# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve -run-pass=arm-low-overhead-loops %s -o - --verify-machineinstrs | FileCheck %s

# TODO: We should be able to handle the VCMP -> VPST -> VCMP -> VCTP case.

--- |
  define dso_local arm_aapcs_vfpcc void @test(i32* noalias nocapture %a, i32* nocapture readonly %b, i32 %N) local_unnamed_addr #0 {
  entry:
    %cmp9 = icmp eq i32 %N, 0
    %tmp = add i32 %N, 3
    %tmp1 = lshr i32 %tmp, 2
    %tmp2 = shl nuw i32 %tmp1, 2
    %tmp3 = add i32 %tmp2, -4
    %tmp4 = lshr i32 %tmp3, 2
    %tmp5 = add nuw nsw i32 %tmp4, 1
    br i1 %cmp9, label %for.cond.cleanup, label %vector.ph

  vector.ph:                                        ; preds = %entry
    %div = lshr i32 %N, 1
    %trip.count.minus.1 = add i32 %N, -1
    %broadcast.splatinsert = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
    %broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
    %start = call i32 @llvm.start.loop.iterations.i32(i32 %tmp5)
    br label %vector.body

  vector.body:                                      ; preds = %vector.body, %vector.ph
    %lsr.iv = phi i32 [ %lsr.iv.next, %vector.body ], [ %start, %vector.ph ]
    %lsr.iv3 = phi i32* [ %scevgep4, %vector.body ], [ %b, %vector.ph ]
    %lsr.iv1 = phi i32* [ %scevgep, %vector.body ], [ %a, %vector.ph ]
    %vec.ind = phi <4 x i32> [ <i32 0, i32 1, i32 2, i32 3>, %vector.ph ], [ %vec.ind.next, %vector.body ]
    %elts.rem = phi i32 [ %N, %vector.ph ], [ %elts.rem.next, %vector.body ]
    %lsr.iv12 = bitcast i32* %lsr.iv1 to <4 x i32>*
    %lsr.iv35 = bitcast i32* %lsr.iv3 to <4 x i32>*
    %tmp7 = insertelement <4 x i32> undef, i32 %div, i32 0
    %tmp8 = shufflevector <4 x i32> %tmp7, <4 x i32> undef, <4 x i32> zeroinitializer
    %tmp9 = icmp ult <4 x i32> %vec.ind, %tmp8
    %lower = icmp uge <4 x i32> %vec.ind, <i32 1, i32 1, i32 1, i32 1>
    %tmp10 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %elts.rem)
    %tmp11 = and <4 x i1> %tmp9, %tmp10
    %pred = and <4 x i1> %tmp11, %lower
    %wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv35, i32 4, <4 x i1> %pred, <4 x i32> undef)
    call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %wide.masked.load, <4 x i32>* %lsr.iv12, i32 4, <4 x i1> %pred)
    %vec.ind.next = add <4 x i32> %vec.ind, <i32 4, i32 4, i32 4, i32 4>
    %elts.rem.next = sub i32 %elts.rem, 4
    %scevgep = getelementptr i32, i32* %lsr.iv1, i32 4
    %scevgep4 = getelementptr i32, i32* %lsr.iv3, i32 4
    %tmp12 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %lsr.iv, i32 1)
    %tmp13 = icmp ne i32 %tmp12, 0
    %lsr.iv.next = add nsw i32 %lsr.iv, -1
    br i1 %tmp13, label %vector.body, label %for.cond.cleanup

  for.cond.cleanup:                                 ; preds = %vector.body, %entry
    ret void
  }

  declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32 immarg, <4 x i1>, <4 x i32>)
  declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32 immarg, <4 x i1>)
  declare <4 x i1> @llvm.arm.mve.vctp32(i32)
  declare i32 @llvm.start.loop.iterations.i32(i32)
  declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32)

