Index: llvm/lib/Target/AArch64/AArch64InstrInfo.td
===================================================================
--- llvm/lib/Target/AArch64/AArch64InstrInfo.td
+++ llvm/lib/Target/AArch64/AArch64InstrInfo.td
@@ -5753,7 +5753,7 @@
             (v4i16 (AArch64uaddv (v4i16 (AArch64uaddlp (v8i8 V64:$op))))),
             (i64 0))), (i64 0))),
           (EXTRACT_SUBREG (INSERT_SUBREG (v4i16 (IMPLICIT_DEF)),
-           (UADDLVv4i16v V64:$op), ssub), ssub)>;
+           (UADDLVv8i8v V64:$op), hsub), ssub)>;
 def : Pat<(i32 (vector_extract (v8i16 (AArch64uaddv (v8i16 (AArch64uaddlp
            (v16i8 V128:$op))))), (i64 0))),
           (EXTRACT_SUBREG (INSERT_SUBREG (v8i16 (IMPLICIT_DEF)),
Index: llvm/test/CodeGen/AArch64/neon-uaddlv.ll
===================================================================
--- llvm/test/CodeGen/AArch64/neon-uaddlv.ll
+++ llvm/test/CodeGen/AArch64/neon-uaddlv.ll
@@ -13,11 +13,13 @@
 declare i64 @llvm.vector.reduce.add.v2i64(<2 x i64>) nounwind readnone
 declare i32 @llvm.vector.reduce.add.v2i32(<2 x i32>) nounwind readnone
 
+declare <4 x i16> @llvm.ctpop.v4i16(<4 x i16>)
+
 define i16 @uaddlv4h_from_v8i8(<8 x i8>* %A) nounwind {
 ; CHECK-LABEL: uaddlv4h_from_v8i8:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    ldr d0, [x0]
-; CHECK-NEXT:    uaddlv s0, v0.4h
+; CHECK-NEXT:    uaddlv h0, v0.8b
 ; CHECK-NEXT:    fmov w0, s0
 ; CHECK-NEXT:    ret
   %tmp1 = load <8 x i8>, <8 x i8>* %A
@@ -77,3 +79,19 @@
   %tmp5 = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> %tmp3)
   ret i32 %tmp5
 }
+
+define i16 @count([4 x i16]* %0) {
+; CHECK-LABEL: count:
+; CHECK:       // %bb.0: // %Entry
+; CHECK-NEXT:    ldr d0, [x0]
+; CHECK-NEXT:    cnt v0.8b, v0.8b
+; CHECK-NEXT:    uaddlv h0, v0.8b
+; CHECK-NEXT:    fmov w0, s0
+; CHECK-NEXT:    ret
+Entry:
+  %1 = bitcast [4 x i16]* %0 to <4 x i16>*
+  %2 = load <4 x i16>, <4 x i16>* %1, align 2
+  %3 = call <4 x i16> @llvm.ctpop.v4i16(<4 x i16> %2)
+  %4 = call i16 @llvm.vector.reduce.add.v4i16(<4 x i16> %3)
+  ret i16 %4
+}