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

--- |
  define dso_local arm_aapcs_vfpcc void @test1(i32* noalias nocapture %a, i32* nocapture readonly %b, i32* nocapture readonly %c, i32 %N) local_unnamed_addr {
  entry:
    %cmp30 = icmp eq 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 %cmp30, label %for.cond.cleanup6, label %vector.ph

  vector.ph:                                        ; preds = %entry
    %start1 = call i32 @llvm.start.loop.iterations.i32(i32 %5)
    br label %vector.body

  vector.body:                                      ; preds = %vector.body, %vector.ph
    %lsr.iv68 = phi i32* [ %scevgep69, %vector.body ], [ %a, %vector.ph ]
    %lsr.iv65 = phi i32* [ %scevgep66, %vector.body ], [ %c, %vector.ph ]
    %lsr.iv62 = phi i32* [ %scevgep63, %vector.body ], [ %b, %vector.ph ]
    %6 = phi i32 [ %start1, %vector.ph ], [ %11, %vector.body ]
    %7 = phi i32 [ %N, %vector.ph ], [ %9, %vector.body ]
    %lsr.iv6870 = bitcast i32* %lsr.iv68 to <4 x i32>*
    %lsr.iv6567 = bitcast i32* %lsr.iv65 to <4 x i32>*
    %lsr.iv6264 = bitcast i32* %lsr.iv62 to <4 x i32>*
    %8 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %7)
    %9 = sub i32 %7, 4
    %wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv6264, i32 4, <4 x i1> %8, <4 x i32> undef)
    %wide.masked.load35 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv6567, i32 4, <4 x i1> %8, <4 x i32> undef)
    %10 = mul nsw <4 x i32> %wide.masked.load35, %wide.masked.load
    call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %10, <4 x i32>* %lsr.iv6870, i32 4, <4 x i1> %8)
    %scevgep63 = getelementptr i32, i32* %lsr.iv62, i32 4
    %scevgep66 = getelementptr i32, i32* %lsr.iv65, i32 4
    %scevgep69 = getelementptr i32, i32* %lsr.iv68, 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.cond4.preheader

  for.cond4.preheader:                              ; preds = %vector.body
    %13 = icmp eq i32 %N, 0
    %14 = add i32 %N, 3
    %15 = lshr i32 %14, 2
    %16 = shl nuw i32 %15, 2
    %17 = add i32 %16, -4
    %18 = lshr i32 %17, 2
    %19 = add nuw nsw i32 %18, 1
    br i1 %13, label %for.cond.cleanup6, label %vector.ph39

  vector.ph39:                                      ; preds = %for.cond4.preheader
    %start2 = call i32 @llvm.start.loop.iterations.i32(i32 %19)
    br label %vector.body38

  vector.body38:                                    ; preds = %vector.body38, %vector.ph39
    %lsr.iv59 = phi i32* [ %scevgep60, %vector.body38 ], [ %a, %vector.ph39 ]
    %lsr.iv56 = phi i32* [ %scevgep57, %vector.body38 ], [ %c, %vector.ph39 ]
    %lsr.iv = phi i32* [ %scevgep, %vector.body38 ], [ %b, %vector.ph39 ]
    %20 = phi i32 [ %start2, %vector.ph39 ], [ %26, %vector.body38 ]
    %21 = phi i32 [ %N, %vector.ph39 ], [ %23, %vector.body38 ]
    %lsr.iv5961 = bitcast i32* %lsr.iv59 to <4 x i32>*
    %lsr.iv5658 = bitcast i32* %lsr.iv56 to <4 x i32>*
    %lsr.iv55 = bitcast i32* %lsr.iv to <4 x i32>*
    %22 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %21)
    %23 = sub i32 %21, 4
    %wide.masked.load52 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv55, i32 4, <4 x i1> %22, <4 x i32> undef)
    %wide.masked.load53 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv5658, i32 4, <4 x i1> %22, <4 x i32> undef)
    %24 = xor <4 x i32> %wide.masked.load53, %wide.masked.load52
    %wide.masked.load54 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv5961, i32 4, <4 x i1> %22, <4 x i32> undef)
    %25 = add nsw <4 x i32> %wide.masked.load54, %24
    call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %25, <4 x i32>* %lsr.iv5961, i32 4, <4 x i1> %22)
    %scevgep = getelementptr i32, i32* %lsr.iv, i32 4
    %scevgep57 = getelementptr i32, i32* %lsr.iv56, i32 4
    %scevgep60 = getelementptr i32, i32* %lsr.iv59, i32 4
    %26 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %20, i32 1)
    %27 = icmp ne i32 %26, 0
    br i1 %27, label %vector.body38, label %for.cond.cleanup6

  for.cond.cleanup6:                                ; preds = %vector.body38, %entry, %for.cond4.preheader
    ret void
  }
  ; Function Attrs: nofree norecurse nounwind
  define dso_local arm_aapcs_vfpcc void @test2(i32* noalias nocapture %a, i32* nocapture readonly %b, i32* nocapture readonly %c, i32 %N) local_unnamed_addr {
  entry:
    %div = lshr i32 %N, 1
    %cmp30 = icmp eq i32 %div, 0
    %0 = add nuw i32 %div, 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 %cmp30, label %for.cond4.preheader, label %vector.ph

  vector.ph:                                        ; preds = %entry
    %start1 = call i32 @llvm.start.loop.iterations.i32(i32 %5)
    br label %vector.body

  vector.body:                                      ; preds = %vector.body, %vector.ph
    %lsr.iv68 = phi i32* [ %scevgep69, %vector.body ], [ %a, %vector.ph ]
    %lsr.iv65 = phi i32* [ %scevgep66, %vector.body ], [ %c, %vector.ph ]
    %lsr.iv62 = phi i32* [ %scevgep63, %vector.body ], [ %b, %vector.ph ]
    %6 = phi i32 [ %start1, %vector.ph ], [ %11, %vector.body ]
    %7 = phi i32 [ %div, %vector.ph ], [ %9, %vector.body ]
    %lsr.iv6870 = bitcast i32* %lsr.iv68 to <4 x i32>*
    %lsr.iv6567 = bitcast i32* %lsr.iv65 to <4 x i32>*
    %lsr.iv6264 = bitcast i32* %lsr.iv62 to <4 x i32>*
    %8 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %7)
    %9 = sub i32 %7, 4
    %wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv6264, i32 4, <4 x i1> %8, <4 x i32> undef)
    %wide.masked.load35 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv6567, i32 4, <4 x i1> %8, <4 x i32> undef)
    %10 = mul nsw <4 x i32> %wide.masked.load35, %wide.masked.load
    call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %10, <4 x i32>* %lsr.iv6870, i32 4, <4 x i1> %8)
    %scevgep63 = getelementptr i32, i32* %lsr.iv62, i32 4
    %scevgep66 = getelementptr i32, i32* %lsr.iv65, i32 4
    %scevgep69 = getelementptr i32, i32* %lsr.iv68, 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.cond4.preheader

