[ARM] Remove DLS lr, lr

[dmgreen]

Summary

A DLS lr, lr only move lr to itself, and can be removed as a result.

[samparker]

llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp

1663

Would be nicer to handle this in ExpandLoopStart.

[dmgreen]

Now in ExpandStart

[samparker]

Cheers, LGTM.

llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp

MachineInstr* ARMLowOverheadLoops::ExpandLoopStart(LowOverheadLoop &LoLoop) {
   IterationCountDCE(LoLoop);
 
   MachineBasicBlock::iterator InsertPt = LoLoop.StartInsertPt;
   MachineInstr *Start = LoLoop.Start;
   MachineBasicBlock *MBB = LoLoop.StartInsertBB;
   unsigned Opc = LoLoop.getStartOpcode();
   MachineOperand &Count = LoLoop.getLoopStartOperand();
 
+  // A DLS lr, lr we needn't emit
+  MachineInstr* NewStart;
+  if (Opc == ARM::t2DLS && Count.isReg() && Count.getReg() == ARM::LR) {
+    LLVM_DEBUG(dbgs() << "ARM Loops: Didn't insert start: DLS lr, lr");
+    NewStart = nullptr;
+  } else {
     MachineInstrBuilder MIB =
       BuildMI(*MBB, InsertPt, Start->getDebugLoc(), TII->get(Opc));
 
     MIB.addDef(ARM::LR);
     MIB.add(Count);
     if (!isDo(Start))
       MIB.add(Start->getOperand(1));
 
-  LoLoop.ToRemove.insert(Start);
     LLVM_DEBUG(dbgs() << "ARM Loops: Inserted start: " << *MIB);
-  return &*MIB;
+    NewStart = &*MIB;
+  }
+
+  LoLoop.ToRemove.insert(Start);
+  return NewStart;
 }
 
 void ARMLowOverheadLoops::ConvertVPTBlocks(LowOverheadLoop &LoLoop) {
   auto RemovePredicate = [](MachineInstr *MI) {
     LLVM_DEBUG(dbgs() << "ARM Loops: Removing predicate from: " << *MI);
     if (int PIdx = llvm::findFirstVPTPredOperandIdx(*MI)) {
       assert(MI->getOperand(PIdx).getImm() == ARMVCC::Then &&
              "Expected Then predicate!");
if (LoLoop.Revert) {
     else
       RevertDo(LoLoop.Start);
     if (LoLoop.Dec == LoLoop.End)
       RevertLoopEndDec(LoLoop.End);
     else
       RevertLoopEnd(LoLoop.End, RevertLoopDec(LoLoop.Dec));
   } else {
     LoLoop.Start = ExpandLoopStart(LoLoop);
+    if (LoLoop.Start)
       RemoveDeadBranch(LoLoop.Start);
     LoLoop.End = ExpandLoopEnd(LoLoop);
     RemoveDeadBranch(LoLoop.End);
     if (LoLoop.IsTailPredicationLegal())
       ConvertVPTBlocks(LoLoop);
     for (auto *I : LoLoop.ToRemove) {
       LLVM_DEBUG(dbgs() << "ARM Loops: Erasing " << *I);
       I->eraseFromParent();
     }
     for (auto *I : LoLoop.BlockMasksToRecompute) {
       LLVM_DEBUG(dbgs() << "ARM Loops: Recomputing VPT/VPST Block Mask: " << *I);
       recomputeVPTBlockMask(*I);
       LLVM_DEBUG(dbgs() << "           ... done: " << *I);
     }
   }

llvm/test/CodeGen/Thumb2/LowOverheadLoops/cond-vector-reduce-mve-codegen.ll

 ; CHECK-NEXT:    push {r4, lr}
 ; CHECK-NEXT:    add.w r12, r3, #3
 ; CHECK-NEXT:    mov.w lr, #1
 ; CHECK-NEXT:    bic r12, r12, #3
 ; CHECK-NEXT:    vmov.i32 q1, #0x0
 ; CHECK-NEXT:    sub.w r12, r12, #4
 ; CHECK-NEXT:    add.w lr, lr, r12, lsr #2
 ; CHECK-NEXT:    mov.w r12, #0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB0_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    and r4, r12, #15
 ; CHECK-NEXT:    vmov q0, q1
 ; CHECK-NEXT:    vctp.32 r3
 ; CHECK-NEXT:    vpstt
 ; CHECK-NEXT:    vldrwt.u32 q1, [r2], #16
 ; CHECK-NEXT:    vldrwt.u32 q2, [r1], #16

 ; CHECK-NEXT:  @ %bb.1: @ %vector.ph
 ; CHECK-NEXT:    add.w r4, r12, #3
 ; CHECK-NEXT:    vmov.i32 q1, #0x0
 ; CHECK-NEXT:    bic r4, r4, #3
 ; CHECK-NEXT:    sub.w lr, r4, #4
 ; CHECK-NEXT:    movs r4, #1
 ; CHECK-NEXT:    add.w lr, r4, lr, lsr #2
 ; CHECK-NEXT:    movs r4, #0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB1_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    and r5, r4, #15
 ; CHECK-NEXT:    vmov q0, q1
 ; CHECK-NEXT:    vctp.32 r12
 ; CHECK-NEXT:    vpsttt
 ; CHECK-NEXT:    vldrwt.u32 q1, [r1], #16
 ; CHECK-NEXT:    vldrwt.u32 q2, [r3], #16

 ; CHECK-NEXT:  @ %bb.1: @ %vector.ph
 ; CHECK-NEXT:    add.w r4, r12, #3
 ; CHECK-NEXT:    vmov.i32 q1, #0x0
 ; CHECK-NEXT:    bic r4, r4, #3
 ; CHECK-NEXT:    sub.w lr, r4, #4
 ; CHECK-NEXT:    movs r4, #1
 ; CHECK-NEXT:    add.w lr, r4, lr, lsr #2
 ; CHECK-NEXT:    movs r4, #0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB2_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.32 r12
 ; CHECK-NEXT:    vmov q0, q1
 ; CHECK-NEXT:    vpstt
 ; CHECK-NEXT:    vldrwt.u32 q1, [r1], #16
 ; CHECK-NEXT:    vldrwt.u32 q2, [r0], #16
 ; CHECK-NEXT:    vstr p0, [sp] @ 4-byte Spill

 ; CHECK-NEXT:  @ %bb.1: @ %vector.ph
 ; CHECK-NEXT:    add.w r4, r12, #3
 ; CHECK-NEXT:    vmov.i32 q1, #0x0
 ; CHECK-NEXT:    bic r4, r4, #3
 ; CHECK-NEXT:    sub.w lr, r4, #4
 ; CHECK-NEXT:    movs r4, #1
 ; CHECK-NEXT:    add.w lr, r4, lr, lsr #2
 ; CHECK-NEXT:    movs r4, #0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB3_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.32 r12
 ; CHECK-NEXT:    vmov q0, q1
 ; CHECK-NEXT:    vpstt
 ; CHECK-NEXT:    vldrwt.u32 q1, [r1], #16
 ; CHECK-NEXT:    vldrwt.u32 q2, [r0], #16
 ; CHECK-NEXT:    vstr p0, [sp] @ 4-byte Spill

llvm/test/CodeGen/Thumb2/LowOverheadLoops/constbound.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+mve %s -o - | FileCheck %s
 
 define dso_local i32 @test_500_504(i32* nocapture readonly %x) {
 ; CHECK-LABEL: test_500_504:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #126
 ; CHECK-NEXT:    adr r2, .LCPI0_0
 ; CHECK-NEXT:    vldrw.u32 q0, [r2]
 ; CHECK-NEXT:    mov.w r2, #500
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vdup.32 q1, r2
 ; CHECK-NEXT:    movs r1, #0
 ; CHECK-NEXT:    movs r2, #0
 ; CHECK-NEXT:  .LBB0_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vadd.i32 q2, q0, r1
 ; CHECK-NEXT:    vdup.32 q3, r1
 ; CHECK-NEXT:    vcmp.u32 hi, q3, q2

llvm/test/CodeGen/Thumb2/LowOverheadLoops/ctlz-non-zeros.mir

body:             |
   ; CHECK:   frame-setup CFI_INSTRUCTION offset $r4, -8
   ; CHECK:   tCMPi8 renamable $r3, 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 $r4, def $pc, implicit killed $itstate
   ; CHECK: bb.1.loop.ph:
   ; CHECK:   successors: %bb.2(0x80000000)
   ; CHECK:   liveins: $r0, $r1, $r2, $r3
   ; CHECK:   renamable $lr = t2LDRi12 $sp, 8, 14 /* CC::al */, $noreg :: (load 4 from %fixed-stack.0, align 8)
-  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK:   $r4 = tMOVr killed $lr, 14 /* CC::al */, $noreg
   ; CHECK: bb.2.loop.body:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $r0, $r1, $r2, $r3, $r4
   ; CHECK:   $lr = tMOVr $r4, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $vpr = MVE_VCTP16 renamable $r3, 0, $noreg
   ; CHECK:   MVE_VPST 4, implicit $vpr
   ; CHECK:   renamable $r1, renamable $q0 = MVE_VLDRHU16_post killed renamable $r1, 16, 1, renamable $vpr :: (load 16 from %ir.addr.b, align 2)
body:             |
   ; CHECK:   frame-setup CFI_INSTRUCTION offset $r7, -8
   ; CHECK:   tCMPi8 renamable $r3, 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 dead $r7, def $pc, implicit killed $itstate
   ; CHECK: bb.1.loop.ph:
   ; CHECK:   successors: %bb.2(0x80000000)
   ; CHECK:   liveins: $r0, $r1, $r2, $r3, $r4
   ; CHECK:   renamable $lr = t2LDRi12 $sp, 8, 14 /* CC::al */, $noreg :: (load 4 from %fixed-stack.0, align 8)
-  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK:   $r12 = tMOVr killed $lr, 14 /* CC::al */, $noreg
   ; CHECK: bb.2.loop.body:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $r0, $r1, $r2, $r3, $r4, $r12
   ; CHECK:   $lr = tMOVr $r12, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r3, 0, $noreg
   ; CHECK:   MVE_VPST 4, implicit $vpr
   ; CHECK:   renamable $r1, renamable $q0 = MVE_VLDRWU32_post killed renamable $r1, 16, 1, renamable $vpr :: (load 16 from %ir.addr.b, align 4)
body:             |
   ; CHECK:   frame-setup CFI_INSTRUCTION offset $r7, -8
   ; CHECK:   tCMPi8 renamable $r3, 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 dead $r7, def $pc, implicit killed $itstate
   ; CHECK: bb.1.loop.ph:
   ; CHECK:   successors: %bb.2(0x80000000)
   ; CHECK:   liveins: $r0, $r1, $r2, $r3, $r4
   ; CHECK:   renamable $lr = t2LDRi12 $sp, 8, 14 /* CC::al */, $noreg :: (load 4 from %fixed-stack.0, align 8)
-  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK:   $r12 = tMOVr killed $lr, 14 /* CC::al */, $noreg
   ; CHECK: bb.2.loop.body:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $r0, $r1, $r2, $r3, $r4, $r12
   ; CHECK:   $lr = tMOVr $r12, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r3, 0, $noreg
   ; CHECK:   MVE_VPST 4, implicit $vpr
   ; CHECK:   renamable $r0, renamable $q0 = MVE_VLDRWU32_post killed renamable $r0, 16, 1, renamable $vpr :: (load 16 from %ir.addr.a, align 4)

llvm/test/CodeGen/Thumb2/LowOverheadLoops/disjoint-vcmp.mir

body:             |
   ; CHECK:   renamable $r12 = t2SUBri killed renamable $r4, 4, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r4, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
   ; CHECK:   $vpr = VMSR_P0 $r5, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $r4, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r12 = t2SUBri killed renamable $r3, 16, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   VSTR_P0_off killed renamable $vpr, $sp, 0, 14 /* CC::al */, $noreg :: (store 4 into %stack.0)
   ; CHECK:   renamable $q0 = MVE_VDUP32 killed renamable $r5, 0, $noreg, undef renamable $q0
   ; CHECK:   $r3 = tMOVr $r0, 14 /* CC::al */, $noreg
-  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK: bb.2.bb9:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $lr, $q0, $r0, $r1, $r2, $r3, $r12
   ; CHECK:   renamable $vpr = VLDR_P0_off $sp, 0, 14 /* CC::al */, $noreg :: (load 4 from %stack.0)
   ; CHECK:   MVE_VPST 2, implicit $vpr
   ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r2, 1, killed renamable $vpr
   ; CHECK:   renamable $r1, renamable $q1 = MVE_VLDRWU32_post killed renamable $r1, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv24, align 4)
   ; CHECK:   renamable $r3, renamable $q2 = MVE_VLDRWU32_post killed renamable $r3, 16, 1, killed renamable $vpr :: (load 16 from %ir.lsr.iv1, align 4)

