Index: llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp
===================================================================
--- llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp
+++ llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp
@@ -127,23 +127,25 @@
       MI(I) { Predicates.insert(Preds.begin(), Preds.end()); }
   };
 
-  // Represent a VPT block, a list of instructions that begins with a VPST and
-  // has a maximum of four proceeding instructions. All instructions within the
-  // block are predicated upon the vpr and we allow instructions to define the
-  // vpr within in the block too.
+  // Represent a VPT block, a list of instructions that begins with a VPT/VPST
+  // and has a maximum of four proceeding instructions. All instructions within
+  // the block are predicated upon the vpr and we allow instructions to define
+  // the vpr within in the block too.
   class VPTBlock {
-    std::unique_ptr<PredicatedMI> VPST;
+    // The predicate then instruction, which is either a VPT, or a VPST
+    // instruction.
+    std::unique_ptr<PredicatedMI> PredicateThen;
     PredicatedMI *Divergent = nullptr;
     SmallVector<PredicatedMI, 4> Insts;
 
   public:
     VPTBlock(MachineInstr *MI, SetVector<MachineInstr*> &Preds) {
-      VPST = std::make_unique<PredicatedMI>(MI, Preds);
+      PredicateThen = std::make_unique<PredicatedMI>(MI, Preds);
     }
 
     void addInst(MachineInstr *MI, SetVector<MachineInstr*> &Preds) {
       LLVM_DEBUG(dbgs() << "ARM Loops: Adding predicated MI: " << *MI);
-      if (!Divergent && !set_difference(Preds, VPST->Predicates).empty()) {
+      if (!Divergent && !set_difference(Preds, PredicateThen->Predicates).empty()) {
         Divergent = &Insts.back();
         LLVM_DEBUG(dbgs() << " - has divergent predicate: " << *Divergent->MI);
       }
@@ -160,18 +162,27 @@
     // Is the given instruction part of the predicate set controlling the entry
     // to the block.
     bool IsPredicatedOn(MachineInstr *MI) const {
-      return VPST->Predicates.count(MI);
+      return PredicateThen->Predicates.count(MI);
+    }
+
+    // Returns true if this is a VPT instruction, which is a predicate-then
+    // instruction that performs a comparison.
+    bool isVPT() const { return !isVPT(); }
+
+    // Returns true if this is a VPST instruction.
+    bool isVPST() const {
+      return PredicateThen->MI->getOpcode() == ARM::MVE_VPST;
     }
 
     // Is the given instruction the only predicate which controls the entry to
     // the block.
     bool IsOnlyPredicatedOn(MachineInstr *MI) const {
-      return IsPredicatedOn(MI) && VPST->Predicates.size() == 1;
+      return IsPredicatedOn(MI) && PredicateThen->Predicates.size() == 1;
     }
 
     unsigned size() const { return Insts.size(); }
     SmallVectorImpl<PredicatedMI> &getInsts() { return Insts; }
-    MachineInstr *getVPST() const { return VPST->MI; }
+    MachineInstr *getPredicateThen() const { return PredicateThen->MI; }
     PredicatedMI *getDivergent() const { return Divergent; }
   };
 
@@ -187,6 +198,7 @@
     MachineInstr *Dec = nullptr;
     MachineInstr *End = nullptr;
     MachineInstr *VCTP = nullptr;
+    SmallPtrSet<MachineInstr*, 4> SecondaryVCTPs;
     VPTBlock *CurrentBlock = nullptr;
     SetVector<MachineInstr*> CurrentPredicate;
     SmallVector<VPTBlock, 4> VPTBlocks;
@@ -485,6 +497,8 @@
   if (auto *Def = RDA.getUniqueReachingMIDef(&MBB->back(), NumElements)) {
     SmallPtrSet<MachineInstr*, 2> ElementChain;
     SmallPtrSet<MachineInstr*, 2> Ignore = { VCTP };
+    Ignore.insert(SecondaryVCTPs.begin(), SecondaryVCTPs.end());
+
     unsigned ExpectedVectorWidth = getTailPredVectorWidth(VCTP->getOpcode());
 
     if (RDA.isSafeToRemove(Def, ElementChain, Ignore)) {
@@ -508,6 +522,7 @@
       ToRemove.insert(ElementChain.begin(), ElementChain.end());
     }
   }
+
   return true;
 }
 
