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

--- |
  define dso_local arm_aapcs_vfpcc float @insert_after_vdup_1(float* nocapture readonly %a, float* nocapture readonly %b, float %init, i32 %N) {
  entry:
    %cmp8.not = 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 %cmp8.not, label %for.cond.cleanup, label %vector.ph

  vector.ph:                                        ; preds = %entry
    %6 = insertelement <4 x float> <float undef, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00>, float %init, i32 0
    %start = call i32 @llvm.start.loop.iterations.i32(i32 %5)
    br label %vector.body

  vector.body:                                      ; preds = %vector.body, %vector.ph
    %lsr.iv13 = phi float* [ %scevgep14, %vector.body ], [ %b, %vector.ph ]
    %lsr.iv = phi float* [ %scevgep, %vector.body ], [ %a, %vector.ph ]
    %vec.phi = phi <4 x float> [ %6, %vector.ph ], [ %13, %vector.body ]
    %7 = phi i32 [ %start, %vector.ph ], [ %14, %vector.body ]
    %8 = phi i32 [ %N, %vector.ph ], [ %10, %vector.body ]
    %lsr.iv12 = bitcast float* %lsr.iv to <4 x float>*
    %lsr.iv1315 = bitcast float* %lsr.iv13 to <4 x float>*
    %9 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %8)
    %10 = sub i32 %8, 4
    %wide.masked.load = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %lsr.iv12, i32 4, <4 x i1> %9, <4 x float> undef)
    %wide.masked.load11 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %lsr.iv1315, i32 4, <4 x i1> %9, <4 x float> undef)
    %11 = fmul fast <4 x float> %wide.masked.load11, %wide.masked.load
    %12 = fadd fast <4 x float> %11, %vec.phi
    %13 = select <4 x i1> %9, <4 x float> %12, <4 x float> %vec.phi
    %scevgep = getelementptr float, float* %lsr.iv, i32 4
    %scevgep14 = getelementptr float, float* %lsr.iv13, i32 4
    %14 = call i32 @llvm.loop.decrement.reg.i32(i32 %7, i32 1)
    %15 = icmp ne i32 %14, 0
    br i1 %15, label %vector.body, label %middle.block

  middle.block:                                     ; preds = %vector.body
    %16 = call fast float @llvm.vector.reduce.fadd.f32.v4f32(float 0.000000e+00, <4 x float> %13)
    br label %for.cond.cleanup

  for.cond.cleanup:                                 ; preds = %middle.block, %entry
    %res.0.lcssa = phi float [ %init, %entry ], [ %16, %middle.block ]
    ret float %res.0.lcssa
  }

  ; Function Attrs: norecurse nounwind readonly
  define dso_local arm_aapcs_vfpcc float @insert_after_vdup_2(float* nocapture readonly %a, float* nocapture readonly %b, float %init, i32 %N) local_unnamed_addr #0 {
  entry:
    %shr = lshr i32 %N, 2
    %cmp9.not = icmp eq i32 %shr, 0
    %0 = add nuw nsw i32 %shr, 3
    %1 = lshr i32 %0, 2
    %2 = shl nuw nsw i32 %1, 2
    %3 = add nsw i32 %2, -4
    %4 = lshr i32 %3, 2
    %5 = add nuw nsw i32 %4, 1
    br i1 %cmp9.not, label %for.cond.cleanup, label %vector.ph

  vector.ph:                                        ; preds = %entry
    %6 = insertelement <4 x float> <float undef, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00>, float %init, i32 0
    %start = call i32 @llvm.start.loop.iterations.i32(i32 %5)
    br label %vector.body

  vector.body:                                      ; preds = %vector.body, %vector.ph
    %lsr.iv14 = phi float* [ %scevgep15, %vector.body ], [ %b, %vector.ph ]
    %lsr.iv = phi float* [ %scevgep, %vector.body ], [ %a, %vector.ph ]
    %vec.phi = phi <4 x float> [ %6, %vector.ph ], [ %13, %vector.body ]
    %7 = phi i32 [ %start, %vector.ph ], [ %14, %vector.body ]
    %8 = phi i32 [ %shr, %vector.ph ], [ %10, %vector.body ]
    %lsr.iv13 = bitcast float* %lsr.iv to <4 x float>*
    %lsr.iv1416 = bitcast float* %lsr.iv14 to <4 x float>*
    %9 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %8)
    %10 = sub i32 %8, 4
    %wide.masked.load = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %lsr.iv13, i32 4, <4 x i1> %9, <4 x float> undef)
    %wide.masked.load12 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %lsr.iv1416, i32 4, <4 x i1> %9, <4 x float> undef)
    %11 = fmul fast <4 x float> %wide.masked.load12, %wide.masked.load
    %12 = fadd fast <4 x float> %11, %vec.phi
    %13 = select <4 x i1> %9, <4 x float> %12, <4 x float> %vec.phi
    %scevgep = getelementptr float, float* %lsr.iv, i32 4
    %scevgep15 = getelementptr float, float* %lsr.iv14, i32 4
    %14 = call i32 @llvm.loop.decrement.reg.i32(i32 %7, i32 1)
    %15 = icmp ne i32 %14, 0
    br i1 %15, label %vector.body, label %middle.block

