diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -46377,6 +46377,60 @@
   return Ret;
 }
 
+static SDValue foldMaskedMergeImpl(SDValue And0_L, SDValue And0_R,
+                                   SDValue And1_L, SDValue And1_R, SDLoc DL,
+                                   SelectionDAG &DAG) {
+  if (!isBitwiseNot(And0_L, true))
+    return SDValue();
+  SDValue NotOp = And0_L->getOperand(0);
+  if (NotOp == And1_R) {
+    std::swap(And1_R, And1_L);
+  }
+  // (~(NotOp) & And0_R) | (NotOp & And1_R)
+  // --> ((And0_R ^ And1_R) & NotOp) ^ And1_R
+  if (NotOp == And1_L) {
+    EVT VT = And1_L->getValueType(0);
+    SDValue Freeze_And0_R = DAG.getNode(ISD::FREEZE, SDLoc(), VT, And0_R);
+    SDValue Xor0 = DAG.getNode(ISD::XOR, DL, VT, And1_R, Freeze_And0_R);
+    SDValue And = DAG.getNode(ISD::AND, DL, VT, Xor0, NotOp);
+    SDValue Xor1 = DAG.getNode(ISD::XOR, DL, VT, And, Freeze_And0_R);
+    return Xor1;
+  }
+  return SDValue();
+}
+
+/// Fold "masked merge" expressions like `(m & x) | (~m & y)` into the
+/// equivalent `((x ^ y) & m) ^ y)` pattern.
+/// This is typically a better representation for  targets without a fused
+/// "and-not" operation. This function is intended to be called from a
+/// `TargetLowering::PerformDAGCombing` callback on `ISD::OR` nodes.
+static SDValue foldMaskedMerge(SDNode *Node, SelectionDAG &DAG) {
+  // Note that masked-merge variants using XOR or ADD expressions are
+  // normalized to OR by InstCombine so we only check for OR.
+  assert(Node->getOpcode() == ISD::OR);
+  SDValue N0 = Node->getOperand(0);
+  if (N0->getOpcode() != ISD::AND)
+    return SDValue();
+  SDValue N1 = Node->getOperand(1);
+  if (N1->getOpcode() != ISD::AND)
+    return SDValue();
+
+  SDLoc DL(Node);
+  SDValue N00 = N0->getOperand(0);
+  SDValue N01 = N0->getOperand(1);
+  SDValue N10 = N1->getOperand(0);
+  SDValue N11 = N1->getOperand(1);
+  if (SDValue Result = foldMaskedMergeImpl(N00, N01, N10, N11, DL, DAG))
+    return Result;
+  if (SDValue Result = foldMaskedMergeImpl(N01, N00, N10, N11, DL, DAG))
+    return Result;
+  if (SDValue Result = foldMaskedMergeImpl(N10, N11, N00, N01, DL, DAG))
+    return Result;
+  if (SDValue Result = foldMaskedMergeImpl(N11, N10, N00, N01, DL, DAG))
+    return Result;
+  return SDValue();
+}
+
 static SDValue combineOr(SDNode *N, SelectionDAG &DAG,
                          TargetLowering::DAGCombinerInfo &DCI,
                          const X86Subtarget &Subtarget) {
@@ -46470,6 +46524,12 @@
       return Res;
   }
 
+  // We should fold "masked merge" patterns when `andn` is not avilable.
+  if (!Subtarget.hasBMI() && VT.isScalarInteger() && VT != MVT::i1) {
+    if (SDValue R = foldMaskedMerge(N, DAG))
+      return R;
+  }
+
   return SDValue();
 }
 
diff --git a/llvm/test/CodeGen/X86/fold-masked-merge.ll b/llvm/test/CodeGen/X86/fold-masked-merge.ll
--- a/llvm/test/CodeGen/X86/fold-masked-merge.ll
+++ b/llvm/test/CodeGen/X86/fold-masked-merge.ll
@@ -8,11 +8,10 @@
 define i32 @masked_merge0(i32 %a0, i32 %a1, i32 %a2) {
 ; CHECK-LABEL: masked_merge0:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    movl %edi, %eax
-; CHECK-NEXT:    andl %edi, %esi
-; CHECK-NEXT:    notl %eax
-; CHECK-NEXT:    andl %edx, %eax
-; CHECK-NEXT:    orl %esi, %eax
+; CHECK-NEXT:    movl %esi, %eax
+; CHECK-NEXT:    xorl %edx, %eax
+; CHECK-NEXT:    andl %edi, %eax
+; CHECK-NEXT:    xorl %edx, %eax
 ; CHECK-NEXT:    retq
 ;
 ; BMI-LABEL: masked_merge0:
@@ -56,11 +55,10 @@
 define i8 @masked_merge2(i8 %a0, i8 %a1, i8 %a2) {
 ; CHECK-LABEL: masked_merge2:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    movl %edi, %eax
-; CHECK-NEXT:    notb %al
-; CHECK-NEXT:    andb %sil, %al
-; CHECK-NEXT:    andb %dil, %sil
-; CHECK-NEXT:    orb %sil, %al
+; CHECK-NEXT:    movl %esi, %eax
+; CHECK-NEXT:    xorb %sil, %al
+; CHECK-NEXT:    andb %dil, %al
+; CHECK-NEXT:    xorb %sil, %al
 ; CHECK-NEXT:    retq
 ;
 ; BMI-LABEL: masked_merge2:
@@ -81,13 +79,12 @@
 define i64 @masked_merge3(i64 %a0, i64 %a1, i64 %a2) {
 ; CHECK-LABEL: masked_merge3:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    movq %rdi, %rax
-; CHECK-NEXT:    notq %rsi
+; CHECK-NEXT:    movq %rsi, %rax
 ; CHECK-NEXT:    notq %rdx
-; CHECK-NEXT:    andq %rdi, %rsi
+; CHECK-NEXT:    xorq %rdx, %rax
 ; CHECK-NEXT:    notq %rax
-; CHECK-NEXT:    andq %rdx, %rax
-; CHECK-NEXT:    orq %rsi, %rax
+; CHECK-NEXT:    andq %rdi, %rax
+; CHECK-NEXT:    xorq %rdx, %rax
 ; CHECK-NEXT:    retq
 ;
 ; BMI-LABEL: masked_merge3: