; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+mve,+fullfp16 -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-MVE
; RUN: llc -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+mve.fp -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-MVEFP

define arm_aapcs_vfpcc <4 x i32> @shuffle1_i32(<4 x i32> %src) {
; CHECK-LABEL: shuffle1_i32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmov.f32 s4, s3
; CHECK-NEXT:    vmov.f32 s5, s2
; CHECK-NEXT:    vmov.f32 s6, s1
; CHECK-NEXT:    vmov.f32 s7, s0
; CHECK-NEXT:    vmov q0, q1
; CHECK-NEXT:    bx lr
entry:
  %out = shufflevector <4 x i32> %src, <4 x i32> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
  ret <4 x i32> %out
}

define arm_aapcs_vfpcc <4 x i32> @shuffle2_i32(<4 x i32> %src) {
; CHECK-LABEL: shuffle2_i32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    bx lr
entry:
  %out = shufflevector <4 x i32> %src, <4 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  ret <4 x i32> %out
}

define arm_aapcs_vfpcc <4 x i32> @shuffle3_i32(<4 x i32> %src) {
; CHECK-LABEL: shuffle3_i32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmov.f32 s4, s3
; CHECK-NEXT:    vmov.f32 s5, s1
; CHECK-NEXT:    vmov.f32 s6, s2
; CHECK-NEXT:    vmov.f32 s7, s0
; CHECK-NEXT:    vmov q0, q1
; CHECK-NEXT:    bx lr
entry:
  %out = shufflevector <4 x i32> %src, <4 x i32> undef, <4 x i32> <i32 3, i32 1, i32 2, i32 0>
  ret <4 x i32> %out
}

define arm_aapcs_vfpcc <4 x i32> @shuffle5_i32(<4 x i32> %src) {
; CHECK-LABEL: shuffle5_i32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vrev64.32 q0, q0
; CHECK-NEXT:    bx lr
entry:
  %out = shufflevector <4 x i32> %src, <4 x i32> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
  ret <4 x i32> %out
}

define arm_aapcs_vfpcc <4 x i32> @shuffle6_i32(<4 x i32> %src) {
; CHECK-LABEL: shuffle6_i32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    bx lr
entry:
  %out = shufflevector <4 x i32> %src, <4 x i32> undef, <4 x i32> <i32 undef, i32 undef, i32 undef, i32 3>
  ret <4 x i32> %out
}

define arm_aapcs_vfpcc <8 x i16> @shuffle1_i16(<8 x i16> %src) {
; CHECK-LABEL: shuffle1_i16:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmov q1, q0
; CHECK-NEXT:    vmov.u16 r0, q0[7]
; CHECK-NEXT:    vmov.16 q0[0], r0
; CHECK-NEXT:    vmov.u16 r0, q1[6]
; CHECK-NEXT:    vmov.16 q0[1], r0
; CHECK-NEXT:    vmov.u16 r0, q1[5]
; CHECK-NEXT:    vmov.16 q0[2], r0
; CHECK-NEXT:    vmov.u16 r0, q1[4]
; CHECK-NEXT:    vmov.16 q0[3], r0
; CHECK-NEXT:    vmov.u16 r0, q1[3]
; CHECK-NEXT:    vmov.16 q0[4], r0
; CHECK-NEXT:    vmov.u16 r0, q1[2]
; CHECK-NEXT:    vmov.16 q0[5], r0
; CHECK-NEXT:    vmov.u16 r0, q1[1]
; CHECK-NEXT:    vmov.16 q0[6], r0
; CHECK-NEXT:    vmov.u16 r0, q1[0]
; CHECK-NEXT:    vmov.16 q0[7], r0
; CHECK-NEXT:    bx lr
entry:
  %out = shufflevector <8 x i16> %src, <8 x i16> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
  ret <8 x i16> %out
}

define arm_aapcs_vfpcc <8 x i16> @shuffle2_i16(<8 x i16> %src) {
; CHECK-LABEL: shuffle2_i16:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    bx lr
entry:
  %out = shufflevector <8 x i16> %src, <8 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
  ret <8 x i16> %out
}

