Compiler projects using llvm
# 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

# A decent sized test to handle a matrix, with scalar and vector low-overhead loops.

--- |
  define dso_local arm_aapcs_vfpcc signext i16 @matrix_test(i32 %d, i32* nocapture %e, i16* nocapture readonly %k, i16* nocapture readonly %l) {
  entry:
    %cmp19.i = icmp sgt i32 %d, 0
    br i1 %cmp19.i, label %for.body.i.preheader, label %c.exit.thread

  for.body.i.preheader:                             ; preds = %entry
    %start1 = call i32 @llvm.start.loop.iterations.i32(i32 %d)
    br label %for.body.i

  c.exit.thread:                                    ; preds = %entry
    %call169 = tail call arm_aapcs_vfpcc signext i16 bitcast (i16 (...)* @crc16 to i16 (i32)*)(i32 0)
    %conv270 = sext i16 %call169 to i32
    br label %c.exit59

  for.body.i:                                       ; preds = %for.body.i, %for.body.i.preheader
    %lsr.iv15 = phi i32* [ %e, %for.body.i.preheader ], [ %scevgep16, %for.body.i ]
    %h.022.i = phi i16 [ %h.1.i, %for.body.i ], [ 0, %for.body.i.preheader ]
    %f.020.i = phi i32 [ %f.1.i, %for.body.i ], [ undef, %for.body.i.preheader ]
    %0 = phi i32 [ %start1, %for.body.i.preheader ], [ %2, %for.body.i ]
    %1 = load i32, i32* %lsr.iv15, align 4
    %add.i = add nsw i32 %1, %f.020.i
    %cmp1.i = icmp sgt i32 %add.i, 0
    %cmp3.i = icmp sgt i32 %1, 0
    %f.1.i = select i1 %cmp1.i, i32 0, i32 %add.i
    %narrow.i = and i1 %cmp3.i, %cmp1.i
    %add6.i = zext i1 %narrow.i to i16
    %h.1.i = add i16 %h.022.i, %add6.i
    %scevgep16 = getelementptr i32, i32* %lsr.iv15, i32 1
    %2 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %0, i32 1)
    %3 = icmp ne i32 %2, 0
    br i1 %3, label %for.body.i, label %c.exit

  c.exit:                                           ; preds = %for.body.i
    %4 = icmp sgt i32 %d, 0
    %phitmp = sext i16 %h.1.i to i32
    %call1 = tail call arm_aapcs_vfpcc signext i16 bitcast (i16 (...)* @crc16 to i16 (i32)*)(i32 %phitmp)
    %conv2 = sext i16 %call1 to i32
    br i1 %4, label %for.cond4.preheader.us.preheader, label %c.exit59

  for.cond4.preheader.us.preheader:                 ; preds = %c.exit
    %n.rnd.up = add i32 %d, 3
    %n.vec = and i32 %n.rnd.up, -4
    %5 = shl i32 %d, 1
    %6 = add i32 %n.vec, -4
    %7 = lshr i32 %6, 2
    %8 = add nuw nsw i32 %7, 1
    %9 = shl i32 %7, 2
    %10 = sub i32 %d, %9
    br label %for.cond4.preheader.us

  for.cond4.preheader.us:                           ; preds = %middle.block, %for.cond4.preheader.us.preheader
    %lsr.iv7 = phi i16* [ %28, %middle.block ], [ %k, %for.cond4.preheader.us.preheader ]
    %i.064.us = phi i32 [ %inc15.us, %middle.block ], [ 0, %for.cond4.preheader.us.preheader ]
    %arrayidx12.us = getelementptr inbounds i32, i32* %e, i32 %i.064.us
    %arrayidx12.promoted.us = load i32, i32* %arrayidx12.us, align 4
    %11 = insertelement <4 x i32> <i32 undef, i32 0, i32 0, i32 0>, i32 %arrayidx12.promoted.us, i32 0
    %start2 = call i32 @llvm.start.loop.iterations.i32(i32 %8)
    br label %vector.body