  middle.block:                                     ; preds = %vector.body
    %16 = call fast float @llvm.vector.reduce.fadd.f32.v4f32(float 0.000000e+00, <4 x float> %13)
    br label %for.cond.cleanup

  for.cond.cleanup:                                 ; preds = %middle.block, %entry
    %res.0.lcssa = phi float [ %init, %entry ], [ %16, %middle.block ]
    ret float %res.0.lcssa
  }

  declare <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32, i32)
  declare <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>*, i32 immarg, <4 x i1>, <4 x float>)
  declare float @llvm.vector.reduce.fadd.f32.v4f32(float, <4 x float>)
  declare i32 @llvm.start.loop.iterations.i32(i32)
  declare i32 @llvm.loop.decrement.reg.i32(i32, i32)
  declare <4 x i1> @llvm.arm.mve.vctp32(i32)

...
---
name:            insert_after_vdup_1
alignment:       4
tracksRegLiveness: true
registers:       []
liveins:
  - { reg: '$r0', virtual-reg: '' }
  - { reg: '$r1', virtual-reg: '' }
  - { reg: '$s0', virtual-reg: '' }
  - { reg: '$r2', virtual-reg: '' }
frameInfo:
  stackSize:       8
  offsetAdjustment: 0
  maxAlignment:    4
  localFrameSize:  0
  savePoint:       ''
  restorePoint:    ''
fixedStack:      []
stack:
  - { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$lr', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
  - { id: 1, name: '', type: spill-slot, offset: -8, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$r7', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
callSites:       []
constants:
  - id:              0
    value:           'float 0.000000e+00'
    alignment:       4
    isTargetSpecific: false
machineFunctionInfo: {}
body:             |
  ; CHECK-LABEL: name: insert_after_vdup_1
  ; CHECK: bb.0.entry:
  ; CHECK:   successors: %bb.1(0x80000000)
  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r7, $s0
  ; CHECK:   tCMPi8 renamable $r2, 0, 14 /* CC::al */, $noreg, implicit-def $cpsr
  ; CHECK:   t2IT 0, 8, implicit-def $itstate
  ; CHECK:   tBX_RET 0 /* CC::eq */, killed $cpsr, implicit $s0, implicit killed $itstate
  ; CHECK: bb.1.vector.ph:
  ; CHECK:   successors: %bb.2(0x80000000)
  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $s0
  ; CHECK:   frame-setup tPUSH 14 /* CC::al */, $noreg, 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:   dead $r7 = frame-setup tMOVr $sp, 14 /* CC::al */, $noreg
  ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_register $r7
  ; CHECK:   renamable $r3, dead $cpsr = tADDi3 renamable $r2, 3, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $r3 = t2BICri killed renamable $r3, 3, 14 /* CC::al */, $noreg, $noreg
  ; CHECK:   renamable $r12 = t2SUBri killed renamable $r3, 4, 14 /* CC::al */, $noreg, $noreg
  ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
  ; CHECK:   renamable $r3 = tLDRpci %const.0, 14 /* CC::al */, $noreg :: (load 4 from constant-pool)
  ; CHECK:   $lr = t2DLS killed renamable $lr
  ; CHECK:   renamable $q1 = MVE_VDUP32 killed renamable $r3, 0, $noreg, undef renamable $q1
  ; CHECK:   $s4 = VMOVS killed $s0, 14 /* CC::al */, $noreg, implicit killed $q1, implicit-def $q1
  ; CHECK: bb.2.vector.body:
  ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
  ; CHECK:   liveins: $lr, $q1, $r0, $r1, $r2
  ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg
  ; CHECK:   renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14 /* CC::al */, $noreg
  ; CHECK:   MVE_VPST 2, implicit $vpr
  ; CHECK:   renamable $r0, renamable $q0 = MVE_VLDRWU32_post killed renamable $r0, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv12, align 4)
  ; CHECK:   renamable $r1, renamable $q2 = MVE_VLDRWU32_post killed renamable $r1, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv1315, align 4)
  ; CHECK:   renamable $q1 = MVE_VFMAf32 killed renamable $q1, killed renamable $q2, killed renamable $q0, 1, killed renamable $vpr
  ; CHECK:   $lr = t2LEUpdate killed renamable $lr, %bb.2
  ; CHECK: bb.3.middle.block:
  ; CHECK:   liveins: $q1
  ; CHECK:   renamable $s0 = nnan ninf nsz arcp contract afn reassoc VADDS renamable $s6, renamable $s7, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $s2 = nnan ninf nsz arcp contract afn reassoc VADDS killed renamable $s4, killed renamable $s5, 14 /* CC::al */, $noreg, implicit killed $q1
  ; CHECK:   renamable $s0 = nnan ninf nsz arcp contract afn reassoc VADDS killed renamable $s2, killed renamable $s0, 14 /* CC::al */, $noreg
  ; CHECK:   $sp = frame-destroy t2LDMIA_UPD $sp, 14 /* CC::al */, $noreg, def $r7, def $lr
  ; CHECK:   tBX_RET 14 /* CC::al */, $noreg, implicit killed $s0
  ; CHECK: bb.4 (align 4):
  ; CHECK:   CONSTPOOL_ENTRY 0, %const.0, 4
  bb.0.entry:
    successors: %bb.1(0x80000000)
    liveins: $r0, $r1, $r2, $s0, $lr