define arm_aapcs_vfpcc <8 x i16> @shuffle3_i16(<8 x i16> %src) {
; CHECK-LABEL: shuffle3_i16:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmov q1, q0
; CHECK-NEXT:    vmov.u16 r0, q0[4]
; CHECK-NEXT:    vmov.16 q0[0], r0
; CHECK-NEXT:    vmov.u16 r0, q1[5]
; CHECK-NEXT:    vmov.16 q0[1], r0
; CHECK-NEXT:    vmov.u16 r0, q1[7]
; CHECK-NEXT:    vmov.16 q0[2], r0
; CHECK-NEXT:    vmov.u16 r0, q1[6]
; CHECK-NEXT:    vmov.16 q0[3], r0
; CHECK-NEXT:    vmov.u16 r0, q1[3]
; CHECK-NEXT:    vmov.16 q0[4], r0
; CHECK-NEXT:    vmov.u16 r0, q1[1]
; CHECK-NEXT:    vmov.16 q0[5], r0
; CHECK-NEXT:    vmov.u16 r0, q1[2]
; CHECK-NEXT:    vmov.16 q0[6], r0
; CHECK-NEXT:    vmov.u16 r0, q1[0]
; CHECK-NEXT:    vmov.16 q0[7], r0
; CHECK-NEXT:    bx lr
entry:
  %out = shufflevector <8 x i16> %src, <8 x i16> undef, <8 x i32> <i32 4, i32 5, i32 7, i32 6, i32 3, i32 1, i32 2, i32 0>
  ret <8 x i16> %out
}

define arm_aapcs_vfpcc <8 x i16> @shuffle5_i16(<8 x i16> %src) {
; CHECK-LABEL: shuffle5_i16:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vrev64.16 q0, q0
; CHECK-NEXT:    bx lr
entry:
  %out = shufflevector <8 x i16> %src, <8 x i16> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
  ret <8 x i16> %out
}

define arm_aapcs_vfpcc <8 x i16> @shuffle6_i16(<8 x i16> %src) {
; CHECK-LABEL: shuffle6_i16:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vrev32.16 q0, q0
; CHECK-NEXT:    bx lr
entry:
  %out = shufflevector <8 x i16> %src, <8 x i16> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
  ret <8 x i16> %out
}

define arm_aapcs_vfpcc <16 x i8> @shuffle1_i8(<16 x i8> %src) {
; CHECK-LABEL: shuffle1_i8:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmov q1, q0
; CHECK-NEXT:    vmov.u8 r0, q0[15]
; CHECK-NEXT:    vmov.8 q0[0], r0
; CHECK-NEXT:    vmov.u8 r0, q1[14]
; CHECK-NEXT:    vmov.8 q0[1], r0
; CHECK-NEXT:    vmov.u8 r0, q1[13]
; CHECK-NEXT:    vmov.8 q0[2], r0
; CHECK-NEXT:    vmov.u8 r0, q1[12]
; CHECK-NEXT:    vmov.8 q0[3], r0
; CHECK-NEXT:    vmov.u8 r0, q1[11]
; CHECK-NEXT:    vmov.8 q0[4], r0
; CHECK-NEXT:    vmov.u8 r0, q1[10]
; CHECK-NEXT:    vmov.8 q0[5], r0
; CHECK-NEXT:    vmov.u8 r0, q1[9]
; CHECK-NEXT:    vmov.8 q0[6], r0
; CHECK-NEXT:    vmov.u8 r0, q1[8]
; CHECK-NEXT:    vmov.8 q0[7], r0
; CHECK-NEXT:    vmov.u8 r0, q1[7]
; CHECK-NEXT:    vmov.8 q0[8], r0
; CHECK-NEXT:    vmov.u8 r0, q1[6]
; CHECK-NEXT:    vmov.8 q0[9], r0
; CHECK-NEXT:    vmov.u8 r0, q1[5]
; CHECK-NEXT:    vmov.8 q0[10], r0
; CHECK-NEXT:    vmov.u8 r0, q1[4]
; CHECK-NEXT:    vmov.8 q0[11], r0
; CHECK-NEXT:    vmov.u8 r0, q1[3]
; CHECK-NEXT:    vmov.8 q0[12], r0
; CHECK-NEXT:    vmov.u8 r0, q1[2]
; CHECK-NEXT:    vmov.8 q0[13], r0
; CHECK-NEXT:    vmov.u8 r0, q1[1]
; CHECK-NEXT:    vmov.8 q0[14], r0
; CHECK-NEXT:    vmov.u8 r0, q1[0]
; CHECK-NEXT:    vmov.8 q0[15], r0
; CHECK-NEXT:    bx lr
entry:
  %out = shufflevector <16 x i8> %src, <16 x i8> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
  ret <16 x i8> %out
}