  vector.body:                                      ; preds = %vector.body, %for.cond4.preheader.us
    %lsr.iv10 = phi i16* [ %scevgep11, %vector.body ], [ %lsr.iv7, %for.cond4.preheader.us ]
    %lsr.iv4 = phi i16* [ %scevgep5, %vector.body ], [ %l, %for.cond4.preheader.us ]
    %vec.phi = phi <4 x i32> [ %11, %for.cond4.preheader.us ], [ %19, %vector.body ]
    %12 = phi i32 [ %start2, %for.cond4.preheader.us ], [ %20, %vector.body ]
    %13 = phi i32 [ %d, %for.cond4.preheader.us ], [ %15, %vector.body ]
    %lsr.iv1012 = bitcast i16* %lsr.iv10 to <4 x i16>*
    %lsr.iv46 = bitcast i16* %lsr.iv4 to <4 x i16>*
    %14 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %13)
    %15 = sub i32 %13, 4
    %wide.masked.load = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* %lsr.iv1012, i32 2, <4 x i1> %14, <4 x i16> undef)
    %16 = sext <4 x i16> %wide.masked.load to <4 x i32>
    %wide.masked.load76 = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* %lsr.iv46, i32 2, <4 x i1> %14, <4 x i16> undef)
    %17 = sext <4 x i16> %wide.masked.load76 to <4 x i32>
    %18 = mul nsw <4 x i32> %17, %16
    %19 = add <4 x i32> %18, %vec.phi
    %scevgep5 = getelementptr i16, i16* %lsr.iv4, i32 4
    %scevgep11 = getelementptr i16, i16* %lsr.iv10, i32 4
    %20 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %12, i32 1)
    %21 = icmp ne i32 %20, 0
    br i1 %21, label %vector.body, label %middle.block

  middle.block:                                     ; preds = %vector.body
    %vec.phi.lcssa = phi <4 x i32> [ %vec.phi, %vector.body ]
    %.lcssa = phi <4 x i32> [ %19, %vector.body ]
    %22 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %10)
    %23 = bitcast i16* %lsr.iv7 to i1*
    %24 = select <4 x i1> %22, <4 x i32> %.lcssa, <4 x i32> %vec.phi.lcssa
    %25 = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %24)
    %sunkaddr = mul i32 %i.064.us, 4
    %26 = bitcast i32* %e to i8*
    %sunkaddr17 = getelementptr inbounds i8, i8* %26, i32 %sunkaddr
    %27 = bitcast i8* %sunkaddr17 to i32*
    store i32 %25, i32* %27, align 4
    %inc15.us = add nuw nsw i32 %i.064.us, 1
    %scevgep9 = getelementptr i1, i1* %23, i32 %5
    %28 = bitcast i1* %scevgep9 to i16*
    %exitcond66 = icmp eq i32 %inc15.us, %d
    br i1 %exitcond66, label %for.end16, label %for.cond4.preheader.us

  for.end16:                                        ; preds = %middle.block
    %29 = icmp sgt i32 %d, 0
    br i1 %29, label %for.body.i57.preheader, label %c.exit59

  for.body.i57.preheader:                           ; preds = %for.end16
    %start3 = call i32 @llvm.start.loop.iterations.i32(i32 %d)
    br label %for.body.i57

  for.body.i57:                                     ; preds = %for.body.i57, %for.body.i57.preheader
    %lsr.iv1 = phi i32* [ %e, %for.body.i57.preheader ], [ %scevgep, %for.body.i57 ]
    %h.022.i44 = phi i16 [ %h.1.i54, %for.body.i57 ], [ 0, %for.body.i57.preheader ]
    %f.020.i46 = phi i32 [ %f.1.i51, %for.body.i57 ], [ undef, %for.body.i57.preheader ]
    %30 = phi i32 [ %start3, %for.body.i57.preheader ], [ %32, %for.body.i57 ]
    %31 = load i32, i32* %lsr.iv1, align 4
    %add.i48 = add nsw i32 %31, %f.020.i46
    %cmp1.i49 = icmp sgt i32 %add.i48, 0
    %cmp3.i50 = icmp sgt i32 %31, 0
    %f.1.i51 = select i1 %cmp1.i49, i32 0, i32 %add.i48
    %narrow.i52 = and i1 %cmp3.i50, %cmp1.i49
    %add6.i53 = zext i1 %narrow.i52 to i16
    %h.1.i54 = add i16 %h.022.i44, %add6.i53
    %scevgep = getelementptr i32, i32* %lsr.iv1, i32 1
    %32 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %30, i32 1)
    %33 = icmp ne i32 %32, 0
    br i1 %33, label %for.body.i57, label %c.exit59.loopexit

  c.exit59.loopexit:                                ; preds = %for.body.i57
    %phitmp67 = sext i16 %h.1.i54 to i32
    br label %c.exit59

  c.exit59:                                         ; preds = %c.exit59.loopexit, %for.end16, %c.exit, %c.exit.thread
    %conv27173 = phi i32 [ %conv2, %for.end16 ], [ %conv2, %c.exit59.loopexit ], [ %conv2, %c.exit ], [ %conv270, %c.exit.thread ]
    %h.0.lcssa.i58 = phi i32 [ 0, %for.end16 ], [ %phitmp67, %c.exit59.loopexit ], [ 0, %c.exit ], [ 0, %c.exit.thread ]
    %call19 = tail call arm_aapcs_vfpcc signext i16 bitcast (i16 (...)* @crc16 to i16 (i32, i32)*)(i32 %h.0.lcssa.i58, i32 %conv27173)
    ret i16 %call19
  }
  declare dso_local arm_aapcs_vfpcc signext i16 @crc16(...) local_unnamed_addr #0
  declare <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>*, i32 immarg, <4 x i1>, <4 x i16>) #1
  declare i32 @llvm.vector.reduce.add.v4i32(<4 x i32>) #2
  declare i32 @llvm.start.loop.iterations.i32(i32) #3
  declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32) #3
  declare <4 x i1> @llvm.arm.mve.vctp32(i32) #4

...
---
name:            matrix_test
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: 0
  maxAlignment:    4
  adjustsStack:    true
  hasCalls:        true
  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: '$lr', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
  - { id: 1, name: '', type: spill-slot, offset: -8, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$r10', 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: '$r9', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
  - { id: 3, name: '', type: spill-slot, offset: -16, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$r8', 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: '$r7', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
  - { id: 5, name: '', type: spill-slot, offset: -24, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$r6', 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: '$r5', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
  - { id: 7, name: '', type: spill-slot, offset: -32, size: 4, alignment: 4,
      stack-id: default, callee-saved-register: '$r4', callee-saved-restored: true,
      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
callSites:       []
constants:       []
machineFunctionInfo: {}
body:             |
  ; CHECK-LABEL: name: matrix_test
  ; CHECK: bb.0.entry:
  ; CHECK:   successors: %bb.1(0x50000000), %bb.12(0x30000000)
  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3, $r4, $r5, $r6, $r7, $r8, $r9, $r10
  ; CHECK:   $sp = frame-setup t2STMDB_UPD $sp, 14 /* CC::al */, $noreg, killed $r4, killed $r5, killed $r6, killed $r7, killed $r8, killed $r9, killed $r10, killed $lr
  ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 32
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $lr, -4
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r10, -8
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r9, -12
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r8, -16
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r7, -20
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r6, -24
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r5, -28
  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r4, -32
  ; CHECK:   tCMPi8 renamable $r0, 1, 14 /* CC::al */, $noreg, implicit-def $cpsr
  ; CHECK:   t2Bcc %bb.12, 11 /* CC::lt */, killed $cpsr
  ; CHECK: bb.1.for.body.i.preheader:
  ; CHECK:   successors: %bb.2(0x80000000)
  ; CHECK:   liveins: $r0, $r1, $r2, $r3
  ; CHECK:   $r5 = tMOVr killed $r2, 14 /* CC::al */, $noreg
  ; CHECK:   $r8 = tMOVr killed $r3, 14 /* CC::al */, $noreg
  ; CHECK:   $r4 = tMOVr $r1, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $r6, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $r2 = IMPLICIT_DEF
  ; CHECK:   $r10 = tMOVr $r0, 14 /* CC::al */, $noreg
  ; CHECK:   dead $lr = tMOVr $r0, 14 /* CC::al */, $noreg
  ; CHECK:   $lr = t2DLS killed renamable $r0
  ; CHECK: bb.2.for.body.i:
  ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
  ; CHECK:   liveins: $lr, $r1, $r2, $r4, $r5, $r6, $r8, $r10
  ; CHECK:   renamable $r3, renamable $r1 = t2LDR_POST killed renamable $r1, 4, 14 /* CC::al */, $noreg :: (load (s32) from %ir.lsr.iv15)
  ; CHECK:   renamable $r2 = nsw tADDhirr killed renamable $r2, renamable $r3, 14 /* CC::al */, $noreg
