# 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 --verify-machineinstrs -o - | FileCheck %s

--- |
  define i16 @predicated_livout(i8* %input_1_vect, i8* %input_2_vect, i32 %block_size) #0 {
  entry:
    %rnd.up = add i32 %block_size, 7
    %div = lshr i32 %rnd.up, 3
    %0 = call i1 @llvm.test.set.loop.iterations.i32(i32 %div)
    br i1 %0, label %for.body.preheader, label %for.cond.cleanup

  for.body.preheader:                               ; preds = %entry
    br label %for.body

  for.body:                                         ; preds = %for.body.preheader, %for.body
    %lsr.iv = phi i32 [ 0, %for.body.preheader ], [ %lsr.iv.next, %for.body ]
    %input_1_vect.addr.052 = phi i8* [ %add.ptr, %for.body ], [ %input_1_vect, %for.body.preheader ]
    %input_2_vect.addr.051 = phi i8* [ %add.ptr14, %for.body ], [ %input_2_vect, %for.body.preheader ]
    %num_elements.049 = phi i32 [ %sub, %for.body ], [ %block_size, %for.body.preheader ]
    %acc = phi <8 x i16> [ %acc.next, %for.body ], [ zeroinitializer, %for.body.preheader ]
    %input_2_cast = bitcast i8* %input_2_vect.addr.051 to <8 x i8>*
    %input_1_cast = bitcast i8* %input_1_vect.addr.052 to <8 x i8>*
    %pred = tail call <8 x i1> @llvm.arm.mve.vctp16(i32 %num_elements.049)
    %load.1 = tail call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>* %input_1_cast, i32 1, <8 x i1> %pred, <8 x i8> undef)
    %zext.load.1 = zext <8 x i8> %load.1 to <8 x i16>
    %load.2 = tail call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>* %input_2_cast, i32 1, <8 x i1> %pred, <8 x i8> undef)
    %zext.load.2 = zext <8 x i8> %load.2 to <8 x i16>
    %add = tail call <8 x i16> @llvm.arm.mve.add.predicated.v8i16.v8i1(<8 x i16> %zext.load.1, <8 x i16> %zext.load.2, <8 x i1> %pred, <8 x i16> undef)
    %acc.next = tail call <8 x i16> @llvm.arm.mve.add.predicated.v8i16.v8i1(<8 x i16> %add, <8 x i16> %acc, <8 x i1> %pred, <8 x i16> undef)
    %add.ptr = getelementptr inbounds i8, i8* %input_1_vect.addr.052, i32 8
    %add.ptr14 = getelementptr inbounds i8, i8* %input_2_vect.addr.051, i32 8
    %sub = add i32 %num_elements.049, -8
    %iv.next = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %lsr.iv, i32 1)
    %cmp = icmp ne i32 %iv.next, 0
    %lsr.iv.next = add i32 %lsr.iv, -1
    br i1 %cmp, label %for.body, label %middle.block

  middle.block:                                     ; preds = %for.body
    %reduce = tail call i16 @llvm.experimental.vector.reduce.add.v8i16(<8 x i16> %acc.next)
    ret i16 %reduce

  for.cond.cleanup:                                 ; preds = %entry
    ret i16 0
  }

  declare <8 x i1> @llvm.arm.mve.vctp16(i32) #1
  declare <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>*, i32 immarg, <8 x i1>, <8 x i8>) #2
  declare i1 @llvm.test.set.loop.iterations.i32(i32) #3
  declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32) #3
  declare i16 @llvm.experimental.vector.reduce.add.v8i16(<8 x i16>) #4
  declare <8 x i16> @llvm.arm.mve.add.predicated.v8i16.v8i1(<8 x i16>, <8 x i16>, <8 x i1>, <8 x i16>) #1