define arm_aapcs_vfpcc <16 x i8> @shuffle2_i8(<16 x i8> %src) {
; CHECK-LABEL: shuffle2_i8:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    bx lr
entry:
  %out = shufflevector <16 x i8> %src, <16 x i8> undef, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
  ret <16 x i8> %out
}

define arm_aapcs_vfpcc <16 x i8> @shuffle3_i8(<16 x i8> %src) {
; CHECK-LABEL: shuffle3_i8:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmov q1, q0
; CHECK-NEXT:    vmov.u8 r0, q0[4]
; CHECK-NEXT:    vmov.8 q0[0], r0
; CHECK-NEXT:    vmov.u8 r0, q1[5]
; CHECK-NEXT:    vmov.8 q0[1], r0
; CHECK-NEXT:    vmov.u8 r0, q1[15]
; CHECK-NEXT:    vmov.8 q0[2], r0
; CHECK-NEXT:    vmov.u8 r0, q1[7]
; CHECK-NEXT:    vmov.8 q0[3], r0
; CHECK-NEXT:    vmov.u8 r0, q1[14]
; CHECK-NEXT:    vmov.8 q0[4], r0
; CHECK-NEXT:    vmov.u8 r0, q1[9]
; CHECK-NEXT:    vmov.8 q0[5], r0
; CHECK-NEXT:    vmov.u8 r0, q1[6]
; CHECK-NEXT:    vmov.8 q0[6], r0
; CHECK-NEXT:    vmov.u8 r0, q1[3]
; CHECK-NEXT:    vmov.8 q0[7], r0
; CHECK-NEXT:    vmov.u8 r0, q1[10]
; CHECK-NEXT:    vmov.8 q0[8], r0
; CHECK-NEXT:    vmov.u8 r0, q1[12]
; CHECK-NEXT:    vmov.8 q0[9], r0
; CHECK-NEXT:    vmov.u8 r0, q1[1]
; CHECK-NEXT:    vmov.8 q0[10], r0
; CHECK-NEXT:    vmov.u8 r0, q1[13]
; CHECK-NEXT:    vmov.8 q0[11], r0
; CHECK-NEXT:    vmov.u8 r0, q1[2]
; CHECK-NEXT:    vmov.8 q0[12], r0
; CHECK-NEXT:    vmov.u8 r0, q1[8]
; CHECK-NEXT:    vmov.8 q0[13], r0
; CHECK-NEXT:    vmov.u8 r0, q1[0]
; CHECK-NEXT:    vmov.8 q0[14], r0
; CHECK-NEXT:    vmov.u8 r0, q1[11]
; CHECK-NEXT:    vmov.8 q0[15], r0
; CHECK-NEXT:    bx lr
entry:
  %out = shufflevector <16 x i8> %src, <16 x i8> undef, <16 x i32> <i32 4, i32 5, i32 15, i32 7, i32 14, i32 9, i32 6, i32 3, i32 10, i32 12, i32 1, i32 13, i32 2, i32 8, i32 0, i32 11>
  ret <16 x i8> %out
}

define arm_aapcs_vfpcc <16 x i8> @shuffle5_i8(<16 x i8> %src) {
; CHECK-LABEL: shuffle5_i8:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vrev64.8 q0, q0
; CHECK-NEXT:    bx lr
entry:
  %out = shufflevector <16 x i8> %src, <16 x i8> undef, <16 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8>
  ret <16 x i8> %out
}

