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

# TODO: Explore the preheader to remove the redundant tMOVr

--- |
  target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"
  target triple = "thumbv8.1m.main"

  define i32 @do_copy(i32 %n, i32* nocapture %p, i32* nocapture readonly %q) {
  entry:
    %scevgep = getelementptr i32, i32* %q, i32 -1
    %scevgep3 = getelementptr i32, i32* %p, i32 -1
    call void @llvm.set.loop.iterations.i32(i32 %n)
    br label %preheader

  preheader:
    br label %while.body

  while.body:                                       ; preds = %while.body, %entry
    %lsr.iv4 = phi i32* [ %scevgep5, %while.body ], [ %scevgep3, %preheader ]
    %lsr.iv = phi i32* [ %scevgep1, %while.body ], [ %scevgep, %preheader ]
    %0 = phi i32 [ %n, %preheader ], [ %2, %while.body ]
    %scevgep6 = getelementptr i32, i32* %lsr.iv, i32 1
    %scevgep2 = getelementptr i32, i32* %lsr.iv4, i32 1
    %1 = load i32, i32* %scevgep6, align 4
    store i32 %1, i32* %scevgep2, align 4
    %scevgep1 = getelementptr i32, i32* %lsr.iv, i32 1
    %scevgep5 = getelementptr i32, i32* %lsr.iv4, i32 1
    %2 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %0, i32 1)
    %3 = icmp ne i32 %2, 0
    br i1 %3, label %while.body, label %while.end

  while.end:                                        ; preds = %while.body
    ret i32 0
  }

  declare void @llvm.set.loop.iterations.i32(i32) #0
  declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32) #0

  attributes #0 = { noduplicate nounwind }
  attributes #1 = { nounwind }

...
---
name:            do_copy
alignment:       2
exposesReturnsTwice: false
legalized:       false
regBankSelected: false
selected:        false
failedISel:      false
tracksRegLiveness: true
hasWinCFI:       false
registers:       []
liveins:
  - { reg: '$r0', virtual-reg: '' }
  - { reg: '$r1', virtual-reg: '' }
  - { reg: '$r2', virtual-reg: '' }
frameInfo:
  isFrameAddressTaken: false
  isReturnAddressTaken: false
  hasStackMap:     false
  hasPatchPoint:   false
  stackSize:       8
  offsetAdjustment: 0
  maxAlignment:    4
  adjustsStack:    false
  hasCalls:        false
  stackProtector:  ''
  maxCallFrameSize: 0
  cvBytesOfCalleeSavedRegisters: 0
  hasOpaqueSPAdjustment: false
  hasVAStart:      false
  hasMustTailInVarArgFunc: false
  localFrameSize:  0
  savePoint:       ''
  restorePoint:    ''
fixedStack:      []
stack:
  - { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$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: do_copy
  ; CHECK: bb.0.entry:
  ; CHECK:   successors: %bb.1(0x80000000)
  ; 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:   dead $lr = t2DLS killed $r0
  ; CHECK:   renamable $r0, dead $cpsr = tSUBi3 killed renamable $r1, 4, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $r1, dead $cpsr = tSUBi3 killed renamable $r2, 4, 14 /* CC::al */, $noreg
  ; CHECK: bb.1.preheader:
  ; CHECK:   successors: %bb.2(0x80000000)
  ; CHECK:   liveins: $r0, $r1
  ; CHECK:   $lr = tMOVr $r0, 14 /* CC::al */, $noreg
  ; CHECK: bb.2.while.body:
  ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
  ; CHECK:   liveins: $lr, $r0, $r1
  ; CHECK:   renamable $r2, renamable $r1 = t2LDR_PRE killed renamable $r1, 4, 14 /* CC::al */, $noreg :: (load 4 from %ir.scevgep6)
  ; CHECK:   early-clobber renamable $r0 = t2STR_PRE killed renamable $r2, killed renamable $r0, 4, 14 /* CC::al */, $noreg :: (store 4 into %ir.scevgep2)
  ; CHECK:   $lr = t2LEUpdate killed renamable $lr, %bb.2
  ; CHECK: bb.3.while.end:
  ; CHECK:   $r0, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
  ; CHECK:   tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc, implicit killed $r0
  bb.0.entry:
    successors: %bb.1(0x80000000)
    liveins: $r0, $r1, $r2, $r7, $lr

    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
    t2DoLoopStart $r0
    renamable $r0, dead $cpsr = tSUBi3 killed renamable $r1, 4, 14, $noreg
    renamable $r1, dead $cpsr = tSUBi3 killed renamable $r2, 4, 14, $noreg

  bb.1.preheader:
    successors: %bb.2(0x80000000)
    liveins: $r0, $r1
    $lr = tMOVr $r0, 14, $noreg

  bb.2.while.body:
    successors: %bb.2(0x7c000000), %bb.3(0x04000000)
    liveins: $lr, $r0, $r1

    renamable $r2, renamable $r1 = t2LDR_PRE killed renamable $r1, 4, 14, $noreg :: (load 4 from %ir.scevgep6)
    early-clobber renamable $r0 = t2STR_PRE killed renamable $r2, killed renamable $r0, 4, 14, $noreg :: (store 4 into %ir.scevgep2)
    renamable $lr = t2LoopDec killed renamable $lr, 1
    t2LoopEnd renamable $lr, %bb.2, implicit-def dead $cpsr
    tB %bb.3, 14, $noreg

  bb.3.while.end:
    $r0, dead $cpsr = tMOVi8 0, 14, $noreg
    tPOP_RET 14, $noreg, def $r7, def $pc, implicit killed $r0

...