Index: llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp
===================================================================
--- llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp
+++ llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp
@@ -508,12 +508,22 @@
   return true;
 }
 
+static bool isVectorPredicated(MachineInstr *MI) {
+  int PIdx = llvm::findFirstVPTPredOperandIdx(*MI);
+  return PIdx != -1 && MI->getOperand(PIdx + 1).getReg() == ARM::VPR;
+}
+
+static bool isRegInClass(const MachineOperand &MO,
+                         const TargetRegisterClass *Class) {
+  return MO.isReg() && MO.getReg() && Class->contains(MO.getReg());
+}
+
 bool LowOverheadLoop::ValidateLiveOuts() const {
   // Collect Q-regs that are live in the exit blocks. We don't collect scalars
   // because they won't be affected by lane predication.
   const TargetRegisterClass *QPRs = TRI.getRegClass(ARM::MQPRRegClassID);
   SmallSet<Register, 2> LiveOuts;
-  SmallVector<MachineBasicBlock*, 2> ExitBlocks;
+  SmallVector<MachineBasicBlock *, 2> ExitBlocks;
   ML.getExitBlocks(ExitBlocks);
   for (auto *MBB : ExitBlocks)
     for (const MachineBasicBlock::RegisterMaskPair &RegMask : MBB->liveins())
@@ -521,7 +531,8 @@
         LiveOuts.insert(RegMask.PhysReg);
 
   // Collect the instructions in the loop body that define the live-out values.
-  SmallPtrSet<MachineInstr*, 2> LiveMIs;
+  SmallPtrSet<MachineInstr *, 2> LiveMIs;
+  assert(ML.getNumBlocks() == 1 && "Expected single block loop!");
   MachineBasicBlock *MBB = ML.getHeader();
   for (auto Reg : LiveOuts)
     if (auto *MI = RDA.getLocalLiveOutMIDef(MBB, Reg))
@@ -534,12 +545,92 @@
   // equivalent when we perform the predication transformation; so we know that
   // any VPT predicated instruction is predicated upon VCTP. Any live-out
   // instruction needs to be predicated, so check this here.
-  for (auto *MI : LiveMIs) {
-    int PIdx = llvm::findFirstVPTPredOperandIdx(*MI);
-    if (PIdx == -1 || MI->getOperand(PIdx+1).getReg() != ARM::VPR)
+  for (auto *MI : LiveMIs)
+    if (!isVectorPredicated(MI))
       return false;
+
+  // We want to find out if the tail-predicated version of this loop will
+  // produce the same values as the loop in its original form. For this to
+  // be true, the newly inserted implicit predication must not change the
+  // the (observable) results.
+  // We're doing this because many instructions in the loop will not be
+  // predicated and so the conversion from VPT predication to tail-predication
+  // can result in different values being produced; due to the tail-predication
+  // preventing many instructions from updating their falsely predicated
+  // lanes. This analyse assumes that all the instructions perform lane-wise
+  // operations and don't perform any exchanges.
+  // A masked load, whether through VPT or tail predication, will write zeros
+  // to any of the falsely predicated bytes. So, from the loads, we know that
+  // the false lanes are zeroed and here we're trying to track that those false
+  // lanes remain zero, or where they change, the differences are masked away
+  // by their user(s).
+  // All MVE loads and stores have to be predicated, so we know that any load
+  // operands, or stored results are equivalent already. Other explicitly
+  // predicated instructions will perform the same operation in the original
+  // loop and the tail-predicated form too. Because of this, we can insert
+  // loads, stores and other predicated instructions into our KnownFalseZeros
+  // set and build from there.
+  SetVector<MachineInstr *> UnknownFalseLanes;
+  SmallPtrSet<MachineInstr *, 4> KnownFalseZeros;
+  for (auto &MI : *MBB) {
+    if (isVectorPredicated(&MI)) {
+      KnownFalseZeros.insert(&MI);
+      continue;
+    }
+
+    // Only evaluate instructions which produce a single value.
+    if (MI.getNumDefs() != 1 || !MI.defs().begin()->isReg()) {
+      UnknownFalseLanes.insert(&MI);
+      continue;
+    }
+
+    Register DefReg = MI.defs().begin()->getReg();
+    for (auto &MO : MI.operands()) {
+      if (!isRegInClass(MO, QPRs) || !MO.isUse() || MO.getReg() != DefReg)
+        continue;
+
+      // If this instruction overwrites one of its operands, and that register
+      // has known lanes, then this instruction also has known predicated false
+      // lanes.
+      if (auto *OpDef = RDA.getMIOperand(&MI, MO)) {
+        if (KnownFalseZeros.count(OpDef)) {
+          KnownFalseZeros.insert(&MI);
+          break;
+        }
+      }
+    }
+    if (!KnownFalseZeros.count(&MI))
+      UnknownFalseLanes.insert(&MI);
   }
 
+  auto HasKnownUsers = [this](MachineInstr *MI, const MachineOperand &MO,
+                              SmallPtrSetImpl<MachineInstr *> &Knowns) {
+    SmallPtrSet<MachineInstr *, 2> Uses;
+    RDA.getGlobalUses(MI, MO.getReg(), Uses);
+    for (auto *Use : Uses) {
+      if (Use != MI && !Knowns.count(Use))
+        return false;
+    }
+    return true;
+  };
+
+  // Now for all the unknown values, see if they're only consumed by known
+  // instructions. Visit in reverse so that we can start at the values being
+  // stored and then we can work towards the leaves, hopefully adding more
+  // instructions to KnownFalseZeros.
+  for (auto *MI : reverse(UnknownFalseLanes)) {
+    for (auto &MO : MI->operands()) {
+      if (!isRegInClass(MO, QPRs) || !MO.isDef())
+        continue;
+      if (!HasKnownUsers(MI, MO, KnownFalseZeros)) {
+        LLVM_DEBUG(dbgs() << "ARM Loops: Found an unknown def of : "
+                          << TRI.getRegAsmName(MO.getReg()) << " at " << *MI);
+        return false;
+      }
+    }
+    // Any unknown false lanes have been masked away by the user(s).
