; 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> @vabas8(ptr %A, ptr %B, ptr %C) nounwind {
; CHECK-LABEL: vabas8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r2]
; CHECK-NEXT:    vldr d17, [r1]
; CHECK-NEXT:    vldr d0, [r0]
; CHECK-NEXT:    vaba.s8 d0, d17, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i8>, ptr %A
	%tmp2 = load <8 x i8>, ptr %B
	%tmp3 = load <8 x i8>, ptr %C
	%tmp4 = call <8 x i8> @llvm.arm.neon.vabds.v8i8(<8 x i8> %tmp2, <8 x i8> %tmp3)
	%tmp5 = add <8 x i8> %tmp1, %tmp4
	ret <8 x i8> %tmp5
}

define <4 x i16> @vabas16(ptr %A, ptr %B, ptr %C) nounwind {
; CHECK-LABEL: vabas16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r2]
; CHECK-NEXT:    vldr d17, [r1]
; CHECK-NEXT:    vldr d0, [r0]
; CHECK-NEXT:    vaba.s16 d0, d17, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i16>, ptr %A
	%tmp2 = load <4 x i16>, ptr %B
	%tmp3 = load <4 x i16>, ptr %C
	%tmp4 = call <4 x i16> @llvm.arm.neon.vabds.v4i16(<4 x i16> %tmp2, <4 x i16> %tmp3)
	%tmp5 = add <4 x i16> %tmp1, %tmp4
	ret <4 x i16> %tmp5
}

define <2 x i32> @vabas32(ptr %A, ptr %B, ptr %C) nounwind {
; CHECK-LABEL: vabas32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r2]
; CHECK-NEXT:    vldr d17, [r1]
; CHECK-NEXT:    vldr d0, [r0]
; CHECK-NEXT:    vaba.s32 d0, d17, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <2 x i32>, ptr %A
	%tmp2 = load <2 x i32>, ptr %B
	%tmp3 = load <2 x i32>, ptr %C
	%tmp4 = call <2 x i32> @llvm.arm.neon.vabds.v2i32(<2 x i32> %tmp2, <2 x i32> %tmp3)
	%tmp5 = add <2 x i32> %tmp1, %tmp4
	ret <2 x i32> %tmp5
}

define <8 x i8> @vabau8(ptr %A, ptr %B, ptr %C) nounwind {
; CHECK-LABEL: vabau8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r2]
; CHECK-NEXT:    vldr d17, [r1]
; CHECK-NEXT:    vldr d0, [r0]
; CHECK-NEXT:    vaba.u8 d0, d17, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i8>, ptr %A
	%tmp2 = load <8 x i8>, ptr %B
	%tmp3 = load <8 x i8>, ptr %C
	%tmp4 = call <8 x i8> @llvm.arm.neon.vabdu.v8i8(<8 x i8> %tmp2, <8 x i8> %tmp3)
	%tmp5 = add <8 x i8> %tmp1, %tmp4
	ret <8 x i8> %tmp5
}

define <4 x i16> @vabau16(ptr %A, ptr %B, ptr %C) nounwind {
; CHECK-LABEL: vabau16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r2]
; CHECK-NEXT:    vldr d17, [r1]
; CHECK-NEXT:    vldr d0, [r0]
; CHECK-NEXT:    vaba.u16 d0, d17, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i16>, ptr %A
	%tmp2 = load <4 x i16>, ptr %B
	%tmp3 = load <4 x i16>, ptr %C
	%tmp4 = call <4 x i16> @llvm.arm.neon.vabdu.v4i16(<4 x i16> %tmp2, <4 x i16> %tmp3)
	%tmp5 = add <4 x i16> %tmp1, %tmp4
	ret <4 x i16> %tmp5
}