    tCMPi8 renamable $r2, 0, 14 /* CC::al */, $noreg, implicit-def $cpsr
    t2IT 0, 8, implicit-def $itstate
    tBX_RET 0 /* CC::eq */, killed $cpsr, implicit $s0, implicit killed $itstate

  bb.1.vector.ph:
    successors: %bb.2(0x80000000)
    liveins: $r0, $r1, $r2, $s0, $lr

    frame-setup tPUSH 14 /* CC::al */, $noreg, 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
    $r7 = frame-setup tMOVr $sp, 14 /* CC::al */, $noreg
    frame-setup CFI_INSTRUCTION def_cfa_register $r7
    renamable $r3, dead $cpsr = tADDi3 renamable $r2, 3, 14 /* CC::al */, $noreg
    renamable $r3 = t2BICri killed renamable $r3, 3, 14 /* CC::al */, $noreg, $noreg
    renamable $r12 = t2SUBri killed renamable $r3, 4, 14 /* CC::al */, $noreg, $noreg
    renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
    renamable $lr = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
    renamable $r3 = tLDRpci %const.0, 14 /* CC::al */, $noreg :: (load 4 from constant-pool)
    $lr = t2DoLoopStart renamable $lr
    renamable $q1 = MVE_VDUP32 killed renamable $r3, 0, $noreg, undef renamable $q1
    $s4 = VMOVS killed $s0, 14 /* CC::al */, $noreg, implicit killed $q1, implicit-def $q1

  bb.2.vector.body:
    successors: %bb.2(0x7c000000), %bb.3(0x04000000)
    liveins: $lr, $q1, $r0, $r1, $r2

    renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg
    renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14 /* CC::al */, $noreg
    renamable $lr = t2LoopDec killed renamable $lr, 1
    MVE_VPST 2, implicit $vpr
    renamable $r0, renamable $q0 = MVE_VLDRWU32_post killed renamable $r0, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv12, align 4)
    renamable $r1, renamable $q2 = MVE_VLDRWU32_post killed renamable $r1, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv1315, align 4)
    renamable $q1 = MVE_VFMAf32 killed renamable $q1, killed renamable $q2, killed renamable $q0, 1, killed renamable $vpr
    t2LoopEnd renamable $lr, %bb.2, implicit-def dead $cpsr
    tB %bb.3, 14 /* CC::al */, $noreg