...
---
name:            test
alignment:       16
tracksRegLiveness: true
registers:       []
liveins:
  - { reg: '$r0', virtual-reg: '' }
  - { reg: '$r1', virtual-reg: '' }
  - { reg: '$r2', virtual-reg: '' }
frameInfo:
  stackSize:       24
  offsetAdjustment: 0
  maxAlignment:    8
fixedStack:      []
stack:
  - { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$lr', callee-saved-restored: false,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
  - { id: 1, name: '', type: spill-slot, offset: -8, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$r4', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
  - { id: 2, name: '', type: spill-slot, offset: -16, size: 8, alignment: 8,
      stack-id: default, callee-saved-register: '$d9', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
  - { id: 3, name: '', type: spill-slot, offset: -24, size: 8, alignment: 8,
      stack-id: default, callee-saved-register: '$d8', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
callSites:       []
constants:
  - id:              0
    value:           '<4 x i32> <i32 0, i32 1, i32 2, i32 3>'
    alignment:       16
    isTargetSpecific: false
machineFunctionInfo: {}
body:             |
  ; CHECK-LABEL: name: test
  ; CHECK: bb.0.entry:
  ; CHECK:   successors: %bb.3(0x30000000), %bb.1(0x50000000)
  ; CHECK:   liveins: $lr, $d8, $d9, $r0, $r1, $r2, $r4
  ; CHECK:   frame-setup tPUSH 14 /* CC::al */, $noreg, killed $r4, killed $lr, implicit-def $sp, implicit $sp
  ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 8
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $lr, -4
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r4, -8
  ; CHECK:   $sp = frame-setup VSTMDDB_UPD $sp, 14 /* CC::al */, $noreg, killed $d8, killed $d9
  ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 24
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $d9, -16
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $d8, -24
  ; CHECK:   tCBZ $r2, %bb.3
  ; CHECK: bb.1.vector.ph:
  ; CHECK:   successors: %bb.2(0x80000000)
  ; CHECK:   liveins: $r0, $r1, $r2
  ; CHECK:   renamable $r3, dead $cpsr = tADDi3 renamable $r2, 3, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $q2 = MVE_VMOVimmi32 1, 0, $noreg, $noreg, undef renamable $q2
  ; CHECK:   renamable $r3 = t2BICri killed renamable $r3, 3, 14 /* CC::al */, $noreg, $noreg
  ; CHECK:   renamable $q3 = MVE_VMOVimmi32 4, 0, $noreg, $noreg, undef renamable $q3
  ; CHECK:   renamable $r12 = t2SUBri killed renamable $r3, 4, 14 /* CC::al */, $noreg, $noreg
  ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $r3 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
  ; CHECK:   dead $lr = t2DLS renamable $r3
  ; CHECK:   $r4 = tMOVr killed $r3, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $r3 = tLEApcrel %const.0, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $q0 = MVE_VLDRWU32 killed renamable $r3, 0, 0, $noreg, $noreg :: (load (s128) from constant-pool)
  ; CHECK:   renamable $r3, dead $cpsr = tLSRri renamable $r2, 1, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $q1 = MVE_VDUP32 killed renamable $r3, 0, $noreg, $noreg, undef renamable $q1
  ; CHECK: bb.2.vector.body:
  ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
  ; CHECK:   liveins: $q0, $q1, $q2, $q3, $r0, $r1, $r2, $r4
  ; CHECK:   $lr = tMOVr $r4, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $r4, dead $cpsr = nsw tSUBi8 killed $r4, 1, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $vpr = MVE_VCMPu32 renamable $q1, renamable $q0, 8, 0, $noreg, $noreg
  ; CHECK:   MVE_VPST 1, implicit $vpr
  ; CHECK:   renamable $vpr = MVE_VCMPu32 renamable $q0, renamable $q2, 2, 1, killed renamable $vpr, $noreg
  ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r2, 1, killed renamable $vpr, $noreg
  ; CHECK:   renamable $r1, renamable $q4 = MVE_VLDRWU32_post killed renamable $r1, 16, 1, renamable $vpr, $noreg :: (load (s128) from %ir.lsr.iv35, align 4)
  ; CHECK:   renamable $r0 = MVE_VSTRWU32_post killed renamable $q4, killed renamable $r0, 16, 1, killed renamable $vpr, $noreg :: (store (s128) into %ir.lsr.iv12, align 4)
  ; CHECK:   renamable $q0 = MVE_VADDi32 killed renamable $q0, renamable $q3, 0, $noreg, $noreg, undef renamable $q0
  ; CHECK:   dead $lr = t2LEUpdate killed renamable $lr, %bb.2
  ; CHECK: bb.3.for.cond.cleanup:
  ; CHECK:   $sp = frame-destroy VLDMDIA_UPD $sp, 14 /* CC::al */, $noreg, def $d8, def $d9
  ; CHECK:   frame-destroy tPOP_RET 14 /* CC::al */, $noreg, def $r4, def $pc
  ; CHECK: bb.4 (align 16):
  ; CHECK:   CONSTPOOL_ENTRY 0, %const.0, 16
  bb.0.entry:
    successors: %bb.3(0x30000000), %bb.1(0x50000000)
    liveins: $r0, $r1, $r2, $r4, $lr, $d8, $d9

