; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -mtriple=armv7a-eabihf -mattr=+neon %s -o - | FileCheck %s

define <8 x i8> @vabds8(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vabds8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vabd.s8 d0, d17, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i8>, ptr %A
	%tmp2 = load <8 x i8>, ptr %B
	%tmp3 = call <8 x i8> @llvm.arm.neon.vabds.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
	ret <8 x i8> %tmp3
}

define <4 x i16> @vabds16(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vabds16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vabd.s16 d0, d17, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i16>, ptr %A
	%tmp2 = load <4 x i16>, ptr %B
	%tmp3 = call <4 x i16> @llvm.arm.neon.vabds.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
	ret <4 x i16> %tmp3
}

define <2 x i32> @vabds32(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vabds32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vabd.s32 d0, d17, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <2 x i32>, ptr %A
	%tmp2 = load <2 x i32>, ptr %B
	%tmp3 = call <2 x i32> @llvm.arm.neon.vabds.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
	ret <2 x i32> %tmp3
}

define <8 x i8> @vabdu8(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vabdu8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vabd.u8 d0, d17, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i8>, ptr %A
	%tmp2 = load <8 x i8>, ptr %B
	%tmp3 = call <8 x i8> @llvm.arm.neon.vabdu.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
	ret <8 x i8> %tmp3
}

define <4 x i16> @vabdu16(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vabdu16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vabd.u16 d0, d17, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i16>, ptr %A
	%tmp2 = load <4 x i16>, ptr %B
	%tmp3 = call <4 x i16> @llvm.arm.neon.vabdu.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
	ret <4 x i16> %tmp3
}

define <2 x i32> @vabdu32(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vabdu32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vabd.u32 d0, d17, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <2 x i32>, ptr %A
	%tmp2 = load <2 x i32>, ptr %B
	%tmp3 = call <2 x i32> @llvm.arm.neon.vabdu.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
	ret <2 x i32> %tmp3
}

define <2 x float> @vabdf32(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vabdf32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vabd.f32 d0, d17, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <2 x float>, ptr %A
	%tmp2 = load <2 x float>, ptr %B
	%tmp3 = call <2 x float> @llvm.arm.neon.vabds.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
	ret <2 x float> %tmp3
}

define <16 x i8> @vabdQs8(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vabdQs8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vabd.s8 q0, q9, q8
; CHECK-NEXT:    bx lr
	%tmp1 = load <16 x i8>, ptr %A
	%tmp2 = load <16 x i8>, ptr %B
	%tmp3 = call <16 x i8> @llvm.arm.neon.vabds.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
	ret <16 x i8> %tmp3
}

define <8 x i16> @vabdQs16(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vabdQs16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vabd.s16 q0, q9, q8
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i16>, ptr %A
	%tmp2 = load <8 x i16>, ptr %B
	%tmp3 = call <8 x i16> @llvm.arm.neon.vabds.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
	ret <8 x i16> %tmp3
}

define <4 x i32> @vabdQs32(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vabdQs32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vabd.s32 q0, q9, q8
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i32>, ptr %A
	%tmp2 = load <4 x i32>, ptr %B
	%tmp3 = call <4 x i32> @llvm.arm.neon.vabds.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
	ret <4 x i32> %tmp3
}

define <16 x i8> @vabdQu8(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vabdQu8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vabd.u8 q0, q9, q8
; CHECK-NEXT:    bx lr
	%tmp1 = load <16 x i8>, ptr %A
	%tmp2 = load <16 x i8>, ptr %B
	%tmp3 = call <16 x i8> @llvm.arm.neon.vabdu.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
	ret <16 x i8> %tmp3
}

define <8 x i16> @vabdQu16(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vabdQu16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vabd.u16 q0, q9, q8
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i16>, ptr %A
	%tmp2 = load <8 x i16>, ptr %B
	%tmp3 = call <8 x i16> @llvm.arm.neon.vabdu.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
	ret <8 x i16> %tmp3
}

define <4 x i32> @vabdQu32(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vabdQu32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vabd.u32 q0, q9, q8
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i32>, ptr %A
	%tmp2 = load <4 x i32>, ptr %B
	%tmp3 = call <4 x i32> @llvm.arm.neon.vabdu.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
	ret <4 x i32> %tmp3
}

define <4 x float> @vabdQf32(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vabdQf32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vabd.f32 q0, q9, q8
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x float>, ptr %A
	%tmp2 = load <4 x float>, ptr %B
	%tmp3 = call <4 x float> @llvm.arm.neon.vabds.v4f32(<4 x float> %tmp1, <4 x float> %tmp2)
	ret <4 x float> %tmp3
}

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 <2 x float> @llvm.arm.neon.vabds.v2f32(<2 x float>, <2 x float>) 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

declare <4 x float> @llvm.arm.neon.vabds.v4f32(<4 x float>, <4 x float>) nounwind readnone

define <8 x i16> @vabdls8(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vabdls8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vabdl.s8 q0, d17, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i8>, ptr %A
	%tmp2 = load <8 x i8>, ptr %B
	%tmp3 = call <8 x i8> @llvm.arm.neon.vabds.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
	%tmp4 = zext <8 x i8> %tmp3 to <8 x i16>
	ret <8 x i16> %tmp4
}

define <4 x i32> @vabdls16(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vabdls16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vabdl.s16 q0, d17, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i16>, ptr %A
	%tmp2 = load <4 x i16>, ptr %B
	%tmp3 = call <4 x i16> @llvm.arm.neon.vabds.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
	%tmp4 = zext <4 x i16> %tmp3 to <4 x i32>
	ret <4 x i32> %tmp4
}

define <2 x i64> @vabdls32(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vabdls32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vabdl.s32 q0, d17, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <2 x i32>, ptr %A
	%tmp2 = load <2 x i32>, ptr %B
	%tmp3 = call <2 x i32> @llvm.arm.neon.vabds.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
	%tmp4 = zext <2 x i32> %tmp3 to <2 x i64>
	ret <2 x i64> %tmp4
}

define <8 x i16> @vabdlu8(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vabdlu8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vabdl.u8 q0, d17, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i8>, ptr %A
	%tmp2 = load <8 x i8>, ptr %B
	%tmp3 = call <8 x i8> @llvm.arm.neon.vabdu.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
	%tmp4 = zext <8 x i8> %tmp3 to <8 x i16>
	ret <8 x i16> %tmp4
}

define <4 x i32> @vabdlu16(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vabdlu16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vabdl.u16 q0, d17, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i16>, ptr %A
	%tmp2 = load <4 x i16>, ptr %B
	%tmp3 = call <4 x i16> @llvm.arm.neon.vabdu.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
	%tmp4 = zext <4 x i16> %tmp3 to <4 x i32>
	ret <4 x i32> %tmp4
}

define <2 x i64> @vabdlu32(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vabdlu32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vabdl.u32 q0, d17, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <2 x i32>, ptr %A
	%tmp2 = load <2 x i32>, ptr %B
	%tmp3 = call <2 x i32> @llvm.arm.neon.vabdu.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
	%tmp4 = zext <2 x i32> %tmp3 to <2 x i64>
	ret <2 x i64> %tmp4
}