  for.cond4.preheader:                              ; preds = %vector.body, %entry
    %cmp528 = icmp eq i32 %N, 0
    %13 = add i32 %N, 3
    %14 = lshr i32 %13, 2
    %15 = shl nuw i32 %14, 2
    %16 = add i32 %15, -4
    %17 = lshr i32 %16, 2
    %18 = add nuw nsw i32 %17, 1
    br i1 %cmp528, label %for.cond.cleanup6, label %vector.ph39

  vector.ph39:                                      ; preds = %for.cond4.preheader
    %start2 = call i32 @llvm.start.loop.iterations.i32(i32 %18)
    br label %vector.body38

  vector.body38:                                    ; preds = %vector.body38, %vector.ph39
    %lsr.iv59 = phi i32* [ %scevgep60, %vector.body38 ], [ %a, %vector.ph39 ]
    %lsr.iv56 = phi i32* [ %scevgep57, %vector.body38 ], [ %c, %vector.ph39 ]
    %lsr.iv = phi i32* [ %scevgep, %vector.body38 ], [ %b, %vector.ph39 ]
    %19 = phi i32 [ %start2, %vector.ph39 ], [ %25, %vector.body38 ]
    %20 = phi i32 [ %N, %vector.ph39 ], [ %22, %vector.body38 ]
    %lsr.iv5961 = bitcast i32* %lsr.iv59 to <4 x i32>*
    %lsr.iv5658 = bitcast i32* %lsr.iv56 to <4 x i32>*
    %lsr.iv55 = bitcast i32* %lsr.iv to <4 x i32>*
    %21 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %20)
    %22 = sub i32 %20, 4
    %wide.masked.load52 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv55, i32 4, <4 x i1> %21, <4 x i32> undef)
    %wide.masked.load53 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv5658, i32 4, <4 x i1> %21, <4 x i32> undef)
    %23 = xor <4 x i32> %wide.masked.load53, %wide.masked.load52
    %wide.masked.load54 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv5961, i32 4, <4 x i1> %21, <4 x i32> undef)
    %24 = add nsw <4 x i32> %wide.masked.load54, %23
    call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %24, <4 x i32>* %lsr.iv5961, i32 4, <4 x i1> %21)
    %scevgep = getelementptr i32, i32* %lsr.iv, i32 4
    %scevgep57 = getelementptr i32, i32* %lsr.iv56, i32 4
    %scevgep60 = getelementptr i32, i32* %lsr.iv59, i32 4
    %25 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %19, i32 1)
    %26 = icmp ne i32 %25, 0
    br i1 %26, label %vector.body38, label %for.cond.cleanup6

  for.cond.cleanup6:                                ; preds = %vector.body38, %for.cond4.preheader
    ret void
  }
  ; Function Attrs: nofree norecurse nounwind
  define dso_local arm_aapcs_vfpcc void @test3(i32* noalias nocapture %a, i32* nocapture readonly %b, i32* nocapture readonly %c, i32 %N) local_unnamed_addr {
  entry:
    %cmp54 = icmp eq 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 %cmp54, label %for.cond.cleanup17, label %vector.ph

  vector.ph:                                        ; preds = %entry
    %start1 = call i32 @llvm.start.loop.iterations.i32(i32 %5)
    br label %vector.body

  vector.body:                                      ; preds = %vector.body, %vector.ph
    %lsr.iv123 = phi i32* [ %scevgep124, %vector.body ], [ %a, %vector.ph ]
    %lsr.iv120 = phi i32* [ %scevgep121, %vector.body ], [ %c, %vector.ph ]
    %lsr.iv117 = phi i32* [ %scevgep118, %vector.body ], [ %b, %vector.ph ]
    %6 = phi i32 [ %start1, %vector.ph ], [ %11, %vector.body ]
    %7 = phi i32 [ %N, %vector.ph ], [ %9, %vector.body ]
    %lsr.iv123125 = bitcast i32* %lsr.iv123 to <4 x i32>*
    %lsr.iv120122 = bitcast i32* %lsr.iv120 to <4 x i32>*
    %lsr.iv117119 = bitcast i32* %lsr.iv117 to <4 x i32>*
    %8 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %7)
    %9 = sub i32 %7, 4
    %wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv117119, i32 4, <4 x i1> %8, <4 x i32> undef)
    %wide.masked.load62 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv120122, i32 4, <4 x i1> %8, <4 x i32> undef)
    %10 = mul nsw <4 x i32> %wide.masked.load62, %wide.masked.load
    call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %10, <4 x i32>* %lsr.iv123125, i32 4, <4 x i1> %8)
    %scevgep118 = getelementptr i32, i32* %lsr.iv117, i32 4
    %scevgep121 = getelementptr i32, i32* %lsr.iv120, i32 4
    %scevgep124 = getelementptr i32, i32* %lsr.iv123, 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.cond4.preheader

  for.cond4.preheader:                              ; preds = %vector.body
    %div = lshr i32 %N, 1
    %cmp552 = icmp eq i32 %div, 0
    %13 = add nuw i32 %div, 3
    %14 = lshr i32 %13, 2
    %15 = shl nuw i32 %14, 2
    %16 = add i32 %15, -4
    %17 = lshr i32 %16, 2
    %18 = add nuw nsw i32 %17, 1
    br i1 %cmp552, label %for.cond15.preheader, label %vector.ph66

  vector.ph66:                                      ; preds = %for.cond4.preheader
    %start2 = call i32 @llvm.start.loop.iterations.i32(i32 %18)
    br label %vector.body65

  vector.body65:                                    ; preds = %vector.body65, %vector.ph66
    %lsr.iv114 = phi i32* [ %scevgep115, %vector.body65 ], [ %a, %vector.ph66 ]
    %lsr.iv111 = phi i32* [ %scevgep112, %vector.body65 ], [ %c, %vector.ph66 ]
    %lsr.iv108 = phi i32* [ %scevgep109, %vector.body65 ], [ %b, %vector.ph66 ]
    %19 = phi i32 [ %start2, %vector.ph66 ], [ %25, %vector.body65 ]
    %20 = phi i32 [ %div, %vector.ph66 ], [ %22, %vector.body65 ]
    %lsr.iv114116 = bitcast i32* %lsr.iv114 to <4 x i32>*
    %lsr.iv111113 = bitcast i32* %lsr.iv111 to <4 x i32>*
    %lsr.iv108110 = bitcast i32* %lsr.iv108 to <4 x i32>*
    %21 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %20)
    %22 = sub i32 %20, 4
    %wide.masked.load79 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv108110, i32 4, <4 x i1> %21, <4 x i32> undef)
    %wide.masked.load80 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv111113, i32 4, <4 x i1> %21, <4 x i32> undef)
    %23 = xor <4 x i32> %wide.masked.load80, %wide.masked.load79
    %wide.masked.load81 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv114116, i32 4, <4 x i1> %21, <4 x i32> undef)
    %24 = add nsw <4 x i32> %wide.masked.load81, %23
    call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %24, <4 x i32>* %lsr.iv114116, i32 4, <4 x i1> %21)
    %scevgep109 = getelementptr i32, i32* %lsr.iv108, i32 4
    %scevgep112 = getelementptr i32, i32* %lsr.iv111, i32 4
    %scevgep115 = getelementptr i32, i32* %lsr.iv114, i32 4
    %25 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %19, i32 1)
    %26 = icmp ne i32 %25, 0
    br i1 %26, label %vector.body65, label %for.cond15.preheader