  bb.3.middle.block:
    liveins: $q1

    renamable $s0 = nnan ninf nsz arcp contract afn reassoc VADDS renamable $s6, renamable $s7, 14 /* CC::al */, $noreg
    renamable $s2 = nnan ninf nsz arcp contract afn reassoc VADDS killed renamable $s4, killed renamable $s5, 14 /* CC::al */, $noreg, implicit $q1
    renamable $s0 = nnan ninf nsz arcp contract afn reassoc VADDS killed renamable $s2, killed renamable $s0, 14 /* CC::al */, $noreg
    $sp = frame-destroy t2LDMIA_UPD $sp, 14 /* CC::al */, $noreg, def $r7, def $lr
    tBX_RET 14 /* CC::al */, $noreg, implicit killed $s0

  bb.4 (align 4):
    CONSTPOOL_ENTRY 0, %const.0, 4

...
---
name:            insert_after_vdup_2
alignment:       4
tracksRegLiveness: true
registers:       []
liveins:
  - { reg: '$r0', virtual-reg: '' }
  - { reg: '$r1', virtual-reg: '' }
  - { reg: '$s0', virtual-reg: '' }
  - { reg: '$r2', virtual-reg: '' }
frameInfo:
  stackSize:       8
  offsetAdjustment: 0
  maxAlignment:    4
  savePoint:       ''
  restorePoint:    ''
fixedStack:      []
stack:
  - { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$lr', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
  - { id: 1, name: '', type: spill-slot, offset: -8, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$r7', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
callSites:       []
constants:
  - id:              0
    value:           'float 0.000000e+00'
    alignment:       4
    isTargetSpecific: false
machineFunctionInfo: {}
body:             |
  ; CHECK-LABEL: name: insert_after_vdup_2
  ; CHECK: bb.0.entry:
  ; CHECK:   successors: %bb.1(0x80000000)
  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r7, $s0
  ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
  ; CHECK:   t2CMPrs killed renamable $r3, renamable $r2, 19, 14 /* CC::al */, $noreg, implicit-def $cpsr
  ; CHECK:   t2IT 0, 8, implicit-def $itstate
  ; CHECK:   tBX_RET 0 /* CC::eq */, killed $cpsr, implicit $s0, implicit killed $itstate
  ; CHECK: bb.1.vector.ph:
  ; CHECK:   successors: %bb.2(0x80000000)
  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $s0
  ; CHECK:   frame-setup tPUSH 14 /* CC::al */, $noreg, 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:   dead $r7 = frame-setup tMOVr $sp, 14 /* CC::al */, $noreg
  ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_register $r7
  ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 3, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $r3 = nuw nsw t2ADDrs killed renamable $r3, renamable $r2, 19, 14 /* CC::al */, $noreg, $noreg
  ; CHECK:   renamable $r3 = t2BICri killed renamable $r3, 3, 14 /* CC::al */, $noreg, $noreg
  ; CHECK:   renamable $r12 = t2SUBri killed renamable $r3, 4, 14 /* CC::al */, $noreg, $noreg
  ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $lr = t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
  ; CHECK:   renamable $r3 = tLDRpci %const.0, 14 /* CC::al */, $noreg :: (load 4 from constant-pool)
  ; CHECK:   $lr = t2DLS killed renamable $lr
  ; CHECK:   renamable $q1 = MVE_VDUP32 killed renamable $r3, 0, $noreg, undef renamable $q1
  ; CHECK:   renamable $r2, dead $cpsr = tLSRri killed renamable $r2, 2, 14 /* CC::al */, $noreg
  ; CHECK:   $s4 = VMOVS killed $s0, 14 /* CC::al */, $noreg, implicit killed $q1, implicit-def $q1
  ; CHECK: bb.2.vector.body:
  ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
  ; CHECK:   liveins: $lr, $q1, $r0, $r1, $r2
  ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg
  ; CHECK:   renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14 /* CC::al */, $noreg
  ; CHECK:   MVE_VPST 2, implicit $vpr
  ; CHECK:   renamable $r0, renamable $q0 = MVE_VLDRWU32_post killed renamable $r0, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv13, align 4)
  ; CHECK:   renamable $r1, renamable $q2 = MVE_VLDRWU32_post killed renamable $r1, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv1416, align 4)
  ; CHECK:   renamable $q1 = MVE_VFMAf32 killed renamable $q1, killed renamable $q2, killed renamable $q0, 1, killed renamable $vpr
  ; CHECK:   $lr = t2LEUpdate killed renamable $lr, %bb.2
  ; CHECK: bb.3.middle.block:
  ; CHECK:   liveins: $q1
  ; CHECK:   renamable $s0 = nnan ninf nsz arcp contract afn reassoc VADDS renamable $s6, renamable $s7, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $s2 = nnan ninf nsz arcp contract afn reassoc VADDS killed renamable $s4, killed renamable $s5, 14 /* CC::al */, $noreg, implicit killed $q1
  ; CHECK:   renamable $s0 = nnan ninf nsz arcp contract afn reassoc VADDS killed renamable $s2, killed renamable $s0, 14 /* CC::al */, $noreg
  ; CHECK:   $sp = frame-destroy t2LDMIA_UPD $sp, 14 /* CC::al */, $noreg, def $r7, def $lr
  ; CHECK:   tBX_RET 14 /* CC::al */, $noreg, implicit killed $s0
  ; CHECK: bb.4 (align 4):
  ; CHECK:   CONSTPOOL_ENTRY 0, %const.0, 4
  bb.0.entry:
    successors: %bb.1(0x80000000)
    liveins: $r0, $r1, $r2, $s0, $lr