+    KnownFalseZeros.insert(MI);
+  }
   return true;
 }
 
Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/invariant-qreg.mir
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/invariant-qreg.mir
@@ -0,0 +1,473 @@
+# 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
+
+--- |
+  define dso_local <4 x i32> @invariant_use_store(i16* nocapture readonly %a, i32* %c, i32 %N, <4 x i32> %pass) {
+  entry:
+    %cmp9 = icmp eq i32 %N, 0
+    %tmp = add i32 %N, 3
+    %tmp1 = lshr i32 %tmp, 2
+    %tmp2 = shl nuw i32 %tmp1, 2
+    %tmp3 = add i32 %tmp2, -4
+    %tmp4 = lshr i32 %tmp3, 2
+    %tmp5 = add nuw nsw i32 %tmp4, 1
+    br i1 %cmp9, label %exit, label %vector.ph
+
+  vector.ph:                                        ; preds = %entry
+    call void @llvm.set.loop.iterations.i32(i32 %tmp5)
+    br label %vector.body
+
+  vector.body:                                      ; preds = %vector.body, %vector.ph
+    %lsr.iv1 = phi i32 [ %lsr.iv.next, %vector.body ], [ %tmp5, %vector.ph ]
+    %lsr.iv20 = phi i32* [ %scevgep20, %vector.body ], [ %c, %vector.ph ]
+    %lsr.iv = phi i16* [ %scevgep, %vector.body ], [ %a, %vector.ph ]
+    %vec.phi = phi <4 x i32> [ zeroinitializer, %vector.ph ], [ %tmp13, %vector.body ]
+    %tmp7 = phi i32 [ %N, %vector.ph ], [ %tmp9, %vector.body ]
+    %lsr.iv17 = bitcast i16* %lsr.iv to <4 x i16>*
+    %lsr.store = bitcast i32* %lsr.iv20 to <4 x i32>*
+    %tmp8 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %tmp7)
+    %tmp9 = sub i32 %tmp7, 4
+    %wide.masked.load = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* %lsr.iv17, i32 2, <4 x i1> %tmp8, <4 x i16> undef)
+    %tmp10 = sext <4 x i16> %wide.masked.load to <4 x i32>
+    %tmp12 = mul nsw <4 x i32> %pass, %tmp10
+    %tmp13 = add <4 x i32> %tmp12, %vec.phi
+    call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %tmp13, <4 x i32>* %lsr.store, i32 4, <4 x i1> %tmp8)
+    %scevgep = getelementptr i16, i16* %lsr.iv, i32 4
+    %scevgep20 = getelementptr i32, i32* %lsr.iv20, i32 4
+    %tmp14 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %lsr.iv1, i32 1)
+    %tmp15 = icmp ne i32 %tmp14, 0
+    %lsr.iv.next = add nsw i32 %lsr.iv1, -1
+    br i1 %tmp15, label %vector.body, label %exit
+
+  exit:                                             ; preds = %vector.body, %entry
+    ret <4 x i32> %pass
+  }
+
+  define dso_local i32 @invariant_mul_use_reduce(i16* nocapture readonly %a, i32* %c, i32 %N, <4 x i32> %pass) {
+  entry:
+    %cmp9 = icmp eq i32 %N, 0
+    %tmp = add i32 %N, 3
+    %tmp1 = lshr i32 %tmp, 2
+    %tmp2 = shl nuw i32 %tmp1, 2
+    %tmp3 = add i32 %tmp2, -4
+    %tmp4 = lshr i32 %tmp3, 2
+    %tmp5 = add nuw nsw i32 %tmp4, 1
+    br i1 %cmp9, label %exit, label %vector.ph
+
+  vector.ph:                                        ; preds = %entry
+    call void @llvm.set.loop.iterations.i32(i32 %tmp5)
+    br label %vector.body
+
+  vector.body:                                      ; preds = %vector.body, %vector.ph
+    %lsr.iv1 = phi i32 [ %lsr.iv.next, %vector.body ], [ %tmp5, %vector.ph ]
+    %lsr.iv = phi i16* [ %scevgep, %vector.body ], [ %a, %vector.ph ]
+    %tmp7 = phi i32 [ %N, %vector.ph ], [ %tmp9, %vector.body ]
+    %lsr.iv17 = bitcast i16* %lsr.iv to <4 x i16>*
+    %tmp8 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %tmp7)
+    %tmp9 = sub i32 %tmp7, 4
+    %wide.masked.load = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* %lsr.iv17, i32 2, <4 x i1> %tmp8, <4 x i16> undef)
+    %tmp10 = sext <4 x i16> %wide.masked.load to <4 x i32>
+    %tmp12 = mul nsw <4 x i32> %pass, %tmp10
+    %tmp13 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> %tmp12)
+    %scevgep = getelementptr i16, i16* %lsr.iv, i32 4
+    %tmp15 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %lsr.iv1, i32 1)
+    %tmp16 = icmp ne i32 %tmp15, 0
+    %lsr.iv.next = add nsw i32 %lsr.iv1, -1
+    br i1 %tmp16, label %vector.body, label %exit
+
+  exit:                                             ; preds = %vector.body, %entry
+    %res = phi i32 [ 0, %entry ], [ %tmp13, %vector.body ]
+    ret i32 %res
+  }
+
+  define dso_local i32 @invariant_add_use_reduce(i16* nocapture readonly %a, i32* %c, i32 %N, <4 x i32> %pass) {
+  entry:
+    %cmp9 = icmp eq i32 %N, 0
+    %tmp = add i32 %N, 3
+    %tmp1 = lshr i32 %tmp, 2
+    %tmp2 = shl nuw i32 %tmp1, 2
+    %tmp3 = add i32 %tmp2, -4
+    %tmp4 = lshr i32 %tmp3, 2
+    %tmp5 = add nuw nsw i32 %tmp4, 1
+    br i1 %cmp9, label %exit, label %vector.ph
+
+  vector.ph:                                        ; preds = %entry
+    call void @llvm.set.loop.iterations.i32(i32 %tmp5)
+    br label %vector.body
+
+  vector.body:                                      ; preds = %vector.body, %vector.ph
+    %lsr.iv1 = phi i32 [ %lsr.iv.next, %vector.body ], [ %tmp5, %vector.ph ]
+    %lsr.iv = phi i16* [ %scevgep, %vector.body ], [ %a, %vector.ph ]
+    %tmp7 = phi i32 [ %N, %vector.ph ], [ %tmp9, %vector.body ]
+    %lsr.iv17 = bitcast i16* %lsr.iv to <4 x i16>*
+    %tmp8 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %tmp7)
+    %tmp9 = sub i32 %tmp7, 4
+    %wide.masked.load = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* %lsr.iv17, i32 2, <4 x i1> %tmp8, <4 x i16> undef)
+    %tmp10 = sext <4 x i16> %wide.masked.load to <4 x i32>
+    %tmp12 = add nsw <4 x i32> %pass, %tmp10