llvm/test/CodeGen/Thumb2/LowOverheadLoops/dont-remove-loop-update.mir

body:             |
   ; CHECK: bb.1.vector.ph:
   ; CHECK:   successors: %bb.2(0x80000000)
   ; CHECK:   liveins: $r0, $r1, $r2, $r3
   ; CHECK:   renamable $r12 = t2ADDri renamable $r3, 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:   renamable $r12 = t2SUBri killed renamable $r12, 4, 14 /* CC::al */, $noreg, $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: bb.2.vector.body:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3
   ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r3, 0, $noreg
   ; CHECK:   MVE_VPST 4, implicit $vpr
   ; CHECK:   renamable $r1, renamable $q0 = MVE_VLDRWU32_post killed renamable $r1, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv13, align 4)
   ; CHECK:   renamable $r2, renamable $q1 = MVE_VLDRWU32_post killed renamable $r2, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv1416, align 4)
   ; CHECK:   renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 4, 14 /* CC::al */, $noreg

llvm/test/CodeGen/Thumb2/LowOverheadLoops/fast-fp-loops.ll

 ; CHECK-NEXT:  @ %bb.1: @ %vector.ph
 ; CHECK-NEXT:    adds r3, r2, #3
 ; CHECK-NEXT:    mov.w r12, #1
 ; CHECK-NEXT:    bic r3, r3, #3
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    subs r3, #4
 ; CHECK-NEXT:    add.w lr, r12, r3, lsr #2
 ; CHECK-NEXT:    movs r3, #0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB1_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.32 r2
 ; CHECK-NEXT:    adds r3, #4
 ; CHECK-NEXT:    subs r2, #4
 ; CHECK-NEXT:    vmov q1, q0
 ; CHECK-NEXT:    vpstt
 ; CHECK-NEXT:    vldrwt.u32 q2, [r0], #16

llvm/test/CodeGen/Thumb2/LowOverheadLoops/incorrect-sub-16.mir

body:             |
   ; CHECK: bb.1.vector.ph:
   ; CHECK:   successors: %bb.2(0x80000000)
   ; CHECK:   liveins: $r0, $r1, $r2, $r3
   ; CHECK:   renamable $r12 = t2ADDri renamable $r3, 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:   renamable $r12 = t2SUBri killed renamable $r12, 4, 14 /* CC::al */, $noreg, $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: bb.2.vector.body:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3
   ; CHECK:   renamable $vpr = MVE_VCTP16 renamable $r3, 0, $noreg
   ; CHECK:   MVE_VPST 4, implicit $vpr
   ; CHECK:   renamable $r1, renamable $q0 = MVE_VLDRHU16_post killed renamable $r1, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv13, align 4)
   ; CHECK:   renamable $r2, renamable $q1 = MVE_VLDRHU16_post killed renamable $r2, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv1416, align 4)
   ; CHECK:   renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 7, 14 /* CC::al */, $noreg

llvm/test/CodeGen/Thumb2/LowOverheadLoops/incorrect-sub-32.mir

body:             |
   ; CHECK: bb.1.vector.ph:
   ; CHECK:   successors: %bb.2(0x80000000)
   ; CHECK:   liveins: $r0, $r1, $r2, $r3
   ; CHECK:   renamable $r12 = t2ADDri renamable $r3, 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:   renamable $r12 = t2SUBri killed renamable $r12, 4, 14 /* CC::al */, $noreg, $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: bb.2.vector.body:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3
   ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r3, 0, $noreg
   ; CHECK:   MVE_VPST 4, implicit $vpr
   ; CHECK:   renamable $r1, renamable $q0 = MVE_VLDRWU32_post killed renamable $r1, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv13, align 4)
   ; CHECK:   renamable $r2, renamable $q1 = MVE_VLDRWU32_post killed renamable $r2, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv1416, align 4)
   ; CHECK:   renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 5, 14 /* CC::al */, $noreg

llvm/test/CodeGen/Thumb2/LowOverheadLoops/incorrect-sub-8.mir

body:             |
   ; CHECK: bb.1.vector.ph:
   ; CHECK:   successors: %bb.2(0x80000000)
   ; CHECK:   liveins: $r0, $r1, $r2, $r3
   ; CHECK:   renamable $r12 = t2ADDri renamable $r3, 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:   renamable $r12 = t2SUBri killed renamable $r12, 4, 14 /* CC::al */, $noreg, $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: bb.2.vector.body:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3
   ; CHECK:   renamable $vpr = MVE_VCTP8 renamable $r3, 0, $noreg
   ; CHECK:   MVE_VPST 4, implicit $vpr
   ; CHECK:   renamable $r1, renamable $q0 = MVE_VLDRBU8_post killed renamable $r1, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv13, align 4)
   ; CHECK:   renamable $r2, renamable $q1 = MVE_VLDRBU8_post killed renamable $r2, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv1416, align 4)
   ; CHECK:   renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 15, 14 /* CC::al */, $noreg

llvm/test/CodeGen/Thumb2/LowOverheadLoops/inloop-vpnot-1.mir

body:             |
   ; CHECK:   liveins: $r0, $r1, $r2, $r3, $r12
   ; CHECK:   renamable $lr = t2ADDri renamable $r12, 3, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r4, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $lr = t2BICri killed renamable $lr, 3, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r5 = tLDRspi $sp, 4, 14 /* CC::al */, $noreg :: (load 4 from %fixed-stack.0, align 8)
   ; CHECK:   renamable $lr = t2SUBri killed renamable $lr, 4, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $q0 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q0
   ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $r4, killed renamable $lr, 19, 14 /* CC::al */, $noreg, $noreg
-  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK:   $r4 = tMOVr killed $lr, 14 /* CC::al */, $noreg
   ; CHECK: bb.2.vector.body:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $q0, $r0, $r1, $r2, $r3, $r4, $r5, $r12
   ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r12, 0, $noreg
   ; CHECK:   MVE_VPST 4, implicit $vpr
   ; CHECK:   renamable $r3, renamable $q1 = MVE_VLDRHS32_post killed renamable $r3, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv17.d, align 2)
   ; CHECK:   renamable $r2, renamable $q2 = MVE_VLDRHS32_post killed renamable $r2, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv1820.c, align 2)

llvm/test/CodeGen/Thumb2/LowOverheadLoops/inloop-vpnot-2.mir

body:             |
   ; CHECK:   liveins: $r0, $r1, $r2, $r3, $r12
   ; CHECK:   renamable $lr = t2ADDri renamable $r12, 3, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r4, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $lr = t2BICri killed renamable $lr, 3, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r5 = tLDRspi $sp, 4, 14 /* CC::al */, $noreg :: (load 4 from %fixed-stack.0, align 8)
   ; CHECK:   renamable $lr = t2SUBri killed renamable $lr, 4, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $q0 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q0
   ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $r4, killed renamable $lr, 19, 14 /* CC::al */, $noreg, $noreg
-  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK:   $r4 = tMOVr killed $lr, 14 /* CC::al */, $noreg
   ; CHECK: bb.2.vector.body:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $q0, $r0, $r1, $r2, $r3, $r4, $r5, $r12
   ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r12, 0, $noreg
   ; CHECK:   MVE_VPST 4, implicit $vpr
   ; CHECK:   renamable $r3, renamable $q1 = MVE_VLDRHS32_post killed renamable $r3, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv17.d, align 2)
   ; CHECK:   renamable $r2, renamable $q2 = MVE_VLDRHS32_post killed renamable $r2, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv1820.c, align 2)

llvm/test/CodeGen/Thumb2/LowOverheadLoops/inloop-vpnot-3.mir

body:             |
   ; CHECK:   liveins: $r0, $r1, $r2, $r3, $r12
   ; CHECK:   renamable $lr = t2ADDri renamable $r12, 3, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r4, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $lr = t2BICri killed renamable $lr, 3, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r5 = tLDRspi $sp, 4, 14 /* CC::al */, $noreg :: (load 4 from %fixed-stack.0, align 8)
   ; CHECK:   renamable $lr = t2SUBri killed renamable $lr, 4, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $q0 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q0
   ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $r4, killed renamable $lr, 19, 14 /* CC::al */, $noreg, $noreg
-  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK:   $r4 = tMOVr killed $lr, 14 /* CC::al */, $noreg
   ; CHECK: bb.2.vector.body:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $q0, $r0, $r1, $r2, $r3, $r4, $r5, $r12
   ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r12, 0, $noreg
   ; CHECK:   MVE_VPST 4, implicit $vpr
   ; CHECK:   renamable $r3, renamable $q1 = MVE_VLDRHS32_post killed renamable $r3, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv17.d, align 2)
   ; CHECK:   renamable $r2, renamable $q2 = MVE_VLDRHS32_post killed renamable $r2, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv1820.c, align 2)

llvm/test/CodeGen/Thumb2/LowOverheadLoops/it-block-chain-store.mir

body:             |
   ; CHECK:   t2CMPri renamable $r12, 4, 14 /* CC::al */, $noreg, implicit-def $cpsr
   ; CHECK:   t2IT 11, 8, implicit-def $itstate
   ; CHECK:   $lr = t2LSLri renamable $r2, 1, 11 /* CC::lt */, killed $cpsr, $noreg, implicit killed renamable $lr, implicit killed $itstate
   ; CHECK:   renamable $r2 = t2RSBrs killed renamable $lr, killed renamable $r2, 10, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $lr = t2ADDri killed renamable $r2, 3, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r2, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $r2, killed renamable $lr, 19, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   t2STRi12 renamable $lr, killed renamable $r3, 0, 14 /* CC::al */, $noreg :: (store 4 into %ir.iter.addr)
-  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK:   $r2 = tMOVr killed $lr, 14 /* CC::al */, $noreg
   ; CHECK: bb.1.do.body:
   ; CHECK:   successors: %bb.1(0x7c000000), %bb.2(0x04000000)
   ; CHECK:   liveins: $r0, $r1, $r2, $r12
   ; CHECK:   $lr = tMOVr $r2, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r12, 0, $noreg
   ; CHECK:   renamable $r2, dead $cpsr = nsw tSUBi8 killed $r2, 1, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $r12 = nsw t2SUBri killed renamable $r12, 4, 14 /* CC::al */, $noreg, $noreg
body:             |
   ; CHECK:   t2CMPri renamable $r12, 4, 14 /* CC::al */, $noreg, implicit-def $cpsr
   ; CHECK:   t2IT 11, 8, implicit-def $itstate
   ; CHECK:   $lr = t2LSLri renamable $r2, 1, 11 /* CC::lt */, killed $cpsr, $noreg, implicit killed renamable $lr, implicit killed $itstate
   ; CHECK:   renamable $r2 = t2RSBrs killed renamable $lr, killed renamable $r2, 10, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $lr = t2ADDri killed renamable $r2, 3, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r2, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $r2, killed renamable $lr, 19, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   t2STRi12 renamable $lr, killed renamable $r3, 0, 14 /* CC::al */, $noreg :: (store 4 into %ir.iter.addr)
-  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK:   $r2 = tMOVr killed $lr, 14 /* CC::al */, $noreg
   ; CHECK: bb.1.do.body:
   ; CHECK:   successors: %bb.1(0x7c000000), %bb.2(0x04000000)
   ; CHECK:   liveins: $r0, $r1, $r2, $r12
   ; CHECK:   $lr = tMOVr $r2, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r12, 0, $noreg
   ; CHECK:   renamable $r2, dead $cpsr = nsw tSUBi8 killed $r2, 1, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $r12 = nsw t2SUBri killed renamable $r12, 4, 14 /* CC::al */, $noreg, $noreg

llvm/test/CodeGen/Thumb2/LowOverheadLoops/loop-guards.ll

 ; CHECK-GLOBAL-NOT: LoopEnd
 
 ; CHECK: ne_and_guard
 ; CHECK: body:
 ; CHECK: bb.0.entry:
 ; CHECK:   t2CMPri renamable $lr, 0
 ; CHECK:   tBcc %bb.4
 ; CHECK: bb.2.while.body.preheader:
-; CHECK:   $lr = t2DLS killed renamable $lr
+; CHECK-NOT:   $lr = t2DLS killed renamable $lr
 ; CHECK: bb.3.while.body:
 ; CHECK:   $lr = t2LEUpdate killed renamable $lr, %bb.3
 define void @ne_and_guard(i1 zeroext %t1, i1 zeroext %t2, i32* nocapture %a, i32* nocapture readonly %b, i32 %N) {
 entry:
   %brmerge.demorgan = and i1 %t1, %t2
   %cmp6 = icmp ne i32 %N, 0
   %or.cond = and i1 %brmerge.demorgan, %cmp6
   br i1 %or.cond, label %while.body, label %if.end

