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

define <8 x i8> @vqrshls8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
;CHECK: vqrshls8:
;CHECK: vqrshl.s8
	%tmp1 = load <8 x i8>* %A
	%tmp2 = load <8 x i8>* %B
	%tmp3 = call <8 x i8> @llvm.arm.neon.vqrshifts.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
	ret <8 x i8> %tmp3
}

define <4 x i16> @vqrshls16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
;CHECK: vqrshls16:
;CHECK: vqrshl.s16
	%tmp1 = load <4 x i16>* %A
	%tmp2 = load <4 x i16>* %B
	%tmp3 = call <4 x i16> @llvm.arm.neon.vqrshifts.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
	ret <4 x i16> %tmp3
}

define <2 x i32> @vqrshls32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
;CHECK: vqrshls32:
;CHECK: vqrshl.s32
	%tmp1 = load <2 x i32>* %A
	%tmp2 = load <2 x i32>* %B
	%tmp3 = call <2 x i32> @llvm.arm.neon.vqrshifts.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
	ret <2 x i32> %tmp3
}

define <1 x i64> @vqrshls64(<1 x i64>* %A, <1 x i64>* %B) nounwind {
;CHECK: vqrshls64:
;CHECK: vqrshl.s64
	%tmp1 = load <1 x i64>* %A
	%tmp2 = load <1 x i64>* %B
	%tmp3 = call <1 x i64> @llvm.arm.neon.vqrshifts.v1i64(<1 x i64> %tmp1, <1 x i64> %tmp2)
	ret <1 x i64> %tmp3
}

define <8 x i8> @vqrshlu8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
;CHECK: vqrshlu8:
;CHECK: vqrshl.u8
	%tmp1 = load <8 x i8>* %A
	%tmp2 = load <8 x i8>* %B
	%tmp3 = call <8 x i8> @llvm.arm.neon.vqrshiftu.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
	ret <8 x i8> %tmp3
}

define <4 x i16> @vqrshlu16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
;CHECK: vqrshlu16:
;CHECK: vqrshl.u16
	%tmp1 = load <4 x i16>* %A
	%tmp2 = load <4 x i16>* %B
	%tmp3 = call <4 x i16> @llvm.arm.neon.vqrshiftu.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
	ret <4 x i16> %tmp3
}

define <2 x i32> @vqrshlu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
;CHECK: vqrshlu32:
;CHECK: vqrshl.u32
	%tmp1 = load <2 x i32>* %A
	%tmp2 = load <2 x i32>* %B
	%tmp3 = call <2 x i32> @llvm.arm.neon.vqrshiftu.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
	ret <2 x i32> %tmp3
}

define <1 x i64> @vqrshlu64(<1 x i64>* %A, <1 x i64>* %B) nounwind {
;CHECK: vqrshlu64:
;CHECK: vqrshl.u64
	%tmp1 = load <1 x i64>* %A
	%tmp2 = load <1 x i64>* %B
	%tmp3 = call <1 x i64> @llvm.arm.neon.vqrshiftu.v1i64(<1 x i64> %tmp1, <1 x i64> %tmp2)
	ret <1 x i64> %tmp3
}

define <16 x i8> @vqrshlQs8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
;CHECK: vqrshlQs8:
;CHECK: vqrshl.s8
	%tmp1 = load <16 x i8>* %A
	%tmp2 = load <16 x i8>* %B
	%tmp3 = call <16 x i8> @llvm.arm.neon.vqrshifts.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
	ret <16 x i8> %tmp3
}

define <8 x i16> @vqrshlQs16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
;CHECK: vqrshlQs16:
;CHECK: vqrshl.s16
	%tmp1 = load <8 x i16>* %A
	%tmp2 = load <8 x i16>* %B
	%tmp3 = call <8 x i16> @llvm.arm.neon.vqrshifts.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
	ret <8 x i16> %tmp3
}

define <4 x i32> @vqrshlQs32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
;CHECK: vqrshlQs32:
;CHECK: vqrshl.s32
	%tmp1 = load <4 x i32>* %A
	%tmp2 = load <4 x i32>* %B
	%tmp3 = call <4 x i32> @llvm.arm.neon.vqrshifts.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
	ret <4 x i32> %tmp3
}