define <2 x i32> @vabau32(ptr %A, ptr %B, ptr %C) nounwind {
; CHECK-LABEL: vabau32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r2]
; CHECK-NEXT:    vldr d17, [r1]
; CHECK-NEXT:    vldr d0, [r0]
; CHECK-NEXT:    vaba.u32 d0, d17, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <2 x i32>, ptr %A
	%tmp2 = load <2 x i32>, ptr %B
	%tmp3 = load <2 x i32>, ptr %C
	%tmp4 = call <2 x i32> @llvm.arm.neon.vabdu.v2i32(<2 x i32> %tmp2, <2 x i32> %tmp3)
	%tmp5 = add <2 x i32> %tmp1, %tmp4
	ret <2 x i32> %tmp5
}

define <16 x i8> @vabaQs8(ptr %A, ptr %B, ptr %C) nounwind {
; CHECK-LABEL: vabaQs8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r2]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r1]
; CHECK-NEXT:    vld1.64 {d0, d1}, [r0]
; CHECK-NEXT:    vaba.s8 q0, q9, q8
; CHECK-NEXT:    bx lr
	%tmp1 = load <16 x i8>, ptr %A
	%tmp2 = load <16 x i8>, ptr %B
	%tmp3 = load <16 x i8>, ptr %C
	%tmp4 = call <16 x i8> @llvm.arm.neon.vabds.v16i8(<16 x i8> %tmp2, <16 x i8> %tmp3)
	%tmp5 = add <16 x i8> %tmp1, %tmp4
	ret <16 x i8> %tmp5
}

define <8 x i16> @vabaQs16(ptr %A, ptr %B, ptr %C) nounwind {
; CHECK-LABEL: vabaQs16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r2]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r1]
; CHECK-NEXT:    vld1.64 {d0, d1}, [r0]
; CHECK-NEXT:    vaba.s16 q0, q9, q8
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i16>, ptr %A
	%tmp2 = load <8 x i16>, ptr %B
	%tmp3 = load <8 x i16>, ptr %C
	%tmp4 = call <8 x i16> @llvm.arm.neon.vabds.v8i16(<8 x i16> %tmp2, <8 x i16> %tmp3)
	%tmp5 = add <8 x i16> %tmp1, %tmp4
	ret <8 x i16> %tmp5
}

define <4 x i32> @vabaQs32(ptr %A, ptr %B, ptr %C) nounwind {
; CHECK-LABEL: vabaQs32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r2]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r1]
; CHECK-NEXT:    vld1.64 {d0, d1}, [r0]
; CHECK-NEXT:    vaba.s32 q0, q9, q8
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i32>, ptr %A
	%tmp2 = load <4 x i32>, ptr %B
	%tmp3 = load <4 x i32>, ptr %C
	%tmp4 = call <4 x i32> @llvm.arm.neon.vabds.v4i32(<4 x i32> %tmp2, <4 x i32> %tmp3)
	%tmp5 = add <4 x i32> %tmp1, %tmp4
	ret <4 x i32> %tmp5
}

define <16 x i8> @vabaQu8(ptr %A, ptr %B, ptr %C) nounwind {
; CHECK-LABEL: vabaQu8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r2]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r1]
; CHECK-NEXT:    vld1.64 {d0, d1}, [r0]
; CHECK-NEXT:    vaba.u8 q0, q9, q8
; CHECK-NEXT:    bx lr
	%tmp1 = load <16 x i8>, ptr %A
	%tmp2 = load <16 x i8>, ptr %B
	%tmp3 = load <16 x i8>, ptr %C
	%tmp4 = call <16 x i8> @llvm.arm.neon.vabdu.v16i8(<16 x i8> %tmp2, <16 x i8> %tmp3)
	%tmp5 = add <16 x i8> %tmp1, %tmp4
	ret <16 x i8> %tmp5
}

define <8 x i16> @vabaQu16(ptr %A, ptr %B, ptr %C) nounwind {
; CHECK-LABEL: vabaQu16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r2]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r1]
; CHECK-NEXT:    vld1.64 {d0, d1}, [r0]
; CHECK-NEXT:    vaba.u16 q0, q9, q8
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i16>, ptr %A
	%tmp2 = load <8 x i16>, ptr %B
	%tmp3 = load <8 x i16>, ptr %C
	%tmp4 = call <8 x i16> @llvm.arm.neon.vabdu.v8i16(<8 x i16> %tmp2, <8 x i16> %tmp3)
	%tmp5 = add <8 x i16> %tmp1, %tmp4
	ret <8 x i16> %tmp5
}