define arm_aapcs_vfpcc <16 x i8> @shuffle6_i8(<16 x i8> %src) {
; CHECK-LABEL: shuffle6_i8:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vrev32.8 q0, q0
; CHECK-NEXT:    bx lr
entry:
  %out = shufflevector <16 x i8> %src, <16 x i8> undef, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
  ret <16 x i8> %out
}

define arm_aapcs_vfpcc <16 x i8> @shuffle7_i8(<16 x i8> %src) {
; CHECK-LABEL: shuffle7_i8:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vrev16.8 q0, q0
; CHECK-NEXT:    bx lr
entry:
  %out = shufflevector <16 x i8> %src, <16 x i8> undef, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14>
  ret <16 x i8> %out
}

define arm_aapcs_vfpcc <4 x float> @shuffle1_f32(<4 x float> %src) {
; CHECK-LABEL: shuffle1_f32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmov.f32 s4, s3
; CHECK-NEXT:    vmov.f32 s5, s2
; CHECK-NEXT:    vmov.f32 s6, s1
; CHECK-NEXT:    vmov.f32 s7, s0
; CHECK-NEXT:    vmov q0, q1
; CHECK-NEXT:    bx lr
entry:
  %out = shufflevector <4 x float> %src, <4 x float> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
  ret <4 x float> %out
}

define arm_aapcs_vfpcc <4 x float> @shuffle2_f32(<4 x float> %src) {
; CHECK-LABEL: shuffle2_f32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    bx lr
entry:
  %out = shufflevector <4 x float> %src, <4 x float> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  ret <4 x float> %out
}

define arm_aapcs_vfpcc <4 x float> @shuffle3_f32(<4 x float> %src) {
; CHECK-LABEL: shuffle3_f32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmov.f32 s4, s3
; CHECK-NEXT:    vmov.f32 s5, s1
; CHECK-NEXT:    vmov.f32 s6, s2
; CHECK-NEXT:    vmov.f32 s7, s0
; CHECK-NEXT:    vmov q0, q1
; CHECK-NEXT:    bx lr
entry:
  %out = shufflevector <4 x float> %src, <4 x float> undef, <4 x i32> <i32 3, i32 1, i32 2, i32 0>
  ret <4 x float> %out
}

define arm_aapcs_vfpcc <4 x float> @shuffle5_f32(<4 x float> %src) {
; CHECK-LABEL: shuffle5_f32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vrev64.32 q0, q0
; CHECK-NEXT:    bx lr
entry:
  %out = shufflevector <4 x float> %src, <4 x float> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
  ret <4 x float> %out
}