    renamable $r3, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
    t2CMPrs killed renamable $r3, renamable $r2, 19, 14 /* CC::al */, $noreg, implicit-def $cpsr
    t2IT 0, 8, implicit-def $itstate
    tBX_RET 0 /* CC::eq */, killed $cpsr, implicit $s0, implicit killed $itstate

  bb.1.vector.ph:
    successors: %bb.2(0x80000000)
    liveins: $r0, $r1, $r2, $s0, $lr

    frame-setup tPUSH 14 /* CC::al */, $noreg, 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
    $r7 = frame-setup tMOVr $sp, 14 /* CC::al */, $noreg
    frame-setup CFI_INSTRUCTION def_cfa_register $r7
    renamable $r3, dead $cpsr = tMOVi8 3, 14 /* CC::al */, $noreg
    renamable $r3 = nuw nsw t2ADDrs killed renamable $r3, renamable $r2, 19, 14 /* CC::al */, $noreg, $noreg
    renamable $r3 = t2BICri killed renamable $r3, 3, 14 /* CC::al */, $noreg, $noreg
    renamable $r12 = t2SUBri killed renamable $r3, 4, 14 /* CC::al */, $noreg, $noreg
    renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
    renamable $lr = t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
    renamable $r3 = tLDRpci %const.0, 14 /* CC::al */, $noreg :: (load 4 from constant-pool)
    $lr = t2DoLoopStart renamable $lr
    renamable $q1 = MVE_VDUP32 killed renamable $r3, 0, $noreg, undef renamable $q1
    renamable $r2, dead $cpsr = tLSRri killed renamable $r2, 2, 14 /* CC::al */, $noreg
    $s4 = VMOVS killed $s0, 14 /* CC::al */, $noreg, implicit killed $q1, implicit-def $q1

  bb.2.vector.body:
    successors: %bb.2(0x7c000000), %bb.3(0x04000000)
    liveins: $lr, $q1, $r0, $r1, $r2

    renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg
    renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14 /* CC::al */, $noreg
    renamable $lr = t2LoopDec killed renamable $lr, 1
    MVE_VPST 2, implicit $vpr
    renamable $r0, renamable $q0 = MVE_VLDRWU32_post killed renamable $r0, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv13, align 4)
    renamable $r1, renamable $q2 = MVE_VLDRWU32_post killed renamable $r1, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv1416, align 4)
    renamable $q1 = MVE_VFMAf32 killed renamable $q1, killed renamable $q2, killed renamable $q0, 1, killed renamable $vpr
    t2LoopEnd renamable $lr, %bb.2, implicit-def dead $cpsr
    tB %bb.3, 14 /* CC::al */, $noreg

  bb.3.middle.block:
    liveins: $q1

    renamable $s0 = nnan ninf nsz arcp contract afn reassoc VADDS renamable $s6, renamable $s7, 14 /* CC::al */, $noreg
    renamable $s2 = nnan ninf nsz arcp contract afn reassoc VADDS killed renamable $s4, killed renamable $s5, 14 /* CC::al */, $noreg, implicit $q1
    renamable $s0 = nnan ninf nsz arcp contract afn reassoc VADDS killed renamable $s2, killed renamable $s0, 14 /* CC::al */, $noreg
    $sp = frame-destroy t2LDMIA_UPD $sp, 14 /* CC::al */, $noreg, def $r7, def $lr
    tBX_RET 14 /* CC::al */, $noreg, implicit killed $s0

  bb.4 (align 4):
    CONSTPOOL_ENTRY 0, %const.0, 4

...