  for.cond15.preheader:                             ; preds = %vector.body65, %for.cond4.preheader
    %27 = icmp eq i32 %N, 0
    %28 = add i32 %N, 3
    %29 = lshr i32 %28, 2
    %30 = shl nuw i32 %29, 2
    %31 = add i32 %30, -4
    %32 = lshr i32 %31, 2
    %33 = add nuw nsw i32 %32, 1
    br i1 %27, label %for.cond.cleanup17, label %vector.ph85

  vector.ph85:                                      ; preds = %for.cond15.preheader
    %start3 = call i32 @llvm.start.loop.iterations.i32(i32 %33)
    br label %vector.body84

  vector.body84:                                    ; preds = %vector.body84, %vector.ph85
    %lsr.iv105 = phi i32* [ %scevgep106, %vector.body84 ], [ %a, %vector.ph85 ]
    %lsr.iv102 = phi i32* [ %scevgep103, %vector.body84 ], [ %c, %vector.ph85 ]
    %lsr.iv = phi i32* [ %scevgep, %vector.body84 ], [ %b, %vector.ph85 ]
    %34 = phi i32 [ %start3, %vector.ph85 ], [ %40, %vector.body84 ]
    %35 = phi i32 [ %N, %vector.ph85 ], [ %37, %vector.body84 ]
    %lsr.iv105107 = bitcast i32* %lsr.iv105 to <4 x i32>*
    %lsr.iv102104 = bitcast i32* %lsr.iv102 to <4 x i32>*
    %lsr.iv101 = bitcast i32* %lsr.iv to <4 x i32>*
    %36 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %35)
    %37 = sub i32 %35, 4
    %wide.masked.load98 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv101, i32 4, <4 x i1> %36, <4 x i32> undef)
    %wide.masked.load99 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv102104, i32 4, <4 x i1> %36, <4 x i32> undef)
    %wide.masked.load100 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv105107, i32 4, <4 x i1> %36, <4 x i32> undef)
    %38 = add <4 x i32> %wide.masked.load99, %wide.masked.load98
    %39 = sub <4 x i32> %wide.masked.load100, %38
    call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %39, <4 x i32>* %lsr.iv105107, i32 4, <4 x i1> %36)
    %scevgep = getelementptr i32, i32* %lsr.iv, i32 4
    %scevgep103 = getelementptr i32, i32* %lsr.iv102, i32 4
    %scevgep106 = getelementptr i32, i32* %lsr.iv105, i32 4
    %40 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %34, i32 1)
    %41 = icmp ne i32 %40, 0
    br i1 %41, label %vector.body84, label %for.cond.cleanup17

  for.cond.cleanup17:                               ; preds = %vector.body84, %entry, %for.cond15.preheader
    ret void
  }
  declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32 immarg, <4 x i1>, <4 x i32>)
  declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32 immarg, <4 x i1>)
  declare i32 @llvm.start.loop.iterations.i32(i32)
  declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32)
  declare <4 x i1> @llvm.arm.mve.vctp32(i32)

...
---
name:            test1
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:       24
  offsetAdjustment: -16
  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: '' }
  - { id: 2, name: '', type: spill-slot, offset: -12, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$r6', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
  - { id: 3, name: '', type: spill-slot, offset: -16, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$r5', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
  - { id: 4, name: '', type: spill-slot, offset: -20, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$r4', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
  - { id: 5, name: '', type: spill-slot, offset: -24, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$r8', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
callSites:       []
constants:       []
machineFunctionInfo: {}
body:             |
  ; CHECK-LABEL: name: test1
  ; CHECK: bb.0.entry:
  ; CHECK:   successors: %bb.6(0x30000000), %bb.1(0x50000000)
  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3, $r4, $r5, $r6, $r8
  ; CHECK:   frame-setup tPUSH 14 /* CC::al */, $noreg, killed $r4, killed $r5, killed $r6, killed $lr, implicit-def $sp, implicit $sp
  ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 20
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $lr, -4
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r7, -8
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r6, -12
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r5, -16
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r4, -20
  ; CHECK:   dead $r7 = frame-setup tADDrSPi $sp, 3, 14 /* CC::al */, $noreg
  ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa $r7, 8
  ; CHECK:   early-clobber $sp = frame-setup t2STR_PRE killed $r8, $sp, -4, 14 /* CC::al */, $noreg
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r8, -24
  ; CHECK:   tCMPi8 renamable $r3, 0, 14 /* CC::al */, $noreg, implicit-def $cpsr
  ; CHECK:   tBcc %bb.6, 0 /* CC::eq */, killed $cpsr
  ; CHECK: bb.1.vector.ph:
  ; CHECK:   successors: %bb.2(0x80000000)
  ; CHECK:   liveins: $r0, $r1, $r2, $r3
  ; CHECK:   $r8 = tMOVr $r0, 14 /* CC::al */, $noreg
  ; CHECK:   $r5 = tMOVr $r2, 14 /* CC::al */, $noreg
  ; CHECK:   $r4 = tMOVr $r3, 14 /* CC::al */, $noreg
  ; CHECK:   $r6 = tMOVr $r1, 14 /* CC::al */, $noreg
  ; CHECK:   $lr = MVE_DLSTP_32 killed renamable $r4
  ; CHECK: bb.2.vector.body:
  ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3, $r5, $r6, $r8
  ; CHECK:   renamable $r6, renamable $q0 = MVE_VLDRWU32_post killed renamable $r6, 16, 0, $noreg :: (load 16 from %ir.lsr.iv6264, align 4)
  ; CHECK:   renamable $r5, renamable $q1 = MVE_VLDRWU32_post killed renamable $r5, 16, 0, $noreg :: (load 16 from %ir.lsr.iv6567, align 4)
  ; CHECK:   renamable $q0 = nsw MVE_VMULi32 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
  ; CHECK:   renamable $r8 = MVE_VSTRWU32_post killed renamable $q0, killed renamable $r8, 16, 0, killed $noreg :: (store 16 into %ir.lsr.iv6870, align 4)
  ; CHECK:   $lr = MVE_LETP killed renamable $lr, %bb.2
  ; CHECK: bb.3.for.cond4.preheader:
  ; CHECK:   successors: %bb.6(0x30000000), %bb.4(0x50000000)
  ; CHECK:   liveins: $r0, $r1, $r2, $r3
  ; CHECK:   tCBZ $r3, %bb.6
  ; CHECK: bb.4.vector.ph39:
  ; CHECK:   successors: %bb.5(0x80000000)
  ; CHECK:   liveins: $r0, $r1, $r2, $r3
  ; CHECK:   $r12 = tMOVr $r0, 14 /* CC::al */, $noreg
  ; CHECK:   $lr = MVE_DLSTP_32 killed renamable $r3
  ; CHECK: bb.5.vector.body38:
  ; CHECK:   successors: %bb.5(0x7c000000), %bb.6(0x04000000)
  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r12
  ; CHECK:   renamable $r1, renamable $q0 = MVE_VLDRWU32_post killed renamable $r1, 16, 0, $noreg :: (load 16 from %ir.lsr.iv55, align 4)
  ; CHECK:   renamable $r2, renamable $q1 = MVE_VLDRWU32_post killed renamable $r2, 16, 0, $noreg :: (load 16 from %ir.lsr.iv5658, align 4)
  ; CHECK:   renamable $r12, renamable $q2 = MVE_VLDRWU32_post killed renamable $r12, 16, 0, $noreg :: (load 16 from %ir.lsr.iv5961, align 4)
  ; CHECK:   renamable $q0 = MVE_VEOR killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
  ; CHECK:   renamable $q0 = nsw MVE_VADDi32 killed renamable $q2, killed renamable $q0, 0, $noreg, undef renamable $q0
  ; CHECK:   MVE_VSTRWU32 killed renamable $q0, killed renamable $r0, 0, 0, killed $noreg :: (store 16 into %ir.lsr.iv5961, align 4)
  ; CHECK:   $r0 = tMOVr $r12, 14 /* CC::al */, $noreg
  ; CHECK:   $lr = MVE_LETP killed renamable $lr, %bb.5
  ; CHECK: bb.6.for.cond.cleanup6:
  ; CHECK:   $r8, $sp = t2LDR_POST $sp, 4, 14 /* CC::al */, $noreg
  ; CHECK:   tPOP_RET 14 /* CC::al */, $noreg, def $r4, def $r5, def $r6, def $r7, def $pc
  bb.0.entry:
    successors: %bb.6(0x30000000), %bb.1(0x50000000)
    liveins: $r0, $r1, $r2, $r3, $r4, $r5, $r6, $lr, $r8

    frame-setup tPUSH 14, $noreg, killed $r4, killed $r5, killed $r6, killed $lr, implicit-def $sp, implicit $sp
    frame-setup CFI_INSTRUCTION def_cfa_offset 20
    frame-setup CFI_INSTRUCTION offset $lr, -4
    frame-setup CFI_INSTRUCTION offset $r7, -8
    frame-setup CFI_INSTRUCTION offset $r6, -12
    frame-setup CFI_INSTRUCTION offset $r5, -16
    frame-setup CFI_INSTRUCTION offset $r4, -20
    $r7 = frame-setup tADDrSPi $sp, 3, 14, $noreg
    frame-setup CFI_INSTRUCTION def_cfa $r7, 8
    early-clobber $sp = frame-setup t2STR_PRE killed $r8, $sp, -4, 14, $noreg
    frame-setup CFI_INSTRUCTION offset $r8, -24
    tCMPi8 renamable $r3, 0, 14, $noreg, implicit-def $cpsr
    tBcc %bb.6, 0, killed $cpsr

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

    renamable $r6, dead $cpsr = tADDi3 renamable $r3, 3, 14, $noreg
    $r8 = tMOVr $r0, 14, $noreg
    renamable $r6 = t2BICri killed renamable $r6, 3, 14, $noreg, $noreg
    $r5 = tMOVr $r2, 14, $noreg
    renamable $r12 = t2SUBri killed renamable $r6, 4, 14, $noreg, $noreg
    renamable $r6, dead $cpsr = tMOVi8 1, 14, $noreg
    $r4 = tMOVr $r3, 14, $noreg
    renamable $lr = nuw nsw t2ADDrs killed renamable $r6, renamable $r12, 19, 14, $noreg, $noreg
    $r6 = tMOVr $r1, 14, $noreg
    $lr = t2DoLoopStart renamable $lr

  bb.2.vector.body:
    successors: %bb.2(0x7c000000), %bb.3(0x04000000)
    liveins: $lr, $r0, $r1, $r2, $r3, $r4, $r5, $r6, $r8, $r12

    renamable $vpr = MVE_VCTP32 renamable $r4, 0, $noreg
    MVE_VPST 4, implicit $vpr
    renamable $r6, renamable $q0 = MVE_VLDRWU32_post killed renamable $r6, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv6264, align 4)
    renamable $r5, renamable $q1 = MVE_VLDRWU32_post killed renamable $r5, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv6567, align 4)
    renamable $r4, dead $cpsr = tSUBi8 killed renamable $r4, 4, 14, $noreg
    renamable $q0 = nsw MVE_VMULi32 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
    MVE_VPST 8, implicit $vpr
    renamable $r8 = MVE_VSTRWU32_post killed renamable $q0, killed renamable $r8, 16, 1, killed renamable $vpr :: (store 16 into %ir.lsr.iv6870, 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.cond4.preheader:
    successors: %bb.6(0x30000000), %bb.4(0x50000000)
    liveins: $r0, $r1, $r2, $r3, $r12

    tCBZ $r3, %bb.6

  bb.4.vector.ph39:
    successors: %bb.5(0x80000000)
    liveins: $r0, $r1, $r2, $r3, $r12

    renamable $r6, dead $cpsr = tMOVi8 1, 14, $noreg
    renamable $lr = nuw nsw t2ADDrs killed renamable $r6, killed renamable $r12, 19, 14, $noreg, $noreg
    $r12 = tMOVr $r0, 14, $noreg
    $lr = t2DoLoopStart renamable $lr

  bb.5.vector.body38:
    successors: %bb.5(0x7c000000), %bb.6(0x04000000)
    liveins: $lr, $r0, $r1, $r2, $r3, $r12

    renamable $vpr = MVE_VCTP32 renamable $r3, 0, $noreg
    MVE_VPST 2, implicit $vpr
    renamable $r1, renamable $q0 = MVE_VLDRWU32_post killed renamable $r1, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv55, align 4)
    renamable $r2, renamable $q1 = MVE_VLDRWU32_post killed renamable $r2, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv5658, align 4)
    renamable $r12, renamable $q2 = MVE_VLDRWU32_post killed renamable $r12, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv5961, align 4)
    renamable $q0 = MVE_VEOR killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
    renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 4, 14, $noreg
    renamable $q0 = nsw MVE_VADDi32 killed renamable $q2, killed renamable $q0, 0, $noreg, undef renamable $q0
    MVE_VPST 8, implicit $vpr
    MVE_VSTRWU32 killed renamable $q0, killed renamable $r0, 0, 1, killed renamable $vpr :: (store 16 into %ir.lsr.iv5961, align 4)
    renamable $lr = t2LoopDec killed renamable $lr, 1
    $r0 = tMOVr $r12, 14, $noreg
    t2LoopEnd renamable $lr, %bb.5, implicit-def dead $cpsr
    tB %bb.6, 14, $noreg

  bb.6.for.cond.cleanup6:
    $r8, $sp = t2LDR_POST $sp, 4, 14, $noreg
    tPOP_RET 14, $noreg, def $r4, def $r5, def $r6, def $r7, def $pc

...
---
name:            test2
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:       24
  offsetAdjustment: -16
  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: '' }
  - { id: 2, name: '', type: spill-slot, offset: -12, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$r6', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
  - { id: 3, name: '', type: spill-slot, offset: -16, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$r5', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
  - { id: 4, name: '', type: spill-slot, offset: -20, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$r4', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
  - { id: 5, name: '', type: spill-slot, offset: -24, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$r8', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
callSites:       []
constants:       []
machineFunctionInfo: {}
body:             |
  ; CHECK-LABEL: name: test2
  ; CHECK: bb.0.entry:
  ; CHECK:   successors: %bb.3(0x30000000), %bb.1(0x50000000)
  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3, $r4, $r5, $r6, $r8
  ; CHECK:   frame-setup tPUSH 14 /* CC::al */, $noreg, killed $r4, killed $r5, killed $r6, killed $lr, implicit-def $sp, implicit $sp
  ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 20
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $lr, -4
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r7, -8
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r6, -12
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r5, -16
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r4, -20
  ; CHECK:   dead $r7 = frame-setup tADDrSPi $sp, 3, 14 /* CC::al */, $noreg
  ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa $r7, 8
  ; CHECK:   early-clobber $sp = frame-setup t2STR_PRE killed $r8, $sp, -4, 14 /* CC::al */, $noreg
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r8, -24
  ; CHECK:   renamable $r6, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
  ; CHECK:   t2CMPrs killed renamable $r6, renamable $r3, 11, 14 /* CC::al */, $noreg, implicit-def $cpsr
  ; CHECK:   tBcc %bb.3, 0 /* CC::eq */, killed $cpsr
  ; CHECK: bb.1.vector.ph:
  ; CHECK:   successors: %bb.2(0x80000000)
  ; CHECK:   liveins: $r0, $r1, $r2, $r3
  ; CHECK:   renamable $r4, dead $cpsr = tLSRri renamable $r3, 1, 14 /* CC::al */, $noreg
  ; CHECK:   $r8 = tMOVr $r0, 14 /* CC::al */, $noreg
  ; CHECK:   $r5 = tMOVr $r1, 14 /* CC::al */, $noreg
  ; CHECK:   $r6 = tMOVr $r2, 14 /* CC::al */, $noreg
  ; CHECK:   $lr = MVE_DLSTP_32 killed renamable $r4
  ; CHECK: bb.2.vector.body:
  ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3, $r5, $r6, $r8
  ; CHECK:   renamable $r5, renamable $q0 = MVE_VLDRWU32_post killed renamable $r5, 16, 0, $noreg :: (load 16 from %ir.lsr.iv6264, align 4)
  ; CHECK:   renamable $r6, renamable $q1 = MVE_VLDRWU32_post killed renamable $r6, 16, 0, $noreg :: (load 16 from %ir.lsr.iv6567, align 4)
  ; CHECK:   renamable $q0 = nsw MVE_VMULi32 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
  ; CHECK:   renamable $r8 = MVE_VSTRWU32_post killed renamable $q0, killed renamable $r8, 16, 0, killed $noreg :: (store 16 into %ir.lsr.iv6870, align 4)
  ; CHECK:   $lr = MVE_LETP killed renamable $lr, %bb.2
  ; CHECK: bb.3.for.cond4.preheader:
  ; CHECK:   successors: %bb.6(0x30000000), %bb.4(0x50000000)
  ; CHECK:   liveins: $r0, $r1, $r2, $r3
  ; CHECK:   tCBZ $r3, %bb.6
  ; CHECK: bb.4.vector.ph39:
  ; CHECK:   successors: %bb.5(0x80000000)
  ; CHECK:   liveins: $r0, $r1, $r2, $r3
  ; CHECK:   $r4 = tMOVr $r0, 14 /* CC::al */, $noreg
  ; CHECK:   $lr = MVE_DLSTP_32 killed renamable $r3
  ; CHECK: bb.5.vector.body38:
  ; CHECK:   successors: %bb.5(0x7c000000), %bb.6(0x04000000)
  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r4
  ; CHECK:   renamable $r1, renamable $q0 = MVE_VLDRWU32_post killed renamable $r1, 16, 0, $noreg :: (load 16 from %ir.lsr.iv55, align 4)
  ; CHECK:   renamable $r2, renamable $q1 = MVE_VLDRWU32_post killed renamable $r2, 16, 0, $noreg :: (load 16 from %ir.lsr.iv5658, align 4)
  ; CHECK:   renamable $r4, renamable $q2 = MVE_VLDRWU32_post killed renamable $r4, 16, 0, $noreg :: (load 16 from %ir.lsr.iv5961, align 4)
  ; CHECK:   renamable $q0 = MVE_VEOR killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
  ; CHECK:   renamable $q0 = nsw MVE_VADDi32 killed renamable $q2, killed renamable $q0, 0, $noreg, undef renamable $q0
  ; CHECK:   MVE_VSTRWU32 killed renamable $q0, killed renamable $r0, 0, 0, killed $noreg :: (store 16 into %ir.lsr.iv5961, align 4)
  ; CHECK:   $r0 = tMOVr $r4, 14 /* CC::al */, $noreg
  ; CHECK:   $lr = MVE_LETP killed renamable $lr, %bb.5
  ; CHECK: bb.6.for.cond.cleanup6:
  ; CHECK:   $r8, $sp = t2LDR_POST $sp, 4, 14 /* CC::al */, $noreg
  ; CHECK:   tPOP_RET 14 /* CC::al */, $noreg, def $r4, def $r5, def $r6, def $r7, def $pc
  bb.0.entry:
    successors: %bb.3(0x30000000), %bb.1(0x50000000)
    liveins: $r0, $r1, $r2, $r3, $r4, $r5, $r6, $lr, $r8

    frame-setup tPUSH 14, $noreg, killed $r4, killed $r5, killed $r6, killed $lr, implicit-def $sp, implicit $sp
    frame-setup CFI_INSTRUCTION def_cfa_offset 20
    frame-setup CFI_INSTRUCTION offset $lr, -4
    frame-setup CFI_INSTRUCTION offset $r7, -8
    frame-setup CFI_INSTRUCTION offset $r6, -12
    frame-setup CFI_INSTRUCTION offset $r5, -16
    frame-setup CFI_INSTRUCTION offset $r4, -20
    $r7 = frame-setup tADDrSPi $sp, 3, 14, $noreg
    frame-setup CFI_INSTRUCTION def_cfa $r7, 8
    early-clobber $sp = frame-setup t2STR_PRE killed $r8, $sp, -4, 14, $noreg
    frame-setup CFI_INSTRUCTION offset $r8, -24
    renamable $r6, dead $cpsr = tMOVi8 0, 14, $noreg
    renamable $r12 = t2MOVi 1, 14, $noreg, $noreg
    t2CMPrs killed renamable $r6, renamable $r3, 11, 14, $noreg, implicit-def $cpsr
    tBcc %bb.3, 0, killed $cpsr

  bb.1.vector.ph:
    successors: %bb.2(0x80000000)
    liveins: $r0, $r1, $r2, $r3, $r12

