# RUN: llc -start-after=machine-sink -stop-after=peephole-opt -mtriple=powerpc64-unknown-linux-gnu -o - %s | FileCheck %s

--- |
  ; ModuleID = '<stdin>'
  source_filename = "<stdin>"
  target datalayout = "E-m:e-i64:64-n32:64"
  target triple = "powerpc64-unknown-linux-gnu"

  ; Function Attrs: nounwind readnone
  declare i128 @llvm.cttz.i128(i128, i1) #0

  define void @fn1(i128, i128, i1) {
  top:
    br label %loop

  loop:                                             ; preds = %loop, %top
    %v = phi i128 [ %3, %loop ], [ %0, %top ]
    %u = phi i128 [ %3, %loop ], [ %1, %top ]
    %s = sub i128 %v, %u
    %3 = call i128 @llvm.cttz.i128(i128 %s, i1 false)
    br label %loop
  }

  ; Function Attrs: nounwind
  declare void @llvm.stackprotector(i8*, i8**) #1

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

...
---
name:            fn1
alignment:       2
exposesReturnsTwice: false
tracksRegLiveness: true
registers:
  - { id: 0, class: g8rc }
  - { id: 1, class: g8rc }
  - { id: 2, class: g8rc }
  - { id: 3, class: g8rc }
  - { id: 4, class: g8rc }
  - { id: 5, class: g8rc }
  - { id: 6, class: g8rc }
  - { id: 7, class: g8rc }
  - { id: 8, class: g8rc }
  - { id: 9, class: g8rc }
  - { id: 10, class: g8rc }
  - { id: 11, class: g8rc }
  - { id: 12, class: g8rc }
  - { id: 13, class: g8rc }
  - { id: 14, class: g8rc }
  - { id: 15, class: g8rc_and_g8rc_nox0 }
  - { id: 16, class: g8rc_and_g8rc_nox0 }
  - { id: 17, class: g8rc }
  - { id: 18, class: g8rc }
  - { id: 19, class: g8rc }
  - { id: 20, class: g8rc }
  - { id: 21, class: g8rc }
  - { id: 22, class: g8rc }
  - { id: 23, class: g8rc }
  - { id: 24, class: g8rc }
  - { id: 25, class: crrc }
  - { id: 26, class: g8rc_and_g8rc_nox0 }
  - { id: 27, class: g8rc_and_g8rc_nox0 }
liveins:
  - { reg: '%x3', virtual-reg: '%6' }
  - { reg: '%x4', virtual-reg: '%7' }
  - { reg: '%x5', virtual-reg: '%8' }
  - { reg: '%x6', virtual-reg: '%9' }
frameInfo:
  isFrameAddressTaken: false
  isReturnAddressTaken: false
  hasStackMap:     false
  hasPatchPoint:   false
  stackSize:       0
  offsetAdjustment: 0
  maxAlignment:    0
  adjustsStack:    false
  hasCalls:        false
  maxCallFrameSize: 0
  hasOpaqueSPAdjustment: false
  hasVAStart:      false
  hasMustTailInVarArgFunc: false
body:             |
  bb.0.top:
    successors: %bb.1.loop
    liveins: %x3, %x4, %x5, %x6

    %9 = COPY %x6
    %8 = COPY %x5
    %7 = COPY %x4
    %6 = COPY %x3
    %14 = COPY %9
    %13 = COPY %8
    %12 = COPY %7
    %11 = COPY %6
    %21 = LI8 128
    %23 = LI8 64

  bb.1.loop:
    successors: %bb.2.loop, %bb.4

    %0 = PHI %11, %bb.0.top, %4, %bb.3.loop
    %1 = PHI %12, %bb.0.top, %5, %bb.3.loop
    %2 = PHI %13, %bb.0.top, %4, %bb.3.loop
    %3 = PHI %14, %bb.0.top, %5, %bb.3.loop
    %15 = SUBFC8 %3, %1, implicit-def %carry
    %16 = SUBFE8 %2, %0, implicit-def dead %carry, implicit %carry
    %17 = ADDI8 %16, -1
    %18 = ADDI8 %15, -1
    %19 = ANDC8 killed %17, %16
    %20 = ANDC8 killed %18, %15
    %22 = CNTLZD killed %19
    %24 = CNTLZD killed %20
    %25 = CMPLDI %15, 0
    BCC 76, %25, %bb.2.loop
    ; CHECK: SUBFC8o %3, %1, implicit-def %carry, implicit-def %cr0
    ; CHECK: COPY killed %cr0
    ; CHECK: BCC

  bb.4:
    successors: %bb.3.loop

    %27 = SUBF8 %24, %23
    B %bb.3.loop

  bb.2.loop:
    successors: %bb.3.loop

    %26 = SUBF8 %22, %21

  bb.3.loop:
    successors: %bb.1.loop

    %5 = PHI %26, %bb.2.loop, %27, %bb.4
    %4 = LI8 0
    B %bb.1.loop

...