 
 ; TODO: This could generate WLS
 ; CHECK: ne_preheader
 ; CHECK: body:
 ; CHECK: bb.0.entry:
 ; CHECK:   t2CMPri renamable $lr, 0
 ; CHECK:   tBcc %bb.4
 ; CHECK: bb.2.while.body.preheader:
-; CHECK:   $lr = t2DLS killed renamable $lr
+; CHECK-NOT:   $lr = t2DLS killed renamable $lr
 ; CHECK: bb.3.while.body:
 ; CHECK:   $lr = t2LEUpdate killed renamable $lr, %bb.3
 define void @ne_preheader(i1 zeroext %t1, i1 zeroext %t2, i32* nocapture %a, i32* nocapture readonly %b, i32 %N) {
 entry:
   %brmerge.demorgan = and i1 %t1, %t2
   br i1 %brmerge.demorgan, label %while.preheader, label %if.end
 
 while.preheader:                                  ; preds = %entry

 
 ; TODO: This could generate WLS
 ; CHECK: eq_preheader
 ; CHECK: body:
 ; CHECK: bb.0.entry:
 ; CHECK:   t2CMPri renamable $lr, 0
 ; CHECK:   tBcc %bb.4
 ; CHECK: bb.2.while.body.preheader:
-; CHECK:   $lr = t2DLS killed renamable $lr
+; CHECK-NOT:   $lr = t2DLS killed renamable $lr
 ; CHECK: bb.3.while.body:
 ; CHECK:   $lr = t2LEUpdate killed renamable $lr, %bb.3
 define void @eq_preheader(i1 zeroext %t1, i1 zeroext %t2, i32* nocapture %a, i32* nocapture readonly %b, i32 %N) {
 entry:
   %brmerge.demorgan = and i1 %t1, %t2
   br i1 %brmerge.demorgan, label %while.preheader, label %if.end
 
 while.preheader:                                  ; preds = %entry

 
 ; TODO: This could generate WLS
 ; CHECK: ne_prepreheader
 ; CHECK: body:
 ; CHECK: bb.0.entry:
 ; CHECK:   t2CMPri renamable $lr, 0
 ; CHECK:   tBcc %bb.4
 ; CHECK: bb.2.while.body.preheader:
-; CHECK:   $lr = t2DLS killed renamable $lr
+; CHECK-NOT:   $lr = t2DLS killed renamable $lr
 ; CHECK: bb.3.while.body:
 ; CHECK:   $lr = t2LEUpdate killed renamable $lr, %bb.3
 define void @ne_prepreheader(i1 zeroext %t1, i1 zeroext %t2, i32* nocapture %a, i32* nocapture readonly %b, i32 %N) {
 entry:
   %cmp = icmp ne i32 %N, 0
   br i1 %cmp, label %while.preheader, label %if.end
 
 while.preheader:                                  ; preds = %entry

llvm/test/CodeGen/Thumb2/LowOverheadLoops/lstp-insertion-position.mir

body:             |
   ; CHECK:   dead $r7 = frame-setup tMOVr $sp, 14 /* CC::al */, $noreg
   ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_register $r7
   ; CHECK:   renamable $r3, dead $cpsr = tADDi3 renamable $r2, 3, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $r3 = t2BICri killed renamable $r3, 3, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r12 = t2SUBri killed renamable $r3, 4, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r3 = tLDRpci %const.0, 14 /* CC::al */, $noreg :: (load 4 from constant-pool)
-  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK:   renamable $q1 = MVE_VDUP32 killed renamable $r3, 0, $noreg, undef renamable $q1
   ; CHECK:   $s4 = VMOVS killed $s0, 14 /* CC::al */, $noreg, implicit killed $q1, implicit-def $q1
   ; CHECK: bb.2.vector.body:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $lr, $q1, $r0, $r1, $r2
   ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg
   ; CHECK:   renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14 /* CC::al */, $noreg
   ; CHECK:   MVE_VPST 2, implicit $vpr
body:             |
   ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_register $r7
   ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 3, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $r3 = nuw nsw t2ADDrs killed renamable $r3, renamable $r2, 19, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r3 = t2BICri killed renamable $r3, 3, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r12 = t2SUBri killed renamable $r3, 4, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $lr = t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r3 = tLDRpci %const.0, 14 /* CC::al */, $noreg :: (load 4 from constant-pool)
-  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK:   renamable $q1 = MVE_VDUP32 killed renamable $r3, 0, $noreg, undef renamable $q1
   ; CHECK:   renamable $r2, dead $cpsr = tLSRri killed renamable $r2, 2, 14 /* CC::al */, $noreg
   ; CHECK:   $s4 = VMOVS killed $s0, 14 /* CC::al */, $noreg, implicit killed $q1, implicit-def $q1
   ; CHECK: bb.2.vector.body:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $lr, $q1, $r0, $r1, $r2
   ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg
   ; CHECK:   renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14 /* CC::al */, $noreg

llvm/test/CodeGen/Thumb2/LowOverheadLoops/matrix.mir

body:             |
   ; 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:   $lr = t2DLS killed renamable $lr
   ; 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 4 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

llvm/test/CodeGen/Thumb2/LowOverheadLoops/minloop.ll

 ; CHECK-NEXT:    movs r6, #0
 ; CHECK-NEXT:    b .LBB0_10
 ; CHECK-NEXT:  .LBB0_4: @ %while.body.preheader.new
 ; CHECK-NEXT:    bic r7, r9, #3
 ; CHECK-NEXT:    movs r6, #1
 ; CHECK-NEXT:    subs r7, #4
 ; CHECK-NEXT:    add.w lr, r6, r7, lsr #2
 ; CHECK-NEXT:    movs r6, #0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    movs r7, #4
 ; CHECK-NEXT:  .LBB0_5: @ %while.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldr r10, [r0, #16]!
 ; CHECK-NEXT:    sub.w r9, r9, #4
 ; CHECK-NEXT:    ldrd r5, r4, [r0, #-12]
 ; CHECK-NEXT:    ldr r11, [r0, #-4]
 ; CHECK-NEXT:    cmp r12, r5

llvm/test/CodeGen/Thumb2/LowOverheadLoops/move-def-before-start.mir

body:             |
   ; CHECK:   liveins: $r0, $r1, $r2, $r3
   ; CHECK:   renamable $r12 = t2MOVi 3, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $lr = t2MOVi 1, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r12 = nuw t2ADDrs killed renamable $r12, renamable $r3, 11, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r12 = t2BICri killed renamable $r12, 3, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r12 = t2SUBri killed renamable $r12, 4, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $lr, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   $r12 = t2MOVr killed $r3, 14 /* CC::al */, $noreg, $noreg
-  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $r12 = t2LSRri killed renamable $r12, 1, 14 /* CC::al */, $noreg, $noreg
   ; CHECK: bb.2.vector.body:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3, $r12
   ; CHECK:   renamable $r4, dead $cpsr = tADDrr renamable $r1, renamable $r3, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r12, 0, $noreg
   ; CHECK:   MVE_VPST 8, implicit $vpr

llvm/test/CodeGen/Thumb2/LowOverheadLoops/move-start-after-def.mir

body:             |
   ; CHECK:   successors: %bb.2(0x80000000)
   ; CHECK:   liveins: $r0, $r1, $r2, $r3
   ; CHECK:   renamable $r12 = t2MOVi 3, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $lr = t2MOVi 1, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r12 = nuw t2ADDrs killed renamable $r12, renamable $r3, 11, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r12 = t2BICri killed renamable $r12, 3, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r12 = t2SUBri killed renamable $r12, 4, 14 /* CC::al */, $noreg, $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:   $r12 = t2MOVr killed $r3, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $r12 = t2LSRri killed renamable $r12, 1, 14 /* CC::al */, $noreg, $noreg
   ; CHECK: bb.2.vector.body:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3, $r12
   ; CHECK:   renamable $r4, dead $cpsr = tADDrr renamable $r1, renamable $r3, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r12, 0, $noreg

llvm/test/CodeGen/Thumb2/LowOverheadLoops/multi-block-cond-iter-count.mir

body:             |
   ; CHECK:   successors: %bb.8(0x80000000)
   ; CHECK:   liveins: $r0, $r1, $r3, $r12
   ; CHECK:   renamable $r2 = t2BICri killed renamable $r3, 2, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r2, 19, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r2, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
-  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK: bb.8 (%ir-block.65):
   ; CHECK:   successors: %bb.8(0x7c000000), %bb.9(0x04000000)
   ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3, $r12
   ; CHECK:   renamable $r4 = tLDRr renamable $r1, $r2, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $r3, dead $cpsr = nuw tADDi8 killed renamable $r3, 4, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $r5 = tLDRr renamable $r0, $r2, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $r4, dead $cpsr = nsw tMUL killed renamable $r5, killed renamable $r4, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $r5, dead $cpsr = tADDrr renamable $r0, renamable $r2, 14 /* CC::al */, $noreg

llvm/test/CodeGen/Thumb2/LowOverheadLoops/mve-float-loops.ll

 ; CHECK-NEXT:  .LBB0_11: @ %vector.ph
 ; CHECK-NEXT:    bic r12, r3, #3
 ; CHECK-NEXT:    movs r6, #1
 ; CHECK-NEXT:    sub.w r7, r12, #4
 ; CHECK-NEXT:    mov r4, r0
 ; CHECK-NEXT:    mov r5, r1
 ; CHECK-NEXT:    add.w lr, r6, r7, lsr #2
 ; CHECK-NEXT:    mov r6, r2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB0_12: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r5], #16
 ; CHECK-NEXT:    vldrw.u32 q1, [r4], #16
 ; CHECK-NEXT:    vmul.f32 q0, q1, q0
 ; CHECK-NEXT:    vstrb.8 q0, [r6], #16
 ; CHECK-NEXT:    le lr, .LBB0_12
 ; CHECK-NEXT:  @ %bb.13: @ %middle.block

 ; CHECK-NEXT:  .LBB1_11: @ %vector.ph
 ; CHECK-NEXT:    bic r12, r3, #3
 ; CHECK-NEXT:    movs r6, #1
 ; CHECK-NEXT:    sub.w r7, r12, #4
 ; CHECK-NEXT:    mov r4, r0
 ; CHECK-NEXT:    mov r5, r1
 ; CHECK-NEXT:    add.w lr, r6, r7, lsr #2
 ; CHECK-NEXT:    mov r6, r2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB1_12: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r5], #16
 ; CHECK-NEXT:    vldrw.u32 q1, [r4], #16
 ; CHECK-NEXT:    vadd.f32 q0, q1, q0
 ; CHECK-NEXT:    vstrb.8 q0, [r6], #16
 ; CHECK-NEXT:    le lr, .LBB1_12
 ; CHECK-NEXT:  @ %bb.13: @ %middle.block

 ; CHECK-NEXT:  .LBB2_11: @ %vector.ph
 ; CHECK-NEXT:    bic r12, r3, #3
 ; CHECK-NEXT:    movs r6, #1
 ; CHECK-NEXT:    sub.w r7, r12, #4
 ; CHECK-NEXT:    mov r4, r0
 ; CHECK-NEXT:    mov r5, r1
 ; CHECK-NEXT:    add.w lr, r6, r7, lsr #2
 ; CHECK-NEXT:    mov r6, r2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB2_12: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r5], #16
 ; CHECK-NEXT:    vldrw.u32 q1, [r4], #16
 ; CHECK-NEXT:    vsub.f32 q0, q1, q0
 ; CHECK-NEXT:    vstrb.8 q0, [r6], #16
 ; CHECK-NEXT:    le lr, .LBB2_12
 ; CHECK-NEXT:  @ %bb.13: @ %middle.block

 ; CHECK-NEXT:  @ %bb.3: @ %vector.ph
 ; CHECK-NEXT:    bic r12, r3, #3
 ; CHECK-NEXT:    movs r6, #1
 ; CHECK-NEXT:    sub.w r7, r12, #4
 ; CHECK-NEXT:    mov r4, r0
 ; CHECK-NEXT:    mov r5, r1
 ; CHECK-NEXT:    add.w lr, r6, r7, lsr #2
 ; CHECK-NEXT:    mov r6, r2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB3_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r5], #16
 ; CHECK-NEXT:    vldrw.u32 q1, [r4], #16
 ; CHECK-NEXT:    vcvt.f32.s32 q0, q0
 ; CHECK-NEXT:    vmul.f32 q0, q1, q0
 ; CHECK-NEXT:    vstrb.8 q0, [r6], #16
 ; CHECK-NEXT:    le lr, .LBB3_4