    renamable $r6, dead $cpsr = tMOVi8 3, 14, $noreg
    renamable $r4, dead $cpsr = tLSRri renamable $r3, 1, 14, $noreg
    renamable $r6 = nuw t2ADDrs killed renamable $r6, renamable $r3, 11, 14, $noreg, $noreg
    $r8 = tMOVr $r0, 14, $noreg
    renamable $r6 = t2BICri killed renamable $r6, 3, 14, $noreg, $noreg
    $r5 = tMOVr $r1, 14, $noreg
    renamable $r6, dead $cpsr = tSUBi8 killed renamable $r6, 4, 14, $noreg
    renamable $lr = nuw nsw t2ADDrs renamable $r12, killed renamable $r6, 19, 14, $noreg, $noreg
    $r6 = tMOVr $r2, 14, $noreg
    $lr = t2DoLoopStart renamable $lr

  bb.2.vector.body:
    successors: %bb.2(0x7c000000), %bb.3(0x04000000)
    liveins: $lr, $r0, $r1, $r2, $r3, $r4, $r5, $r6, $r8, $r12

    renamable $vpr = MVE_VCTP32 renamable $r4, 0, $noreg
    MVE_VPST 4, implicit $vpr
    renamable $r5, renamable $q0 = MVE_VLDRWU32_post killed renamable $r5, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv6264, align 4)
    renamable $r6, renamable $q1 = MVE_VLDRWU32_post killed renamable $r6, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv6567, align 4)
    renamable $r4, dead $cpsr = tSUBi8 killed renamable $r4, 4, 14, $noreg
    renamable $q0 = nsw MVE_VMULi32 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
    MVE_VPST 8, implicit $vpr
    renamable $r8 = MVE_VSTRWU32_post killed renamable $q0, killed renamable $r8, 16, 1, killed renamable $vpr :: (store 16 into %ir.lsr.iv6870, 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.cond4.preheader:
    successors: %bb.6(0x30000000), %bb.4(0x50000000)
    liveins: $r0, $r1, $r2, $r3, $r12

    tCBZ $r3, %bb.6

  bb.4.vector.ph39:
    successors: %bb.5(0x80000000)
    liveins: $r0, $r1, $r2, $r3, $r12

    renamable $r6, dead $cpsr = tADDi3 renamable $r3, 3, 14, $noreg
    $r4 = tMOVr $r0, 14, $noreg
    renamable $r6 = t2BICri killed renamable $r6, 3, 14, $noreg, $noreg
    renamable $r6, dead $cpsr = tSUBi8 killed renamable $r6, 4, 14, $noreg
    renamable $lr = nuw nsw t2ADDrs killed renamable $r12, killed renamable $r6, 19, 14, $noreg, $noreg
    $lr = t2DoLoopStart renamable $lr

  bb.5.vector.body38:
    successors: %bb.5(0x7c000000), %bb.6(0x04000000)
    liveins: $lr, $r0, $r1, $r2, $r3, $r4

    renamable $vpr = MVE_VCTP32 renamable $r3, 0, $noreg
    MVE_VPST 2, implicit $vpr
    renamable $r1, renamable $q0 = MVE_VLDRWU32_post killed renamable $r1, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv55, align 4)
    renamable $r2, renamable $q1 = MVE_VLDRWU32_post killed renamable $r2, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv5658, align 4)
    renamable $r4, renamable $q2 = MVE_VLDRWU32_post killed renamable $r4, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv5961, align 4)
    renamable $q0 = MVE_VEOR killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
    renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 4, 14, $noreg
    renamable $q0 = nsw MVE_VADDi32 killed renamable $q2, killed renamable $q0, 0, $noreg, undef renamable $q0
    MVE_VPST 8, implicit $vpr
    MVE_VSTRWU32 killed renamable $q0, killed renamable $r0, 0, 1, killed renamable $vpr :: (store 16 into %ir.lsr.iv5961, align 4)
    renamable $lr = t2LoopDec killed renamable $lr, 1
    $r0 = tMOVr $r4, 14, $noreg
    t2LoopEnd renamable $lr, %bb.5, implicit-def dead $cpsr
    tB %bb.6, 14, $noreg

  bb.6.for.cond.cleanup6:
    $r8, $sp = t2LDR_POST $sp, 4, 14, $noreg
    tPOP_RET 14, $noreg, def $r4, def $r5, def $r6, def $r7, def $pc

