; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=arm64-eabi -aarch64-neon-syntax=apple | FileCheck %s

define <8 x i8> @vzipi8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
; CHECK-LABEL: vzipi8:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ldr d0, [x0]
; CHECK-NEXT:    ldr d1, [x1]
; CHECK-NEXT:    zip1.8b v2, v0, v1
; CHECK-NEXT:    zip2.8b v0, v0, v1
; CHECK-NEXT:    add.8b v0, v2, v0
; CHECK-NEXT:    ret
  %tmp1 = load <8 x i8>, <8 x i8>* %A
  %tmp2 = load <8 x i8>, <8 x i8>* %B
  %tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
  %tmp4 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
  %tmp5 = add <8 x i8> %tmp3, %tmp4
  ret <8 x i8> %tmp5
}

define <4 x i16> @vzipi16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
; CHECK-LABEL: vzipi16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ldr d0, [x0]
; CHECK-NEXT:    ldr d1, [x1]
; CHECK-NEXT:    zip1.4h v2, v0, v1
; CHECK-NEXT:    zip2.4h v0, v0, v1
; CHECK-NEXT:    add.4h v0, v2, v0
; CHECK-NEXT:    ret
  %tmp1 = load <4 x i16>, <4 x i16>* %A
  %tmp2 = load <4 x i16>, <4 x i16>* %B
  %tmp3 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
  %tmp4 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
  %tmp5 = add <4 x i16> %tmp3, %tmp4
  ret <4 x i16> %tmp5
}

define <16 x i8> @vzipQi8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
; CHECK-LABEL: vzipQi8:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ldr q0, [x0]
; CHECK-NEXT:    ldr q1, [x1]
; CHECK-NEXT:    zip1.16b v2, v0, v1
; CHECK-NEXT:    zip2.16b v0, v0, v1
; CHECK-NEXT:    add.16b v0, v2, v0
; CHECK-NEXT:    ret
  %tmp1 = load <16 x i8>, <16 x i8>* %A
  %tmp2 = load <16 x i8>, <16 x i8>* %B
  %tmp3 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23>
  %tmp4 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>
  %tmp5 = add <16 x i8> %tmp3, %tmp4
  ret <16 x i8> %tmp5
}

define <8 x i16> @vzipQi16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
; CHECK-LABEL: vzipQi16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ldr q0, [x0]
; CHECK-NEXT:    ldr q1, [x1]
; CHECK-NEXT:    zip1.8h v2, v0, v1
; CHECK-NEXT:    zip2.8h v0, v0, v1
; CHECK-NEXT:    add.8h v0, v2, v0
; CHECK-NEXT:    ret
  %tmp1 = load <8 x i16>, <8 x i16>* %A
  %tmp2 = load <8 x i16>, <8 x i16>* %B
  %tmp3 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
  %tmp4 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
  %tmp5 = add <8 x i16> %tmp3, %tmp4
  ret <8 x i16> %tmp5
}

define <4 x i32> @vzipQi32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
; CHECK-LABEL: vzipQi32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ldr q0, [x0]
; CHECK-NEXT:    ldr q1, [x1]
; CHECK-NEXT:    zip1.4s v2, v0, v1
; CHECK-NEXT:    zip2.4s v0, v0, v1
; CHECK-NEXT:    add.4s v0, v2, v0
; CHECK-NEXT:    ret
  %tmp1 = load <4 x i32>, <4 x i32>* %A
  %tmp2 = load <4 x i32>, <4 x i32>* %B
  %tmp3 = shufflevector <4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
  %tmp4 = shufflevector <4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
  %tmp5 = add <4 x i32> %tmp3, %tmp4
  ret <4 x i32> %tmp5
}

define <4 x float> @vzipQf(<4 x float>* %A, <4 x float>* %B) nounwind {
; CHECK-LABEL: vzipQf:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ldr q0, [x0]
; CHECK-NEXT:    ldr q1, [x1]
; CHECK-NEXT:    zip1.4s v2, v0, v1
; CHECK-NEXT:    zip2.4s v0, v0, v1
; CHECK-NEXT:    fadd.4s v0, v2, v0
; CHECK-NEXT:    ret
  %tmp1 = load <4 x float>, <4 x float>* %A
  %tmp2 = load <4 x float>, <4 x float>* %B
  %tmp3 = shufflevector <4 x float> %tmp1, <4 x float> %tmp2, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
  %tmp4 = shufflevector <4 x float> %tmp1, <4 x float> %tmp2, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
  %tmp5 = fadd <4 x float> %tmp3, %tmp4
  ret <4 x float> %tmp5
}