 ; CHECK-NEXT:    b .LBB4_6
 ; CHECK-NEXT:  .LBB4_3: @ %vector.ph
 ; CHECK-NEXT:    bic r12, r3, #3
 ; CHECK-NEXT:    movs r5, #1
 ; CHECK-NEXT:    sub.w r6, r12, #4
 ; CHECK-NEXT:    mov r4, r0
 ; CHECK-NEXT:    add.w lr, r5, r6, lsr #2
 ; CHECK-NEXT:    mov r5, r1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    mov r6, r2
 ; CHECK-NEXT:  .LBB4_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r4], #16
 ; CHECK-NEXT:    vldrw.u32 q1, [r5], #16
 ; CHECK-NEXT:    vmul.i32 q0, q1, q0
 ; CHECK-NEXT:    vcvt.f32.s32 q0, q0
 ; CHECK-NEXT:    vstrb.8 q0, [r6], #16
 ; CHECK-NEXT:    le lr, .LBB4_4
 ; CHECK-NEXT:  @ %bb.5: @ %middle.block
 ; CHECK-NEXT:    cmp r12, r3
 ; CHECK-NEXT:    it eq
 ; CHECK-NEXT:    popeq {r4, r5, r6, pc}
 ; CHECK-NEXT:  .LBB4_6: @ %for.body.preheader11
 ; CHECK-NEXT:    sub.w lr, r3, r12
 ; CHECK-NEXT:    add.w r0, r0, r12, lsl #2
 ; CHECK-NEXT:    add.w r1, r1, r12, lsl #2
 ; CHECK-NEXT:    add.w r2, r2, r12, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB4_7: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldr r3, [r0], #4
 ; CHECK-NEXT:    ldr r6, [r1], #4
 ; CHECK-NEXT:    muls r3, r6, r3
 ; CHECK-NEXT:    vmov s0, r3
 ; CHECK-NEXT:    vcvt.f32.s32 s0, s0
 ; CHECK-NEXT:    vstmia r2!, {s0}

 ; CHECK-NEXT:    b .LBB5_6
 ; CHECK-NEXT:  .LBB5_3: @ %vector.ph
 ; CHECK-NEXT:    bic r12, r3, #3
 ; CHECK-NEXT:    movs r5, #1
 ; CHECK-NEXT:    sub.w r6, r12, #4
 ; CHECK-NEXT:    mov r4, r0
 ; CHECK-NEXT:    add.w lr, r5, r6, lsr #2
 ; CHECK-NEXT:    mov r5, r1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    mov r6, r2
 ; CHECK-NEXT:  .LBB5_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldr.w r9, [r4]
 ; CHECK-NEXT:    ldr r7, [r5]
 ; CHECK-NEXT:    ldr.w r8, [r4, #4]
 ; CHECK-NEXT:    vmov.32 q0[0], r9
 ; CHECK-NEXT:    ldr.w r10, [r5, #4]

 ; CHECK-NEXT:  @ %bb.5: @ %middle.block
 ; CHECK-NEXT:    cmp r12, r3
 ; CHECK-NEXT:    beq .LBB5_8
 ; CHECK-NEXT:  .LBB5_6: @ %for.body.preheader11
 ; CHECK-NEXT:    sub.w lr, r3, r12
 ; CHECK-NEXT:    add.w r0, r0, r12, lsl #1
 ; CHECK-NEXT:    add.w r1, r1, r12, lsl #1
 ; CHECK-NEXT:    add.w r2, r2, r12, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB5_7: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldr.16 s0, [r1]
 ; CHECK-NEXT:    vldr.16 s2, [r0]
 ; CHECK-NEXT:    adds r0, #2
 ; CHECK-NEXT:    adds r1, #2
 ; CHECK-NEXT:    vmul.f16 s0, s2, s0
 ; CHECK-NEXT:    vcvtb.f32.f16 s0, s0

 ; CHECK-NEXT:    b .LBB6_6
 ; CHECK-NEXT:  .LBB6_3: @ %vector.ph
 ; CHECK-NEXT:    bic r12, r3, #3
 ; CHECK-NEXT:    movs r5, #1
 ; CHECK-NEXT:    sub.w r6, r12, #4
 ; CHECK-NEXT:    mov r4, r0
 ; CHECK-NEXT:    add.w lr, r5, r6, lsr #2
 ; CHECK-NEXT:    mov r5, r1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    mov r6, r2
 ; CHECK-NEXT:  .LBB6_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldr.w r9, [r4]
 ; CHECK-NEXT:    ldr r7, [r5]
 ; CHECK-NEXT:    ldr.w r8, [r4, #4]
 ; CHECK-NEXT:    vmov.32 q0[0], r9
 ; CHECK-NEXT:    ldr.w r10, [r5, #4]

 ; CHECK-NEXT:  @ %bb.5: @ %middle.block
 ; CHECK-NEXT:    cmp r12, r3
 ; CHECK-NEXT:    beq .LBB6_8
 ; CHECK-NEXT:  .LBB6_6: @ %for.body.preheader11
 ; CHECK-NEXT:    sub.w lr, r3, r12
 ; CHECK-NEXT:    add.w r0, r0, r12, lsl #1
 ; CHECK-NEXT:    add.w r1, r1, r12, lsl #1
 ; CHECK-NEXT:    add.w r2, r2, r12, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB6_7: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldr.16 s0, [r1]
 ; CHECK-NEXT:    vldr.16 s2, [r0]
 ; CHECK-NEXT:    adds r0, #2
 ; CHECK-NEXT:    adds r1, #2
 ; CHECK-NEXT:    vadd.f16 s0, s2, s0
 ; CHECK-NEXT:    vcvtb.f32.f16 s0, s0

 ; CHECK-NEXT:    b .LBB7_6
 ; CHECK-NEXT:  .LBB7_3: @ %vector.ph
 ; CHECK-NEXT:    bic r12, r3, #3
 ; CHECK-NEXT:    movs r5, #1
 ; CHECK-NEXT:    sub.w r6, r12, #4
 ; CHECK-NEXT:    mov r4, r0
 ; CHECK-NEXT:    add.w lr, r5, r6, lsr #2
 ; CHECK-NEXT:    mov r5, r1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    mov r6, r2
 ; CHECK-NEXT:  .LBB7_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldr.w r9, [r4]
 ; CHECK-NEXT:    ldr r7, [r5]
 ; CHECK-NEXT:    ldr.w r8, [r4, #4]
 ; CHECK-NEXT:    vmov.32 q0[0], r9
 ; CHECK-NEXT:    ldr.w r10, [r5, #4]

 ; CHECK-NEXT:  @ %bb.5: @ %middle.block
 ; CHECK-NEXT:    cmp r12, r3
 ; CHECK-NEXT:    beq .LBB7_8
 ; CHECK-NEXT:  .LBB7_6: @ %for.body.preheader11
 ; CHECK-NEXT:    sub.w lr, r3, r12
 ; CHECK-NEXT:    add.w r0, r0, r12, lsl #1
 ; CHECK-NEXT:    add.w r1, r1, r12, lsl #1
 ; CHECK-NEXT:    add.w r2, r2, r12, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB7_7: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldr.16 s0, [r1]
 ; CHECK-NEXT:    vldr.16 s2, [r0]
 ; CHECK-NEXT:    adds r0, #2
 ; CHECK-NEXT:    adds r1, #2
 ; CHECK-NEXT:    vsub.f16 s0, s2, s0
 ; CHECK-NEXT:    vcvtb.f32.f16 s0, s0

 ; CHECK-NEXT:    b .LBB8_6
 ; CHECK-NEXT:  .LBB8_3: @ %vector.ph
 ; CHECK-NEXT:    bic r12, r3, #3
 ; CHECK-NEXT:    movs r5, #1
 ; CHECK-NEXT:    sub.w r6, r12, #4
 ; CHECK-NEXT:    mov r4, r0
 ; CHECK-NEXT:    add.w lr, r5, r6, lsr #2
 ; CHECK-NEXT:    mov r5, r1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    mov r6, r2
 ; CHECK-NEXT:  .LBB8_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.u32 q0, [r5], #8
 ; CHECK-NEXT:    ldr.w r9, [r4]
 ; CHECK-NEXT:    ldr.w r8, [r4, #4]
 ; CHECK-NEXT:    adds r4, #8
 ; CHECK-NEXT:    vmov r7, s0

 ; CHECK-NEXT:  @ %bb.5: @ %middle.block
 ; CHECK-NEXT:    cmp r12, r3
 ; CHECK-NEXT:    beq .LBB8_8
 ; CHECK-NEXT:  .LBB8_6: @ %for.body.preheader13
 ; CHECK-NEXT:    sub.w lr, r3, r12
 ; CHECK-NEXT:    add.w r0, r0, r12, lsl #1
 ; CHECK-NEXT:    add.w r1, r1, r12, lsl #1
 ; CHECK-NEXT:    add.w r2, r2, r12, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB8_7: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldrsh r3, [r1], #2
 ; CHECK-NEXT:    vldr.16 s0, [r0]
 ; CHECK-NEXT:    adds r0, #2
 ; CHECK-NEXT:    vmov s2, r3
 ; CHECK-NEXT:    vcvt.f16.s32 s2, s2
 ; CHECK-NEXT:    vmul.f16 s0, s0, s2

llvm/test/CodeGen/Thumb2/LowOverheadLoops/mve-tail-data-types.ll

 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    adds r3, r2, #3
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    bic r3, r3, #3
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
 ; CHECK-NEXT:    movs r3, #0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB0_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.32 r2
 ; CHECK-NEXT:    adds r3, #4
 ; CHECK-NEXT:    subs r2, #4
 ; CHECK-NEXT:    vmov q1, q0
 ; CHECK-NEXT:    vpst
 ; CHECK-NEXT:    vldrbt.u32 q2, [r1], #4

 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    adds r3, r2, #3
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    bic r3, r3, #3
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
 ; CHECK-NEXT:    movs r3, #0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB1_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.32 r2
 ; CHECK-NEXT:    adds r3, #4
 ; CHECK-NEXT:    subs r2, #4
 ; CHECK-NEXT:    vmov q1, q0
 ; CHECK-NEXT:    vpst
 ; CHECK-NEXT:    vldrht.s32 q2, [r1], #8

 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    adds r3, r2, #3
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    bic r3, r3, #3
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
 ; CHECK-NEXT:    movs r3, #0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB2_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.32 r2
 ; CHECK-NEXT:    adds r3, #4
 ; CHECK-NEXT:    subs r2, #4
 ; CHECK-NEXT:    vmov q1, q0
 ; CHECK-NEXT:    vpst
 ; CHECK-NEXT:    vldrbt.u32 q2, [r1], #4

 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    adds r3, r2, #3
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    bic r3, r3, #3
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
 ; CHECK-NEXT:    movs r3, #0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB3_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.32 r2
 ; CHECK-NEXT:    adds r3, #4
 ; CHECK-NEXT:    subs r2, #4
 ; CHECK-NEXT:    vmov q1, q0
 ; CHECK-NEXT:    vpst
 ; CHECK-NEXT:    vldrht.u32 q2, [r1], #8