@@ -781,29 +796,35 @@
   if (CannotTailPredicate)
     return false;
 
-  // Only support a single vctp.
-  if (isVCTP(MI) && VCTP)
-    return false;
-
-  // Start a new vpt block when we discover a vpt.
-  if (MI->getOpcode() == ARM::MVE_VPST) {
+  if (isVCTP(MI)) {
+    // If we find another VCTP, check whether it's identical to the "main" VCTP.
+    // If it is, store it in the SecondaryVCTPs set.
+    if (VCTP) {
+      if (!VCTP->getOperand(1).isIdenticalTo(MI->getOperand(1)))
+        return false;
+      LLVM_DEBUG(dbgs() << "ARM Loops: Found secondary VCTP: " << *MI);
+      SecondaryVCTPs.insert(MI);
+    } else {
+      LLVM_DEBUG(dbgs() << "ARM Loops: Found 'main' VCTP: " << *MI);
+      VCTP = MI;
+    }
+  } else if (isVPTOpcode(MI->getOpcode())) {
+    // Start a new vpt block when we discover a VPT or a VPST.
     VPTBlocks.emplace_back(MI, CurrentPredicate);
     CurrentBlock = &VPTBlocks.back();
     return true;
-  } else if (isVCTP(MI))
-    VCTP = MI;
-  else if (MI->getOpcode() == ARM::MVE_VPSEL ||
-           MI->getOpcode() == ARM::MVE_VPNOT)
-    return false;
-
+  }
   // TODO: Allow VPSEL and VPNOT, we currently cannot because:
   // 1) It will use the VPR as a predicate operand, but doesn't have to be
   //    instead a VPT block, which means we can assert while building up
-  //    the VPT block because we don't find another VPST to being a new
+  //    the VPT block because we don't find another VPT or VPST to being a new
   //    one.
   // 2) VPSEL still requires a VPR operand even after tail predicating,
   //    which means we can't remove it unless there is another
   //    instruction, such as vcmp, that can provide the VPR def.
+  else if (MI->getOpcode() == ARM::MVE_VPSEL ||
+           MI->getOpcode() == ARM::MVE_VPNOT)
+    return false;
 
   bool IsUse = false;
   bool IsDef = false;
@@ -1197,12 +1218,12 @@
     if (Block.HasNonUniformPredicate()) {
       PredicatedMI *Divergent = Block.getDivergent();
       if (isVCTP(Divergent->MI)) {
-        // The vctp will be removed, so the block mask of the VPST/VPT will need
+        // The vctp will be removed, so the block mask of the vp(s)t will need
         // to be recomputed.
-        LoLoop.BlockMasksToRecompute.insert(Block.getVPST());
-      } else if (Block.IsOnlyPredicatedOn(LoLoop.VCTP)) {
-        // The VPT block has a non-uniform predicate but it's entry is guarded
-        // only by a vctp, which means we:
+        LoLoop.BlockMasksToRecompute.insert(Block.getPredicateThen());
+      } else if (Block.isVPST() && Block.IsOnlyPredicatedOn(LoLoop.VCTP)) {
+        // The VPT block has a non-uniform predicate but it uses a vpst and its
+        // entry is guarded only by a vctp, which means we:
         // - Need to remove the original vpst.
         // - Then need to unpredicate any following instructions, until
         //   we come across the divergent vpr def.
@@ -1210,7 +1231,7 @@
         //   the divergent vpr def.
         // TODO: We could be producing more VPT blocks than necessary and could
         // fold the newly created one into a proceeding one.
-        for (auto I = ++MachineBasicBlock::iterator(Block.getVPST()),
+        for (auto I = ++MachineBasicBlock::iterator(Block.getPredicateThen()),
              E = ++MachineBasicBlock::iterator(Divergent->MI); I != E; ++I)
           RemovePredicate(&*I);
 
