-BMI-NEXT:    xorl %edi, %esi
-; CHECK-BMI-NEXT:    movl %esi, %eax
+; CHECK-BMI-NEXT:    orl %esi, %eax
 ; CHECK-BMI-NEXT:    retq
   %n0 = xor i32 %x, %y
   %n1 = and i32 %n0, %mask
@@ -494,10 +488,9 @@
 ;
 ; CHECK-BMI-LABEL: in_commutativity_1_0_1:
 ; CHECK-BMI:       # %bb.0:
-; CHECK-BMI-NEXT:    xorl %edi, %esi
+; CHECK-BMI-NEXT:    andnl %edi, %edx, %eax
 ; CHECK-BMI-NEXT:    andl %edx, %esi
-; CHECK-BMI-NEXT:    xorl %edi, %esi
-; CHECK-BMI-NEXT:    movl %esi, %eax
+; CHECK-BMI-NEXT:    orl %esi, %eax
 ; CHECK-BMI-NEXT:    retq
   %n0 = xor i32 %x, %y
   %n1 = and i32 %mask, %n0 ; swapped
@@ -516,10 +509,9 @@
 ;
 ; CHECK-BMI-LABEL: in_commutativity_1_1_0:
 ; CHECK-BMI:       # %bb.0:
-; CHECK-BMI-NEXT:    xorl %edi, %esi
+; CHECK-BMI-NEXT:    andnl %edi, %edx, %eax
 ; CHECK-BMI-NEXT:    andl %edx, %esi
-; CHECK-BMI-NEXT:    xorl %edi, %esi
-; CHECK-BMI-NEXT:    movl %esi, %eax
+; CHECK-BMI-NEXT:    orl %esi, %eax
 ; CHECK-BMI-NEXT:    retq
   %n0 = xor i32 %x, %y
   %n1 = and i32 %n0, %mask
@@ -538,10 +530,9 @@
 ;
 ; CHECK-BMI-LABEL: in_commutativity_1_1_1:
 ; CHECK-BMI:       # %bb.0:
-; CHECK-BMI-NEXT:    xorl %edi, %esi
+; CHECK-BMI-NEXT:    andnl %edi, %edx, %eax
 ; CHECK-BMI-NEXT:    andl %edx, %esi
-; CHECK-BMI-NEXT:    xorl %edi, %esi
-; CHECK-BMI-NEXT:    movl %esi, %eax
+; CHECK-BMI-NEXT:    orl %esi, %eax
 ; CHECK-BMI-NEXT:    retq
   %n0 = xor i32 %x, %y
   %n1 = and i32 %mask, %n0 ; swapped
@@ -636,10 +627,9 @@
 ; CHECK-BMI-LABEL: in_complex_y0:
 ; CHECK-BMI:       # %bb.0:
 ; CHECK-BMI-NEXT:    andl %edx, %esi
-; CHECK-BMI-NEXT:    xorl %esi, %edi
 ; CHECK-BMI-NEXT:    andl %ecx, %edi
-; CHECK-BMI-NEXT:    xorl %esi, %edi
-; CHECK-BMI-NEXT:    movl %edi, %eax
+; CHECK-BMI-NEXT:    andnl %esi, %ecx, %eax
+; CHECK-BMI-NEXT:    orl %edi, %eax
 ; CHECK-BMI-NEXT:    retq
   %y = and i32 %y_hi, %y_low
   %n0 = xor i32 %x, %y
@@ -661,10 +651,9 @@
 ; CHECK-BMI-LABEL: in_complex_y1:
 ; CHECK-BMI:       # %bb.0:
 ; CHECK-BMI-NEXT:    andl %edx, %esi
-; CHECK-BMI-NEXT:    xorl %esi, %edi
 ; CHECK-BMI-NEXT:    andl %ecx, %edi
-; CHECK-BMI-NEXT:    xorl %esi, %edi
-; CHECK-BMI-NEXT:    movl %edi, %eax
+; CHECK-BMI-NEXT:    andnl %esi, %ecx, %eax
+; CHECK-BMI-NEXT:    orl %edi, %eax
 ; CHECK-BMI-NEXT:    retq
   %y = and i32 %y_hi, %y_low
   %n0 = xor i32 %x, %y
@@ -740,10 +729,9 @@
 ; CHECK-BMI-LABEL: in_complex_m0:
 ; CHECK-BMI:       # %bb.0:
 ; CHECK-BMI-NEXT:    xorl %ecx, %edx
-; CHECK-BMI-NEXT:    xorl %esi, %edi
-; CHECK-BMI-NEXT:    andl %edx, %edi
-; CHECK-BMI-NEXT:    xorl %esi, %edi
-; CHECK-BMI-NEXT:    movl %edi, %eax