define arm_aapcs_vfpcc <8 x half> @shuffle1_f16(<8 x half> %src) {
; CHECK-MVE-LABEL: shuffle1_f16:
; CHECK-MVE:       @ %bb.0: @ %entry
; CHECK-MVE-NEXT:    movs r2, #0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[7]
; CHECK-MVE-NEXT:    vdup.16 q1, r2
; CHECK-MVE-NEXT:    vmov.u16 r1, q0[6]
; CHECK-MVE-NEXT:    vmov.16 q1[0], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[5]
; CHECK-MVE-NEXT:    vmov.16 q1[1], r1
; CHECK-MVE-NEXT:    vmov.16 q1[2], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[4]
; CHECK-MVE-NEXT:    vmov.16 q1[3], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[3]
; CHECK-MVE-NEXT:    vmov.16 q1[4], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[2]
; CHECK-MVE-NEXT:    vmov.16 q1[5], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[1]
; CHECK-MVE-NEXT:    vmov.16 q1[6], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[0]
; CHECK-MVE-NEXT:    vmov.16 q1[7], r0
; CHECK-MVE-NEXT:    vmov q0, q1
; CHECK-MVE-NEXT:    bx lr
;
; CHECK-MVEFP-LABEL: shuffle1_f16:
; CHECK-MVEFP:       @ %bb.0: @ %entry
; CHECK-MVEFP-NEXT:    vmov.u16 r0, q0[7]
; CHECK-MVEFP-NEXT:    vmov.u16 r1, q0[6]
; CHECK-MVEFP-NEXT:    vmov.16 q1[0], r0
; CHECK-MVEFP-NEXT:    vmov.u16 r0, q0[5]
; CHECK-MVEFP-NEXT:    vmov.16 q1[1], r1
; CHECK-MVEFP-NEXT:    vmov.16 q1[2], r0
; CHECK-MVEFP-NEXT:    vmov.u16 r0, q0[4]
; CHECK-MVEFP-NEXT:    vmov.16 q1[3], r0
; CHECK-MVEFP-NEXT:    vmov.u16 r0, q0[3]
; CHECK-MVEFP-NEXT:    vmov.16 q1[4], r0
; CHECK-MVEFP-NEXT:    vmov.u16 r0, q0[2]
; CHECK-MVEFP-NEXT:    vmov.16 q1[5], r0
; CHECK-MVEFP-NEXT:    vmov.u16 r0, q0[1]
; CHECK-MVEFP-NEXT:    vmov.16 q1[6], r0
; CHECK-MVEFP-NEXT:    vmov.u16 r0, q0[0]
; CHECK-MVEFP-NEXT:    vmov.16 q1[7], r0
; CHECK-MVEFP-NEXT:    vmov q0, q1
; CHECK-MVEFP-NEXT:    bx lr
entry:
  %out = shufflevector <8 x half> %src, <8 x half> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
  ret <8 x half> %out
}

define arm_aapcs_vfpcc <8 x half> @shuffle2_f16(<8 x half> %src) {
; CHECK-LABEL: shuffle2_f16:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    bx lr
entry:
  %out = shufflevector <8 x half> %src, <8 x half> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
  ret <8 x half> %out
}

define arm_aapcs_vfpcc <8 x half> @shuffle3_f16(<8 x half> %src) {
; CHECK-MVE-LABEL: shuffle3_f16:
; CHECK-MVE:       @ %bb.0: @ %entry
; CHECK-MVE-NEXT:    movs r2, #0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[4]
; CHECK-MVE-NEXT:    vdup.16 q1, r2
; CHECK-MVE-NEXT:    vmov.u16 r1, q0[5]
; CHECK-MVE-NEXT:    vmov.16 q1[0], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[7]
; CHECK-MVE-NEXT:    vmov.16 q1[1], r1
; CHECK-MVE-NEXT:    vmov.16 q1[2], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[6]
; CHECK-MVE-NEXT:    vmov.16 q1[3], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[3]
; CHECK-MVE-NEXT:    vmov.16 q1[4], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[1]
; CHECK-MVE-NEXT:    vmov.16 q1[5], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[2]
; CHECK-MVE-NEXT:    vmov.16 q1[6], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[0]
; CHECK-MVE-NEXT:    vmov.16 q1[7], r0
; CHECK-MVE-NEXT:    vmov q0, q1
; CHECK-MVE-NEXT:    bx lr
;
; CHECK-MVEFP-LABEL: shuffle3_f16:
; CHECK-MVEFP:       @ %bb.0: @ %entry
; CHECK-MVEFP-NEXT:    vmov.u16 r0, q0[4]
; CHECK-MVEFP-NEXT:    vmov.u16 r1, q0[5]
; CHECK-MVEFP-NEXT:    vmov.16 q1[0], r0
; CHECK-MVEFP-NEXT:    vmov.u16 r0, q0[7]
; CHECK-MVEFP-NEXT:    vmov.16 q1[1], r1
; CHECK-MVEFP-NEXT:    vmov.16 q1[2], r0
; CHECK-MVEFP-NEXT:    vmov.u16 r0, q0[6]
; CHECK-MVEFP-NEXT:    vmov.16 q1[3], r0
; CHECK-MVEFP-NEXT:    vmov.u16 r0, q0[3]
; CHECK-MVEFP-NEXT:    vmov.16 q1[4], r0
; CHECK-MVEFP-NEXT:    vmov.u16 r0, q0[1]
; CHECK-MVEFP-NEXT:    vmov.16 q1[5], r0
; CHECK-MVEFP-NEXT:    vmov.u16 r0, q0[2]
; CHECK-MVEFP-NEXT:    vmov.16 q1[6], r0
; CHECK-MVEFP-NEXT:    vmov.u16 r0, q0[0]
; CHECK-MVEFP-NEXT:    vmov.16 q1[7], r0
; CHECK-MVEFP-NEXT:    vmov q0, q1
; CHECK-MVEFP-NEXT:    bx lr
entry:
  %out = shufflevector <8 x half> %src, <8 x half> undef, <8 x i32> <i32 4, i32 5, i32 7, i32 6, i32 3, i32 1, i32 2, i32 0>
  ret <8 x half> %out
}