@@ -1223,29 +1244,57 @@
           ++Size;
           ++I;
         }
-        // Create a VPST with a null mask, we'll recompute it later.
+        // Create a VPST (with a null mask for now, we'll recompute it later).
         MachineInstrBuilder MIB = BuildMI(*InsertAt->getParent(), InsertAt,
                                           InsertAt->getDebugLoc(),
                                           TII->get(ARM::MVE_VPST));
         MIB.addImm(0);
-        LLVM_DEBUG(dbgs() << "ARM Loops: Removing VPST: " << *Block.getVPST());
+        LLVM_DEBUG(dbgs() << "ARM Loops: Removing VPST: " << *Block.getPredicateThen());
         LLVM_DEBUG(dbgs() << "ARM Loops: Created VPST: " << *MIB);
-        LoLoop.ToRemove.insert(Block.getVPST());
+        LoLoop.ToRemove.insert(Block.getPredicateThen());
         LoLoop.BlockMasksToRecompute.insert(MIB.getInstr());
       }
-    } else if (Block.IsOnlyPredicatedOn(LoLoop.VCTP)) {
-      // A vpt block which is only predicated upon vctp and has no internal vpr
-      // defs:
+      // Else, iterate over the block, removing the extra VCTPs it may contain.
+      else {
+        bool RemovedVCTP = false;
+        for(PredicatedMI &Elt : Block.getInsts()) {
+          MachineInstr* MI = Elt.MI;
+          if(isVCTP(MI)) {
+            LLVM_DEBUG(dbgs() << "ARM Loops: Removing VCTP: " << *MI);
+            LoLoop.ToRemove.insert(MI);
+            RemovedVCTP = true;
+            continue;
+          }
+        }
+        if(RemovedVCTP)
+          LoLoop.BlockMasksToRecompute.insert(Block.getPredicateThen());
+      }
+    } else if (Block.IsOnlyPredicatedOn(LoLoop.VCTP) && Block.isVPST()) {
+      // A vpt block starting with VPST, is only predicated upon vctp and has no
+      // internal vpr defs:
       // - Remove vpst.
       // - Unpredicate the remaining instructions.
-      LLVM_DEBUG(dbgs() << "ARM Loops: Removing VPST: " << *Block.getVPST());
-      LoLoop.ToRemove.insert(Block.getVPST());
+      LLVM_DEBUG(dbgs() << "ARM Loops: Removing VPST: " << *Block.getPredicateThen());
+      LoLoop.ToRemove.insert(Block.getPredicateThen());
       for (auto &PredMI : Insts)
         RemovePredicate(PredMI.MI);
     }
   }
-  LLVM_DEBUG(dbgs() << "ARM Loops: Removing VCTP: " << *LoLoop.VCTP);
+  LLVM_DEBUG(dbgs() << "ARM Loops: Removing remaining VCTPs...\n");
+  // Remove the "main" VCTP
   LoLoop.ToRemove.insert(LoLoop.VCTP);
+  LLVM_DEBUG(dbgs() << "    " << *LoLoop.VCTP);
+  // Remove remaining secondary VCTPs
+  for (MachineInstr *VCTP : LoLoop.SecondaryVCTPs) {
+    // All VCTPs that aren't marked for removal yet should be unpredicated ones.
+    // The predicated ones should have already been marked for removal when
+    // visiting the VPT blocks.
+    if (LoLoop.ToRemove.insert(VCTP).second) {
+      assert(getVPTInstrPredicate(*VCTP) == ARMVCC::None &&
+             "Removing Predicated VCTP without updating the block mask!");
+      LLVM_DEBUG(dbgs() << "    " << *VCTP);
+    }
+  }
 }
 
 void ARMLowOverheadLoops::Expand(LowOverheadLoop &LoLoop) {
Index: llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
===================================================================
--- llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
+++ llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
@@ -1268,6 +1268,7 @@
                                              TargetLibraryInfo *TLI,
                                              DominatorTree *DT,
                                              const LoopAccessInfo *LAI) {
+                                               return true;
   if (DisableTailPredication)
     return false;
 
Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/cond-vector-reduce-mve-codegen.ll
===================================================================
--- llvm/test/CodeGen/Thumb2/LowOverheadLoops/cond-vector-reduce-mve-codegen.ll
+++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/cond-vector-reduce-mve-codegen.ll
@@ -449,26 +449,17 @@
 ; CHECK-NEXT:    cmp r3, #0
 ; CHECK-NEXT:    it eq
 ; CHECK-NEXT:    popeq {r7, pc}
-; CHECK-NEXT:    add.w r12, r3, #3
-; CHECK-NEXT:    mov.w lr, #1
-; CHECK-NEXT:    bic r12, r12, #3
-; CHECK-NEXT:    sub.w r12, r12, #4
-; CHECK-NEXT:    add.w lr, lr, r12, lsr #2
-; CHECK-NEXT:    dls lr, lr
+; CHECK-NEXT:    dlstp.32 lr, r3
 ; CHECK-NEXT:  .LBB5_1: @ %bb12
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    vctp.32 r3
-; CHECK-NEXT:    vpst
-; CHECK-NEXT:    vldrwt.u32 q0, [r0]
-; CHECK-NEXT:    vpttt.i32 ne, q0, zr
+; CHECK-NEXT:    vldrw.u32 q0, [r0]
+; CHECK-NEXT:    vptt.i32 ne, q0, zr
 ; CHECK-NEXT:    vcmpt.s32 le, q0, r2
-; CHECK-NEXT:    vctpt.32 r3
 ; CHECK-NEXT:    vldrwt.u32 q1, [r1], #16
-; CHECK-NEXT:    subs r3, #4
 ; CHECK-NEXT:    vmul.i32 q0, q1, q0
 ; CHECK-NEXT:    vpst
 ; CHECK-NEXT:    vstrwt.32 q0, [r0], #16
-; CHECK-NEXT:    le lr, .LBB5_1
+; CHECK-NEXT:    letp lr, .LBB5_1
 ; CHECK-NEXT:  @ %bb.2: @ %bb32
 ; CHECK-NEXT:    pop {r7, pc}
 bb:
Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/vctp-in-vpt-2.mir
===================================================================
--- llvm/test/CodeGen/Thumb2/LowOverheadLoops/vctp-in-vpt-2.mir
+++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/vctp-in-vpt-2.mir
@@ -118,24 +118,16 @@
   ; CHECK: bb.1.bb3:
   ; CHECK:   successors: %bb.2(0x80000000)
   ; CHECK:   liveins: $r0, $r1, $r2, $r3
-  ; CHECK:   renamable $r12 = t2ADDri renamable $r2, 3, 14 /* CC::al */, $noreg, $noreg
-  ; CHECK:   renamable $lr = t2MOVi 1, 14 /* CC::al */, $noreg, $noreg
-  ; CHECK:   renamable $r12 = t2BICri killed renamable $r12, 3, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   $vpr = VMSR_P0 killed $r3, 14 /* CC::al */, $noreg
-  ; CHECK:   renamable $r12 = t2SUBri killed renamable $r12, 4, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   VSTR_P0_off killed renamable $vpr, $sp, 0, 14 /* CC::al */, $noreg :: (store 4 into %stack.0)
   ; CHECK:   $r3 = tMOVr $r0, 14 /* CC::al */, $noreg
-  ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $lr, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
-  ; CHECK:   $lr = t2DLS killed renamable $lr
+  ; CHECK:   $lr = MVE_DLSTP_32 killed renamable $r2
   ; CHECK: bb.2.bb9:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
-  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3
+  ; CHECK:   liveins: $lr, $r0, $r1, $r3
   ; CHECK:   renamable $vpr = VLDR_P0_off $sp, 0, 14 /* CC::al */, $noreg :: (load 4 from %stack.0)
-  ; CHECK:   MVE_VPST 4, implicit $vpr
-  ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r2, 1, killed renamable $vpr
-  ; CHECK:   renamable $r1, renamable $q0 = MVE_VLDRWU32_post killed renamable $r1, 16, 1, killed renamable $vpr :: (load 16 from %ir.lsr.iv24, align 4)
-  ; 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 8, implicit $vpr
+  ; CHECK:   renamable $r1, renamable $q0 = MVE_VLDRWU32_post killed renamable $r1, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv24, align 4)