; Undef shuffle indices should not prevent matching to VZIP:

define <8 x i8> @vzipi8_undef(<8 x i8>* %A, <8 x i8>* %B) nounwind {
; CHECK-LABEL: vzipi8_undef:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ldr d0, [x0]
; CHECK-NEXT:    ldr d1, [x1]
; CHECK-NEXT:    zip1.8b v2, v0, v1
; CHECK-NEXT:    zip2.8b v0, v0, v1
; CHECK-NEXT:    add.8b v0, v2, v0
; CHECK-NEXT:    ret
  %tmp1 = load <8 x i8>, <8 x i8>* %A
  %tmp2 = load <8 x i8>, <8 x i8>* %B
  %tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 0, i32 undef, i32 1, i32 9, i32 undef, i32 10, i32 3, i32 11>
  %tmp4 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 undef, i32 undef, i32 15>
  %tmp5 = add <8 x i8> %tmp3, %tmp4
  ret <8 x i8> %tmp5
}

define <16 x i8> @vzipQi8_undef(<16 x i8>* %A, <16 x i8>* %B) nounwind {
; CHECK-LABEL: vzipQi8_undef:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ldr q0, [x0]
; CHECK-NEXT:    ldr q1, [x1]
; CHECK-NEXT:    zip1.16b v2, v0, v1
; CHECK-NEXT:    zip2.16b v0, v0, v1
; CHECK-NEXT:    add.16b v0, v2, v0
; CHECK-NEXT:    ret
  %tmp1 = load <16 x i8>, <16 x i8>* %A
  %tmp2 = load <16 x i8>, <16 x i8>* %B
  %tmp3 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 0, i32 16, i32 1, i32 undef, i32 undef, i32 undef, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23>
  %tmp4 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 8, i32 24, i32 9, i32 undef, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 undef, i32 14, i32 30, i32 undef, i32 31>
  %tmp5 = add <16 x i8> %tmp3, %tmp4
  ret <16 x i8> %tmp5
}

define <16 x i8> @combine_v16i8(<8 x i8> %0, <8 x i8> %1) {
; CHECK-LABEL: combine_v16i8:
; CHECK:       // %bb.0:
; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
; CHECK-NEXT:    zip1.16b v0, v0, v1
; CHECK-NEXT:    ret
  %3 = shufflevector <8 x i8> %0, <8 x i8> %1, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
  ret <16 x i8> %3
}

define <16 x i8> @combine2_v16i8(<8 x i8> %0, <8 x i8> %1) {
; CHECK-LABEL: combine2_v16i8:
; CHECK:       // %bb.0:
; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
; CHECK-NEXT:    zip1.16b v0, v0, v1
; CHECK-NEXT:    ret
  %3 = shufflevector <8 x i8> %0, <8 x i8> %1, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
  %4 = shufflevector <8 x i8> %0, <8 x i8> %1, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
  %5 = shufflevector <8 x i8> %3, <8 x i8> %4, <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> %5
}

define <8 x i16> @combine_v8i16(<4 x i16> %0, <4 x i16> %1) {
; CHECK-LABEL: combine_v8i16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
; CHECK-NEXT:    zip1.8h v0, v0, v1
; CHECK-NEXT:    ret
  %3 = shufflevector <4 x i16> %0, <4 x i16> %1, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
  ret <8 x i16> %3
}

define <8 x i16> @combine2_v8i16(<4 x i16> %0, <4 x i16> %1) {
; CHECK-LABEL: combine2_v8i16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
; CHECK-NEXT:    zip1.8h v0, v0, v1
; CHECK-NEXT:    ret
  %3 = shufflevector <4 x i16> %0, <4 x i16> %1, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
  %4 = shufflevector <4 x i16> %0, <4 x i16> %1, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
  %5 = shufflevector <4 x i16> %3, <4 x i16> %4, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
  ret <8 x i16> %5
}