  ; CHECK:   tCMPi8 renamable $r2, 0, 14 /* CC::al */, $noreg, implicit-def $cpsr
  ; CHECK:   renamable $r7 = t2CSINC $zr, $zr, 13, implicit killed $cpsr
  ; CHECK:   tCMPi8 killed renamable $r3, 0, 14 /* CC::al */, $noreg, implicit-def $cpsr
  ; CHECK:   renamable $r3 = t2CSINC $zr, $zr, 13, implicit killed $cpsr
  ; CHECK:   tCMPi8 renamable $r2, 0, 14 /* CC::al */, $noreg, implicit-def $cpsr
  ; CHECK:   renamable $r3 = t2ANDrr killed renamable $r3, killed renamable $r7, 14 /* CC::al */, $noreg, $noreg
  ; CHECK:   t2IT 12, 8, implicit-def $itstate
  ; CHECK:   $r2 = tMOVi8 $noreg, 0, 12 /* CC::gt */, killed $cpsr, implicit killed renamable $r2, implicit killed $itstate
  ; CHECK:   renamable $r6 = tADDhirr killed renamable $r6, killed renamable $r3, 14 /* CC::al */, $noreg
  ; CHECK:   $lr = t2LEUpdate killed renamable $lr, %bb.2
  ; CHECK: bb.3.c.exit:
  ; CHECK:   successors: %bb.4(0x50000000), %bb.14(0x30000000)
  ; CHECK:   liveins: $r4, $r5, $r6, $r8, $r10
  ; CHECK:   renamable $r0 = tSXTH killed renamable $r6, 14 /* CC::al */, $noreg
  ; CHECK:   tBL 14 /* CC::al */, $noreg, @crc16, csr_aapcs, implicit-def dead $lr, implicit $sp, implicit killed $r0, implicit-def $sp, implicit-def $r0
  ; CHECK:   $r12 = tMOVr killed $r0, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $r7, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
  ; CHECK:   t2CMPri $r10, 1, 14 /* CC::al */, $noreg, implicit-def $cpsr
  ; CHECK:   tBcc %bb.14, 11 /* CC::lt */, killed $cpsr
  ; CHECK: bb.4.for.cond4.preheader.us.preheader:
  ; CHECK:   successors: %bb.5(0x80000000)
  ; CHECK:   liveins: $r4, $r5, $r7, $r8, $r10, $r12
  ; CHECK:   renamable $r0 = t2ADDri $r10, 3, 14 /* CC::al */, $noreg, $noreg
  ; CHECK:   $lr = tMOVr $r10, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $r0 = t2BICri killed renamable $r0, 3, 14 /* CC::al */, $noreg, $noreg
  ; CHECK:   renamable $r3 = t2LSLri $r10, 1, 14 /* CC::al */, $noreg, $noreg
  ; CHECK:   renamable $r1, dead $cpsr = tSUBi3 killed renamable $r0, 4, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $r0, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $q0 = MVE_VDUP32 renamable $r7, 0, $noreg, $noreg, undef renamable $q0
  ; CHECK:   renamable $r0 = nuw nsw t2ADDrs killed renamable $r0, renamable $r1, 19, 14 /* CC::al */, $noreg, $noreg
  ; CHECK:   renamable $r1, dead $cpsr = tLSRri killed renamable $r1, 2, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $r9 = t2SUBrs $r10, killed renamable $r1, 18, 14 /* CC::al */, $noreg, $noreg
  ; CHECK: bb.5.for.cond4.preheader.us:
  ; CHECK:   successors: %bb.6(0x80000000)
  ; CHECK:   liveins: $lr, $q0, $r0, $r3, $r4, $r5, $r7, $r8, $r9, $r10, $r12
  ; CHECK:   renamable $r1 = t2LDRs renamable $r4, renamable $r7, 2, 14 /* CC::al */, $noreg :: (load (s32) from %ir.arrayidx12.us)
  ; CHECK:   $q1 = MVE_VORR $q0, $q0, 0, $noreg, $noreg, undef $q1
  ; CHECK:   $r2 = tMOVr killed $lr, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $q1 = MVE_VMOV_to_lane_32 killed renamable $q1, killed renamable $r1, 0, 14 /* CC::al */, $noreg
  ; CHECK:   $r6 = tMOVr $r5, 14 /* CC::al */, $noreg
  ; CHECK:   $r1 = tMOVr $r8, 14 /* CC::al */, $noreg
  ; CHECK:   dead $lr = tMOVr $r0, 14 /* CC::al */, $noreg
  ; CHECK:   $lr = t2DLS renamable $r0
  ; CHECK: bb.6.vector.body:
  ; CHECK:   successors: %bb.6(0x7c000000), %bb.7(0x04000000)
  ; CHECK:   liveins: $lr, $q0, $q1, $r0, $r1, $r2, $r3, $r4, $r5, $r6, $r7, $r8, $r9, $r10, $r12
  ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg, $noreg
  ; CHECK:   $q2 = MVE_VORR killed $q1, killed $q1, 0, $noreg, $noreg, undef $q2
  ; CHECK:   MVE_VPST 4, implicit $vpr
  ; CHECK:   renamable $r6, renamable $q1 = MVE_VLDRHS32_post killed renamable $r6, 8, 1, renamable $vpr, $noreg :: (load (s64) from %ir.lsr.iv1012, align 2)
  ; CHECK:   renamable $r1, renamable $q3 = MVE_VLDRHS32_post killed renamable $r1, 8, 1, killed renamable $vpr, $noreg :: (load (s64) from %ir.lsr.iv46, align 2)
  ; CHECK:   renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $q1 = nsw MVE_VMULi32 killed renamable $q3, killed renamable $q1, 0, $noreg, $noreg, undef renamable $q1
  ; CHECK:   renamable $q1 = MVE_VADDi32 killed renamable $q1, renamable $q2, 0, $noreg, $noreg, undef renamable $q1