...
---
name:            test3
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:       32
  offsetAdjustment: -24
  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: '' }
  - { id: 2, name: '', type: spill-slot, offset: -12, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$r6', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
  - { id: 3, name: '', type: spill-slot, offset: -16, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$r5', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
  - { id: 4, name: '', type: spill-slot, offset: -20, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$r4', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
  - { id: 5, name: '', type: spill-slot, offset: -24, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$r10', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
  - { id: 6, name: '', type: spill-slot, offset: -28, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$r9', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
  - { id: 7, name: '', type: spill-slot, offset: -32, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$r8', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
callSites:       []
constants:       []
machineFunctionInfo: {}
body:             |
  ; CHECK-LABEL: name: test3
  ; CHECK: bb.0.entry:
  ; CHECK:   successors: %bb.9(0x30000000), %bb.1(0x50000000)
  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3, $r4, $r5, $r6, $r8, $r9, $r10
  ; CHECK:   frame-setup tPUSH 14 /* CC::al */, $noreg, killed $r4, killed $r5, killed $r6, killed $lr, implicit-def $sp, implicit $sp
  ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 20
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $lr, -4
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r7, -8
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r6, -12
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r5, -16
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r4, -20
  ; CHECK:   dead $r7 = frame-setup tADDrSPi $sp, 3, 14 /* CC::al */, $noreg
  ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa $r7, 8
  ; CHECK:   $sp = frame-setup t2STMDB_UPD $sp, 14 /* CC::al */, $noreg, killed $r8, killed $r9, killed $r10
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r10, -24
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r9, -28
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r8, -32
  ; CHECK:   tCMPi8 renamable $r3, 0, 14 /* CC::al */, $noreg, implicit-def $cpsr
  ; CHECK:   tBcc %bb.9, 0 /* CC::eq */, killed $cpsr
  ; CHECK: bb.1.vector.ph:
  ; CHECK:   successors: %bb.2(0x80000000)
  ; CHECK:   liveins: $r0, $r1, $r2, $r3
  ; CHECK:   $r8 = tMOVr $r0, 14 /* CC::al */, $noreg
  ; CHECK:   $r5 = tMOVr $r2, 14 /* CC::al */, $noreg
  ; CHECK:   $r4 = tMOVr $r3, 14 /* CC::al */, $noreg
  ; CHECK:   $r6 = tMOVr $r1, 14 /* CC::al */, $noreg
  ; CHECK:   $lr = MVE_DLSTP_32 killed renamable $r4
  ; CHECK: bb.2.vector.body:
  ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3, $r5, $r6, $r8
  ; CHECK:   renamable $r6, renamable $q0 = MVE_VLDRWU32_post killed renamable $r6, 16, 0, $noreg :: (load 16 from %ir.lsr.iv117119, align 4)
  ; CHECK:   renamable $r5, renamable $q1 = MVE_VLDRWU32_post killed renamable $r5, 16, 0, $noreg :: (load 16 from %ir.lsr.iv120122, align 4)
  ; CHECK:   renamable $q0 = nsw MVE_VMULi32 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
  ; CHECK:   renamable $r8 = MVE_VSTRWU32_post killed renamable $q0, killed renamable $r8, 16, 0, killed $noreg :: (store 16 into %ir.lsr.iv123125, align 4)
  ; CHECK:   $lr = MVE_LETP killed renamable $lr, %bb.2
  ; CHECK: bb.3.for.cond4.preheader:
  ; CHECK:   successors: %bb.6(0x30000000), %bb.4(0x50000000)
  ; CHECK:   liveins: $r0, $r1, $r2, $r3
  ; CHECK:   renamable $r6, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
  ; CHECK:   t2CMPrs killed renamable $r6, renamable $r3, 11, 14 /* CC::al */, $noreg, implicit-def $cpsr
  ; CHECK:   tBcc %bb.6, 0 /* CC::eq */, killed $cpsr
  ; CHECK: bb.4.vector.ph66:
  ; CHECK:   successors: %bb.5(0x80000000)
  ; CHECK:   liveins: $r0, $r1, $r2, $r3
  ; CHECK:   renamable $r5, dead $cpsr = tLSRri renamable $r3, 1, 14 /* CC::al */, $noreg
  ; CHECK:   $r10 = tMOVr $r0, 14 /* CC::al */, $noreg
  ; CHECK:   $r9 = tMOVr $r2, 14 /* CC::al */, $noreg
  ; CHECK:   $r4 = tMOVr $r1, 14 /* CC::al */, $noreg
  ; CHECK:   $r6 = tMOVr $r0, 14 /* CC::al */, $noreg
  ; CHECK:   $lr = MVE_DLSTP_32 killed renamable $r5
  ; CHECK: bb.5.vector.body65:
  ; CHECK:   successors: %bb.5(0x7c000000), %bb.6(0x04000000)
  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3, $r4, $r6, $r9, $r10
  ; CHECK:   renamable $r4, renamable $q0 = MVE_VLDRWU32_post killed renamable $r4, 16, 0, $noreg :: (load 16 from %ir.lsr.iv108110, align 4)
  ; CHECK:   renamable $r9, renamable $q1 = MVE_VLDRWU32_post killed renamable $r9, 16, 0, $noreg :: (load 16 from %ir.lsr.iv111113, align 4)
  ; CHECK:   renamable $r6, renamable $q2 = MVE_VLDRWU32_post killed renamable $r6, 16, 0, $noreg :: (load 16 from %ir.lsr.iv114116, align 4)
  ; CHECK:   renamable $q0 = MVE_VEOR killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
  ; CHECK:   renamable $q0 = nsw MVE_VADDi32 killed renamable $q2, killed renamable $q0, 0, $noreg, undef renamable $q0
  ; CHECK:   MVE_VSTRWU32 killed renamable $q0, killed renamable $r10, 0, 0, killed $noreg :: (store 16 into %ir.lsr.iv114116, align 4)
  ; CHECK:   $r10 = tMOVr $r6, 14 /* CC::al */, $noreg
  ; CHECK:   $lr = MVE_LETP killed renamable $lr, %bb.5
  ; CHECK: bb.6.for.cond15.preheader:
  ; CHECK:   successors: %bb.9(0x30000000), %bb.7(0x50000000)
  ; CHECK:   liveins: $r0, $r1, $r2, $r3
  ; CHECK:   tCBZ $r3, %bb.9
  ; CHECK: bb.7.vector.ph85:
  ; CHECK:   successors: %bb.8(0x80000000)
  ; CHECK:   liveins: $r0, $r1, $r2, $r3
  ; CHECK:   $r5 = tMOVr $r0, 14 /* CC::al */, $noreg
  ; CHECK:   $lr = MVE_DLSTP_32 killed renamable $r3
  ; CHECK: bb.8.vector.body84:
  ; CHECK:   successors: %bb.8(0x7c000000), %bb.9(0x04000000)
  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r5
  ; CHECK:   renamable $r1, renamable $q0 = MVE_VLDRWU32_post killed renamable $r1, 16, 0, $noreg :: (load 16 from %ir.lsr.iv101, align 4)
  ; CHECK:   renamable $r2, renamable $q1 = MVE_VLDRWU32_post killed renamable $r2, 16, 0, $noreg :: (load 16 from %ir.lsr.iv102104, align 4)
  ; CHECK:   renamable $r5, renamable $q2 = MVE_VLDRWU32_post killed renamable $r5, 16, 0, $noreg :: (load 16 from %ir.lsr.iv105107, align 4)
  ; CHECK:   renamable $q0 = MVE_VADDi32 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
  ; CHECK:   renamable $q0 = MVE_VSUBi32 killed renamable $q2, killed renamable $q0, 0, $noreg, undef renamable $q0
  ; CHECK:   MVE_VSTRWU32 killed renamable $q0, killed renamable $r0, 0, 0, killed $noreg :: (store 16 into %ir.lsr.iv105107, align 4)
  ; CHECK:   $r0 = tMOVr $r5, 14 /* CC::al */, $noreg
  ; CHECK:   $lr = MVE_LETP killed renamable $lr, %bb.8
  ; CHECK: bb.9.for.cond.cleanup17:
  ; CHECK:   $sp = t2LDMIA_UPD $sp, 14 /* CC::al */, $noreg, def $r8, def $r9, def $r10
  ; CHECK:   tPOP_RET 14 /* CC::al */, $noreg, def $r4, def $r5, def $r6, def $r7, def $pc
  bb.0.entry:
    successors: %bb.9(0x30000000), %bb.1(0x50000000)
    liveins: $r0, $r1, $r2, $r3, $r4, $r5, $r6, $lr, $r8, $r9, $r10

    frame-setup tPUSH 14, $noreg, killed $r4, killed $r5, killed $r6, killed $lr, implicit-def $sp, implicit $sp
    frame-setup CFI_INSTRUCTION def_cfa_offset 20
    frame-setup CFI_INSTRUCTION offset $lr, -4
    frame-setup CFI_INSTRUCTION offset $r7, -8
    frame-setup CFI_INSTRUCTION offset $r6, -12
    frame-setup CFI_INSTRUCTION offset $r5, -16
    frame-setup CFI_INSTRUCTION offset $r4, -20
    $r7 = frame-setup tADDrSPi $sp, 3, 14, $noreg
    frame-setup CFI_INSTRUCTION def_cfa $r7, 8
    $sp = frame-setup t2STMDB_UPD $sp, 14, $noreg, killed $r8, killed $r9, killed $r10
    frame-setup CFI_INSTRUCTION offset $r10, -24
    frame-setup CFI_INSTRUCTION offset $r9, -28
    frame-setup CFI_INSTRUCTION offset $r8, -32
    tCMPi8 renamable $r3, 0, 14, $noreg, implicit-def $cpsr
    tBcc %bb.9, 0, killed $cpsr