define arm_aapcs_vfpcc <8 x half> @shuffle5_f16(<8 x half> %src) {
; CHECK-LABEL: shuffle5_f16:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vrev64.16 q0, q0
; CHECK-NEXT:    bx lr
entry:
  %out = shufflevector <8 x half> %src, <8 x half> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
  ret <8 x half> %out
}

define arm_aapcs_vfpcc <8 x half> @shuffle6_f16(<8 x half> %src) {
; CHECK-LABEL: shuffle6_f16:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vrev32.16 q0, q0
; CHECK-NEXT:    bx lr
entry:
  %out = shufflevector <8 x half> %src, <8 x half> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
  ret <8 x half> %out
}


define arm_aapcs_vfpcc <4 x i32> @insert_i32(i32 %a) {
; CHECK-LABEL: insert_i32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmov.32 q0[0], r0
; CHECK-NEXT:    bx lr
entry:
  %res = insertelement <4 x i32> undef, i32 %a, i32 0
  ret <4 x i32> %res
}

define arm_aapcs_vfpcc <8 x i16> @insert_i16(i16 %a) {
; CHECK-LABEL: insert_i16:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmov.16 q0[0], r0
; CHECK-NEXT:    bx lr
entry:
  %res = insertelement <8 x i16> undef, i16 %a, i32 0
  ret <8 x i16> %res
}

define arm_aapcs_vfpcc <16 x i8> @insert_i8(i8 %a) {
; CHECK-LABEL: insert_i8:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmov.8 q0[0], r0
; CHECK-NEXT:    bx lr
entry:
  %res = insertelement <16 x i8> undef, i8 %a, i32 0
  ret <16 x i8> %res
}

define arm_aapcs_vfpcc <4 x float> @insert_f32(float %a) {
; CHECK-LABEL: insert_f32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    @ kill: def $s0 killed $s0 def $q0
; CHECK-NEXT:    bx lr
entry:
  %res = insertelement <4 x float> undef, float %a, i32 0
  ret <4 x float> %res
}

; TODO: Calling convention needs fixing to pass half types directly to functions
define arm_aapcs_vfpcc <8 x half> @insert_f16(half *%aa) {
; CHECK-LABEL: insert_f16:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vldr.16 s0, [r0]
; CHECK-NEXT:    bx lr
entry:
  %a = load half, half* %aa
  %res = insertelement <8 x half> undef, half %a, i32 0
  ret <8 x half> %res
}

define arm_aapcs_vfpcc i64 @scalar_to_vector_i32(<8 x i16> %v) {
; CHECK-LABEL: scalar_to_vector_i32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .pad #8
; CHECK-NEXT:    sub sp, #8
; CHECK-NEXT:    adr r1, .LCPI30_0
; CHECK-NEXT:    vmov.u16 r0, q0[0]
; CHECK-NEXT:    vldrw.u32 q1, [r1]
; CHECK-NEXT:    vmov.32 q0[0], r0
; CHECK-NEXT:    mov r2, sp
; CHECK-NEXT:    vmov.f32 s1, s5
; CHECK-NEXT:    vmov.f32 s2, s6
; CHECK-NEXT:    vmov.f32 s3, s7
; CHECK-NEXT:    vstrh.32 q0, [r2]
; CHECK-NEXT:    ldrd r0, r1, [sp], #8
; CHECK-NEXT:    bx lr
; CHECK-NEXT:    .p2align 4
; CHECK-NEXT:  @ %bb.1:
; CHECK-NEXT:  .LCPI30_0:
; CHECK-NEXT:    .zero 4
; CHECK-NEXT:    .long 7 @ 0x7
; CHECK-NEXT:    .long 1 @ 0x1
; CHECK-NEXT:    .long 9 @ 0x9
entry:
  %f = shufflevector <8 x i16> %v, <8 x i16> <i16 undef, i16 7, i16 1, i16 9, i16 undef, i16 undef, i16 undef, i16 undef>, <4 x i32> <i32 0, i32 9, i32 10, i32 11>
  %0 = bitcast <4 x i16> %f to i64
  ret i64 %0
}