   ; CHECK:   MVE_VPST 4, implicit $vpr
   ; CHECK:   renamable $vpr = MVE_VCMPi32r renamable $q0, $zr, 1, 1, killed renamable $vpr
   ; CHECK:   renamable $r3, renamable $q1 = MVE_VLDRWU32_post killed renamable $r3, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv1, align 4)
@@ -143,7 +135,7 @@
   ; CHECK:   MVE_VPST 8, implicit $vpr
   ; CHECK:   MVE_VSTRWU32 killed renamable $q0, killed renamable $r0, 0, 1, killed renamable $vpr :: (store 16 into %ir.lsr.iv1, align 4)
   ; CHECK:   $r0 = tMOVr $r3, 14 /* CC::al */, $noreg
-  ; CHECK:   $lr = t2LEUpdate killed renamable $lr, %bb.2
+  ; CHECK:   $lr = MVE_LETP killed renamable $lr, %bb.2
   ; CHECK: bb.3.bb27:
   ; CHECK:   $sp = tADDspi $sp, 1, 14 /* CC::al */, $noreg
   ; CHECK:   tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc
Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/vpt-blocks.mir
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/vpt-blocks.mir
@@ -0,0 +1,165 @@
+# 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 - | FileCheck %s
+
+--- |
+  @_ZL3arr = internal global [10 x i32] [i32 1, i32 2, i32 3, i32 5, i32 5, i32 5, i32 -2, i32 0, i32 -8, i32 -1], align 4
+  @.str = private unnamed_addr constant [5 x i8] c"%d, \00", align 1
+
+  define arm_aapcs_vfpcc void @vpt_block(i32* nocapture %A, i32 %n, i32 %x) {
+  entry:
+    %cmp9 = icmp sgt 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 %cmp9, label %vector.ph, label %for.cond.cleanup
+
+  vector.ph:                                        ; preds = %entry
+    %sub = sub nsw i32 0, %x
+    call void @llvm.set.loop.iterations.i32(i32 %5)
+    br label %vector.body
+
+  vector.body:                                      ; preds = %vector.body, %vector.ph
+    %lsr.iv1 = phi i32* [ %scevgep, %vector.body ], [ %A, %vector.ph ]
+    %6 = phi i32 [ %5, %vector.ph ], [ %18, %vector.body ]
+    %7 = phi i32 [ %n, %vector.ph ], [ %9, %vector.body ]
+    %lsr.iv12 = bitcast i32* %lsr.iv1 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.iv12, i32 4, <4 x i1> %8, <4 x i32> undef)
+    %10 = insertelement <4 x i32> undef, i32 %x, i32 0
+    %11 = shufflevector <4 x i32> %10, <4 x i32> undef, <4 x i32> zeroinitializer
+    %12 = icmp slt <4 x i32> %wide.masked.load, %11
+    %13 = insertelement <4 x i32> undef, i32 %sub, i32 0
+    %14 = shufflevector <4 x i32> %13, <4 x i32> undef, <4 x i32> zeroinitializer
+    %15 = icmp sgt <4 x i32> %wide.masked.load, %14
+    %16 = and <4 x i1> %12, %15
+    %17 = and <4 x i1> %16, %8
+    call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> zeroinitializer, <4 x i32>* %lsr.iv12, i32 4, <4 x i1> %17)
+    %scevgep = getelementptr i32, i32* %lsr.iv1, i32 4
+    %18 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %6, i32 1)
+    %19 = icmp ne i32 %18, 0
+    br i1 %19, label %vector.body, label %for.cond.cleanup
+
+  for.cond.cleanup:                                 ; preds = %vector.body, %entry
+    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 void @llvm.set.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:            vpt_block
+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: '' }
+frameInfo:
+  isFrameAddressTaken: false
+  isReturnAddressTaken: false
+  hasStackMap:     false
+  hasPatchPoint:   false
+  stackSize:       8
+  offsetAdjustment: 0