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

    renamable $r6, dead $cpsr = tADDi3 renamable $r3, 3, 14, $noreg
    $r8 = tMOVr $r0, 14, $noreg
    renamable $r6 = t2BICri killed renamable $r6, 3, 14, $noreg, $noreg
    $r5 = tMOVr $r2, 14, $noreg
    renamable $r12 = t2SUBri killed renamable $r6, 4, 14, $noreg, $noreg
    renamable $r6, dead $cpsr = tMOVi8 1, 14, $noreg
    $r4 = tMOVr $r3, 14, $noreg
    renamable $lr = nuw nsw t2ADDrs killed renamable $r6, renamable $r12, 19, 14, $noreg, $noreg
    $r6 = tMOVr $r1, 14, $noreg
    $lr = t2DoLoopStart renamable $lr

  bb.2.vector.body:
    successors: %bb.2(0x7c000000), %bb.3(0x04000000)
    liveins: $lr, $r0, $r1, $r2, $r3, $r4, $r5, $r6, $r8, $r12

    renamable $vpr = MVE_VCTP32 renamable $r4, 0, $noreg
    MVE_VPST 4, implicit $vpr
    renamable $r6, renamable $q0 = MVE_VLDRWU32_post killed renamable $r6, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv117119, align 4)
    renamable $r5, renamable $q1 = MVE_VLDRWU32_post killed renamable $r5, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv120122, align 4)
    renamable $r4, dead $cpsr = tSUBi8 killed renamable $r4, 4, 14, $noreg
    renamable $q0 = nsw MVE_VMULi32 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
    MVE_VPST 8, implicit $vpr
    renamable $r8 = MVE_VSTRWU32_post killed renamable $q0, killed renamable $r8, 16, 1, killed renamable $vpr :: (store 16 into %ir.lsr.iv123125, 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.cond4.preheader:
    successors: %bb.6(0x30000000), %bb.4(0x50000000)
    liveins: $r0, $r1, $r2, $r3, $r12

    renamable $r6, dead $cpsr = tMOVi8 0, 14, $noreg
    renamable $r8 = t2MOVi 1, 14, $noreg, $noreg
    t2CMPrs killed renamable $r6, renamable $r3, 11, 14, $noreg, implicit-def $cpsr
    tBcc %bb.6, 0, killed $cpsr

  bb.4.vector.ph66:
    successors: %bb.5(0x80000000)
    liveins: $r0, $r1, $r2, $r3, $r8, $r12

    renamable $r6, dead $cpsr = tMOVi8 3, 14, $noreg
    renamable $r5, dead $cpsr = tLSRri renamable $r3, 1, 14, $noreg
    renamable $r6 = nuw t2ADDrs killed renamable $r6, renamable $r3, 11, 14, $noreg, $noreg
    $r10 = tMOVr $r0, 14, $noreg
    renamable $r6 = t2BICri killed renamable $r6, 3, 14, $noreg, $noreg
    $r9 = tMOVr $r2, 14, $noreg
    renamable $r6, dead $cpsr = tSUBi8 killed renamable $r6, 4, 14, $noreg
    $r4 = tMOVr $r1, 14, $noreg
    renamable $lr = nuw nsw t2ADDrs renamable $r8, killed renamable $r6, 19, 14, $noreg, $noreg
    $r6 = tMOVr $r0, 14, $noreg
    $lr = t2DoLoopStart renamable $lr

  bb.5.vector.body65:
    successors: %bb.5(0x7c000000), %bb.6(0x04000000)
    liveins: $lr, $r0, $r1, $r2, $r3, $r4, $r5, $r6, $r8, $r9, $r10, $r12

    renamable $vpr = MVE_VCTP32 renamable $r5, 0, $noreg
    MVE_VPST 2, implicit $vpr
    renamable $r4, renamable $q0 = MVE_VLDRWU32_post killed renamable $r4, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv108110, align 4)
    renamable $r9, renamable $q1 = MVE_VLDRWU32_post killed renamable $r9, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv111113, align 4)
    renamable $r6, renamable $q2 = MVE_VLDRWU32_post killed renamable $r6, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv114116, align 4)
    renamable $q0 = MVE_VEOR killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
    renamable $r5, dead $cpsr = tSUBi8 killed renamable $r5, 4, 14, $noreg
    renamable $q0 = nsw MVE_VADDi32 killed renamable $q2, killed renamable $q0, 0, $noreg, undef renamable $q0
    MVE_VPST 8, implicit $vpr
    MVE_VSTRWU32 killed renamable $q0, killed renamable $r10, 0, 1, killed renamable $vpr :: (store 16 into %ir.lsr.iv114116, align 4)
    renamable $lr = t2LoopDec killed renamable $lr, 1
    $r10 = tMOVr $r6, 14, $noreg
    t2LoopEnd renamable $lr, %bb.5, implicit-def dead $cpsr
    tB %bb.6, 14, $noreg

  bb.6.for.cond15.preheader:
    successors: %bb.9(0x30000000), %bb.7(0x50000000)
    liveins: $r0, $r1, $r2, $r3, $r8, $r12

    tCBZ $r3, %bb.9

  bb.7.vector.ph85:
    successors: %bb.8(0x80000000)
    liveins: $r0, $r1, $r2, $r3, $r8, $r12

    renamable $lr = nuw nsw t2ADDrs killed renamable $r8, killed renamable $r12, 19, 14, $noreg, $noreg
    $r5 = tMOVr $r0, 14, $noreg
    $lr = t2DoLoopStart renamable $lr

  bb.8.vector.body84:
    successors: %bb.8(0x7c000000), %bb.9(0x04000000)
    liveins: $lr, $r0, $r1, $r2, $r3, $r5

    renamable $vpr = MVE_VCTP32 renamable $r3, 0, $noreg
    MVE_VPST 2, implicit $vpr
    renamable $r1, renamable $q0 = MVE_VLDRWU32_post killed renamable $r1, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv101, align 4)
    renamable $r2, renamable $q1 = MVE_VLDRWU32_post killed renamable $r2, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv102104, align 4)
    renamable $r5, renamable $q2 = MVE_VLDRWU32_post killed renamable $r5, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv105107, align 4)
    renamable $q0 = MVE_VADDi32 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
    renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 4, 14, $noreg
    renamable $q0 = MVE_VSUBi32 killed renamable $q2, killed renamable $q0, 0, $noreg, undef renamable $q0
    MVE_VPST 8, implicit $vpr
    MVE_VSTRWU32 killed renamable $q0, killed renamable $r0, 0, 1, killed renamable $vpr :: (store 16 into %ir.lsr.iv105107, align 4)
    renamable $lr = t2LoopDec killed renamable $lr, 1
    $r0 = tMOVr $r5, 14, $noreg
    t2LoopEnd renamable $lr, %bb.8, implicit-def dead $cpsr
    tB %bb.9, 14, $noreg

  bb.9.for.cond.cleanup17:
    $sp = t2LDMIA_UPD $sp, 14, $noreg, def $r8, def $r9, def $r10
    tPOP_RET 14, $noreg, def $r4, def $r5, def $r6, def $r7, def $pc

...