define arm_aapcs_vfpcc i32 @extract_i32_0(<4 x i32> %a) {
; CHECK-LABEL: extract_i32_0:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmov r0, s0
; CHECK-NEXT:    bx lr
entry:
  %res = extractelement <4 x i32> %a, i32 0
  ret i32 %res
}

define arm_aapcs_vfpcc i32 @extract_i32_3(<4 x i32> %a) {
; CHECK-LABEL: extract_i32_3:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmov r0, s3
; CHECK-NEXT:    bx lr
entry:
  %res = extractelement <4 x i32> %a, i32 3
  ret i32 %res
}

define arm_aapcs_vfpcc i16 @extract_i16_0(<8 x i16> %a) {
; CHECK-LABEL: extract_i16_0:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmov.u16 r0, q0[0]
; CHECK-NEXT:    bx lr
entry:
  %res = extractelement <8 x i16> %a, i32 0
  ret i16 %res
}

define arm_aapcs_vfpcc i16 @extract_i16_3(<8 x i16> %a) {
; CHECK-LABEL: extract_i16_3:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmov.u16 r0, q0[3]
; CHECK-NEXT:    bx lr
entry:
  %res = extractelement <8 x i16> %a, i32 3
  ret i16 %res
}

define arm_aapcs_vfpcc i8 @extract_i8_0(<16 x i8> %a) {
; CHECK-LABEL: extract_i8_0:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmov.u8 r0, q0[0]
; CHECK-NEXT:    bx lr
entry:
  %res = extractelement <16 x i8> %a, i32 0
  ret i8 %res
}

define arm_aapcs_vfpcc i8 @extract_i8_3(<16 x i8> %a) {
; CHECK-LABEL: extract_i8_3:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmov.u8 r0, q0[3]
; CHECK-NEXT:    bx lr
entry:
  %res = extractelement <16 x i8> %a, i32 3
  ret i8 %res
}

define arm_aapcs_vfpcc float @extract_f32_0(<4 x float> %a) {
; CHECK-LABEL: extract_f32_0:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    @ kill: def $s0 killed $s0 killed $q0
; CHECK-NEXT:    bx lr
entry:
  %res = extractelement <4 x float> %a, i32 0
  ret float %res
}

define arm_aapcs_vfpcc float @extract_f32_3(<4 x float> %a) {
; CHECK-LABEL: extract_f32_3:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmov.f32 s0, s3
; CHECK-NEXT:    bx lr
entry:
  %res = extractelement <4 x float> %a, i32 3
  ret float %res
}

define arm_aapcs_vfpcc half @extract_f16_0(<8 x half> %a) {
; CHECK-LABEL: extract_f16_0:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmov.u16 r1, q0[0]
; CHECK-NEXT:    vmov s0, r1
; CHECK-NEXT:    vstr.16 s0, [r0]
; CHECK-NEXT:    bx lr
entry:
  %res = extractelement <8 x half> %a, i32 0
  ret half %res
}

define arm_aapcs_vfpcc half @extract_f16_3(<8 x half> %a) {
; CHECK-LABEL: extract_f16_3:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmov.u16 r1, q0[3]
; CHECK-NEXT:    vmov s0, r1
; CHECK-NEXT:    vstr.16 s0, [r0]
; CHECK-NEXT:    bx lr
entry:
  %res = extractelement <8 x half> %a, i32 3
  ret half %res
}