  ; CHECK:   $lr = t2LEUpdate killed renamable $lr, %bb.6
  ; CHECK: bb.7.middle.block:
  ; CHECK:   successors: %bb.8(0x04000000), %bb.5(0x7c000000)
  ; CHECK:   liveins: $q0, $q1, $q2, $r0, $r3, $r4, $r5, $r7, $r8, $r9, $r10, $r12
  ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r9, 0, $noreg, $noreg
  ; CHECK:   renamable $r5 = tADDhirr killed renamable $r5, renamable $r3, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $q1 = MVE_VPSEL killed renamable $q1, killed renamable $q2, 0, killed renamable $vpr, $noreg
  ; CHECK:   $lr = tMOVr $r10, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $r2 = MVE_VADDVu32no_acc killed renamable $q1, 0, $noreg, $noreg
  ; CHECK:   t2STRs killed renamable $r2, renamable $r4, renamable $r7, 2, 14 /* CC::al */, $noreg :: (store (s32) into %ir.27)
  ; CHECK:   renamable $r7, dead $cpsr = nuw nsw tADDi8 killed renamable $r7, 1, 14 /* CC::al */, $noreg
  ; CHECK:   tCMPhir renamable $r7, $r10, 14 /* CC::al */, $noreg, implicit-def $cpsr
  ; CHECK:   tBcc %bb.5, 1 /* CC::ne */, killed $cpsr
  ; CHECK: bb.8.for.end16:
  ; CHECK:   successors: %bb.9(0x50000000), %bb.13(0x30000000)
  ; CHECK:   liveins: $lr, $r4, $r12
  ; CHECK:   t2CMPri renamable $lr, 1, 14 /* CC::al */, $noreg, implicit-def $cpsr
  ; CHECK:   tBcc %bb.13, 11 /* CC::lt */, killed $cpsr
  ; CHECK: bb.9.for.body.i57.preheader:
  ; CHECK:   successors: %bb.10(0x80000000)
  ; CHECK:   liveins: $lr, $r4, $r12
  ; CHECK:   renamable $r0, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $r1 = IMPLICIT_DEF
  ; CHECK: bb.10.for.body.i57:
  ; CHECK:   successors: %bb.10(0x7c000000), %bb.11(0x04000000)
  ; CHECK:   liveins: $lr, $r0, $r1, $r4, $r12
  ; CHECK:   renamable $r2, renamable $r4 = t2LDR_POST killed renamable $r4, 4, 14 /* CC::al */, $noreg :: (load (s32) from %ir.lsr.iv1)
  ; CHECK:   renamable $r1 = nsw tADDhirr killed renamable $r1, renamable $r2, 14 /* CC::al */, $noreg
  ; CHECK:   tCMPi8 renamable $r1, 0, 14 /* CC::al */, $noreg, implicit-def $cpsr
  ; CHECK:   renamable $r3 = t2CSINC $zr, $zr, 13, implicit killed $cpsr
  ; CHECK:   tCMPi8 killed renamable $r2, 0, 14 /* CC::al */, $noreg, implicit-def $cpsr
  ; CHECK:   renamable $r2 = t2CSINC $zr, $zr, 13, implicit killed $cpsr
  ; CHECK:   tCMPi8 renamable $r1, 0, 14 /* CC::al */, $noreg, implicit-def $cpsr
  ; CHECK:   renamable $r2 = t2ANDrr killed renamable $r2, killed renamable $r3, 14 /* CC::al */, $noreg, $noreg
  ; CHECK:   t2IT 12, 8, implicit-def $itstate
  ; CHECK:   $r1 = tMOVi8 $noreg, 0, 12 /* CC::gt */, killed $cpsr, implicit killed renamable $r1, implicit killed $itstate
  ; CHECK:   renamable $r0 = tADDhirr killed renamable $r0, killed renamable $r2, 14 /* CC::al */, $noreg
  ; CHECK:   $lr = t2LEUpdate killed renamable $lr, %bb.10
  ; CHECK: bb.11.c.exit59.loopexit:
  ; CHECK:   successors: %bb.14(0x80000000)
  ; CHECK:   liveins: $r0, $r12
  ; CHECK:   renamable $r7 = tSXTH killed renamable $r0, 14 /* CC::al */, $noreg
  ; CHECK:   tB %bb.14, 14 /* CC::al */, $noreg
  ; CHECK: bb.12.c.exit.thread:
  ; CHECK:   successors: %bb.14(0x80000000)
  ; CHECK:   $r0, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
  ; CHECK:   renamable $r7, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
  ; CHECK:   tBL 14 /* CC::al */, $noreg, @crc16, csr_aapcs, implicit-def dead $lr, implicit $sp, implicit killed $r0, implicit-def $sp, implicit-def $r0
  ; CHECK:   $r12 = tMOVr killed $r0, 14 /* CC::al */, $noreg
  ; CHECK:   tB %bb.14, 14 /* CC::al */, $noreg
  ; CHECK: bb.13:
  ; CHECK:   successors: %bb.14(0x80000000)
  ; CHECK:   liveins: $r12
  ; CHECK:   renamable $r7, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
  ; CHECK: bb.14.c.exit59:
  ; CHECK:   liveins: $r7, $r12
  ; CHECK:   $r0 = tMOVr killed $r7, 14 /* CC::al */, $noreg
  ; CHECK:   $r1 = tMOVr killed $r12, 14 /* CC::al */, $noreg
  ; CHECK:   $sp = t2LDMIA_UPD $sp, 14 /* CC::al */, $noreg, def $r4, def $r5, def $r6, def $r7, def $r8, def $r9, def $r10, def $lr
  ; CHECK:   tTAILJMPdND @crc16, 14 /* CC::al */, $noreg, implicit $sp, implicit $sp, implicit killed $r0, implicit killed $r1
  bb.0.entry:
    successors: %bb.1(0x50000000), %bb.12(0x30000000)
    liveins: $r0, $r1, $r2, $r3, $r4, $r5, $r6, $r7, $r8, $r9, $r10, $lr

