# RUN: llc -mtriple=aarch64 -run-pass=pipeliner -debug-only=pipeliner -aarch64-enable-pipeliner -pipeliner-mve-cg %s -o /dev/null 2>&1 | FileCheck %s
# REQUIRES: asserts

# Test a case where fenv is enabled, there are instructions that may raise a
# floating-point exception, and there is an instruction for barrier event. In
# this case the order of them must not change.
#
# SU(2): May raise FP exception
# SU(3): May raise FP exception
# SU(4): Store
# SU(5): Barrier
# SU(7): Barrier

# CHECK:      ===== Loop Carried Edges Begin =====
# CHECK-NEXT: Loop carried edges from SU(7)
# CHECK-NEXT:   Order
# CHECK-NEXT:     SU(2)
# CHECK-NEXT:     SU(3)
# CHECK-NEXT:     SU(4)
# CHECK-NEXT:     SU(5)
# CHECK-NEXT: ===== Loop Carried Edges End =====

--- |
  @x = dso_local global i32 0, align 4

  define dso_local void @f(ptr nocapture noundef writeonly %a, float noundef %y, i32 noundef %n) {
  entry:
    %cmp6 = icmp sgt i32 %n, 0
    br i1 %cmp6, label %for.body.preheader, label %for.cond.cleanup

  for.body.preheader:
    %wide.trip.count = zext nneg i32 %n to i64
    br label %for.body

  for.cond.cleanup:
    ret void

  for.body:
    %indvars.iv = phi i64 [ 0, %for.body.preheader ], [ %indvars.iv.next, %for.body ]
    %tmp9 = trunc i64 %indvars.iv to i32
    %conv = tail call float @llvm.experimental.constrained.sitofp.f32.i32(i32 %tmp9, metadata !"round.dynamic", metadata !"fpexcept.strict") #2
    %add = tail call float @llvm.experimental.constrained.fadd.f32(float %conv, float %y, metadata !"round.dynamic", metadata !"fpexcept.strict") #2
    %0 = shl nuw nsw i64 %indvars.iv, 2
    %scevgep = getelementptr i8, ptr %a, i64 %0
    store float %add, ptr %scevgep, align 4, !tbaa !6
    %1 = load volatile i32, ptr @x, align 4, !tbaa !10
    %2 = zext i32 %1 to i64
    %3 = add i64 %indvars.iv, %2
    %tmp = trunc i64 %3 to i32
    store volatile i32 %tmp, ptr @x, align 4, !tbaa !10
    %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
    %exitcond.not = icmp eq i64 %wide.trip.count, %indvars.iv.next
    br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
  }

  declare float @llvm.experimental.constrained.sitofp.f32.i32(i32, metadata, metadata)

  declare float @llvm.experimental.constrained.fadd.f32(float, float, metadata, metadata)

  attributes #2 = { strictfp }

  !6 = !{!7, !7, i64 0}
  !7 = !{!"float", !8, i64 0}
  !8 = !{!"omnipotent char", !9, i64 0}
  !9 = !{!"Simple C/C++ TBAA"}
  !10 = !{!11, !11, i64 0}
  !11 = !{!"int", !8, i64 0}

...
---
name:            f
tracksRegLiveness: true
body:             |
  bb.0.entry:
    successors: %bb.1, %bb.2
    liveins: $x0, $s0, $w1
  
    %5:gpr32common = COPY $w1
    %4:fpr32 = COPY $s0
    %3:gpr64common = COPY $x0
    dead $wzr = SUBSWri %5, 1, 0, implicit-def $nzcv
    Bcc 11, %bb.2, implicit $nzcv
    B %bb.1
  
  bb.1.for.body.preheader:
    %8:gpr32 = ORRWrs $wzr, %5, 0
    %0:gpr64 = SUBREG_TO_REG killed %8, %subreg.sub_32
    %9:gpr64all = COPY $xzr
    %7:gpr64all = COPY %9
    %13:gpr64common = ADRP target-flags(aarch64-page) @x
    B %bb.3
  
  bb.2.for.cond.cleanup:
    RET_ReallyLR
  
  bb.3.for.body:
    successors: %bb.2, %bb.3
  
    %1:gpr64common = PHI %7, %bb.1, %2, %bb.3
    %10:gpr32 = COPY %1.sub_32
    %11:fpr32 = SCVTFUWSri %10, implicit $fpcr
    %12:fpr32 = FADDSrr killed %11, %4, implicit $fpcr
    STRSroX killed %12, %3, %1, 0, 1 :: (store (s32) into %ir.scevgep, !tbaa !6)
    %14:gpr32 = LDRWui %13, target-flags(aarch64-pageoff, aarch64-nc) @x :: (volatile dereferenceable load (s32) from @x, !tbaa !10)
    %15:gpr32 = ADDWrr %10, killed %14
    STRWui killed %15, %13, target-flags(aarch64-pageoff, aarch64-nc) @x :: (volatile store (s32) into @x, !tbaa !10)
    %16:gpr64common = nuw nsw ADDXri %1, 1, 0
    %2:gpr64all = COPY %16
    dead $xzr = SUBSXrr %0, %16, implicit-def $nzcv
    Bcc 0, %bb.2, implicit $nzcv
    B %bb.3
...