 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    adds r3, r2, #3
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    bic r3, r3, #3
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
 ; CHECK-NEXT:    movs r3, #0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB4_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.32 r2
 ; CHECK-NEXT:    adds r3, #4
 ; CHECK-NEXT:    subs r2, #4
 ; CHECK-NEXT:    vmov q1, q0
 ; CHECK-NEXT:    vpst
 ; CHECK-NEXT:    vldrwt.u32 q2, [r1], #16

llvm/test/CodeGen/Thumb2/LowOverheadLoops/non-masked-load.mir

body:             |
   ; CHECK:   renamable $r3 = t2ADDri renamable $r2, 15, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $q0 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q0
   ; CHECK:   renamable $r3 = t2BICri killed renamable $r3, 15, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r12 = t2SUBri killed renamable $r3, 16, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $r3, renamable $r12, 35, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r3 = t2LSRri killed renamable $r12, 4, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r3 = t2SUBrs renamable $r2, killed renamable $r3, 34, 14 /* CC::al */, $noreg, $noreg
-  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK: bb.2.vector.body:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $lr, $q0, $r0, $r1, $r2, $r3
   ; CHECK:   renamable $vpr = MVE_VCTP8 renamable $r2, 0, $noreg
   ; CHECK:   $q1 = MVE_VORR killed $q0, killed $q0, 0, $noreg, undef $q1
   ; CHECK:   MVE_VPST 2, implicit $vpr
   ; CHECK:   renamable $r1, renamable $q0 = MVE_VLDRBU8_post killed renamable $r1, 16, 1, killed renamable $vpr :: (load 16 from %ir.lsr.iv2022, align 1)
   ; CHECK:   renamable $r0, renamable $q2 = MVE_VLDRBU8_post killed renamable $r0, 16, 1, $noreg :: (load 16 from %ir.lsr.iv19, align 1)

llvm/test/CodeGen/Thumb2/LowOverheadLoops/non-masked-store.mir

body:             |
   ; CHECK: bb.1.vector.ph:
   ; CHECK:   successors: %bb.2(0x80000000)
   ; CHECK:   liveins: $r0, $r1, $r2, $r3
   ; CHECK:   renamable $r12 = t2ADDri renamable $r3, 15, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $lr = t2MOVi 1, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r12 = t2BICri killed renamable $r12, 15, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r12 = t2SUBri killed renamable $r12, 16, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $lr, killed renamable $r12, 35, 14 /* CC::al */, $noreg, $noreg
-  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK: bb.2.vector.body:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3
   ; CHECK:   renamable $vpr = MVE_VCTP8 renamable $r3, 0, $noreg
   ; CHECK:   renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 16, 14 /* CC::al */, $noreg
   ; CHECK:   MVE_VPST 4, implicit $vpr
   ; CHECK:   renamable $r1, renamable $q0 = MVE_VLDRBU8_post killed renamable $r1, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv15, align 1)
   ; CHECK:   renamable $r2, renamable $q1 = MVE_VLDRBU8_post killed renamable $r2, 16, 1, killed renamable $vpr :: (load 16 from %ir.lsr.iv1618, align 1)

llvm/test/CodeGen/Thumb2/LowOverheadLoops/reductions.ll

 ; CHECK-NEXT:  .LBB1_1: @ %vector.ph
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    adds r3, r2, #7
 ; CHECK-NEXT:    vmov.i32 q1, #0x0
 ; CHECK-NEXT:    bic r3, r3, #7
 ; CHECK-NEXT:    sub.w r12, r3, #8
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #3
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB1_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.16 r2
 ; CHECK-NEXT:    vmov q0, q1
 ; CHECK-NEXT:    vpst
 ; CHECK-NEXT:    vldrbt.u16 q1, [r0], #8
 ; CHECK-NEXT:    subs r2, #8
 ; CHECK-NEXT:    vadd.i16 q1, q0, q1

 ; CHECK-NEXT:  .LBB2_1: @ %vector.ph
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    add.w r3, r2, #15
 ; CHECK-NEXT:    vmov.i32 q1, #0x0
 ; CHECK-NEXT:    bic r3, r3, #15
 ; CHECK-NEXT:    sub.w r12, r3, #16
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #4
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB2_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.8 r2
 ; CHECK-NEXT:    vmov q0, q1
 ; CHECK-NEXT:    vpstt
 ; CHECK-NEXT:    vldrbt.u8 q1, [r1], #16
 ; CHECK-NEXT:    vldrbt.u8 q2, [r0], #16
 ; CHECK-NEXT:    subs r2, #16

 ; CHECK-NEXT:  .LBB3_1: @ %vector.ph
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    adds r3, r2, #7
 ; CHECK-NEXT:    vmov.i32 q1, #0x0
 ; CHECK-NEXT:    bic r3, r3, #7
 ; CHECK-NEXT:    sub.w r12, r3, #8
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #3
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB3_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.16 r2
 ; CHECK-NEXT:    vmov q0, q1
 ; CHECK-NEXT:    vpstt
 ; CHECK-NEXT:    vldrbt.u16 q1, [r0], #8
 ; CHECK-NEXT:    vldrbt.u16 q2, [r1], #8
 ; CHECK-NEXT:    subs r2, #8

 ; CHECK-NEXT:  .LBB4_1: @ %vector.ph
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    add.w r3, r2, #15
 ; CHECK-NEXT:    vmov.i32 q1, #0x0
 ; CHECK-NEXT:    bic r3, r3, #15
 ; CHECK-NEXT:    sub.w r12, r3, #16
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #4
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB4_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.8 r2
 ; CHECK-NEXT:    vmov q0, q1
 ; CHECK-NEXT:    vpstt
 ; CHECK-NEXT:    vldrbt.u8 q1, [r0], #16
 ; CHECK-NEXT:    vldrbt.u8 q2, [r1], #16
 ; CHECK-NEXT:    subs r2, #16

 ; CHECK-NEXT:  .LBB5_1: @ %vector.ph
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    adds r3, r2, #7
 ; CHECK-NEXT:    vmov.i32 q1, #0x0
 ; CHECK-NEXT:    bic r3, r3, #7
 ; CHECK-NEXT:    sub.w r12, r3, #8
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #3
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB5_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.16 r2
 ; CHECK-NEXT:    vmov q0, q1
 ; CHECK-NEXT:    vpstt
 ; CHECK-NEXT:    vldrbt.u16 q1, [r0], #8
 ; CHECK-NEXT:    vldrbt.u16 q2, [r1], #8
 ; CHECK-NEXT:    subs r2, #8

 ; CHECK-NEXT:    vmov.i32 q1, #0x0
 ; CHECK-NEXT:    bic r3, r3, #3
 ; CHECK-NEXT:    mov r4, r0
 ; CHECK-NEXT:    subs r6, r3, #4
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    mov r5, r1
 ; CHECK-NEXT:    add.w lr, r3, r6, lsr #2
 ; CHECK-NEXT:    mov r3, r2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB6_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.32 r3
 ; CHECK-NEXT:    vmov q0, q1
 ; CHECK-NEXT:    vpstt
 ; CHECK-NEXT:    vldrbt.u32 q1, [r4], #4
 ; CHECK-NEXT:    vldrbt.u32 q2, [r5], #4
 ; CHECK-NEXT:    subs r3, #4
 ; CHECK-NEXT:    vmul.i32 q1, q2, q1
 ; CHECK-NEXT:    vadd.i32 q1, q1, q0
 ; CHECK-NEXT:    le lr, .LBB6_2
 ; CHECK-NEXT:  @ %bb.3: @ %middle.block
 ; CHECK-NEXT:    vpsel q0, q1, q0
 ; CHECK-NEXT:    vaddv.u32 r12, q0
 ; CHECK-NEXT:    cbz r2, .LBB6_7
 ; CHECK-NEXT:  @ %bb.4: @ %vector.ph47
 ; CHECK-NEXT:    movs r3, #0
 ; CHECK-NEXT:    vdup.32 q0, r3
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r6, lsr #2
 ; CHECK-NEXT:    vmov.32 q0[0], r12
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB6_5: @ %vector.body46
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.32 r2
 ; CHECK-NEXT:    vmov q1, q0
 ; CHECK-NEXT:    vpstt
 ; CHECK-NEXT:    vldrbt.u32 q0, [r0], #4
 ; CHECK-NEXT:    vldrbt.u32 q2, [r1], #4
 ; CHECK-NEXT:    subs r2, #4

 ; CHECK-NEXT:    vmov.i32 q1, #0x0
 ; CHECK-NEXT:    bic r3, r3, #7
 ; CHECK-NEXT:    movs r4, #1
 ; CHECK-NEXT:    subs r3, #8
 ; CHECK-NEXT:    vmov q3, q1
 ; CHECK-NEXT:    add.w lr, r4, r3, lsr #3
 ; CHECK-NEXT:    mov r3, r0
 ; CHECK-NEXT:    mov r4, r1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB7_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.16 r2
 ; CHECK-NEXT:    vmov q0, q1
 ; CHECK-NEXT:    vpstt
 ; CHECK-NEXT:    vldrbt.u16 q1, [r3], #8
 ; CHECK-NEXT:    vldrbt.u16 q4, [r4], #8
 ; CHECK-NEXT:    vmov q2, q3

 ; CHECK-NEXT:    mla r1, r1, r4, r3
 ; CHECK-NEXT:    movs r3, #0
 ; CHECK-NEXT:    vdup.32 q0, r3
 ; CHECK-NEXT:    vmov.32 q0[0], r0
 ; CHECK-NEXT:    adds r0, r2, #3
 ; CHECK-NEXT:    bic r0, r0, #3
 ; CHECK-NEXT:    subs r0, #4
 ; CHECK-NEXT:    add.w lr, r12, r0, lsr #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB8_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.32 r2
 ; CHECK-NEXT:    vmov q1, q0
 ; CHECK-NEXT:    vpst
 ; CHECK-NEXT:    vldrwt.u32 q0, [r1], #16
 ; CHECK-NEXT:    subs r2, #4
 ; CHECK-NEXT:    vadd.i32 q0, q0, q1

llvm/test/CodeGen/Thumb2/LowOverheadLoops/remat-vctp.ll

 ; CHECK-NEXT:    vmvn.i32 q0, #0x80000000
 ; CHECK-NEXT:    csel r5, r12, r4, lt
 ; CHECK-NEXT:    vmov.i32 q1, #0x3f
 ; CHECK-NEXT:    sub.w r5, r12, r5
 ; CHECK-NEXT:    vmov.i32 q2, #0x1
 ; CHECK-NEXT:    add.w lr, r5, #3
 ; CHECK-NEXT:    movs r5, #1
 ; CHECK-NEXT:    add.w lr, r5, lr, lsr #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB1_1: @ %bb6
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.32 r12
 ; CHECK-NEXT:    sub.w r12, r12, #4
 ; CHECK-NEXT:    vpst
 ; CHECK-NEXT:    vctpt.32 r4
 ; CHECK-NEXT:    vstr p0, [sp, #4] @ 4-byte Spill
 ; CHECK-NEXT:    vpst

llvm/test/CodeGen/Thumb2/LowOverheadLoops/remove-elem-moves.mir

body:             |
   ; CHECK:   $lr = tMOVr killed $r2, 14 /* CC::al */, $noreg
   ; CHECK:   $r12 = tMOVr killed $r0, 14 /* CC::al */, $noreg
   ; CHECK:   $r3 = tMOVr killed $r1, 14 /* CC::al */, $noreg
   ; CHECK: bb.7.while.body.preheader19:
   ; CHECK:   successors: %bb.8(0x80000000)
   ; CHECK:   liveins: $lr, $r3, $r12
   ; CHECK:   renamable $r0, dead $cpsr = tSUBi3 killed renamable $r3, 4, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $r1 = t2SUBri killed renamable $r12, 4, 14 /* CC::al */, $noreg, $noreg
-  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK: bb.8.while.body:
   ; CHECK:   successors: %bb.8(0x7c000000), %bb.9(0x04000000)
   ; CHECK:   liveins: $lr, $r0, $r1
   ; CHECK:   renamable $s0 = VLDRS renamable $r1, 1, 14 /* CC::al */, $noreg :: (load 4 from %ir.scevgep3)
   ; CHECK:   renamable $r1, dead $cpsr = tADDi8 killed renamable $r1, 4, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $s0 = nnan ninf nsz arcp contract afn reassoc VABSS killed renamable $s0, 14 /* CC::al */, $noreg
   ; CHECK:   VSTRS killed renamable $s0, renamable $r0, 1, 14 /* CC::al */, $noreg :: (store 4 into %ir.scevgep7)
   ; CHECK:   renamable $r0, dead $cpsr = tADDi8 killed renamable $r0, 4, 14 /* CC::al */, $noreg

llvm/test/CodeGen/Thumb2/LowOverheadLoops/skip-debug.mir

body:             |
   ; CHECK:   renamable $r3 = t2BICri killed renamable $r3, 3, 14 /* CC::al */, $noreg, $noreg, debug-location !28
   ; CHECK:   renamable $r4, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 4, 14 /* CC::al */, $noreg, debug-location !28
   ; CHECK:   renamable $q0 = MVE_VDUP32 killed renamable $r4, 0, $noreg, undef renamable $q0, debug-location !28
   ; CHECK:   renamable $q0 = MVE_VMOV_to_lane_32 killed renamable $q0, killed renamable $r12, 0, 14 /* CC::al */, $noreg, debug-location !28
   ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $lr, renamable $r3, 19, 14 /* CC::al */, $noreg, $noreg, debug-location !28
   ; CHECK:   renamable $r3, dead $cpsr = tLSRri killed renamable $r3, 2, 14 /* CC::al */, $noreg, debug-location !28
   ; CHECK:   renamable $r3 = t2SUBrs renamable $r2, killed renamable $r3, 18, 14 /* CC::al */, $noreg, $noreg, debug-location !28
-  ; CHECK:   $lr = t2DLS killed renamable $lr, debug-location !28
   ; CHECK: bb.2.vector.body:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $lr, $q0, $r0, $r1, $r2, $r3
   ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg, debug-location !30
   ; CHECK:   DBG_VALUE $vpr, $noreg, !17, !DIExpression(), debug-location !30
   ; CHECK:   $q1 = MVE_VORR killed $q0, killed $q0, 0, $noreg, undef $q1
   ; CHECK:   MVE_VPST 8, implicit $vpr, debug-location !30
   ; CHECK:   renamable $r1, renamable $q0 = MVE_VLDRHU32_post killed renamable $r1, 8, 1, killed renamable $vpr, debug-location !30 :: (load 8 from %ir.lsr.iv14, align 2)