+    %tmp13 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> %tmp12)
+    %scevgep = getelementptr i16, i16* %lsr.iv, i32 4
+    %tmp15 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %lsr.iv1, i32 1)
+    %tmp16 = icmp ne i32 %tmp15, 0
+    %lsr.iv.next = add nsw i32 %lsr.iv1, -1
+    br i1 %tmp16, label %vector.body, label %exit
+
+  exit:                                             ; preds = %vector.body, %entry
+    %res = phi i32 [ 0, %entry ], [ %tmp13, %vector.body ]
+    ret i32 %res
+  }
+
+  declare i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32>)
+  declare <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>*, i32 immarg, <4 x i1>, <4 x i16>)
+  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:            invariant_use_store
+alignment:       2
+tracksRegLiveness: true
+registers:       []
+liveins:
+  - { reg: '$r0', virtual-reg: '' }
+  - { reg: '$r1', virtual-reg: '' }
+  - { reg: '$r2', virtual-reg: '' }
+frameInfo:
+  stackSize:       8
+  offsetAdjustment: 0
+  maxAlignment:    8
+fixedStack:
+  - { id: 0, type: default, offset: 0, size: 16, alignment: 8, stack-id: default,
+      isImmutable: true, isAliased: false, callee-saved-register: '', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+stack:
+  - { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$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: invariant_use_store
+  ; CHECK: bb.0.entry:
+  ; CHECK:   successors: %bb.3(0x30000000), %bb.1(0x50000000)
+  ; 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:   renamable $r3 = tADDrSPi $sp, 2, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $q0 = MVE_VLDRWU32 killed renamable $r3, 0, 0, $noreg :: (load 16 from %fixed-stack.0, align 8)
+  ; CHECK:   tCBZ $r2, %bb.3
+  ; CHECK: bb.1.vector.ph:
+  ; CHECK:   successors: %bb.2(0x80000000)
+  ; CHECK:   liveins: $q0, $r0, $r1, $r2
+  ; CHECK:   renamable $q1 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q1
+  ; CHECK:   $lr = MVE_DLSTP_32 killed renamable $r2
+  ; CHECK: bb.2.vector.body:
+  ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
+  ; CHECK:   liveins: $lr, $q0, $q1, $r0, $r1
+  ; CHECK:   renamable $r0, renamable $q2 = MVE_VLDRHS32_post killed renamable $r0, 8, 0, $noreg :: (load 8 from %ir.lsr.iv17, align 2)
+  ; CHECK:   renamable $q2 = nsw MVE_VMULi32 renamable $q0, killed renamable $q2, 0, $noreg, undef renamable $q2
+  ; CHECK:   renamable $q1 = MVE_VADDi32 killed renamable $q2, killed renamable $q1, 0, $noreg, undef renamable $q1
+  ; CHECK:   renamable $r1 = MVE_VSTRWU32_post renamable $q1, killed renamable $r1, 16, 0, killed $noreg :: (store 16 into %ir.lsr.store, align 4)
+  ; CHECK:   $lr = MVE_LETP killed renamable $lr, %bb.2
+  ; CHECK: bb.3.exit:
+  ; CHECK:   liveins: $q0
+  ; CHECK:   renamable $r0, renamable $r1 = VMOVRRD renamable $d0, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r2, renamable $r3 = VMOVRRD killed renamable $d1, 14 /* CC::al */, $noreg, implicit killed $q0
+  ; CHECK:   tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc, implicit killed $r0, implicit killed $r1, implicit killed $r2, implicit killed $r3
+  bb.0.entry:
+    successors: %bb.3(0x30000000), %bb.1(0x50000000)
+    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
+    renamable $r3 = tADDrSPi $sp, 2, 14 /* CC::al */, $noreg
+    renamable $q0 = MVE_VLDRWU32 killed renamable $r3, 0, 0, $noreg :: (load 16 from %fixed-stack.0, align 8)
+    tCBZ $r2, %bb.3
+
+  bb.1.vector.ph:
+    successors: %bb.2(0x80000000)
+    liveins: $q0, $r0, $r1, $r2
+
+    renamable $r3, dead $cpsr = tADDi3 renamable $r2, 3, 14 /* CC::al */, $noreg
+    renamable $q1 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q1
+    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 $r12 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
+    t2DoLoopStart renamable $r12
+    $r3 = tMOVr killed $r12, 14 /* CC::al */, $noreg
+
+  bb.2.vector.body:
+    successors: %bb.2(0x7c000000), %bb.3(0x04000000)
+    liveins: $q0, $q1, $r0, $r1, $r2, $r3
+
+    renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg
+    MVE_VPST 8, implicit $vpr
+    renamable $r0, renamable $q2 = MVE_VLDRHS32_post killed renamable $r0, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv17, align 2)
+    $lr = tMOVr $r3, 14 /* CC::al */, $noreg
+    renamable $q2 = nsw MVE_VMULi32 renamable $q0, killed renamable $q2, 0, $noreg, undef renamable $q2
+    renamable $r3, dead $cpsr = nsw tSUBi8 killed $r3, 1, 14 /* CC::al */, $noreg
+    renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14 /* CC::al */, $noreg
+    renamable $q1 = MVE_VADDi32 killed renamable $q2, killed renamable $q1, 0, $noreg, undef renamable $q1
+    renamable $lr = t2LoopDec killed renamable $lr, 1
+    MVE_VPST 8, implicit $vpr
+    renamable $r1 = MVE_VSTRWU32_post renamable $q1, killed renamable $r1, 16, 1, killed renamable $vpr :: (store 16 into %ir.lsr.store, align 4)
+    t2LoopEnd killed renamable $lr, %bb.2, implicit-def dead $cpsr
+    tB %bb.3, 14 /* CC::al */, $noreg
+
+  bb.3.exit:
+    liveins: $q0
+
+    renamable $r0, renamable $r1 = VMOVRRD renamable $d0, 14 /* CC::al */, $noreg
+    renamable $r2, renamable $r3 = VMOVRRD killed renamable $d1, 14 /* CC::al */, $noreg, implicit $q0
+    tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc, implicit killed $r0, implicit killed $r1, implicit killed $r2, implicit killed $r3
+
+...