+  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: '' }
+callSites:       []
+constants:       []
+machineFunctionInfo: {}
+body:             |
+  ; CHECK-LABEL: name: vpt_block
+  ; CHECK: bb.0.entry:
+  ; CHECK:   successors: %bb.1(0x80000000)
+  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r7
+  ; CHECK:   frame-setup tPUSH 14 /* CC::al */, $noreg, killed $r7, 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:   tCMPi8 renamable $r1, 1, 14 /* CC::al */, $noreg, implicit-def $cpsr
+  ; CHECK:   t2IT 11, 8, implicit-def $itstate
+  ; CHECK:   frame-destroy tPOP_RET 11 /* CC::lt */, killed $cpsr, def $r7, def $pc, implicit killed $itstate
+  ; CHECK:   renamable $q0 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q0
+  ; CHECK:   renamable $r3, dead $cpsr = nsw tRSB renamable $r2, 14 /* CC::al */, $noreg
+  ; CHECK:   $lr = MVE_DLSTP_32 killed renamable $r1
+  ; CHECK: bb.1.vector.body:
+  ; CHECK:   successors: %bb.1(0x7c000000), %bb.2(0x04000000)
+  ; CHECK:   liveins: $lr, $q0, $r0, $r2, $r3
+  ; CHECK:   renamable $q1 = MVE_VLDRWU32 renamable $r0, 0, 0, killed $noreg
+  ; CHECK:   MVE_VPTv4s32r 4, renamable $q1, renamable $r2, 11, implicit-def $vpr
+  ; CHECK:   renamable $vpr = MVE_VCMPs32r killed renamable $q1, renamable $r3, 12, 1, killed renamable $vpr
+  ; CHECK:   renamable $r0 = MVE_VSTRWU32_post renamable $q0, killed renamable $r0, 16, 1, killed renamable $vpr
+  ; CHECK:   $lr = MVE_LETP killed renamable $lr, %bb.1
+  ; CHECK: bb.2.for.cond.cleanup:
+  ; CHECK:   frame-destroy tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc
+  bb.0.entry:
+    successors: %bb.1(0x80000000)
+    liveins: $r0, $r1, $r2, $r7, $lr
+
+    frame-setup tPUSH 14 /* CC::al */, $noreg, killed $r7, 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
+    tCMPi8 renamable $r1, 1, 14 /* CC::al */, $noreg, implicit-def $cpsr
+    t2IT 11, 8, implicit-def $itstate
+    frame-destroy tPOP_RET 11 /* CC::lt */, killed $cpsr, def $r7, def $pc, implicit killed $itstate
+    renamable $r3, dead $cpsr = tADDi3 renamable $r1, 3, 14 /* CC::al */, $noreg
+    renamable $q0 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q0
+    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, dead $cpsr = nsw tRSB renamable $r2, 14 /* CC::al */, $noreg
+    t2DoLoopStart renamable $lr
+
+  bb.1.vector.body:
+    successors: %bb.1(0x7c000000), %bb.2(0x04000000)
+    liveins: $lr, $q0, $r0, $r1, $r2, $r3
+
+    renamable $vpr = MVE_VCTP32 renamable $r1, 0, $noreg
+    MVE_VPST 8, implicit $vpr
+    renamable $q1 = MVE_VLDRWU32 renamable $r0, 0, 1, killed renamable $vpr
+    MVE_VPTv4s32r 2, renamable $q1, renamable $r2, 11, implicit-def $vpr
+    renamable $vpr = MVE_VCMPs32r killed renamable $q1, renamable $r3, 12, 1, killed renamable $vpr
+    renamable $vpr = MVE_VCTP32 renamable $r1, 1, killed renamable $vpr
+    renamable $r0 = MVE_VSTRWU32_post renamable $q0, killed renamable $r0, 16, 1, killed renamable $vpr
+    renamable $r1, dead $cpsr = tSUBi8 killed renamable $r1, 4, 14 /* CC::al */, $noreg
+    renamable $lr = t2LoopDec killed renamable $lr, 1
+    t2LoopEnd renamable $lr, %bb.1, implicit-def dead $cpsr
+    tB %bb.2, 14 /* CC::al */, $noreg
+
+  bb.2.for.cond.cleanup:
+    frame-destroy tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc
+
+...