llvm/test/CodeGen/Thumb2/LowOverheadLoops/unpredload.ll

 ; CHECK-NEXT:    cmp r2, #4
 ; CHECK-NEXT:    it ge
 ; CHECK-NEXT:    movge r3, #4
 ; CHECK-NEXT:    subs r3, r2, r3
 ; CHECK-NEXT:    add.w r12, r3, #3
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
 ; CHECK-NEXT:    mov.w r12, #0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB1_1: @ %do.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.32 r2
 ; CHECK-NEXT:    vpst
 ; CHECK-NEXT:    vldrwt.u32 q0, [r0], #16
 ; CHECK-NEXT:    vldrw.u32 q1, [r1], #16
 ; CHECK-NEXT:    subs r2, #4
 ; CHECK-NEXT:    vmlava.s32 r12, q0, q1

llvm/test/CodeGen/Thumb2/LowOverheadLoops/unrolled-and-vector.mir

body:             |
   ; CHECK:   tB %bb.11, 14 /* CC::al */, $noreg
   ; CHECK: bb.6.for.body.preheader.new:
   ; CHECK:   successors: %bb.7(0x80000000)
   ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3, $r12
   ; CHECK:   renamable $r3 = t2BICri killed renamable $r3, 3, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 4, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $lr, killed renamable $r3, 19, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
-  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK: bb.7.for.body:
   ; CHECK:   successors: %bb.7(0x7c000000), %bb.8(0x04000000)
   ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3, $r12
   ; CHECK:   renamable $r4 = tLDRBr renamable $r1, $r3, 14 /* CC::al */, $noreg :: (load 1 from %ir.scevgep2453)
   ; CHECK:   renamable $r9 = t2ADDrr renamable $r1, renamable $r3, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r5 = tLDRBr renamable $r2, $r3, 14 /* CC::al */, $noreg :: (load 1 from %ir.scevgep2854)
   ; CHECK:   renamable $r6, dead $cpsr = tADDrr renamable $r2, renamable $r3, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $r4 = tADDhirr killed renamable $r4, killed renamable $r5, 14 /* CC::al */, $noreg

llvm/test/CodeGen/Thumb2/LowOverheadLoops/vaddv.mir

body:             |
   ; CHECK: bb.1.while.body.preheader:
   ; CHECK:   successors: %bb.2(0x80000000)
   ; CHECK:   liveins: $r0, $r1, $r2, $r3
   ; CHECK:   renamable $r2, dead $cpsr = tSUBrr renamable $r3, killed renamable $r2, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $r12 = t2ADDri killed renamable $r2, 7, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r2, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $r2, killed renamable $r12, 27, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r2, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
-  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK: bb.2.while.body:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3
   ; CHECK:   renamable $vpr = MVE_VCTP16 renamable $r3, 0, $noreg
   ; CHECK:   MVE_VPST 4, implicit $vpr
   ; CHECK:   renamable $r1, renamable $q0 = MVE_VLDRHU16_post killed renamable $r1, 16, 1, renamable $vpr :: (load 16 from %ir.tmp3, align 2)
   ; CHECK:   renamable $r0, renamable $q1 = MVE_VLDRHU16_post killed renamable $r0, 16, 1, killed renamable $vpr :: (load 16 from %ir.tmp1, align 2)
   ; CHECK:   renamable $q2 = MVE_VMULLBs16 renamable $q1, renamable $q0, 0, $noreg, undef renamable $q2

llvm/test/CodeGen/Thumb2/LowOverheadLoops/vctp-in-vpt.mir

body:             |
   ; 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: bb.2.bb9:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3
   ; CHECK:   renamable $vpr = VLDR_P0_off $sp, 0, 14 /* CC::al */, $noreg :: (load 4 from %stack.0)
   ; CHECK:   MVE_VPST 2, 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, renamable $vpr
   ; CHECK:   renamable $r3, renamable $q1 = MVE_VLDRWU32_post killed renamable $r3, 16, 1, renamable $vpr
body:             |
   ; 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: bb.2.bb9:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3
   ; CHECK:   renamable $vpr = VLDR_P0_off $sp, 0, 14 /* CC::al */, $noreg :: (load 4 from %stack.0)
   ; CHECK:   MVE_VPST 2, 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, renamable $vpr
   ; CHECK:   renamable $r3, renamable $q1 = MVE_VLDRWU32_post killed renamable $r3, 16, 1, killed renamable $vpr
body:             |
   ; 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: bb.2.bb9:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3
   ; CHECK:   renamable $vpr = VLDR_P0_off $sp, 0, 14 /* CC::al */, $noreg :: (load 4 from %stack.0)
   ; CHECK:   MVE_VPST 2, 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, renamable $vpr
   ; CHECK:   dead renamable $r3, renamable $q1 = MVE_VLDRWU32_post killed renamable $r3, 16, 1, renamable $vpr

llvm/test/CodeGen/Thumb2/LowOverheadLoops/vctp16-reduce.mir

body:             |
   ; CHECK:   renamable $r3 = t2BICri killed renamable $r3, 7, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r12 = t2SUBri killed renamable $r3, 8, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $r3, renamable $r12, 27, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r3 = tLEApcrel %const.0, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $r12 = t2LSRri killed renamable $r12, 3, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $q0 = MVE_VLDRWU32 killed renamable $r3, 0, 0, $noreg :: (load 16 from constant-pool)
   ; CHECK:   renamable $r3 = t2SUBrs renamable $r2, killed renamable $r12, 26, 14 /* CC::al */, $noreg, $noreg
-  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK: bb.2.vector.body:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $lr, $q0, $r0, $r1, $r2, $r3
   ; CHECK:   renamable $vpr = MVE_VCTP16 renamable $r2, 0, $noreg
   ; CHECK:   $q1 = MVE_VORR killed $q0, killed $q0, 0, $noreg, undef $q1
   ; CHECK:   MVE_VPST 4, implicit $vpr
   ; CHECK:   renamable $r0, renamable $q0 = MVE_VLDRBU16_post killed renamable $r0, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv19, align 1)
   ; CHECK:   renamable $r1, renamable $q2 = MVE_VLDRBU16_post killed renamable $r1, 8, 1, killed renamable $vpr :: (load 8 from %ir.lsr.iv2022, align 1)

llvm/test/CodeGen/Thumb2/LowOverheadLoops/vector-arith-codegen.ll

 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    adds r3, r2, #3
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    bic r3, r3, #3
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
 ; CHECK-NEXT:    movs r3, #0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB0_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.32 r2
 ; CHECK-NEXT:    vmov q1, q0
 ; CHECK-NEXT:    vpstt
 ; CHECK-NEXT:    vldrwt.u32 q0, [r0], #16
 ; CHECK-NEXT:    vldrwt.u32 q2, [r1], #16
 ; CHECK-NEXT:    adds r3, #4

 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    adds r1, r2, #3
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    bic r1, r1, #3
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    subs r1, #4
 ; CHECK-NEXT:    add.w lr, r3, r1, lsr #2
 ; CHECK-NEXT:    movs r1, #0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB1_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.32 r2
 ; CHECK-NEXT:    vmov q1, q0
 ; CHECK-NEXT:    vpst
 ; CHECK-NEXT:    vldrwt.u32 q0, [r0], #16
 ; CHECK-NEXT:    adds r1, #4
 ; CHECK-NEXT:    subs r2, #4

 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    adds r1, r2, #3
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    bic r1, r1, #3
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    subs r1, #4
 ; CHECK-NEXT:    add.w lr, r3, r1, lsr #2
 ; CHECK-NEXT:    movs r1, #0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB2_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.32 r2
 ; CHECK-NEXT:    vmov q1, q0
 ; CHECK-NEXT:    vpst
 ; CHECK-NEXT:    vldrwt.u32 q0, [r0], #16
 ; CHECK-NEXT:    adds r1, #4
 ; CHECK-NEXT:    subs r2, #4

llvm/test/CodeGen/Thumb2/LowOverheadLoops/vpt-blocks.mir

body:             |
   ; CHECK:   liveins: $r0, $r1, $r2
   ; CHECK:   renamable $r3, dead $cpsr = tADDi3 renamable $r1, 3, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $q0 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q0
   ; CHECK:   renamable $r3 = t2BICri killed renamable $r3, 3, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r12 = t2SUBri killed renamable $r3, 4, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r3, dead $cpsr = nsw tRSB renamable $r2, 14 /* CC::al */, $noreg
-  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK: bb.2.vector.body:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $lr, $q0, $r0, $r1, $r2, $r3
   ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r1, 0, $noreg
   ; CHECK:   MVE_VPST 8, implicit $vpr
   ; CHECK:   renamable $r1 = MVE_VSTRWU32_post renamable $q0, killed renamable $r1, 16, 1, renamable $vpr
   ; CHECK:   renamable $q1 = MVE_VLDRWU32 renamable $r0, 0, 1, killed renamable $vpr
   ; CHECK:   MVE_VPTv4s32r 2, renamable $q1, renamable $r2, 11, implicit-def $vpr
body:             |
   ; CHECK:   liveins: $r0, $r1, $r2
   ; CHECK:   renamable $r3, dead $cpsr = tADDi3 renamable $r1, 3, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $q0 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q0
   ; CHECK:   renamable $r3 = t2BICri killed renamable $r3, 3, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r12 = t2SUBri killed renamable $r3, 4, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r3, dead $cpsr = nsw tRSB renamable $r2, 14 /* CC::al */, $noreg
-  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK: bb.2.vector.body:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $lr, $q0, $r0, $r1, $r2, $r3
   ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r1, 0, $noreg
   ; CHECK:   MVE_VPST 8, implicit $vpr
   ; CHECK:   renamable $q1 = MVE_VLDRWU32 renamable $r0, 0, 1, killed renamable $vpr
   ; CHECK:   MVE_VPTv4s32r 2, renamable $q1, renamable $r2, 11, implicit-def $vpr
   ; CHECK:   renamable $vpr = MVE_VCMPs32r killed renamable $q1, renamable $r3, 12, 1, killed renamable $vpr
body:             |
   ; CHECK:   liveins: $r0, $r1, $r2
   ; CHECK:   renamable $r3, dead $cpsr = tADDi3 renamable $r1, 3, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $q0 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q0
   ; CHECK:   renamable $r3 = t2BICri killed renamable $r3, 3, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r12 = t2SUBri killed renamable $r3, 4, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   dead renamable $r3, dead $cpsr = nsw tRSB renamable $r2, 14 /* CC::al */, $noreg
-  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK: bb.2.vector.body:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $lr, $q0, $r0, $r1, $r2
   ; CHECK:   MVE_VPTv4s32r 2, killed renamable $q0, renamable $r2, 2, implicit-def $vpr
   ; CHECK:   renamable $q0 = MVE_VLDRWU32 renamable $r0, 0, 1, $vpr
   ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r1, 1, killed $vpr
   ; CHECK:   MVE_VSTRWU32 renamable $q0, renamable $r0, 0, 1, killed $vpr
   ; CHECK:   renamable $r1, dead $cpsr = tSUBi8 killed renamable $r1, 4, 14 /* CC::al */, $noreg
body:             |
   ; CHECK:   renamable $r3, dead $cpsr = nuw tADDi3 renamable $r2, 3, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $r3 = t2BICri killed renamable $r3, 3, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $q1 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q1
   ; CHECK:   renamable $q0 = MVE_VLDRWU32 killed renamable $r12, 0, 0, $noreg :: (load 16 from constant-pool, align 8)
   ; CHECK:   renamable $r12 = t2SUBri killed renamable $r3, 4, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $q2 = MVE_VMOVimmi32 4, 0, $noreg, undef renamable $q2
-  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK: bb.2 (align 4):
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $lr, $q0, $q1, $q2, $r0, $r1, $r2
   ; CHECK:   MVE_VPTv4s32r 8, renamable $q0, renamable $r1, 11, implicit-def $vpr
   ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r2, 1, killed $vpr
   ; CHECK:   MVE_VPST 8, implicit $vpr
   ; CHECK:   renamable $r0 = MVE_VSTRWU32_post renamable $q1, killed renamable $r0, 16, 1, killed renamable $vpr :: (store 16, align 4)
   ; CHECK:   renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14 /* CC::al */, $noreg