+---
+name:            invariant_mul_use_reduce
+alignment:       2
+tracksRegLiveness: true
+registers:       []
+liveins:
+  - { reg: '$r0', virtual-reg: '' }
+  - { reg: '$r2', virtual-reg: '' }
+frameInfo:
+  stackSize:       8
+  offsetAdjustment: 0
+  maxAlignment:    8
+fixedStack:
+  - { id: 0, type: default, offset: 0, size: 16, alignment: 8, stack-id: default,
+      isImmutable: true, isAliased: false, callee-saved-register: '', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+stack:
+  - { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$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: invariant_mul_use_reduce
+  ; CHECK: bb.0.entry:
+  ; CHECK:   successors: %bb.4(0x30000000), %bb.1(0x50000000)
+  ; CHECK:   liveins: $lr, $r0, $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:   tCBZ $r2, %bb.4
+  ; CHECK: bb.1.vector.ph:
+  ; CHECK:   successors: %bb.2(0x80000000)
+  ; CHECK:   liveins: $r0, $r2
+  ; CHECK:   renamable $r1, dead $cpsr = tADDi3 renamable $r2, 3, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r1 = t2BICri killed renamable $r1, 3, 14 /* CC::al */, $noreg, $noreg
+  ; CHECK:   renamable $r1, dead $cpsr = tSUBi8 killed renamable $r1, 4, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r3 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r1, 19, 14 /* CC::al */, $noreg, $noreg
+  ; CHECK:   renamable $r1 = tADDrSPi $sp, 2, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $q0 = MVE_VLDRWU32 killed renamable $r1, 0, 0, $noreg :: (load 16 from %fixed-stack.0, align 8)
+  ; CHECK:   dead $lr = t2DLS renamable $r3
+  ; CHECK:   $r1 = tMOVr killed $r3, 14 /* CC::al */, $noreg
+  ; CHECK: bb.2.vector.body:
+  ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
+  ; CHECK:   liveins: $q0, $r0, $r1, $r2
+  ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg
+  ; CHECK:   $lr = tMOVr $r1, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r1, dead $cpsr = nsw tSUBi8 killed $r1, 1, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14 /* CC::al */, $noreg
+  ; CHECK:   MVE_VPST 8, implicit $vpr
+  ; CHECK:   renamable $r0, renamable $q1 = MVE_VLDRHS32_post killed renamable $r0, 8, 1, killed renamable $vpr :: (load 8 from %ir.lsr.iv17, align 2)
+  ; CHECK:   renamable $r12 = MVE_VMLADAVu32 renamable $q0, killed renamable $q1, 0, $noreg
+  ; CHECK:   dead $lr = t2LEUpdate killed renamable $lr, %bb.2
+  ; CHECK: bb.3.exit:
+  ; CHECK:   liveins: $r12
+  ; CHECK:   $r0 = tMOVr killed $r12, 14 /* CC::al */, $noreg
+  ; CHECK:   tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc, implicit killed $r0
+  ; CHECK: bb.4:
+  ; CHECK:   renamable $r12 = t2MOVi 0, 14 /* CC::al */, $noreg, $noreg
+  ; CHECK:   $r0 = tMOVr killed $r12, 14 /* CC::al */, $noreg
+  ; CHECK:   tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc, implicit killed $r0
+  bb.0.entry:
+    successors: %bb.4(0x30000000), %bb.1(0x50000000)
+    liveins: $r0, $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
+    tCBZ $r2, %bb.4
+
+  bb.1.vector.ph:
+    successors: %bb.2(0x80000000)
+    liveins: $r0, $r2
+
+    renamable $r1, dead $cpsr = tADDi3 renamable $r2, 3, 14 /* CC::al */, $noreg
+    renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
+    renamable $r1 = t2BICri killed renamable $r1, 3, 14 /* CC::al */, $noreg, $noreg
+    renamable $r1, dead $cpsr = tSUBi8 killed renamable $r1, 4, 14 /* CC::al */, $noreg
+    renamable $r3 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r1, 19, 14 /* CC::al */, $noreg, $noreg
+    renamable $r1 = tADDrSPi $sp, 2, 14 /* CC::al */, $noreg
+    renamable $q0 = MVE_VLDRWU32 killed renamable $r1, 0, 0, $noreg :: (load 16 from %fixed-stack.0, align 8)
+    t2DoLoopStart renamable $r3
+    $r1 = tMOVr killed $r3, 14 /* CC::al */, $noreg
+
+  bb.2.vector.body:
+    successors: %bb.2(0x7c000000), %bb.3(0x04000000)
+    liveins: $q0, $r0, $r1, $r2
+
+    renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg
+    $lr = tMOVr $r1, 14 /* CC::al */, $noreg
+    renamable $r1, dead $cpsr = nsw tSUBi8 killed $r1, 1, 14 /* CC::al */, $noreg
+    renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14 /* CC::al */, $noreg
+    MVE_VPST 8, implicit $vpr
+    renamable $r0, renamable $q1 = MVE_VLDRHS32_post killed renamable $r0, 8, 1, killed renamable $vpr :: (load 8 from %ir.lsr.iv17, align 2)
+    renamable $r12 = MVE_VMLADAVu32 renamable $q0, killed renamable $q1, 0, $noreg
+    renamable $lr = t2LoopDec killed renamable $lr, 1
+    t2LoopEnd killed renamable $lr, %bb.2, implicit-def dead $cpsr
+    tB %bb.3, 14 /* CC::al */, $noreg
+
+  bb.3.exit:
+    liveins: $r12
+
+    $r0 = tMOVr killed $r12, 14 /* CC::al */, $noreg
+    tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc, implicit killed $r0
+
+  bb.4:
+    renamable $r12 = t2MOVi 0, 14 /* CC::al */, $noreg, $noreg
+    $r0 = tMOVr killed $r12, 14 /* CC::al */, $noreg
+    tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc, implicit killed $r0
+
+...