    frame-setup tPUSH 14 /* CC::al */, $noreg, killed $r4, killed $lr, implicit-def $sp, implicit $sp
    frame-setup CFI_INSTRUCTION def_cfa_offset 8
    frame-setup CFI_INSTRUCTION offset $lr, -4
    frame-setup CFI_INSTRUCTION offset $r4, -8
    $sp = frame-setup VSTMDDB_UPD $sp, 14 /* CC::al */, $noreg, killed $d8, killed $d9
    frame-setup CFI_INSTRUCTION def_cfa_offset 24
    frame-setup CFI_INSTRUCTION offset $d9, -16
    frame-setup CFI_INSTRUCTION offset $d8, -24
    tCBZ $r2, %bb.3

  bb.1.vector.ph:
    successors: %bb.2(0x80000000)
    liveins: $r0, $r1, $r2

    renamable $r3, dead $cpsr = tADDi3 renamable $r2, 3, 14 /* CC::al */, $noreg
    renamable $q2 = MVE_VMOVimmi32 1, 0, $noreg, $noreg, undef renamable $q2
    renamable $r3 = t2BICri killed renamable $r3, 3, 14 /* CC::al */, $noreg, $noreg
    renamable $q3 = MVE_VMOVimmi32 4, 0, $noreg, $noreg, undef renamable $q3
    renamable $r12 = t2SUBri killed renamable $r3, 4, 14 /* CC::al */, $noreg, $noreg
    renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
    renamable $r3 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
    $lr = t2DoLoopStart renamable $r3
    $r4 = tMOVr killed $r3, 14 /* CC::al */, $noreg
    renamable $r3 = tLEApcrel %const.0, 14 /* CC::al */, $noreg
    renamable $q0 = MVE_VLDRWU32 killed renamable $r3, 0, 0, $noreg, $noreg :: (load (s128) from constant-pool)
    renamable $r3, dead $cpsr = tLSRri renamable $r2, 1, 14 /* CC::al */, $noreg
    renamable $q1 = MVE_VDUP32 killed renamable $r3, 0, $noreg, $noreg, undef renamable $q1

  bb.2.vector.body:
    successors: %bb.2(0x7c000000), %bb.3(0x04000000)
    liveins: $q0, $q1, $q2, $q3, $r0, $r1, $r2, $r4

    $lr = tMOVr $r4, 14 /* CC::al */, $noreg
    renamable $r4, dead $cpsr = nsw tSUBi8 killed $r4, 1, 14 /* CC::al */, $noreg
    renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14 /* CC::al */, $noreg
    renamable $vpr = MVE_VCMPu32 renamable $q1, renamable $q0, 8, 0, $noreg, $noreg
    MVE_VPST 1, implicit $vpr
    renamable $vpr = MVE_VCMPu32 renamable $q0, renamable $q2, 2, 1, killed renamable $vpr, $noreg
    renamable $vpr = MVE_VCTP32 renamable $r2, 1, killed renamable $vpr, $noreg
    renamable $r1, renamable $q4 = MVE_VLDRWU32_post killed renamable $r1, 16, 1, renamable $vpr, $noreg :: (load (s128) from %ir.lsr.iv35, align 4)
    renamable $r0 = MVE_VSTRWU32_post killed renamable $q4, killed renamable $r0, 16, 1, killed renamable $vpr, $noreg :: (store (s128) into %ir.lsr.iv12, align 4)
    renamable $q0 = MVE_VADDi32 killed renamable $q0, renamable $q3, 0, $noreg, $noreg, undef renamable $q0
    renamable $lr = t2LoopDec killed renamable $lr, 1
    t2LoopEnd killed renamable $lr, %bb.2, implicit-def dead $cpsr
    tB %bb.3, 14 /* CC::al */, $noreg

  bb.3.for.cond.cleanup:
    $sp = frame-destroy VLDMDIA_UPD $sp, 14 /* CC::al */, $noreg, def $d8, def $d9
    frame-destroy tPOP_RET 14 /* CC::al */, $noreg, def $r4, def $pc

  bb.4 (align 16):
    CONSTPOOL_ENTRY 0, %const.0, 16

...