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

--- |
  define dso_local void @vctp_tsubi3(i32* noalias nocapture %A, i32* noalias nocapture readonly %B, i32* noalias nocapture readonly %C, i32 %N) local_unnamed_addr #0 {
  entry:
    %cmp8 = icmp sgt i32 %N, 0
    %0 = add i32 %N, 3
    %1 = lshr i32 %0, 2
    %2 = shl nuw i32 %1, 2
    %3 = add i32 %2, -4
    %4 = lshr i32 %3, 2
    %5 = add nuw nsw i32 %4, 1
    br i1 %cmp8, label %vector.ph, label %for.cond.cleanup

  vector.ph:                                        ; preds = %entry
    %start = call i32 @llvm.start.loop.iterations.i32(i32 %5)
    br label %vector.body

  vector.body:                                      ; preds = %vector.body, %vector.ph
    %lsr.iv17 = phi i32* [ %scevgep18, %vector.body ], [ %A, %vector.ph ]
    %lsr.iv14 = phi i32* [ %scevgep15, %vector.body ], [ %C, %vector.ph ]
    %lsr.iv = phi i32* [ %scevgep, %vector.body ], [ %B, %vector.ph ]
    %6 = phi i32 [ %start, %vector.ph ], [ %11, %vector.body ]
    %7 = phi i32 [ %N, %vector.ph ], [ %9, %vector.body ]
    %lsr.iv13 = bitcast i32* %lsr.iv to <4 x i32>*
    %lsr.iv1416 = bitcast i32* %lsr.iv14 to <4 x i32>*
    %lsr.iv1719 = bitcast i32* %lsr.iv17 to <4 x i32>*
    %8 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %7)
    %9 = sub i32 %7, 5
    %wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv13, i32 4, <4 x i1> %8, <4 x i32> undef)
    %wide.masked.load12 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv1416, i32 4, <4 x i1> %8, <4 x i32> undef)
    %10 = add nsw <4 x i32> %wide.masked.load12, %wide.masked.load
    call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %10, <4 x i32>* %lsr.iv1719, i32 4, <4 x i1> %8)
    %scevgep = getelementptr i32, i32* %lsr.iv, i32 4
    %scevgep15 = getelementptr i32, i32* %lsr.iv14, i32 4
    %scevgep18 = getelementptr i32, i32* %lsr.iv17, i32 4
    %11 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %6, i32 1)
    %12 = icmp ne i32 %11, 0
    br i1 %12, label %vector.body, label %for.cond.cleanup

  for.cond.cleanup:                                 ; preds = %vector.body, %entry
    ret void
  }
  declare i32 @llvm.start.loop.iterations.i32(i32) #1
  declare <4 x i1> @llvm.arm.mve.vctp32(i32) #2
  declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32) #1
  declare void @llvm.lifetime.start.p0i8(i64 immarg, i8* nocapture) #3
  declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32 immarg, <4 x i1>, <4 x i32>) #4
  declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32 immarg, <4 x i1>) #3

...
---
name:            vctp_tsubi3
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: '$r2', virtual-reg: '' }
  - { reg: '$r3', 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: vctp_tsubi3
  ; CHECK: bb.0.entry:
  ; CHECK:   successors: %bb.1(0x80000000)
  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3, $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:   tCMPi8 renamable $r3, 1, 14 /* CC::al */, $noreg, implicit-def $cpsr
  ; CHECK:   t2IT 11, 8, implicit-def $itstate
  ; CHECK:   tPOP_RET 11 /* CC::lt */, killed $cpsr, def $r7, def $pc, implicit killed $itstate
  ; CHECK: bb.1.vector.ph:
  ; CHECK:   successors: %bb.2(0x80000000)
  ; CHECK:   liveins: $r0, $r1, $r2, $r3
  ; CHECK:   $lr = MVE_DLSTP_32 killed renamable $r3
  ; CHECK: bb.2.vector.body:
  ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
  ; CHECK:   liveins: $lr, $r0, $r1, $r2
  ; CHECK:   renamable $r1, renamable $q0 = MVE_VLDRWU32_post killed renamable $r1, 16, 0, $noreg, $noreg :: (load (s128) from %ir.lsr.iv13, align 4)
  ; CHECK:   renamable $r2, renamable $q1 = MVE_VLDRWU32_post killed renamable $r2, 16, 0, $noreg, $noreg :: (load (s128) from %ir.lsr.iv1416, align 4)
  ; CHECK:   renamable $q0 = nsw MVE_VADDi32 killed renamable $q1, killed renamable $q0, 0, $noreg, $noreg, undef renamable $q0
  ; CHECK:   renamable $r0 = MVE_VSTRWU32_post killed renamable $q0, killed renamable $r0, 16, 0, killed $noreg, $noreg :: (store (s128) into %ir.lsr.iv1719, align 4)
  ; CHECK:   $lr = MVE_LETP killed renamable $lr, %bb.2
  ; CHECK: bb.3.for.cond.cleanup:
  ; CHECK:   tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc
  bb.0.entry:
    successors: %bb.1(0x80000000)
    liveins: $r0, $r1, $r2, $r3, $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
    tCMPi8 renamable $r3, 1, 14, $noreg, implicit-def $cpsr
    t2IT 11, 8, implicit-def $itstate
    tPOP_RET 11, killed $cpsr, def $r7, def $pc, implicit killed $itstate

  bb.1.vector.ph:
    successors: %bb.2(0x80000000)
    liveins: $r0, $r1, $r2, $r3, $r7, $lr

    renamable $r12 = t2ADDri renamable $r3, 3, 14, $noreg, $noreg
    renamable $lr = t2MOVi 1, 14, $noreg, $noreg
    renamable $r12 = t2BICri killed renamable $r12, 3, 14, $noreg, $noreg
    renamable $r12 = t2SUBri killed renamable $r12, 4, 14, $noreg, $noreg
    renamable $lr = nuw nsw t2ADDrs killed renamable $lr, killed renamable $r12, 19, 14, $noreg, $noreg
    $lr = t2DoLoopStart renamable $lr

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

    renamable $vpr = MVE_VCTP32 renamable $r3, 0, $noreg, $noreg
    MVE_VPST 4, implicit $vpr
    renamable $r1, renamable $q0 = MVE_VLDRWU32_post killed renamable $r1, 16, 1, renamable $vpr, $noreg :: (load (s128) from %ir.lsr.iv13, align 4)
    renamable $r2, renamable $q1 = MVE_VLDRWU32_post killed renamable $r2, 16, 1, renamable $vpr, $noreg :: (load (s128) from %ir.lsr.iv1416, align 4)
    renamable $r3, dead $cpsr = tSUBi3 killed renamable $r3, 4, 14, $noreg
    renamable $q0 = nsw MVE_VADDi32 killed renamable $q1, killed renamable $q0, 0, $noreg, $noreg, undef renamable $q0
    MVE_VPST 8, implicit $vpr
    renamable $r0 = MVE_VSTRWU32_post killed renamable $q0, killed renamable $r0, 16, 1, killed renamable $vpr, $noreg :: (store (s128) into %ir.lsr.iv1719, align 4)
    renamable $lr = t2LoopDec killed renamable $lr, 1
    t2LoopEnd renamable $lr, %bb.2, implicit-def dead $cpsr
    tB %bb.3, 14, $noreg

  bb.3.for.cond.cleanup:
    tPOP_RET 14, $noreg, def $r7, def $pc

...