diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.h b/llvm/lib/Target/AArch64/AArch64ISelLowering.h
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.h
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.h
@@ -158,6 +158,7 @@
   DUPLANE16,
   DUPLANE32,
   DUPLANE64,
+  DUPLANE128,
 
   // Vector immedate moves
   MOVI,
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
@@ -2049,6 +2049,7 @@
     MAKE_CASE(AArch64ISD::DUPLANE16)
     MAKE_CASE(AArch64ISD::DUPLANE32)
     MAKE_CASE(AArch64ISD::DUPLANE64)
+    MAKE_CASE(AArch64ISD::DUPLANE128)
     MAKE_CASE(AArch64ISD::MOVI)
     MAKE_CASE(AArch64ISD::MOVIshift)
     MAKE_CASE(AArch64ISD::MOVIedit)
@@ -10558,18 +10559,17 @@
     return SDValue();
 
   // The DUPQ operation is indepedent of element type so normalise to i64s.
-  SDValue V = DAG.getNode(ISD::BITCAST, DL, MVT::nxv2i64, Op.getOperand(1));
   SDValue Idx128 = Op.getOperand(2);
 
   // DUPQ can be used when idx is in range.
   auto *CIdx = dyn_cast<ConstantSDNode>(Idx128);
   if (CIdx && (CIdx->getZExtValue() <= 3)) {
     SDValue CI = DAG.getTargetConstant(CIdx->getZExtValue(), DL, MVT::i64);
-    SDNode *DUPQ =
-        DAG.getMachineNode(AArch64::DUP_ZZI_Q, DL, MVT::nxv2i64, V, CI);
-    return DAG.getNode(ISD::BITCAST, DL, VT, SDValue(DUPQ, 0));
+    return DAG.getNode(AArch64ISD::DUPLANE128, DL, VT, Op.getOperand(1), CI);
   }
 
+  SDValue V = DAG.getNode(ISD::BITCAST, DL, MVT::nxv2i64, Op.getOperand(1));
+
   // The ACLE says this must produce the same result as:
   //   svtbl(data, svadd_x(svptrue_b64(),
   //                       svand_x(svptrue_b64(), svindex_u64(0, 1), 1),
diff --git a/llvm/lib/Target/AArch64/AArch64InstrInfo.td b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
--- a/llvm/lib/Target/AArch64/AArch64InstrInfo.td
+++ b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
@@ -583,6 +583,7 @@
 def AArch64duplane16 : SDNode<"AArch64ISD::DUPLANE16", SDT_AArch64DupLane>;
 def AArch64duplane32 : SDNode<"AArch64ISD::DUPLANE32", SDT_AArch64DupLane>;
 def AArch64duplane64 : SDNode<"AArch64ISD::DUPLANE64", SDT_AArch64DupLane>;
+def AArch64duplane128 : SDNode<"AArch64ISD::DUPLANE128", SDT_AArch64DupLane>;
 
 def AArch64insr      : SDNode<"AArch64ISD::INSR", SDT_AArch64Insr>;
 
diff --git a/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td b/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
--- a/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
+++ b/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
@@ -672,6 +672,23 @@
   def : Pat<(nxv2bf16 (splat_vector (bf16 FPR16:$src))),
             (DUP_ZZI_H (INSERT_SUBREG (IMPLICIT_DEF), FPR16:$src, hsub), 0)>;
 
+  def : Pat<(nxv16i8 (AArch64duplane128 nxv16i8:$Op1, i64:$imm)),
+            (nxv16i8 (DUP_ZZI_Q $Op1, $imm))>;
+  def : Pat<(nxv8i16 (AArch64duplane128 nxv8i16:$Op1, i64:$imm)),
+            (nxv8i16 (DUP_ZZI_Q $Op1, $imm))>;
+  def : Pat<(nxv4i32 (AArch64duplane128 nxv4i32:$Op1, i64:$imm)),
+            (nxv4i32 (DUP_ZZI_Q $Op1, $imm))>;
+  def : Pat<(nxv2i64 (AArch64duplane128 nxv2i64:$Op1, i64:$imm)),
+            (nxv2i64 (DUP_ZZI_Q $Op1, $imm))>;
+  def : Pat<(nxv8f16 (AArch64duplane128 nxv8f16:$Op1, i64:$imm)),
+            (nxv8f16 (DUP_ZZI_Q $Op1, $imm))>;
+  def : Pat<(nxv4f32 (AArch64duplane128 nxv4f32:$Op1, i64:$imm)),
+            (nxv4f32 (DUP_ZZI_Q $Op1, $imm))>;
+  def : Pat<(nxv2f64 (AArch64duplane128 nxv2f64:$Op1, i64:$imm)),
+            (nxv2f64 (DUP_ZZI_Q $Op1, $imm))>;
+  def : Pat<(nxv8bf16 (AArch64duplane128 nxv8bf16:$Op1, i64:$imm)),
+            (nxv8bf16 (DUP_ZZI_Q $Op1, $imm))>;
+
   // Duplicate +0.0 into all vector elements
   def : Pat<(nxv8f16 (splat_vector (f16 fpimm0))), (DUP_ZI_H 0, 0)>;
   def : Pat<(nxv4f16 (splat_vector (f16 fpimm0))), (DUP_ZI_H 0, 0)>;