; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -S -loop-rotate -o - -verify-loop-info -verify-dom-info | FileCheck %s

@d = external global i64, align 8
@f = external global i32, align 4
@g = external global i32, align 4
@i = external global i32, align 4
@h = external global i32, align 4

define i32 @o() #0 {
; CHECK-LABEL: @o(
; CHECK-NEXT:    [[TMP1:%.*]] = alloca [1 x i32], align 4
; CHECK-NEXT:    [[TMP2:%.*]] = load i8*, i8** bitcast (i64* @d to i8**), align 8
; CHECK-NEXT:    [[TMP3:%.*]] = load i32, i32* @f, align 4
; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq i32 [[TMP3]], 0
; CHECK-NEXT:    br i1 [[TMP4]], label [[TMP17:%.*]], label [[DOTLR_PH2:%.*]]
; CHECK:       .lr.ph2:
; CHECK-NEXT:    br label [[TMP5:%.*]]
; CHECK:         [[TMP6:%.*]] = phi i32 [ [[TMP3]], [[DOTLR_PH2]] ], [ [[TMP15:%.*]], [[M_EXIT:%.*]] ]
; CHECK-NEXT:    [[TMP7:%.*]] = icmp ult i32 [[TMP6]], 4
; CHECK-NEXT:    [[TMP8:%.*]] = zext i1 [[TMP7]] to i32
; CHECK-NEXT:    store i32 [[TMP8]], i32* @g, align 4
; CHECK-NEXT:    [[TMP9:%.*]] = bitcast [1 x i32]* [[TMP1]] to i8*
; CHECK-NEXT:    [[TMP10:%.*]] = call i32 @n(i8* nonnull [[TMP9]], i8* [[TMP2]])
; CHECK-NEXT:    [[TMP11:%.*]] = icmp eq i32 [[TMP10]], 0
; CHECK-NEXT:    br i1 [[TMP11]], label [[THREAD_PRE_SPLIT:%.*]], label [[DOT_CRIT_EDGE:%.*]]
; CHECK:       thread-pre-split:
; CHECK-NEXT:    [[DOTPR:%.*]] = load i32, i32* @i, align 4
; CHECK-NEXT:    [[TMP12:%.*]] = icmp eq i32 [[DOTPR]], 0
; CHECK-NEXT:    br i1 [[TMP12]], label [[M_EXIT]], label [[DOTLR_PH:%.*]]
; CHECK:       .lr.ph:
; CHECK-NEXT:    br label [[TMP13:%.*]]
; CHECK:         [[DOT11:%.*]] = phi i32 [ undef, [[DOTLR_PH]] ], [ [[TMP14:%.*]], [[J_EXIT_I:%.*]] ]
; CHECK-NEXT:    callbr void asm sideeffect "", "X,~{dirflag},~{fpsr},~{flags}"(i8* blockaddress(@o, [[M_EXIT]])) #1
; CHECK-NEXT:    to label [[J_EXIT_I]] [label %m.exit]
; CHECK:       j.exit.i:
; CHECK-NEXT:    [[TMP14]] = tail call i32 asm "", "={ax},~{dirflag},~{fpsr},~{flags}"() #2
; CHECK-NEXT:    br i1 [[TMP12]], label [[DOTM_EXIT_CRIT_EDGE:%.*]], label [[TMP13]]
; CHECK:       .m.exit_crit_edge:
; CHECK-NEXT:    [[SPLIT:%.*]] = phi i32 [ [[TMP14]], [[J_EXIT_I]] ]
; CHECK-NEXT:    br label [[M_EXIT]]
; CHECK:       m.exit:
; CHECK-NEXT:    [[DOT1_LCSSA:%.*]] = phi i32 [ [[DOT11]], [[TMP13]] ], [ [[SPLIT]], [[DOTM_EXIT_CRIT_EDGE]] ], [ undef, [[THREAD_PRE_SPLIT]] ]
; CHECK-NEXT:    store i32 [[DOT1_LCSSA]], i32* @h, align 4
; CHECK-NEXT:    [[TMP15]] = load i32, i32* @f, align 4
; CHECK-NEXT:    [[TMP16:%.*]] = icmp eq i32 [[TMP15]], 0
; CHECK-NEXT:    br i1 [[TMP16]], label [[DOT_CRIT_EDGE3:%.*]], label [[TMP5]]
; CHECK:       ._crit_edge:
; CHECK-NEXT:    br label [[TMP17]]
; CHECK:       ._crit_edge3:
; CHECK-NEXT:    br label [[TMP17]]
; CHECK:         ret i32 undef
;
  %1 = alloca [1 x i32], align 4
  %2 = load i8*, i8** bitcast (i64* @d to i8**), align 8
  br label %3

; <label>:3:                                      ; preds = %m.exit, %0
  %4 = load i32, i32* @f, align 4
  %5 = icmp eq i32 %4, 0
  br i1 %5, label %16, label %6

; <label>:6:                                      ; preds = %3
  %7 = icmp ult i32 %4, 4
  %8 = zext i1 %7 to i32
  store i32 %8, i32* @g, align 4
  %9 = bitcast [1 x i32]* %1 to i8*
  %10 = call i32 @n(i8* nonnull %9, i8* %2)
  %11 = icmp eq i32 %10, 0
  br i1 %11, label %thread-pre-split, label %16

thread-pre-split:                                 ; preds = %6
  %.pr = load i32, i32* @i, align 4
  br label %12

; <label>:12:                                     ; preds = %j.exit.i, %thread-pre-split
  %.1 = phi i32 [ %15, %j.exit.i ], [ undef, %thread-pre-split ]
  %13 = icmp eq i32 %.pr, 0
  br i1 %13, label %m.exit, label %14

; <label>:14:                                     ; preds = %12
  callbr void asm sideeffect "", "X,~{dirflag},~{fpsr},~{flags}"(i8* blockaddress(@o, %m.exit)) #1
  to label %j.exit.i [label %m.exit]

j.exit.i:                                         ; preds = %14
  %15 = tail call i32 asm "", "={ax},~{dirflag},~{fpsr},~{flags}"() #2
  br label %12

m.exit:                                           ; preds = %14, %12
  %.1.lcssa = phi i32 [ %.1, %14 ], [ %.1, %12 ]
  store i32 %.1.lcssa, i32* @h, align 4
  br label %3

; <label>:16:                                     ; preds = %6, %3
  ret i32 undef
}

declare i32 @n(i8*, i8*)  #0

attributes #0 = { "use-soft-float"="false" }
attributes #1 = { nounwind }
attributes #2 = { nounwind readnone }