+; CHECK-BMI-NEXT:    andnl %esi, %edx, %eax
+; CHECK-BMI-NEXT:    andl %edi, %edx
+; CHECK-BMI-NEXT:    orl %edx, %eax
 ; CHECK-BMI-NEXT:    retq
   %mask = xor i32 %m_a, %m_b
   %n0 = xor i32 %x, %y
@@ -765,10 +753,9 @@
 ; CHECK-BMI-LABEL: in_complex_m1:
 ; CHECK-BMI:       # %bb.0:
 ; CHECK-BMI-NEXT:    xorl %ecx, %edx
-; CHECK-BMI-NEXT:    xorl %esi, %edi
-; CHECK-BMI-NEXT:    andl %edx, %edi
-; CHECK-BMI-NEXT:    xorl %esi, %edi
-; CHECK-BMI-NEXT:    movl %edi, %eax
+; CHECK-BMI-NEXT:    andnl %esi, %edx, %eax
+; CHECK-BMI-NEXT:    andl %edi, %edx
+; CHECK-BMI-NEXT:    orl %edx, %eax
 ; CHECK-BMI-NEXT:    retq
   %mask = xor i32 %m_a, %m_b
   %n0 = xor i32 %x, %y
@@ -796,10 +783,9 @@
 ; CHECK-BMI:       # %bb.0:
 ; CHECK-BMI-NEXT:    andl %edx, %esi
 ; CHECK-BMI-NEXT:    xorl %r8d, %ecx
-; CHECK-BMI-NEXT:    xorl %esi, %edi
-; CHECK-BMI-NEXT:    andl %ecx, %edi
-; CHECK-BMI-NEXT:    xorl %esi, %edi
-; CHECK-BMI-NEXT:    movl %edi, %eax
+; CHECK-BMI-NEXT:    andnl %esi, %ecx, %eax
+; CHECK-BMI-NEXT:    andl %edi, %ecx
+; CHECK-BMI-NEXT:    orl %ecx, %eax
 ; CHECK-BMI-NEXT:    retq
   %y = and i32 %y_hi, %y_low
   %mask = xor i32 %m_a, %m_b
@@ -824,10 +810,9 @@
 ; CHECK-BMI:       # %bb.0:
 ; CHECK-BMI-NEXT:    andl %edx, %esi
 ; CHECK-BMI-NEXT:    xorl %r8d, %ecx
-; CHECK-BMI-NEXT:    xorl %esi, %edi
-; CHECK-BMI-NEXT:    andl %ecx, %edi
-; CHECK-BMI-NEXT:    xorl %esi, %edi
-; CHECK-BMI-NEXT:    movl %edi, %eax
+; CHECK-BMI-NEXT:    andnl %esi, %ecx, %eax
+; CHECK-BMI-NEXT:    andl %edi, %ecx
+; CHECK-BMI-NEXT:    orl %ecx, %eax
 ; CHECK-BMI-NEXT:    retq
   %y = and i32 %y_hi, %y_low
   %mask = xor i32 %m_a, %m_b
@@ -852,10 +837,9 @@
 ; CHECK-BMI:       # %bb.0:
 ; CHECK-BMI-NEXT:    andl %edx, %esi
 ; CHECK-BMI-NEXT:    xorl %r8d, %ecx
-; CHECK-BMI-NEXT:    xorl %esi, %edi
-; CHECK-BMI-NEXT:    andl %ecx, %edi
-; CHECK-BMI-NEXT:    xorl %esi, %edi
-; CHECK-BMI-NEXT:    movl %edi, %eax
+; CHECK-BMI-NEXT:    andnl %esi, %ecx, %eax
+; CHECK-BMI-NEXT:    andl %edi, %ecx
+; CHECK-BMI-NEXT:    orl %ecx, %eax
 ; CHECK-BMI-NEXT:    retq
   %y = and i32 %y_hi, %y_low
   %mask = xor i32 %m_a, %m_b
@@ -880,10 +864,9 @@
 ; CHECK-BMI:       # %bb.0:
 ; CHECK-BMI-NEXT:    andl %edx, %esi
 ; CHECK-BMI-NEXT:    xorl %r8d, %ecx
-; CHECK-BMI-NEXT:    xorl %esi, %edi
-; CHECK-BMI-NEXT:    andl %ecx, %edi
-; CHECK-BMI-NEXT:    xorl %esi, %edi
-; CHECK-BMI-NEXT:    movl %edi, %eax
+; CHECK-BMI-NEXT:    andnl %esi, %ecx, %eax
+; CHECK-BMI-NEXT:    andl %edi, %ecx
+; CHECK-BMI-NEXT:    orl %ecx, %eax
 ; CHECK-BMI-NEXT:    retq
   %y = and i32 %y_hi, %y_low
   %mask = xor i32 %m_a, %m_b