define <4 x i32> @combine_v4i32(<2 x i32> %0, <2 x i32> %1) {
; CHECK-LABEL: combine_v4i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
; CHECK-NEXT:    zip1.4s v0, v0, v1
; CHECK-NEXT:    ret
  %3 = shufflevector <2 x i32> %0, <2 x i32> %1, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
  ret <4 x i32> %3
}

define <4 x i32> @combine2_v4i32(<2 x i32> %0, <2 x i32> %1) {
; CHECK-LABEL: combine2_v4i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
; CHECK-NEXT:    zip1.4s v0, v0, v1
; CHECK-NEXT:    ret
  %3 = shufflevector <2 x i32> %0, <2 x i32> %1, <2 x i32> <i32 0, i32 2>
  %4 = shufflevector <2 x i32> %0, <2 x i32> %1, <2 x i32> <i32 1, i32 3>
  %5 = shufflevector <2 x i32> %3, <2 x i32> %4, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  ret <4 x i32> %5
}

define <16 x i8> @combine_v16i8_undef(<8 x i8> %0, <8 x i8> %1) {
; CHECK-LABEL: combine_v16i8_undef:
; CHECK:       // %bb.0:
; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
; CHECK-NEXT:    zip1.16b v0, v0, v1
; CHECK-NEXT:    ret
  %3 = shufflevector <8 x i8> %0, <8 x i8> %1, <16 x i32> <i32 0, i32 undef, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
  ret <16 x i8> %3
}

define <16 x i8> @combine2_v16i8_undef(<8 x i8> %0, <8 x i8> %1) {
; CHECK-LABEL: combine2_v16i8_undef:
; CHECK:       // %bb.0:
; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
; CHECK-NEXT:    zip1.16b v0, v0, v1
; CHECK-NEXT:    ret
  %3 = shufflevector <8 x i8> %0, <8 x i8> %1, <8 x i32> <i32 0, i32 undef, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
  %4 = shufflevector <8 x i8> %0, <8 x i8> %1, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
  %5 = shufflevector <8 x i8> %3, <8 x i8> %4, <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> %5
}

define <8 x i16> @combine_v8i16_undef(<4 x i16> %0, <4 x i16> %1) {
; CHECK-LABEL: combine_v8i16_undef:
; CHECK:       // %bb.0:
; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
; CHECK-NEXT:    zip1.8h v0, v0, v1
; CHECK-NEXT:    ret
  %3 = shufflevector <4 x i16> %0, <4 x i16> %1, <8 x i32> <i32 0, i32 undef, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
  ret <8 x i16> %3
}

; FIXME: This could be zip1 too, 8,0,9,1... pattern is handled
define <16 x i8> @combine_v8i16_8first(<8 x i8> %0, <8 x i8> %1) {
; CHECK-LABEL: combine_v8i16_8first:
; CHECK:       // %bb.0:
; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1_q2
; CHECK-NEXT:    adrp x8, .LCPI17_0
; CHECK-NEXT:    fmov d2, d0
; CHECK-NEXT:    ldr q3, [x8, :lo12:.LCPI17_0]
; CHECK-NEXT:    tbl.16b v0, { v1, v2 }, v3
; CHECK-NEXT:    ret
  %3 = shufflevector <8 x i8> %1, <8 x i8> %0, <16 x i32> <i32 8, i32 0, i32 9, i32 1, i32 10, i32 2, i32 11, i32 3, i32 12, i32 4, i32 13, i32 5, i32 14, i32 6, i32 15, i32 7>
  ret <16 x i8> %3
}


; FIXME: This could be zip1 too, 8,0,9,1... pattern is handled
define <16 x i8> @combine_v8i16_8firstundef(<8 x i8> %0, <8 x i8> %1) {
; CHECK-LABEL: combine_v8i16_8firstundef:
; CHECK:       // %bb.0:
; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1_q2
; CHECK-NEXT:    adrp x8, .LCPI18_0
; CHECK-NEXT:    fmov d2, d0
; CHECK-NEXT:    ldr q3, [x8, :lo12:.LCPI18_0]
; CHECK-NEXT:    tbl.16b v0, { v1, v2 }, v3
; CHECK-NEXT:    ret
  %3 = shufflevector <8 x i8> %1, <8 x i8> %0, <16 x i32> <i32 8, i32 0, i32 9, i32 1, i32 10, i32 2, i32 11, i32 3, i32 12, i32 4, i32 13, i32 5, i32 14, i32 6, i32 15, i32 undef>
  ret <16 x i8> %3
}

