+declare <8 x i8> @llvm.arm.neon.vabds.v8i8(<8 x i8>, <8 x i8>) nounwind readnone
+declare <4 x i16> @llvm.arm.neon.vabds.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
+declare <2 x i32> @llvm.arm.neon.vabds.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
+
+declare <8 x i8> @llvm.arm.neon.vabdu.v8i8(<8 x i8>, <8 x i8>) nounwind readnone
+declare <4 x i16> @llvm.arm.neon.vabdu.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
+declare <2 x i32> @llvm.arm.neon.vabdu.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
+
+declare <16 x i8> @llvm.arm.neon.vabds.v16i8(<16 x i8>, <16 x i8>) nounwind readnone
+declare <8 x i16> @llvm.arm.neon.vabds.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
+declare <4 x i32> @llvm.arm.neon.vabds.v4i32(<4 x i32>, <4 x i32>) nounwind readnone
+
+declare <16 x i8> @llvm.arm.neon.vabdu.v16i8(<16 x i8>, <16 x i8>) nounwind readnone
+declare <8 x i16> @llvm.arm.neon.vabdu.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
+declare <4 x i32> @llvm.arm.neon.vabdu.v4i32(<4 x i32>, <4 x i32>) nounwind readnone
+
+define <8 x i16> @vabals8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
+;CHECK-LABEL: vabals8:
+;CHECK: vabal.s8
+ %tmp1 = load <8 x i16>, <8 x i16>* %A
+ %tmp2 = load <8 x i8>, <8 x i8>* %B
+ %tmp3 = load <8 x i8>, <8 x i8>* %C
+ %tmp4 = call <8 x i8> @llvm.arm.neon.vabds.v8i8(<8 x i8> %tmp2, <8 x i8> %tmp3)
+ %tmp5 = zext <8 x i8> %tmp4 to <8 x i16>
+ %tmp6 = add <8 x i16> %tmp1, %tmp5
+ ret <8 x i16> %tmp6
+}
+
+define <4 x i32> @vabals16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
+;CHECK-LABEL: vabals16:
+;CHECK: vabal.s16
+ %tmp1 = load <4 x i32>, <4 x i32>* %A
+ %tmp2 = load <4 x i16>, <4 x i16>* %B
+ %tmp3 = load <4 x i16>, <4 x i16>* %C
+ %tmp4 = call <4 x i16> @llvm.arm.neon.vabds.v4i16(<4 x i16> %tmp2, <4 x i16> %tmp3)
+ %tmp5 = zext <4 x i16> %tmp4 to <4 x i32>
+ %tmp6 = add <4 x i32> %tmp1, %tmp5
+ ret <4 x i32> %tmp6
+}
+
+define <2 x i64> @vabals32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
+;CHECK-LABEL: vabals32:
+;CHECK: vabal.s32
+ %tmp1 = load <2 x i64>, <2 x i64>* %A
+ %tmp2 = load <2 x i32>, <2 x i32>* %B
+ %tmp3 = load <2 x i32>, <2 x i32>* %C
+ %tmp4 = call <2 x i32> @llvm.arm.neon.vabds.v2i32(<2 x i32> %tmp2, <2 x i32> %tmp3)
+ %tmp5 = zext <2 x i32> %tmp4 to <2 x i64>
+ %tmp6 = add <2 x i64> %tmp1, %tmp5
+ ret <2 x i64> %tmp6
+}