test/CodeGen/ARM/vpadd.ll

; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s

define <8 x i8> @vpaddi8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
;CHECK: vpaddi8:
;CHECK: vpadd.i8
	%tmp1 = load <8 x i8>* %A
	%tmp2 = load <8 x i8>* %B
	%tmp3 = call <8 x i8> @llvm.arm.neon.vpadd.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
	ret <8 x i8> %tmp3
}

define <4 x i16> @vpaddi16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
;CHECK: vpaddi16:
;CHECK: vpadd.i16
	%tmp1 = load <4 x i16>* %A
	%tmp2 = load <4 x i16>* %B
	%tmp3 = call <4 x i16> @llvm.arm.neon.vpadd.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
	ret <4 x i16> %tmp3
}

define <2 x i32> @vpaddi32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
;CHECK: vpaddi32:
;CHECK: vpadd.i32
	%tmp1 = load <2 x i32>* %A
	%tmp2 = load <2 x i32>* %B
	%tmp3 = call <2 x i32> @llvm.arm.neon.vpadd.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
	ret <2 x i32> %tmp3
}

define <2 x float> @vpaddf32(<2 x float>* %A, <2 x float>* %B) nounwind {
;CHECK: vpaddf32:
;CHECK: vpadd.f32
	%tmp1 = load <2 x float>* %A
	%tmp2 = load <2 x float>* %B
	%tmp3 = call <2 x float> @llvm.arm.neon.vpadd.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
	ret <2 x float> %tmp3
}

declare <8 x i8>  @llvm.arm.neon.vpadd.v8i8(<8 x i8>, <8 x i8>) nounwind readnone
declare <4 x i16> @llvm.arm.neon.vpadd.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
declare <2 x i32> @llvm.arm.neon.vpadd.v2i32(<2 x i32>, <2 x i32>) nounwind readnone

declare <2 x float> @llvm.arm.neon.vpadd.v2f32(<2 x float>, <2 x float>) nounwind readnone