    $sp = frame-setup t2STMDB_UPD $sp, 14, $noreg, killed $r4, killed $r5, killed $r6, killed $r7, killed $r8, killed $r9, killed $r10, killed $lr
    frame-setup CFI_INSTRUCTION def_cfa_offset 32
    frame-setup CFI_INSTRUCTION offset $lr, -4
    frame-setup CFI_INSTRUCTION offset $r10, -8
    frame-setup CFI_INSTRUCTION offset $r9, -12
    frame-setup CFI_INSTRUCTION offset $r8, -16
    frame-setup CFI_INSTRUCTION offset $r7, -20
    frame-setup CFI_INSTRUCTION offset $r6, -24
    frame-setup CFI_INSTRUCTION offset $r5, -28
    frame-setup CFI_INSTRUCTION offset $r4, -32
    tCMPi8 renamable $r0, 1, 14, $noreg, implicit-def $cpsr
    t2Bcc %bb.12, 11, killed $cpsr

  bb.1.for.body.i.preheader:
    successors: %bb.2(0x80000000)
    liveins: $r0, $r1, $r2, $r3

    $r5 = tMOVr killed $r2, 14, $noreg
    $r8 = tMOVr killed $r3, 14, $noreg
    $r4 = tMOVr $r1, 14, $noreg
    renamable $r6, dead $cpsr = tMOVi8 0, 14, $noreg
    renamable $r2 = IMPLICIT_DEF
    $r10 = tMOVr $r0, 14, $noreg
    $lr = tMOVr $r0, 14, $noreg
    $lr = t2DoLoopStart killed renamable $r0

  bb.2.for.body.i:
    successors: %bb.2(0x7c000000), %bb.3(0x04000000)
    liveins: $lr, $r1, $r2, $r4, $r5, $r6, $r8, $r10

    renamable $r3, renamable $r1 = t2LDR_POST killed renamable $r1, 4, 14, $noreg :: (load (s32) from %ir.lsr.iv15)
    renamable $lr = t2LoopDec killed renamable $lr, 1
    renamable $r2 = nsw tADDhirr killed renamable $r2, renamable $r3, 14, $noreg
    tCMPi8 renamable $r2, 0, 14, $noreg, implicit-def $cpsr
    renamable $r7 = t2CSINC $zr, $zr, 13, implicit killed $cpsr
    tCMPi8 killed renamable $r3, 0, 14, $noreg, implicit-def $cpsr
    renamable $r3 = t2CSINC $zr, $zr, 13, implicit killed $cpsr
    tCMPi8 renamable $r2, 0, 14, $noreg, implicit-def $cpsr
    renamable $r3 = t2ANDrr killed renamable $r3, killed renamable $r7, 14, $noreg, $noreg
    t2IT 12, 8, implicit-def $itstate
    $r2 = tMOVi8 $noreg, 0, 12, killed $cpsr, implicit killed renamable $r2, implicit killed $itstate
    renamable $r6 = tADDhirr killed renamable $r6, killed renamable $r3, 14, $noreg
    t2LoopEnd renamable $lr, %bb.2, implicit-def dead $cpsr
    tB %bb.3, 14, $noreg

