diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -14332,6 +14332,52 @@
 
     return true;
   }
+  case Instruction::Or: {
+    // Pattern: Or(And(MaskValue, A), And(Not(MaskValue), B)) ->
+    // bitselect(MaskValue, A, B) where Not(MaskValue) = Xor(MaskValue, -1)
+    if (Subtarget->hasNEON()) {
+      // If any of the intermediate Ands have uses other than Or, don't fold
+      if (!I->getOperand(0)->hasOneUse() || !I->getOperand(0)->hasOneUse())
+        return false;
+
+      Instruction *OtherAnd, *IA, *IB;
+      Value *MaskValue;
+      // MainAnd refers to And instruction that has 'Not' as one of its operands
+      if (match(I, m_c_Or(m_Instruction(OtherAnd),
+                          m_c_And(m_Not(m_Value(MaskValue)),
+                                  m_Instruction(IA))))) {
+        if (match(OtherAnd,
+                  m_c_And(m_Specific(MaskValue), m_Instruction(IB)))) {
+          Instruction *MainAnd = I->getOperand(0) == OtherAnd
+                                     ? cast<Instruction>(I->getOperand(1))
+                                     : cast<Instruction>(I->getOperand(0));
+
+          // Both Ands should be in same basic block as Or
+          if (I->getParent() != MainAnd->getParent() ||
+              I->getParent() != OtherAnd->getParent())
+            return false;
+
+          // Non-mask operands of both Ands should also be in same basic block
+          if (I->getParent() != IA->getParent() ||
+              I->getParent() != IB->getParent())
+            return false;
+
+          for (unsigned Idx = 0; Idx < MainAnd->getNumOperands(); Idx++) {
+            if (MainAnd->getOperand(Idx) != IA &&
+                MainAnd->getOperand(Idx)->hasOneUse()) {
+              Ops.push_back(&MainAnd->getOperandUse(Idx));
+              Ops.push_back(&I->getOperandUse(0));
+              Ops.push_back(&I->getOperandUse(1));
+
+              return true;
+            }
+          }
+        }
+      }
+    }
+
+    return false;
+  }
   case Instruction::Mul: {
     int NumZExts = 0, NumSExts = 0;
     for (auto &Op : I->operands()) {
diff --git a/llvm/test/CodeGen/AArch64/aarch64-bit-gen.ll b/llvm/test/CodeGen/AArch64/aarch64-bit-gen.ll
--- a/llvm/test/CodeGen/AArch64/aarch64-bit-gen.ll
+++ b/llvm/test/CodeGen/AArch64/aarch64-bit-gen.ll
@@ -144,3 +144,30 @@
   %or = or <16 x i8> %and, %and1
   ret <16 x i8> %or
 }
+
+define <4 x i32> @test_bit_sink_operand(<4 x i32> %src, <4 x i32> %dst, <4 x i32> %mask, i32 %scratch) {
+; CHECK-LABEL: test_bit_sink_operand
+; CHECK: // %do.body
+; CHECK: bit v1.16b, v0.16b, v2.16b
+
+entry:
+  %0 = xor <4 x i32> %mask, <i32 -1, i32 -1, i32 -1, i32 -1>
+  %div = sdiv i32 %scratch, 2
+  br label %do.body
+
+do.body:                                         
+  %dst.addr.0 = phi <4 x i32> [ %dst, %entry ], [ %vecins, %do.body ]
+  %src.addr.0 = phi <4 x i32> [ %src, %entry ], [ %vecins1, %do.body ]
+  %i.0 = phi i32 [ 0, %entry ], [ %inc, %do.body ]
+  %vbsl3.i = and <4 x i32> %src.addr.0, %mask
+  %vbsl4.i = and <4 x i32> %dst.addr.0, %0
+  %vbsl5.i = or <4 x i32> %vbsl3.i, %vbsl4.i
+  %vecins = insertelement <4 x i32> %vbsl5.i, i32 %scratch, i32 %i.0
+  %vecins1 = insertelement <4 x i32> %src.addr.0, i32 %div, i32 %i.0
+  %inc = add nuw nsw i32 %i.0, 1
+  %exitcond.not = icmp eq i32 %inc, 5
+  br i1 %exitcond.not, label %do.end, label %do.body
+
+do.end:
+  ret <4 x i32> %vecins
+}
\ No newline at end of file