Index: llvm/lib/Target/ARM/ARMISelLowering.cpp
===================================================================
--- llvm/lib/Target/ARM/ARMISelLowering.cpp
+++ llvm/lib/Target/ARM/ARMISelLowering.cpp
@@ -260,6 +260,7 @@
     setOperationAction(ISD::ABS, VT, Legal);
     setOperationAction(ISD::SETCC, VT, Custom);
     setOperationAction(ISD::CTLZ, VT, Legal);
+    setOperationAction(ISD::CTTZ, VT, Custom);
 
     // No native support for these.
     setOperationAction(ISD::UDIV, VT, Expand);
@@ -5738,9 +5739,7 @@
                          const ARMSubtarget *ST) {
   SDLoc dl(N);
   EVT VT = N->getValueType(0);
-  if (VT.isVector()) {
-    assert(ST->hasNEON());
-
+  if (VT.isVector() && ST->hasNEON()) {
     // Compute the least significant set bit: LSB = X & -X
     SDValue X = N->getOperand(0);
     SDValue NX = DAG.getNode(ISD::SUB, dl, VT, getZeroVector(VT, DAG, dl), X);
Index: llvm/test/CodeGen/Thumb2/mve-cttz.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/Thumb2/mve-cttz.ll
@@ -0,0 +1,39 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+mve %s -o - | FileCheck %s
+
+define arm_aapcs_vfpcc <4 x i32> @cttz_4i32_t(<4 x i32> %src){
+; CHECK-LABEL: cttz_4i32_t:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vbrsr.32 q0, q0, #0
+; CHECK-NEXT:    vclz.i32 q0, q0
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = call <4 x i32> @llvm.cttz.v4i32(<4 x i32> %src)
+  ret <4 x i32> %0
+}
+
+define arm_aapcs_vfpcc <8 x i16> @cttz_8i16_t(<8 x i16> %src){
+; CHECK-LABEL: cttz_8i16_t:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vbrsr.16 q0, q0, #0
+; CHECK-NEXT:    vclz.i16 q0, q0
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = call <8 x i16> @llvm.cttz.v8i16(<8 x i16> %src)
+  ret <8 x i16> %0
+}
+
+define arm_aapcs_vfpcc <16 x i8> @cttz_16i8_t(<16 x i8> %src){
+; CHECK-LABEL: cttz_16i8_t:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vbrsr.8 q0, q0, #0
+; CHECK-NEXT:    vclz.i8 q0, q0
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = call <16 x i8> @llvm.cttz.v16i8(<16 x i8> %src)
+  ret <16 x i8> %0
+}
+
+declare <4 x i32> @llvm.cttz.v4i32(<4 x i32>)
+declare <8 x i16> @llvm.cttz.v8i16(<8 x i16>)
+declare <16 x i8> @llvm.cttz.v16i8(<16 x i8>)