Index: llvm/lib/Target/ARM/ARMISelLowering.cpp
===================================================================
--- llvm/lib/Target/ARM/ARMISelLowering.cpp
+++ llvm/lib/Target/ARM/ARMISelLowering.cpp
@@ -934,6 +934,7 @@
     setTargetDAGCombine(ISD::BUILD_VECTOR);
     setTargetDAGCombine(ISD::VECTOR_SHUFFLE);
     setTargetDAGCombine(ISD::INSERT_VECTOR_ELT);
+    setTargetDAGCombine(ISD::EXTRACT_VECTOR_ELT);
     setTargetDAGCombine(ISD::STORE);
     setTargetDAGCombine(ISD::SIGN_EXTEND);
     setTargetDAGCombine(ISD::ZERO_EXTEND);
@@ -13266,6 +13267,29 @@
   return DAG.getNode(ISD::BITCAST, dl, VT, InsElt);
 }
 
+static SDValue PerformExtractEltCombine(SDNode *N,
+                                        TargetLowering::DAGCombinerInfo &DCI) {
+  SDValue Op0 = N->getOperand(0);
+  EVT VT = N->getValueType(0);
+  SDLoc dl(N);
+
+  // extract (vdup x) -> x
+  if (Op0->getOpcode() == ARMISD::VDUP) {
+    SDValue X = Op0->getOperand(0);
+    if (VT == MVT::f16 && X.getValueType() == MVT::i32)
+      return DCI.DAG.getNode(ARMISD::VMOVhr, dl, VT, X);
+    if (VT == MVT::i32 && X.getValueType() == MVT::f16)
+      return DCI.DAG.getNode(ARMISD::VMOVrh, dl, VT, X);
+
+    while (X.getValueType() != VT && X->getOpcode() == ISD::BITCAST)
+      X = X->getOperand(0);
+    if (X.getValueType() == VT)
+      return X;
+  }
+
+  return SDValue();
+}
+
 /// PerformVECTOR_SHUFFLECombine - Target-specific dag combine xforms for
 /// ISD::VECTOR_SHUFFLE.
 static SDValue PerformVECTOR_SHUFFLECombine(SDNode *N, SelectionDAG &DAG) {
@@ -15253,6 +15277,7 @@
   case ISD::STORE:      return PerformSTORECombine(N, DCI, Subtarget);
   case ISD::BUILD_VECTOR: return PerformBUILD_VECTORCombine(N, DCI, Subtarget);
   case ISD::INSERT_VECTOR_ELT: return PerformInsertEltCombine(N, DCI);
+  case ISD::EXTRACT_VECTOR_ELT: return PerformExtractEltCombine(N, DCI);
   case ISD::VECTOR_SHUFFLE: return PerformVECTOR_SHUFFLECombine(N, DCI.DAG);
   case ARMISD::VDUPLANE: return PerformVDUPLANECombine(N, DCI);
   case ARMISD::VDUP: return PerformVDUPCombine(N, DCI, Subtarget);
Index: llvm/test/CodeGen/Thumb2/mve-vdup.ll
===================================================================
--- llvm/test/CodeGen/Thumb2/mve-vdup.ll
+++ llvm/test/CodeGen/Thumb2/mve-vdup.ll
@@ -240,9 +240,6 @@
 define arm_aapcs_vfpcc float @vdup_f32_extract(float %src) {
 ; CHECK-LABEL: vdup_f32_extract:
 ; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    vmov r0, s0
-; CHECK-NEXT:    vdup.32 q0, r0
-; CHECK-NEXT:    vmov.f32 s0, s2
 ; CHECK-NEXT:    bx lr
 entry:
   %srcbc = bitcast float %src to i32
@@ -260,8 +257,8 @@
 ; CHECK-NEXT:    vldr.16 s2, [r1]
 ; CHECK-NEXT:    vadd.f16 s0, s2, s0
 ; CHECK-NEXT:    vmov.f16 r1, s0
-; CHECK-NEXT:    vdup.16 q0, r1
-; CHECK-NEXT:    vstr.16 s1, [r0]
+; CHECK-NEXT:    vmov.f16 s0, r1
+; CHECK-NEXT:    vstr.16 s0, [r0]
 ; CHECK-NEXT:    bx lr
 entry:
   %0 = load half, half *%src1, align 2