llvm/test/CodeGen/Thumb2/LowOverheadLoops/wrong-liveout-lsr-shift.mir

body:             |
   ; CHECK:   renamable $r3 = t2BICri killed renamable $r3, 7, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r12 = t2SUBri killed renamable $r3, 8, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $r3, renamable $r12, 27, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $r3 = tLEApcrel %const.0, 14 /* CC::al */, $noreg
   ; CHECK:   renamable $r12 = t2LSRri killed renamable $r12, 2, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   renamable $q0 = MVE_VLDRWU32 killed renamable $r3, 0, 0, $noreg :: (load 16 from constant-pool)
   ; CHECK:   renamable $r3 = t2SUBrs renamable $r2, killed renamable $r12, 26, 14 /* CC::al */, $noreg, $noreg
-  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK: bb.2.vector.body:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
   ; CHECK:   liveins: $lr, $q0, $r0, $r1, $r2, $r3
   ; CHECK:   renamable $vpr = MVE_VCTP16 renamable $r2, 0, $noreg
   ; CHECK:   $q1 = MVE_VORR killed $q0, killed $q0, 0, $noreg, undef $q1
   ; CHECK:   MVE_VPST 4, implicit $vpr
   ; CHECK:   renamable $r0, renamable $q0 = MVE_VLDRBU16_post killed renamable $r0, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv19, align 1)
   ; CHECK:   renamable $r1, renamable $q2 = MVE_VLDRBU16_post killed renamable $r1, 8, 1, killed renamable $vpr :: (load 8 from %ir.lsr.iv2022, align 1)

llvm/test/CodeGen/Thumb2/active_lane_mask.ll

 ; CHECK-NEXT:    bic r0, r0, #1
 ; CHECK-NEXT:    adr r2, .LCPI4_0
 ; CHECK-NEXT:    subs r0, #2
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    vmov.i64 q0, #0xffffffff
 ; CHECK-NEXT:    vldrw.u32 q2, [r2]
 ; CHECK-NEXT:    add.w lr, r3, r0, lsr #1
 ; CHECK-NEXT:    mov.w r8, #0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vand q1, q1, q0
 ; CHECK-NEXT:  .LBB4_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmov q3[2], q3[0], r8, r8
 ; CHECK-NEXT:    vmov r7, s6
 ; CHECK-NEXT:    vand q3, q3, q0
 ; CHECK-NEXT:    vmov r6, s7
 ; CHECK-NEXT:    vmov r3, s14

llvm/test/CodeGen/Thumb2/aligned-nonfallthrough.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=thumbv8.1-m.main-none-eabi -mcpu=cortex-m55 -O3 < %s | FileCheck %s
 
 define i32 @loop(i32* nocapture readonly %x) {
 ; CHECK-LABEL: loop:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #500
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    movs r1, #0
 ; CHECK-NEXT:    .p2align 2
 ; CHECK-NEXT:  .LBB0_1: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldr r2, [r0], #4
 ; CHECK-NEXT:    add r1, r2
 ; CHECK-NEXT:    le lr, .LBB0_1
 ; CHECK-NEXT:    .p2align 2

llvm/test/CodeGen/Thumb2/mve-float16regloops.ll

 
 define dso_local void @test_nested(half* noalias nocapture %pInT1, half* noalias nocapture readonly %pOutT1, half* noalias nocapture readonly %pPRT_in, half* noalias nocapture readnone %pPRT_pDst, i32 %numRows, i32 %numCols, i32 %l) local_unnamed_addr #0 {
 ; CHECK-LABEL: test_nested:
 ; CHECK:       @ %bb.0: @ %for.body.us.preheader
 ; CHECK-NEXT:    .save {r4, r5, r6, lr}
 ; CHECK-NEXT:    push {r4, r5, r6, lr}
 ; CHECK-NEXT:    ldrd lr, r12, [sp, #16]
 ; CHECK-NEXT:    lsl.w r3, r12, #1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB14_1: @ %for.body.us
 ; CHECK-NEXT:    @ =>This Loop Header: Depth=1
 ; CHECK-NEXT:    @ Child Loop BB14_2 Depth 2
 ; CHECK-NEXT:    ldrh r4, [r1]
 ; CHECK-NEXT:    mov r5, r2
 ; CHECK-NEXT:    mov r6, r12
 ; CHECK-NEXT:    vdup.16 q0, r4
 ; CHECK-NEXT:    mov r4, r0

llvm/test/CodeGen/Thumb2/mve-float32regloops.ll

 
 define dso_local void @test_nested(float* noalias nocapture %pInT1, float* noalias nocapture readonly %pOutT1, float* noalias nocapture readonly %pPRT_in, float* noalias nocapture readnone %pPRT_pDst, i32 %numRows, i32 %numCols, i32 %l) local_unnamed_addr #0 {
 ; CHECK-LABEL: test_nested:
 ; CHECK:       @ %bb.0: @ %for.body.us.preheader
 ; CHECK-NEXT:    .save {r4, r5, r6, lr}
 ; CHECK-NEXT:    push {r4, r5, r6, lr}
 ; CHECK-NEXT:    ldrd lr, r12, [sp, #16]
 ; CHECK-NEXT:    lsl.w r3, r12, #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB14_1: @ %for.body.us
 ; CHECK-NEXT:    @ =>This Loop Header: Depth=1
 ; CHECK-NEXT:    @ Child Loop BB14_2 Depth 2
 ; CHECK-NEXT:    ldr r4, [r1]
 ; CHECK-NEXT:    mov r5, r2
 ; CHECK-NEXT:    mov r6, r12
 ; CHECK-NEXT:    vdup.32 q0, r4
 ; CHECK-NEXT:    mov r4, r0

llvm/test/CodeGen/Thumb2/mve-fp16convertloops.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+mve.fp -verify-machineinstrs %s -o - | FileCheck %s
 
 define void @to_4(float* nocapture readonly %x, half* noalias nocapture %y) {
 ; CHECK-LABEL: to_4:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #256
 ; CHECK-NEXT:    adr r2, .LCPI0_0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q0, [r2]
 ; CHECK-NEXT:  .LBB0_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q1, [r0], #16
 ; CHECK-NEXT:    vmul.f32 q1, q1, q0
 ; CHECK-NEXT:    vcvtb.f16.f32 q1, q1
 ; CHECK-NEXT:    vstrh.32 q1, [r1], #8
 ; CHECK-NEXT:    le lr, .LBB0_1

 
 define void @to_8(float* nocapture readonly %x, half* noalias nocapture %y) {
 ; CHECK-LABEL: to_8:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #128
 ; CHECK-NEXT:    adr r2, .LCPI1_0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q0, [r2]
 ; CHECK-NEXT:  .LBB1_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q1, [r0, #16]
 ; CHECK-NEXT:    vmul.f32 q1, q1, q0
 ; CHECK-NEXT:    vcvtb.f16.f32 q1, q1
 ; CHECK-NEXT:    vstrh.32 q1, [r1, #8]
 ; CHECK-NEXT:    vldrw.u32 q1, [r0], #32

 
 define void @to_16(float* nocapture readonly %x, half* noalias nocapture %y) {
 ; CHECK-LABEL: to_16:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #64
 ; CHECK-NEXT:    adr r2, .LCPI2_0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q0, [r2]
 ; CHECK-NEXT:  .LBB2_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q1, [r0, #48]
 ; CHECK-NEXT:    vmul.f32 q1, q1, q0
 ; CHECK-NEXT:    vcvtb.f16.f32 q1, q1
 ; CHECK-NEXT:    vstrh.32 q1, [r1, #24]
 ; CHECK-NEXT:    vldrw.u32 q1, [r0, #32]

 
 define void @from_4(half* nocapture readonly %x, float* noalias nocapture %y) {
 ; CHECK-LABEL: from_4:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #256
 ; CHECK-NEXT:    adr r2, .LCPI3_0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q0, [r2]
 ; CHECK-NEXT:  .LBB3_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.u32 q1, [r0], #8
 ; CHECK-NEXT:    vcvtb.f32.f16 q1, q1
 ; CHECK-NEXT:    vmul.f32 q1, q1, q0
 ; CHECK-NEXT:    vstrb.8 q1, [r1], #16
 ; CHECK-NEXT:    le lr, .LBB3_1

 
 define void @from_8(half* nocapture readonly %x, float* noalias nocapture %y) {
 ; CHECK-LABEL: from_8:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #128
 ; CHECK-NEXT:    adr r2, .LCPI4_0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q0, [r2]
 ; CHECK-NEXT:  .LBB4_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.u32 q1, [r0, #8]
 ; CHECK-NEXT:    vcvtb.f32.f16 q1, q1
 ; CHECK-NEXT:    vmul.f32 q1, q1, q0
 ; CHECK-NEXT:    vstrw.32 q1, [r1, #16]
 ; CHECK-NEXT:    vldrh.u32 q1, [r0], #16

 
 define void @from_16(half* nocapture readonly %x, float* noalias nocapture %y) {
 ; CHECK-LABEL: from_16:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #64
 ; CHECK-NEXT:    adr r2, .LCPI5_0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q0, [r2]
 ; CHECK-NEXT:  .LBB5_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.u32 q1, [r0, #24]
 ; CHECK-NEXT:    vcvtb.f32.f16 q1, q1
 ; CHECK-NEXT:    vmul.f32 q1, q1, q0
 ; CHECK-NEXT:    vstrw.32 q1, [r1, #48]
 ; CHECK-NEXT:    vldrh.u32 q1, [r0, #16]

 
 define void @both_4(half* nocapture readonly %x, half* noalias nocapture %y) {
 ; CHECK-LABEL: both_4:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #256
 ; CHECK-NEXT:    adr r2, .LCPI6_0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q0, [r2]
 ; CHECK-NEXT:  .LBB6_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.u32 q1, [r0], #8
 ; CHECK-NEXT:    vcvtb.f32.f16 q1, q1
 ; CHECK-NEXT:    vmul.f32 q1, q1, q0
 ; CHECK-NEXT:    vcvtb.f16.f32 q1, q1
 ; CHECK-NEXT:    vstrh.32 q1, [r1], #8

 
 define void @both_8(half* nocapture readonly %x, half* noalias nocapture %y) {
 ; CHECK-LABEL: both_8:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #128
 ; CHECK-NEXT:    adr r2, .LCPI7_0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q0, [r2]
 ; CHECK-NEXT:  .LBB7_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.u32 q1, [r0, #8]
 ; CHECK-NEXT:    vcvtb.f32.f16 q1, q1
 ; CHECK-NEXT:    vmul.f32 q1, q1, q0
 ; CHECK-NEXT:    vcvtb.f16.f32 q1, q1
 ; CHECK-NEXT:    vstrh.32 q1, [r1, #8]

 
 define void @both_16(half* nocapture readonly %x, half* noalias nocapture %y) {
 ; CHECK-LABEL: both_16:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #64
 ; CHECK-NEXT:    adr r2, .LCPI8_0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q0, [r2]
 ; CHECK-NEXT:  .LBB8_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.u32 q1, [r0, #24]
 ; CHECK-NEXT:    vcvtb.f32.f16 q1, q1
 ; CHECK-NEXT:    vmul.f32 q1, q1, q0
 ; CHECK-NEXT:    vcvtb.f16.f32 q1, q1
 ; CHECK-NEXT:    vstrh.32 q1, [r1, #24]

 
 define void @both_8_I(half* nocapture readonly %x, half* noalias nocapture %y) {
 ; CHECK-LABEL: both_8_I:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #128
 ; CHECK-NEXT:    adr r2, .LCPI9_0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q0, [r2]
 ; CHECK-NEXT:  .LBB9_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.u16 q1, [r0], #16
 ; CHECK-NEXT:    vcvtb.f32.f16 q2, q1
 ; CHECK-NEXT:    vcvtt.f32.f16 q1, q1
 ; CHECK-NEXT:    vmul.f32 q2, q2, q0
 ; CHECK-NEXT:    vmul.f32 q1, q1, q0

 
 define void @both_16_I(half* nocapture readonly %x, half* noalias nocapture %y) {
 ; CHECK-LABEL: both_16_I:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #128
 ; CHECK-NEXT:    adr r2, .LCPI10_0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q0, [r2]
 ; CHECK-NEXT:  .LBB10_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.u16 q1, [r0]
 ; CHECK-NEXT:    vcvtb.f32.f16 q2, q1
 ; CHECK-NEXT:    vcvtt.f32.f16 q1, q1
 ; CHECK-NEXT:    vmul.f32 q2, q2, q0
 ; CHECK-NEXT:    vmul.f32 q1, q1, q0

llvm/test/CodeGen/Thumb2/mve-gather-ptrs.ll

 ; CHECK-NEXT:    bic r2, r2, #15
 ; CHECK-NEXT:    cmp r2, #1
 ; CHECK-NEXT:    it lt
 ; CHECK-NEXT:    poplt {r7, pc}
 ; CHECK-NEXT:  .LBB22_1: @ %vector.body.preheader
 ; CHECK-NEXT:    subs r2, #4
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r2, lsr #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB22_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r1], #16
 ; CHECK-NEXT:    vptt.i32 ne, q0, zr
 ; CHECK-NEXT:    vldrwt.u32 q1, [q0]
 ; CHECK-NEXT:    vstrwt.32 q1, [r0], #16
 ; CHECK-NEXT:    le lr, .LBB22_2
 ; CHECK-NEXT:  @ %bb.3: @ %for.end