define <4 x i32> @vabaQu32(ptr %A, ptr %B, ptr %C) nounwind {
; CHECK-LABEL: vabaQu32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r2]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r1]
; CHECK-NEXT:    vld1.64 {d0, d1}, [r0]
; CHECK-NEXT:    vaba.u32 q0, q9, q8
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i32>, ptr %A
	%tmp2 = load <4 x i32>, ptr %B
	%tmp3 = load <4 x i32>, ptr %C
	%tmp4 = call <4 x i32> @llvm.arm.neon.vabdu.v4i32(<4 x i32> %tmp2, <4 x i32> %tmp3)
	%tmp5 = add <4 x i32> %tmp1, %tmp4
	ret <4 x i32> %tmp5
}

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(ptr %A, ptr %B, ptr %C) nounwind {
; CHECK-LABEL: vabals8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r2]
; CHECK-NEXT:    vldr d17, [r1]
; CHECK-NEXT:    vld1.64 {d0, d1}, [r0]
; CHECK-NEXT:    vabal.s8 q0, d17, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i16>, ptr %A
	%tmp2 = load <8 x i8>, ptr %B
	%tmp3 = load <8 x i8>, ptr %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(ptr %A, ptr %B, ptr %C) nounwind {
; CHECK-LABEL: vabals16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r2]
; CHECK-NEXT:    vldr d17, [r1]
; CHECK-NEXT:    vld1.64 {d0, d1}, [r0]
; CHECK-NEXT:    vabal.s16 q0, d17, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i32>, ptr %A
	%tmp2 = load <4 x i16>, ptr %B
	%tmp3 = load <4 x i16>, ptr %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(ptr %A, ptr %B, ptr %C) nounwind {
; CHECK-LABEL: vabals32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r2]
; CHECK-NEXT:    vldr d17, [r1]
; CHECK-NEXT:    vld1.64 {d0, d1}, [r0]
; CHECK-NEXT:    vabal.s32 q0, d17, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <2 x i64>, ptr %A
	%tmp2 = load <2 x i32>, ptr %B
	%tmp3 = load <2 x i32>, ptr %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
}

define <8 x i16> @vabalu8(ptr %A, ptr %B, ptr %C) nounwind {
; CHECK-LABEL: vabalu8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r2]
; CHECK-NEXT:    vldr d17, [r1]
; CHECK-NEXT:    vld1.64 {d0, d1}, [r0]
; CHECK-NEXT:    vabal.u8 q0, d17, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i16>, ptr %A
	%tmp2 = load <8 x i8>, ptr %B
	%tmp3 = load <8 x i8>, ptr %C
	%tmp4 = call <8 x i8> @llvm.arm.neon.vabdu.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> @vabalu16(ptr %A, ptr %B, ptr %C) nounwind {
; CHECK-LABEL: vabalu16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r2]
; CHECK-NEXT:    vldr d17, [r1]
; CHECK-NEXT:    vld1.64 {d0, d1}, [r0]
; CHECK-NEXT:    vabal.u16 q0, d17, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i32>, ptr %A
	%tmp2 = load <4 x i16>, ptr %B
	%tmp3 = load <4 x i16>, ptr %C
	%tmp4 = call <4 x i16> @llvm.arm.neon.vabdu.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> @vabalu32(ptr %A, ptr %B, ptr %C) nounwind {
; CHECK-LABEL: vabalu32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r2]
; CHECK-NEXT:    vldr d17, [r1]
; CHECK-NEXT:    vld1.64 {d0, d1}, [r0]
; CHECK-NEXT:    vabal.u32 q0, d17, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <2 x i64>, ptr %A
	%tmp2 = load <2 x i32>, ptr %B
	%tmp3 = load <2 x i32>, ptr %C
	%tmp4 = call <2 x i32> @llvm.arm.neon.vabdu.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
}