  bb.3.c.exit:
    successors: %bb.4(0x50000000), %bb.14(0x30000000)
    liveins: $r4, $r5, $r6, $r8, $r10

    renamable $r0 = tSXTH killed renamable $r6, 14, $noreg
    tBL 14, $noreg, @crc16, csr_aapcs, implicit-def dead $lr, implicit $sp, implicit killed $r0, implicit-def $sp, implicit-def $r0
    $r12 = tMOVr killed $r0, 14, $noreg
    renamable $r7, dead $cpsr = tMOVi8 0, 14, $noreg
    t2CMPri $r10, 1, 14, $noreg, implicit-def $cpsr
    tBcc %bb.14, 11, killed $cpsr

  bb.4.for.cond4.preheader.us.preheader:
    successors: %bb.5(0x80000000)
    liveins: $r4, $r5, $r7, $r8, $r10, $r12

    renamable $r0 = t2ADDri $r10, 3, 14, $noreg, $noreg
    $lr = tMOVr $r10, 14, $noreg
    renamable $r0 = t2BICri killed renamable $r0, 3, 14, $noreg, $noreg
    renamable $r3 = t2LSLri $r10, 1, 14, $noreg, $noreg
    renamable $r1, dead $cpsr = tSUBi3 killed renamable $r0, 4, 14, $noreg
    renamable $r0, dead $cpsr = tMOVi8 1, 14, $noreg
    renamable $q0 = MVE_VDUP32 renamable $r7, 0, $noreg, $noreg, undef renamable $q0
    renamable $r0 = nuw nsw t2ADDrs killed renamable $r0, renamable $r1, 19, 14, $noreg, $noreg
    renamable $r1, dead $cpsr = tLSRri killed renamable $r1, 2, 14, $noreg
    renamable $r9 = t2SUBrs $r10, killed renamable $r1, 18, 14, $noreg, $noreg

  bb.5.for.cond4.preheader.us:
    successors: %bb.6(0x80000000)
    liveins: $lr, $q0, $r0, $r3, $r4, $r5, $r7, $r8, $r9, $r10, $r12

    renamable $r1 = t2LDRs renamable $r4, renamable $r7, 2, 14, $noreg :: (load (s32) from %ir.arrayidx12.us)
    $q1 = MVE_VORR $q0, $q0, 0, $noreg, $noreg, undef $q1
    $r2 = tMOVr killed $lr, 14, $noreg
    renamable $q1 = MVE_VMOV_to_lane_32 killed renamable $q1, killed renamable $r1, 0, 14, $noreg
    $r6 = tMOVr $r5, 14, $noreg
    $r1 = tMOVr $r8, 14, $noreg
    $lr = tMOVr $r0, 14, $noreg
    $lr = t2DoLoopStart renamable $r0

  bb.6.vector.body:
    successors: %bb.6(0x7c000000), %bb.7(0x04000000)
    liveins: $lr, $q0, $q1, $r0, $r1, $r2, $r3, $r4, $r5, $r6, $r7, $r8, $r9, $r10, $r12

    renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg, $noreg
    $q2 = MVE_VORR killed $q1, $q1, 0, $noreg, $noreg, undef $q2
    MVE_VPST 4, implicit $vpr
    renamable $r6, renamable $q1 = MVE_VLDRHS32_post killed renamable $r6, 8, 1, renamable $vpr, $noreg :: (load (s64) from %ir.lsr.iv1012, align 2)
    renamable $r1, renamable $q3 = MVE_VLDRHS32_post killed renamable $r1, 8, 1, killed renamable $vpr, $noreg :: (load (s64) from %ir.lsr.iv46, align 2)
    renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14, $noreg
    renamable $q1 = nsw MVE_VMULi32 killed renamable $q3, killed renamable $q1, 0, $noreg, $noreg, undef renamable $q1
    renamable $lr = t2LoopDec killed renamable $lr, 1
    renamable $q1 = MVE_VADDi32 killed renamable $q1, renamable $q2, 0, $noreg, $noreg, undef renamable $q1
    t2LoopEnd renamable $lr, %bb.6, implicit-def dead $cpsr
    tB %bb.7, 14, $noreg