define <4 x float> @shuffle_zip1(<4 x float> %arg) {
; CHECK-LABEL: shuffle_zip1:
; CHECK:       // %bb.0: // %bb
; CHECK-NEXT:    movi.2d v1, #0000000000000000
; CHECK-NEXT:    fcmgt.4s v0, v0, v1
; CHECK-NEXT:    uzp1.8h v1, v0, v0
; CHECK-NEXT:    xtn.4h v0, v0
; CHECK-NEXT:    xtn.4h v1, v1
; CHECK-NEXT:    zip2.4h v0, v0, v1
; CHECK-NEXT:    fmov.4s v1, #1.00000000
; CHECK-NEXT:    zip1.4h v0, v0, v0
; CHECK-NEXT:    sshll.4s v0, v0, #0
; CHECK-NEXT:    and.16b v0, v1, v0
; CHECK-NEXT:    ret
bb:
  %inst = fcmp olt <4 x float> zeroinitializer, %arg
  %inst1 = shufflevector <4 x i1> %inst, <4 x i1> zeroinitializer, <2 x i32> <i32 2, i32 0>
  %inst2 = shufflevector <2 x i1> %inst1, <2 x i1> zeroinitializer, <4 x i32> <i32 0, i32 0, i32 1, i32 1>
  %inst3 = select <4 x i1> %inst2, <4 x float> <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>, <4 x float> zeroinitializer
  ret <4 x float> %inst3
}

define <4 x i32> @shuffle_zip2(<4 x i32> %arg) {
; CHECK-LABEL: shuffle_zip2:
; CHECK:       // %bb.0: // %bb
; CHECK-NEXT:    cmtst.4s v0, v0, v0
; CHECK-NEXT:    uzp1.8h v1, v0, v0
; CHECK-NEXT:    xtn.4h v0, v0
; CHECK-NEXT:    xtn.4h v1, v1
; CHECK-NEXT:    zip2.4h v0, v0, v1
; CHECK-NEXT:    movi.4s v1, #1
; CHECK-NEXT:    zip1.4h v0, v0, v0
; CHECK-NEXT:    ushll.4s v0, v0, #0
; CHECK-NEXT:    and.16b v0, v0, v1
; CHECK-NEXT:    ret
bb:
  %inst = icmp ult <4 x i32> zeroinitializer, %arg
  %inst1 = shufflevector <4 x i1> %inst, <4 x i1> zeroinitializer, <2 x i32> <i32 2, i32 0>
  %inst2 = shufflevector <2 x i1> %inst1, <2 x i1> zeroinitializer, <4 x i32> <i32 0, i32 0, i32 1, i32 1>
  %inst3 = select <4 x i1> %inst2, <4 x i32> <i32 1, i32 1, i32 1, i32 1>, <4 x i32> zeroinitializer
  ret <4 x i32> %inst3
}

define <4 x i32> @shuffle_zip3(<4 x i32> %arg) {
; CHECK-LABEL: shuffle_zip3:
; CHECK:       // %bb.0: // %bb
; CHECK-NEXT:    cmgt.4s v0, v0, #0
; CHECK-NEXT:    uzp1.8h v1, v0, v0
; CHECK-NEXT:    xtn.4h v0, v0
; CHECK-NEXT:    xtn.4h v1, v1
; CHECK-NEXT:    zip2.4h v0, v0, v1
; CHECK-NEXT:    movi.4s v1, #1
; CHECK-NEXT:    zip1.4h v0, v0, v0
; CHECK-NEXT:    sshll.4s v0, v0, #0
; CHECK-NEXT:    and.16b v0, v0, v1
; CHECK-NEXT:    ret
bb:
  %inst = icmp slt <4 x i32> zeroinitializer, %arg
  %inst1 = shufflevector <4 x i1> %inst, <4 x i1> zeroinitializer, <2 x i32> <i32 2, i32 0>
  %inst2 = shufflevector <2 x i1> %inst1, <2 x i1> zeroinitializer, <4 x i32> <i32 0, i32 0, i32 1, i32 1>
  %inst3 = select <4 x i1> %inst2, <4 x i32> <i32 1, i32 1, i32 1, i32 1>, <4 x i32> zeroinitializer
  ret <4 x i32> %inst3
}