define <2 x i64> @vqrshlQs64(<2 x i64>* %A, <2 x i64>* %B) nounwind {
;CHECK: vqrshlQs64:
;CHECK: vqrshl.s64
	%tmp1 = load <2 x i64>* %A
	%tmp2 = load <2 x i64>* %B
	%tmp3 = call <2 x i64> @llvm.arm.neon.vqrshifts.v2i64(<2 x i64> %tmp1, <2 x i64> %tmp2)
	ret <2 x i64> %tmp3
}

define <16 x i8> @vqrshlQu8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
;CHECK: vqrshlQu8:
;CHECK: vqrshl.u8
	%tmp1 = load <16 x i8>* %A
	%tmp2 = load <16 x i8>* %B
	%tmp3 = call <16 x i8> @llvm.arm.neon.vqrshiftu.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
	ret <16 x i8> %tmp3
}

define <8 x i16> @vqrshlQu16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
;CHECK: vqrshlQu16:
;CHECK: vqrshl.u16
	%tmp1 = load <8 x i16>* %A
	%tmp2 = load <8 x i16>* %B
	%tmp3 = call <8 x i16> @llvm.arm.neon.vqrshiftu.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
	ret <8 x i16> %tmp3
}

define <4 x i32> @vqrshlQu32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
;CHECK: vqrshlQu32:
;CHECK: vqrshl.u32
	%tmp1 = load <4 x i32>* %A
	%tmp2 = load <4 x i32>* %B
	%tmp3 = call <4 x i32> @llvm.arm.neon.vqrshiftu.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
	ret <4 x i32> %tmp3
}

define <2 x i64> @vqrshlQu64(<2 x i64>* %A, <2 x i64>* %B) nounwind {
;CHECK: vqrshlQu64:
;CHECK: vqrshl.u64
	%tmp1 = load <2 x i64>* %A
	%tmp2 = load <2 x i64>* %B
	%tmp3 = call <2 x i64> @llvm.arm.neon.vqrshiftu.v2i64(<2 x i64> %tmp1, <2 x i64> %tmp2)
	ret <2 x i64> %tmp3
}

declare <8 x i8>  @llvm.arm.neon.vqrshifts.v8i8(<8 x i8>, <8 x i8>) nounwind readnone
declare <4 x i16> @llvm.arm.neon.vqrshifts.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
declare <2 x i32> @llvm.arm.neon.vqrshifts.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
declare <1 x i64> @llvm.arm.neon.vqrshifts.v1i64(<1 x i64>, <1 x i64>) nounwind readnone

declare <8 x i8>  @llvm.arm.neon.vqrshiftu.v8i8(<8 x i8>, <8 x i8>) nounwind readnone
declare <4 x i16> @llvm.arm.neon.vqrshiftu.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
declare <2 x i32> @llvm.arm.neon.vqrshiftu.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
declare <1 x i64> @llvm.arm.neon.vqrshiftu.v1i64(<1 x i64>, <1 x i64>) nounwind readnone

declare <16 x i8> @llvm.arm.neon.vqrshifts.v16i8(<16 x i8>, <16 x i8>) nounwind readnone
declare <8 x i16> @llvm.arm.neon.vqrshifts.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
declare <4 x i32> @llvm.arm.neon.vqrshifts.v4i32(<4 x i32>, <4 x i32>) nounwind readnone
declare <2 x i64> @llvm.arm.neon.vqrshifts.v2i64(<2 x i64>, <2 x i64>) nounwind readnone

declare <16 x i8> @llvm.arm.neon.vqrshiftu.v16i8(<16 x i8>, <16 x i8>) nounwind readnone
declare <8 x i16> @llvm.arm.neon.vqrshiftu.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
declare <4 x i32> @llvm.arm.neon.vqrshiftu.v4i32(<4 x i32>, <4 x i32>) nounwind readnone
declare <2 x i64> @llvm.arm.neon.vqrshiftu.v2i64(<2 x i64>, <2 x i64>) nounwind readnone