  bb.7.middle.block:
    successors: %bb.8(0x04000000), %bb.5(0x7c000000)
    liveins: $q0, $q1, $q2, $r0, $r3, $r4, $r5, $r7, $r8, $r9, $r10, $r12

    renamable $vpr = MVE_VCTP32 renamable $r9, 0, $noreg, $noreg
    renamable $r5 = tADDhirr killed renamable $r5, renamable $r3, 14, $noreg
    renamable $q1 = MVE_VPSEL killed renamable $q1, killed renamable $q2, 0, killed renamable $vpr, $noreg
    $lr = tMOVr $r10, 14, $noreg
    renamable $r2 = MVE_VADDVu32no_acc killed renamable $q1, 0, $noreg, $noreg
    t2STRs killed renamable $r2, renamable $r4, renamable $r7, 2, 14, $noreg :: (store (s32) into %ir.27)
    renamable $r7, dead $cpsr = nuw nsw tADDi8 killed renamable $r7, 1, 14, $noreg
    tCMPhir renamable $r7, $r10, 14, $noreg, implicit-def $cpsr
    tBcc %bb.5, 1, killed $cpsr

  bb.8.for.end16:
    successors: %bb.9(0x50000000), %bb.13(0x30000000)
    liveins: $lr, $r4, $r12

    t2CMPri renamable $lr, 1, 14, $noreg, implicit-def $cpsr
    tBcc %bb.13, 11, killed $cpsr

  bb.9.for.body.i57.preheader:
    successors: %bb.10(0x80000000)
    liveins: $lr, $r4, $r12

    renamable $r0, dead $cpsr = tMOVi8 0, 14, $noreg
    renamable $r1 = IMPLICIT_DEF
    $lr = t2DoLoopStart renamable $lr

  bb.10.for.body.i57:
    successors: %bb.10(0x7c000000), %bb.11(0x04000000)
    liveins: $lr, $r0, $r1, $r4, $r12

    renamable $r2, renamable $r4 = t2LDR_POST killed renamable $r4, 4, 14, $noreg :: (load (s32) from %ir.lsr.iv1)
    renamable $lr = t2LoopDec killed renamable $lr, 1
    renamable $r1 = nsw tADDhirr killed renamable $r1, renamable $r2, 14, $noreg
    tCMPi8 renamable $r1, 0, 14, $noreg, implicit-def $cpsr
    renamable $r3 = t2CSINC $zr, $zr, 13, implicit killed $cpsr
    tCMPi8 killed renamable $r2, 0, 14, $noreg, implicit-def $cpsr
    renamable $r2 = t2CSINC $zr, $zr, 13, implicit killed $cpsr
    tCMPi8 renamable $r1, 0, 14, $noreg, implicit-def $cpsr
    renamable $r2 = t2ANDrr killed renamable $r2, killed renamable $r3, 14, $noreg, $noreg
    t2IT 12, 8, implicit-def $itstate
    $r1 = tMOVi8 $noreg, 0, 12, killed $cpsr, implicit killed renamable $r1, implicit killed $itstate
    renamable $r0 = tADDhirr killed renamable $r0, killed renamable $r2, 14, $noreg
    t2LoopEnd renamable $lr, %bb.10, implicit-def dead $cpsr
    tB %bb.11, 14, $noreg

  bb.11.c.exit59.loopexit:
    successors: %bb.14(0x80000000)
    liveins: $r0, $r12

    renamable $r7 = tSXTH killed renamable $r0, 14, $noreg
    tB %bb.14, 14, $noreg

  bb.12.c.exit.thread:
    successors: %bb.14(0x80000000)

    $r0, dead $cpsr = tMOVi8 0, 14, $noreg
    renamable $r7, dead $cpsr = tMOVi8 0, 14, $noreg
    tBL 14, $noreg, @crc16, csr_aapcs, implicit-def dead $lr, implicit $sp, implicit killed $r0, implicit-def $sp, implicit-def $r0
    $r12 = tMOVr killed $r0, 14, $noreg
    tB %bb.14, 14, $noreg

  bb.13:
    successors: %bb.14(0x80000000)
    liveins: $r12

    renamable $r7, dead $cpsr = tMOVi8 0, 14, $noreg

  bb.14.c.exit59:
    liveins: $r7, $r12

    $r0 = tMOVr killed $r7, 14, $noreg
    $r1 = tMOVr killed $r12, 14, $noreg
    $sp = t2LDMIA_UPD $sp, 14, $noreg, def $r4, def $r5, def $r6, def $r7, def $r8, def $r9, def $r10, def $lr
    tTAILJMPdND @crc16, 14, $noreg, implicit $sp, implicit $sp, implicit killed $r0, implicit killed $r1

...