+---
+name:            invariant_add_use_reduce
+alignment:       2
+tracksRegLiveness: true
+registers:       []
+liveins:
+  - { reg: '$r0', virtual-reg: '' }
+  - { reg: '$r2', virtual-reg: '' }
+frameInfo:
+  stackSize:       8
+  offsetAdjustment: 0
+  maxAlignment:    8
+fixedStack:
+  - { id: 0, type: default, offset: 0, size: 16, alignment: 8, stack-id: default,
+      isImmutable: true, isAliased: false, callee-saved-register: '', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+stack:
+  - { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$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: invariant_add_use_reduce
+  ; CHECK: bb.0.entry:
+  ; CHECK:   successors: %bb.4(0x30000000), %bb.1(0x50000000)
+  ; CHECK:   liveins: $lr, $r0, $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:   tCBZ $r2, %bb.4
+  ; CHECK: bb.1.vector.ph:
+  ; CHECK:   successors: %bb.2(0x80000000)
+  ; CHECK:   liveins: $r0, $r2
+  ; CHECK:   renamable $r1, dead $cpsr = tADDi3 renamable $r2, 3, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r1 = t2BICri killed renamable $r1, 3, 14 /* CC::al */, $noreg, $noreg
+  ; CHECK:   renamable $r1, dead $cpsr = tSUBi8 killed renamable $r1, 4, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r3 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r1, 19, 14 /* CC::al */, $noreg, $noreg
+  ; CHECK:   renamable $r1 = tADDrSPi $sp, 2, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $q0 = MVE_VLDRWU32 killed renamable $r1, 0, 0, $noreg :: (load 16 from %fixed-stack.0, align 8)
+  ; CHECK:   dead $lr = t2DLS renamable $r3
+  ; CHECK:   $r1 = tMOVr killed $r3, 14 /* CC::al */, $noreg
+  ; CHECK: bb.2.vector.body:
+  ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
+  ; CHECK:   liveins: $q0, $r0, $r1, $r2
+  ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg
+  ; CHECK:   MVE_VPST 8, implicit $vpr
+  ; CHECK:   renamable $r0, renamable $q1 = MVE_VLDRHS32_post killed renamable $r0, 8, 1, killed renamable $vpr :: (load 8 from %ir.lsr.iv17, align 2)
+  ; CHECK:   $lr = tMOVr $r1, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $q1 = nsw MVE_VADDi32 renamable $q0, killed renamable $q1, 0, $noreg, undef renamable $q1
+  ; CHECK:   renamable $r1, dead $cpsr = nsw tSUBi8 killed $r1, 1, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r12 = MVE_VADDVu32no_acc killed renamable $q1, 0, $noreg
+  ; CHECK:   dead $lr = t2LEUpdate killed renamable $lr, %bb.2
+  ; CHECK: bb.3.exit:
+  ; CHECK:   liveins: $r12
+  ; CHECK:   $r0 = tMOVr killed $r12, 14 /* CC::al */, $noreg
+  ; CHECK:   tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc, implicit killed $r0
+  ; CHECK: bb.4:
+  ; CHECK:   renamable $r12 = t2MOVi 0, 14 /* CC::al */, $noreg, $noreg
+  ; CHECK:   $r0 = tMOVr killed $r12, 14 /* CC::al */, $noreg
+  ; CHECK:   tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc, implicit killed $r0
+  bb.0.entry:
+    successors: %bb.4(0x30000000), %bb.1(0x50000000)
+    liveins: $r0, $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
+    tCBZ $r2, %bb.4
+
+  bb.1.vector.ph:
+    successors: %bb.2(0x80000000)
+    liveins: $r0, $r2
+
+    renamable $r1, dead $cpsr = tADDi3 renamable $r2, 3, 14 /* CC::al */, $noreg
+    renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
+    renamable $r1 = t2BICri killed renamable $r1, 3, 14 /* CC::al */, $noreg, $noreg
+    renamable $r1, dead $cpsr = tSUBi8 killed renamable $r1, 4, 14 /* CC::al */, $noreg
+    renamable $r3 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r1, 19, 14 /* CC::al */, $noreg, $noreg
+    renamable $r1 = tADDrSPi $sp, 2, 14 /* CC::al */, $noreg
+    renamable $q0 = MVE_VLDRWU32 killed renamable $r1, 0, 0, $noreg :: (load 16 from %fixed-stack.0, align 8)
+    t2DoLoopStart renamable $r3
+    $r1 = tMOVr killed $r3, 14 /* CC::al */, $noreg
+
+  bb.2.vector.body:
+    successors: %bb.2(0x7c000000), %bb.3(0x04000000)
+    liveins: $q0, $r0, $r1, $r2
+
+    renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg
+    MVE_VPST 8, implicit $vpr
+    renamable $r0, renamable $q1 = MVE_VLDRHS32_post killed renamable $r0, 8, 1, killed renamable $vpr :: (load 8 from %ir.lsr.iv17, align 2)
+    $lr = tMOVr $r1, 14 /* CC::al */, $noreg
+    renamable $q1 = nsw MVE_VADDi32 renamable $q0, killed renamable $q1, 0, $noreg, undef renamable $q1
+    renamable $r1, dead $cpsr = nsw tSUBi8 killed $r1, 1, 14 /* CC::al */, $noreg
+    renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14 /* CC::al */, $noreg
+    renamable $r12 = MVE_VADDVu32no_acc killed renamable $q1, 0, $noreg
+    renamable $lr = t2LoopDec killed renamable $lr, 1
+    t2LoopEnd killed renamable $lr, %bb.2, implicit-def dead $cpsr
+    tB %bb.3, 14 /* CC::al */, $noreg
+
+  bb.3.exit:
+    liveins: $r12
+
+    $r0 = tMOVr killed $r12, 14 /* CC::al */, $noreg
+    tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc, implicit killed $r0
+
+  bb.4:
+    renamable $r12 = t2MOVi 0, 14 /* CC::al */, $noreg, $noreg
+    $r0 = tMOVr killed $r12, 14 /* CC::al */, $noreg
+    tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc, implicit killed $r0
+
+...
Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/predicated-invariant.mir
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/predicated-invariant.mir
@@ -0,0 +1,156 @@
+# 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
+
+--- |
+  define dso_local <4 x i32> @invariant_predicated_add_use(i16* nocapture readonly %a, i32* %c, i32 %N, <4 x i32> %pass) #0 {
+  entry:
+    %cmp9 = icmp eq i32 %N, 0
+    %tmp = add i32 %N, 3
+    %tmp1 = lshr i32 %tmp, 2
+    %tmp2 = shl nuw i32 %tmp1, 2
+    %tmp3 = add i32 %tmp2, -4
+    %tmp4 = lshr i32 %tmp3, 2
+    %tmp5 = add nuw nsw i32 %tmp4, 1
+    br i1 %cmp9, label %exit, label %vector.ph
+
+  vector.ph:                                        ; preds = %entry
+    call void @llvm.set.loop.iterations.i32(i32 %tmp5)
+    br label %vector.body
+
+  vector.body:                                      ; preds = %vector.body, %vector.ph
+    %lsr.iv1 = phi i32 [ %lsr.iv.next, %vector.body ], [ %tmp5, %vector.ph ]
+    %lsr.iv = phi i16* [ %scevgep, %vector.body ], [ %a, %vector.ph ]
+    %tmp7 = phi i32 [ %N, %vector.ph ], [ %tmp9, %vector.body ]
+    %lsr.iv17 = bitcast i16* %lsr.iv to <4 x i16>*
+    %tmp8 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %tmp7)
+    %tmp9 = sub i32 %tmp7, 4
+    %wide.masked.load = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* %lsr.iv17, i32 2, <4 x i1> %tmp8, <4 x i16> undef)
+    %tmp10 = sext <4 x i16> %wide.masked.load to <4 x i32>
+    %acc.next = tail call <4 x i32> @llvm.arm.mve.add.predicated.v4i32.v4i1(<4 x i32> %pass, <4 x i32> %tmp10, <4 x i1> %tmp8, <4 x i32> undef)
+    %scevgep = getelementptr i16, i16* %lsr.iv, i32 4
+    %tmp11 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %lsr.iv1, i32 1)
+    %tmp12 = icmp ne i32 %tmp11, 0
+    %lsr.iv.next = add nsw i32 %lsr.iv1, -1
+    br i1 %tmp12, label %vector.body, label %exit
+
+  exit:                                             ; preds = %vector.body, %entry
+    %res = phi <4 x i32> [ zeroinitializer, %entry ], [ %acc.next, %vector.body ]
+    ret <4 x i32> %res
+  }
+
+  declare <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>*, i32 immarg, <4 x i1>, <4 x i16>)
+  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)
+  declare <4 x i32> @llvm.arm.mve.add.predicated.v4i32.v4i1(<4 x i32>, <4 x i32>, <4 x i1>, <4 x i32>)
+
+...
+---
+name:            invariant_predicated_add_use
+alignment:       2
+tracksRegLiveness: true
+registers:       []
+liveins:
+  - { reg: '$r0', virtual-reg: '' }
+  - { reg: '$r2', virtual-reg: '' }
+frameInfo:
+  stackSize:       8
+  offsetAdjustment: 0
+  maxAlignment:    8
+fixedStack:
+  - { id: 0, type: default, offset: 0, size: 16, alignment: 8, stack-id: default,
+      isImmutable: true, isAliased: false, callee-saved-register: '', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+stack:
+  - { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$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: invariant_predicated_add_use
+  ; CHECK: bb.0.entry:
+  ; CHECK:   successors: %bb.3(0x30000000), %bb.1(0x50000000)
+  ; CHECK:   liveins: $lr, $r0, $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:   tCBZ $r2, %bb.3
+  ; CHECK: bb.1.vector.ph:
+  ; CHECK:   successors: %bb.2(0x80000000)
+  ; CHECK:   liveins: $r0, $r2
+  ; CHECK:   renamable $r1 = tADDrSPi $sp, 2, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $q0 = MVE_VLDRWU32 killed renamable $r1, 0, 0, $noreg :: (load 16 from %fixed-stack.0, align 8)
+  ; CHECK:   $lr = MVE_DLSTP_32 killed renamable $r2
+  ; CHECK: bb.2.vector.body:
+  ; CHECK:   successors: %bb.2(0x7c000000), %bb.4(0x04000000)
+  ; CHECK:   liveins: $lr, $q0, $r0
+  ; CHECK:   renamable $r0, renamable $q1 = MVE_VLDRHS32_post killed renamable $r0, 8, 0, $noreg :: (load 8 from %ir.lsr.iv17, align 2)
+  ; CHECK:   renamable $q1 = MVE_VADDi32 renamable $q0, killed renamable $q1, 0, killed $noreg, undef renamable $q1
+  ; CHECK:   $lr = MVE_LETP killed renamable $lr, %bb.2
+  ; CHECK:   tB %bb.4, 14 /* CC::al */, $noreg
+  ; CHECK: bb.3:
+  ; CHECK:   successors: %bb.4(0x80000000)
+  ; CHECK:   renamable $q1 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q1
+  ; CHECK: bb.4.exit:
+  ; CHECK:   liveins: $q1
+  ; CHECK:   renamable $r0, renamable $r1 = VMOVRRD renamable $d2, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r2, renamable $r3 = VMOVRRD killed renamable $d3, 14 /* CC::al */, $noreg, implicit killed $q1
+  ; CHECK:   tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc, implicit killed $r0, implicit killed $r1, implicit killed $r2, implicit killed $r3
+  bb.0.entry:
+    successors: %bb.3(0x30000000), %bb.1(0x50000000)
+    liveins: $r0, $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
+    tCBZ $r2, %bb.3
+
+  bb.1.vector.ph:
+    successors: %bb.2(0x80000000)
+    liveins: $r0, $r2
+
+    renamable $r1, dead $cpsr = tADDi3 renamable $r2, 3, 14 /* CC::al */, $noreg
+    renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
+    renamable $r1 = t2BICri killed renamable $r1, 3, 14 /* CC::al */, $noreg, $noreg
+    renamable $r1, dead $cpsr = tSUBi8 killed renamable $r1, 4, 14 /* CC::al */, $noreg
+    renamable $r3 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r1, 19, 14 /* CC::al */, $noreg, $noreg
+    renamable $r1 = tADDrSPi $sp, 2, 14 /* CC::al */, $noreg
+    renamable $q0 = MVE_VLDRWU32 killed renamable $r1, 0, 0, $noreg :: (load 16 from %fixed-stack.0, align 8)
+    t2DoLoopStart renamable $r3
+    $r1 = tMOVr killed $r3, 14 /* CC::al */, $noreg
+
+  bb.2.vector.body:
+    successors: %bb.2(0x7c000000), %bb.4(0x04000000)
+    liveins: $q0, $r0, $r1, $r2
+
+    renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg
+    $lr = tMOVr $r1, 14 /* CC::al */, $noreg
+    renamable $r1, dead $cpsr = nsw tSUBi8 killed $r1, 1, 14 /* CC::al */, $noreg
+    renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14 /* CC::al */, $noreg
+    renamable $lr = t2LoopDec killed renamable $lr, 1
+    MVE_VPST 4, implicit $vpr
+    renamable $r0, renamable $q1 = MVE_VLDRHS32_post killed renamable $r0, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv17, align 2)
+    renamable $q1 = MVE_VADDi32 renamable $q0, killed renamable $q1, 1, killed renamable $vpr, undef renamable $q1
+    t2LoopEnd killed renamable $lr, %bb.2, implicit-def dead $cpsr
+    tB %bb.4, 14 /* CC::al */, $noreg
+
+  bb.3:
+    successors: %bb.4(0x80000000)
+
+    renamable $q1 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q1
+
+  bb.4.exit:
+    liveins: $q1
+
+    renamable $r0, renamable $r1 = VMOVRRD renamable $d2, 14 /* CC::al */, $noreg
+    renamable $r2, renamable $r3 = VMOVRRD killed renamable $d3, 14 /* CC::al */, $noreg, implicit $q1
+    tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc, implicit killed $r0, implicit killed $r1, implicit killed $r2, implicit killed $r3
+
+...
Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/unpredicated-min.mir
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/unpredicated-min.mir
@@ -0,0 +1,150 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve %s -run-pass=arm-low-overhead-loops -o - | FileCheck %s
+
+--- |
+  define dso_local void @variant_max_use(i16* nocapture readonly %a, i16* %c, i32 %N) #0 {
+  entry:
+    %cmp9 = icmp eq i32 %N, 0
+    %tmp = add i32 %N, 3
+    %tmp1 = lshr i32 %tmp, 2
+    %tmp2 = shl nuw i32 %tmp1, 2
+    %tmp3 = add i32 %tmp2, -4
+    %tmp4 = lshr i32 %tmp3, 2
+    %tmp5 = add nuw nsw i32 %tmp4, 1
+    br i1 %cmp9, label %exit, label %vector.ph
+
+  vector.ph:                                        ; preds = %entry
+    call void @llvm.set.loop.iterations.i32(i32 %tmp5)
+    br label %vector.body
+
+  vector.body:                                      ; preds = %vector.body, %vector.ph
+    %lsr.iv1 = phi i32 [ %lsr.iv.next, %vector.body ], [ %tmp5, %vector.ph ]
+    %lsr.iv = phi i16* [ %scevgep, %vector.body ], [ %a, %vector.ph ]
+    %lsr.iv.2 = phi i16* [ %scevgep.2, %vector.body ], [ %c, %vector.ph ]
+    %tmp7 = phi i32 [ %N, %vector.ph ], [ %tmp9, %vector.body ]
+    %lsr.iv17 = bitcast i16* %lsr.iv to <8 x i16>*
+    %tmp8 = call <8 x i1> @llvm.arm.mve.vctp16(i32 %tmp7)
+    %tmp9 = sub i32 %tmp7, 8
+    %wide.masked.load = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* %lsr.iv17, i32 2, <8 x i1> %tmp8, <8 x i16> undef)
+    %min = tail call i16 @llvm.experimental.vector.reduce.smax.v8i16(<8 x i16> %wide.masked.load)
+    store i16 %min, i16* %lsr.iv.2
+    %scevgep = getelementptr i16, i16* %lsr.iv, i32 8
+    %scevgep.2 = getelementptr i16, i16* %lsr.iv.2, i32 1
+    %tmp10 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %lsr.iv1, i32 1)
+    %tmp11 = icmp ne i32 %tmp10, 0
+    %lsr.iv.next = add nsw i32 %lsr.iv1, -1
+    br i1 %tmp11, label %vector.body, label %exit
+
+  exit:                                             ; preds = %vector.body, %entry
+    ret void
+  }
+
+  declare <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>*, i32 immarg, <8 x i1>, <8 x i16>)
+  declare void @llvm.set.loop.iterations.i32(i32)
+  declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32)
+  declare <8 x i1> @llvm.arm.mve.vctp16(i32)
+  declare i16 @llvm.experimental.vector.reduce.smax.v8i16(<8 x i16>)
+
+...