...
---
name:            predicated_livout
alignment:       2
tracksRegLiveness: true
registers:       []
liveins:
  - { reg: '$r0', virtual-reg: '' }
  - { reg: '$r1', virtual-reg: '' }
  - { reg: '$r2', virtual-reg: '' }
frameInfo:
  stackSize:       8
  offsetAdjustment: 0
  maxAlignment:    4
fixedStack:      []
stack:
  - { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$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: '$r7', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
callSites:       []
constants:       []
machineFunctionInfo: {}
body:             |
  ; CHECK-LABEL: name: predicated_livout
  ; CHECK: bb.0.entry:
  ; CHECK:   successors: %bb.1(0x40000000), %bb.4(0x40000000)
  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r7
  ; CHECK:   frame-setup tPUSH 14 /* CC::al */, $noreg, killed $r7, 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 $r7, -8
  ; CHECK:   $lr = MVE_WLSTP_16 killed renamable $r2, %bb.4
  ; CHECK: bb.1.for.body.preheader:
  ; CHECK:   successors: %bb.2(0x80000000)
  ; CHECK:   liveins: $lr, $r0, $r1
  ; CHECK:   renamable $q0 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q0
  ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
  ; CHECK: bb.2.for.body:
  ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
  ; CHECK:   liveins: $lr, $q0, $r0, $r1, $r3
  ; CHECK:   renamable $r3, dead $cpsr = tSUBi8 killed $r3, 1, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $r1, renamable $q1 = MVE_VLDRBU16_post killed renamable $r1, 8, 0, $noreg :: (load 8 from %ir.input_2_cast, align 1)
  ; CHECK:   renamable $r0, renamable $q2 = MVE_VLDRBU16_post killed renamable $r0, 8, 0, $noreg :: (load 8 from %ir.input_1_cast, align 1)
  ; CHECK:   renamable $q1 = MVE_VADDi16 killed renamable $q2, killed renamable $q1, 0, $noreg, undef renamable $q1
  ; CHECK:   renamable $q0 = MVE_VADDi16 killed renamable $q1, killed renamable $q0, 0, killed $noreg, undef renamable $q0
  ; CHECK:   $lr = MVE_LETP killed renamable $lr, %bb.2
  ; CHECK: bb.3.middle.block:
  ; CHECK:   liveins: $q0
  ; CHECK:   renamable $r0 = MVE_VADDVu16no_acc killed renamable $q0, 0, $noreg
  ; CHECK:   tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc, implicit killed $r0
  ; CHECK: bb.4.for.cond.cleanup:
  ; CHECK:   liveins: $lr
  ; CHECK:   $r0, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
  ; CHECK:   tBX_RET 14 /* CC::al */, $noreg, implicit killed $r0
  bb.0.entry:
    successors: %bb.1(0x40000000), %bb.4(0x40000000)
    liveins: $r0, $r1, $r2, $lr, $r7

    frame-setup tPUSH 14, $noreg, killed $r7, 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 $r7, -8
    renamable $r3, dead $cpsr = tADDi3 renamable $r2, 7, 14, $noreg
    renamable $lr = t2LSRri killed renamable $r3, 3, 14, $noreg, $noreg
    t2WhileLoopStart renamable $lr, %bb.4, implicit-def dead $cpsr
    tB %bb.1, 14, $noreg

  bb.1.for.body.preheader:
    successors: %bb.2(0x80000000)
    liveins: $r0, $r1, $r2, $lr

    renamable $q0 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q0
    renamable $r3, dead $cpsr = tMOVi8 0, 14, $noreg

  bb.2.for.body:
    successors: %bb.2(0x7c000000), %bb.3(0x04000000)
    liveins: $q0, $r0, $r1, $r2, $r3, $lr

    renamable $vpr = MVE_VCTP16 renamable $r2, 0, $noreg
    renamable $r3, dead $cpsr = tSUBi8 killed $r3, 1, 14, $noreg
    renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 8, 14, $noreg
    renamable $lr = t2LoopDec killed renamable $lr, 1
    MVE_VPST 1, implicit $vpr
    renamable $r1, renamable $q1 = MVE_VLDRBU16_post killed renamable $r1, 8, 1, renamable $vpr :: (load 8 from %ir.input_2_cast, align 1)
    renamable $r0, renamable $q2 = MVE_VLDRBU16_post killed renamable $r0, 8, 1, renamable $vpr :: (load 8 from %ir.input_1_cast, align 1)
    renamable $q1 = MVE_VADDi16 killed renamable $q2, killed renamable $q1, 1, renamable $vpr, undef renamable $q1
    renamable $q0 = MVE_VADDi16 killed renamable $q1, killed renamable $q0, 1, killed renamable $vpr, undef renamable $q0
    t2LoopEnd renamable $lr, %bb.2, implicit-def dead $cpsr
    tB %bb.3, 14, $noreg

  bb.3.middle.block:
    liveins: $q0

    renamable $r0 = MVE_VADDVu16no_acc killed renamable $q0, 0, $noreg
    tPOP_RET 14, $noreg, def $r7, def $pc, implicit killed $r0

  bb.4.for.cond.cleanup:
    liveins: $lr

    $r0, dead $cpsr = tMOVi8 0, 14, $noreg
    tBX_RET 14, $noreg, implicit killed $r0

...