+---
+name:            variant_max_use
+alignment:       2
+tracksRegLiveness: true
+registers:       []
+liveins:
+  - { reg: '$r0', virtual-reg: '' }
+  - { reg: '$r1', virtual-reg: '' }
+  - { reg: '$r2', virtual-reg: '' }
+frameInfo:
+  stackSize:       8
+  offsetAdjustment: 0
+  maxAlignment:    4
+fixedStack:      []
+stack:
+  - { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$lr', callee-saved-restored: false,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+  - { id: 1, name: '', type: spill-slot, offset: -8, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$r5', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+callSites:       []
+constants:       []
+machineFunctionInfo: {}
+body:             |
+  ; CHECK-LABEL: name: variant_max_use
+  ; CHECK: bb.0.entry:
+  ; CHECK:   successors: %bb.1(0x80000000)
+  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r5
+  ; CHECK:   frame-setup tPUSH 14 /* CC::al */, $noreg, killed $r5, 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 $r5, -8
+  ; CHECK:   tCMPi8 renamable $r2, 0, 14 /* CC::al */, $noreg, implicit-def $cpsr
+  ; CHECK:   t2IT 0, 8, implicit-def $itstate
+  ; CHECK:   tPOP_RET 0 /* CC::eq */, killed $cpsr, def $r5, def $pc, implicit killed $itstate
+  ; 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 $r3 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
+  ; CHECK:   $r12 = t2MOVi16 32768, 14 /* CC::al */, $noreg
+  ; CHECK:   $r12 = t2MOVTi16 killed $r12, 65535, 14 /* CC::al */, $noreg
+  ; CHECK:   dead $lr = t2DLS renamable $r3
+  ; CHECK:   $r5 = tMOVr killed $r3, 14 /* CC::al */, $noreg
+  ; CHECK: bb.1.vector.body:
+  ; CHECK:   successors: %bb.1(0x7c000000), %bb.2(0x04000000)
+  ; CHECK:   liveins: $r0, $r1, $r2, $r5, $r12
+  ; CHECK:   $r3 = tMOVr $r12, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $vpr = MVE_VCTP16 renamable $r2, 0, $noreg
+  ; CHECK:   MVE_VPST 8, implicit $vpr
+  ; CHECK:   renamable $r0, renamable $q0 = MVE_VLDRHU16_post killed renamable $r0, 16, 1, killed renamable $vpr :: (load 16 from %ir.lsr.iv17, align 2)
+  ; CHECK:   renamable $r3 = MVE_VMAXVs16 killed renamable $r3, killed renamable $q0, 0, $noreg
+  ; CHECK:   $lr = tMOVr $r5, 14 /* CC::al */, $noreg
+  ; CHECK:   early-clobber renamable $r1 = t2STRH_POST killed renamable $r3, killed renamable $r1, 2, 14 /* CC::al */, $noreg :: (store 2 into %ir.lsr.iv.2)
+  ; CHECK:   renamable $r5, dead $cpsr = nsw tSUBi8 killed $r5, 1, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 8, 14 /* CC::al */, $noreg
+  ; CHECK:   dead $lr = t2LEUpdate killed renamable $lr, %bb.1
+  ; CHECK: bb.2.exit:
+  ; CHECK:   tPOP_RET 14 /* CC::al */, $noreg, def $r5, def $pc
+  bb.0.entry:
+    successors: %bb.1(0x80000000)
+    liveins: $r0, $r1, $r2, $r5, $lr
+
+    frame-setup tPUSH 14 /* CC::al */, $noreg, killed $r5, 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 $r5, -8
+    tCMPi8 renamable $r2, 0, 14 /* CC::al */, $noreg, implicit-def $cpsr
+    t2IT 0, 8, implicit-def $itstate
+    tPOP_RET 0 /* CC::eq */, killed $cpsr, def $r5, def $pc, implicit killed $itstate
+    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 $r3 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
+    $r12 = t2MOVi16 32768, 14 /* CC::al */, $noreg
+    $r12 = t2MOVTi16 killed $r12, 65535, 14 /* CC::al */, $noreg
+    t2DoLoopStart renamable $r3
+    $r5 = tMOVr killed $r3, 14 /* CC::al */, $noreg
+
+  bb.1.vector.body:
+    successors: %bb.1(0x7c000000), %bb.2(0x04000000)
+    liveins: $r0, $r1, $r2, $r5, $r12
+
+    $r3 = tMOVr $r12, 14 /* CC::al */, $noreg
+    renamable $vpr = MVE_VCTP16 renamable $r2, 0, $noreg
+    MVE_VPST 8, implicit $vpr
+    renamable $r0, renamable $q0 = MVE_VLDRHU16_post killed renamable $r0, 16, 1, killed renamable $vpr :: (load 16 from %ir.lsr.iv17, align 2)
+    renamable $r3 = MVE_VMAXVs16 killed renamable $r3, killed renamable $q0, 0, $noreg
+    $lr = tMOVr $r5, 14 /* CC::al */, $noreg
+    early-clobber renamable $r1 = t2STRH_POST killed renamable $r3, killed renamable $r1, 2, 14 /* CC::al */, $noreg :: (store 2 into %ir.lsr.iv.2)
+    renamable $r5, dead $cpsr = nsw tSUBi8 killed $r5, 1, 14 /* CC::al */, $noreg
+    renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 8, 14 /* CC::al */, $noreg
+    renamable $lr = t2LoopDec killed renamable $lr, 1
+    t2LoopEnd killed renamable $lr, %bb.1, implicit-def dead $cpsr
+    tB %bb.2, 14 /* CC::al */, $noreg
+
+  bb.2.exit:
+    tPOP_RET 14 /* CC::al */, $noreg, def $r5, def $pc
+
+...