 ; CHECK-NEXT:    bic r2, r2, #15
 ; CHECK-NEXT:    cmp r2, #1
 ; CHECK-NEXT:    it lt
 ; CHECK-NEXT:    poplt {r7, pc}
 ; CHECK-NEXT:  .LBB23_1: @ %vector.body.preheader
 ; CHECK-NEXT:    subs r2, #4
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r2, lsr #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB23_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r1], #16
 ; CHECK-NEXT:    vptt.i32 ne, q0, zr
 ; CHECK-NEXT:    vldrwt.u32 q1, [q0]
 ; CHECK-NEXT:    vstrwt.32 q1, [r0], #16
 ; CHECK-NEXT:    le lr, .LBB23_2
 ; CHECK-NEXT:  @ %bb.3: @ %for.end

llvm/test/CodeGen/Thumb2/mve-gather-scatter-optimisation.ll

 ; CHECK-NEXT:    beq .LBB10_7
 ; CHECK-NEXT:  .LBB10_13: @ %for.body8.us.us.preheader
 ; CHECK-NEXT:    @ in Loop: Header=BB10_8 Depth=2
 ; CHECK-NEXT:    ldr r0, [sp, #112]
 ; CHECK-NEXT:    add.w r5, r8, r7
 ; CHECK-NEXT:    sub.w lr, r9, r7
 ; CHECK-NEXT:    mla r3, r0, r7, r1
 ; CHECK-NEXT:    ldr r0, [sp, #20] @ 4-byte Reload
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    add.w r5, r0, r5, lsl #1
 ; CHECK-NEXT:    add.w r3, r6, r3, lsl #1
 ; CHECK-NEXT:  .LBB10_14: @ %for.body8.us.us
 ; CHECK-NEXT:    @ Parent Loop BB10_5 Depth=1
 ; CHECK-NEXT:    @ Parent Loop BB10_8 Depth=2
 ; CHECK-NEXT:    @ => This Inner Loop Header: Depth=3
 ; CHECK-NEXT:    ldrsh.w r0, [r3]
 ; CHECK-NEXT:    add r3, r4

llvm/test/CodeGen/Thumb2/mve-gather-scatter-ptr-address.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 
 ; RUN: llc -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+mve.fp %s -o 2>/dev/null - | FileCheck %s
 
 define void @ptr_iv_v4i32(i32* noalias nocapture readonly %A, i32* noalias nocapture %B, i32 %y) {
 ; CHECK-LABEL: ptr_iv_v4i32:
 ; CHECK:       @ %bb.0: @ %vector.ph
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #249
 ; CHECK-NEXT:    adr r3, .LCPI0_0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q0, [r3]
 ; CHECK-NEXT:  .LBB0_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q1, [r0, q0, uxtw #2]
 ; CHECK-NEXT:    adds r0, #64
 ; CHECK-NEXT:    vadd.i32 q1, q1, r2
 ; CHECK-NEXT:    vstrw.32 q1, [r1, q0, uxtw #2]
 ; CHECK-NEXT:    adds r1, #64

 define void @ptr_iv_v4i32_mult(i32* noalias nocapture readonly %A, i32* noalias nocapture %B, i32 %y) {
 ; CHECK-LABEL: ptr_iv_v4i32_mult:
 ; CHECK:       @ %bb.0: @ %vector.ph
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #249
 ; CHECK-NEXT:    adr r1, .LCPI1_0
 ; CHECK-NEXT:    adr r3, .LCPI1_1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q0, [r3]
 ; CHECK-NEXT:    vldrw.u32 q1, [r1]
 ; CHECK-NEXT:  .LBB1_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q2, [r0, q0, uxtw #2]
 ; CHECK-NEXT:    vadd.i32 q2, q2, r2
 ; CHECK-NEXT:    vstrw.32 q2, [r0, q1, uxtw #2]
 ; CHECK-NEXT:    adds r0, #64

 
 define void @ptr_iv_v8i16(i16* noalias nocapture readonly %A, i16* noalias nocapture %B, i16 %y) {
 ; CHECK-LABEL: ptr_iv_v8i16:
 ; CHECK:       @ %bb.0: @ %vector.ph
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #249
 ; CHECK-NEXT:    adr r3, .LCPI2_0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q0, [r3]
 ; CHECK-NEXT:  .LBB2_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.u16 q1, [r0, q0, uxtw #1]
 ; CHECK-NEXT:    adds r0, #64
 ; CHECK-NEXT:    vadd.i16 q1, q1, r2
 ; CHECK-NEXT:    vstrh.16 q1, [r1, q0, uxtw #1]
 ; CHECK-NEXT:    adds r1, #64

 define void @ptr_iv_v8i16_mult(i16* noalias nocapture readonly %A, i16* noalias nocapture %B, i16 %y) {
 ; CHECK-LABEL: ptr_iv_v8i16_mult:
 ; CHECK:       @ %bb.0: @ %vector.ph
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #249
 ; CHECK-NEXT:    adr.w r12, .LCPI3_0
 ; CHECK-NEXT:    adr r3, .LCPI3_1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q0, [r3]
 ; CHECK-NEXT:    vldrw.u32 q1, [r12]
 ; CHECK-NEXT:  .LBB3_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.u16 q2, [r0, q0, uxtw #1]
 ; CHECK-NEXT:    adds r0, #64
 ; CHECK-NEXT:    vadd.i16 q2, q2, r2
 ; CHECK-NEXT:    vstrh.16 q2, [r1, q1, uxtw #1]

 
 define void @ptr_iv_v16i8(i8* noalias nocapture readonly %A, i8* noalias nocapture %B, i8 %y) {
 ; CHECK-LABEL: ptr_iv_v16i8:
 ; CHECK:       @ %bb.0: @ %vector.ph
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #249
 ; CHECK-NEXT:    adr r3, .LCPI4_0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q0, [r3]
 ; CHECK-NEXT:  .LBB4_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrb.u8 q1, [r0, q0]
 ; CHECK-NEXT:    adds r0, #64
 ; CHECK-NEXT:    vadd.i8 q1, q1, r2
 ; CHECK-NEXT:    vstrb.8 q1, [r1, q0]
 ; CHECK-NEXT:    adds r1, #64

 define void @ptr_iv_v16i8_mult(i8* noalias nocapture readonly %A, i8* noalias nocapture %B, i8 %y) {
 ; CHECK-LABEL: ptr_iv_v16i8_mult:
 ; CHECK:       @ %bb.0: @ %vector.ph
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #249
 ; CHECK-NEXT:    adr.w r12, .LCPI5_0
 ; CHECK-NEXT:    adr r3, .LCPI5_1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q0, [r3]
 ; CHECK-NEXT:    vldrw.u32 q1, [r12]
 ; CHECK-NEXT:  .LBB5_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrb.u8 q2, [r0, q0]
 ; CHECK-NEXT:    adds r0, #64
 ; CHECK-NEXT:    vadd.i8 q2, q2, r2
 ; CHECK-NEXT:    vstrb.8 q2, [r1, q1]

 
 define void @ptr_iv_v4f32(float* noalias nocapture readonly %A, float* noalias nocapture %B, float %y) {
 ; CHECK-LABEL: ptr_iv_v4f32:
 ; CHECK:       @ %bb.0: @ %vector.ph
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #249
 ; CHECK-NEXT:    adr r3, .LCPI6_0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q0, [r3]
 ; CHECK-NEXT:  .LBB6_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q1, [r0, q0, uxtw #2]
 ; CHECK-NEXT:    adds r0, #64
 ; CHECK-NEXT:    vadd.f32 q1, q1, r2
 ; CHECK-NEXT:    vstrw.32 q1, [r1, q0, uxtw #2]
 ; CHECK-NEXT:    adds r1, #64

 define void @ptr_iv_v4f32_mult(float* noalias nocapture readonly %A, float* noalias nocapture %B, float %y) {
 ; CHECK-LABEL: ptr_iv_v4f32_mult:
 ; CHECK:       @ %bb.0: @ %vector.ph
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #249
 ; CHECK-NEXT:    adr r1, .LCPI7_0
 ; CHECK-NEXT:    adr r3, .LCPI7_1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q0, [r3]
 ; CHECK-NEXT:    vldrw.u32 q1, [r1]
 ; CHECK-NEXT:  .LBB7_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q2, [r0, q0, uxtw #2]
 ; CHECK-NEXT:    vadd.f32 q2, q2, r2
 ; CHECK-NEXT:    vstrw.32 q2, [r0, q1, uxtw #2]
 ; CHECK-NEXT:    adds r0, #64

 ; CHECK:       @ %bb.0: @ %vector.ph
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    vmov s0, r2
 ; CHECK-NEXT:    mov.w lr, #249
 ; CHECK-NEXT:    vcvtb.f16.f32 s0, s0
 ; CHECK-NEXT:    adr r3, .LCPI8_0
 ; CHECK-NEXT:    vmov.f16 r2, s0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q0, [r3]
 ; CHECK-NEXT:  .LBB8_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.u16 q1, [r0, q0, uxtw #1]
 ; CHECK-NEXT:    adds r0, #64
 ; CHECK-NEXT:    vadd.f16 q1, q1, r2
 ; CHECK-NEXT:    vstrh.16 q1, [r1, q0, uxtw #1]
 ; CHECK-NEXT:    adds r1, #64

 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    vmov s0, r2
 ; CHECK-NEXT:    adr r2, .LCPI9_0
 ; CHECK-NEXT:    vcvtb.f16.f32 s0, s0
 ; CHECK-NEXT:    mov.w lr, #249
 ; CHECK-NEXT:    vmov.f16 r1, s0
 ; CHECK-NEXT:    vldrw.u32 q0, [r2]
 ; CHECK-NEXT:    adr r2, .LCPI9_1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q1, [r2]
 ; CHECK-NEXT:  .LBB9_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.u16 q2, [r0, q0, uxtw #1]
 ; CHECK-NEXT:    vadd.f16 q2, q2, r1
 ; CHECK-NEXT:    vstrh.16 q2, [r0, q1, uxtw #1]
 ; CHECK-NEXT:    adds r0, #64
 ; CHECK-NEXT:    le lr, .LBB9_1

llvm/test/CodeGen/Thumb2/mve-gather-scatter-tailpred.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+mve.fp -enable-arm-maskedldst -enable-mem-access-versioning=false -tail-predication=force-enabled %s -o - | FileCheck %s
 
 define dso_local void @mve_gather_qi_wb(i32* noalias nocapture readonly %A, i32* noalias nocapture readonly %B, i32* noalias nocapture %C, i32 %n, i32 %m, i32 %l) {
 ; CHECK-LABEL: mve_gather_qi_wb:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    add.w r12, r0, r3, lsl #2
 ; CHECK-NEXT:    adr r0, .LCPI0_0
 ; CHECK-NEXT:    vldrw.u32 q0, [r0]
 ; CHECK-NEXT:    vmov.i32 q1, #0x0
 ; CHECK-NEXT:    movw lr, #1250
 ; CHECK-NEXT:    vadd.i32 q0, q0, r1
 ; CHECK-NEXT:    adds r1, r3, #4
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB0_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.32 r3
 ; CHECK-NEXT:    vmov q2, q1
 ; CHECK-NEXT:    vpstt
 ; CHECK-NEXT:    vldrwt.u32 q1, [r12], #16
 ; CHECK-NEXT:    vldrwt.u32 q3, [q0, #80]!
 ; CHECK-NEXT:    subs r3, #4

 ; CHECK-NEXT:    vpush {d8, d9}
 ; CHECK-NEXT:    add.w r4, r0, r3, lsl #2
 ; CHECK-NEXT:    adr r0, .LCPI1_0
 ; CHECK-NEXT:    vldrw.u32 q1, [r0]
 ; CHECK-NEXT:    add.w r12, r3, #4
 ; CHECK-NEXT:    vmov.i32 q2, #0x0
 ; CHECK-NEXT:    vmov.i32 q0, #0x14
 ; CHECK-NEXT:    movw lr, #1250
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB1_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.32 r3
 ; CHECK-NEXT:    vmov q3, q2
 ; CHECK-NEXT:    vpstt
 ; CHECK-NEXT:    vldrwt.u32 q2, [r1, q1, uxtw #2]
 ; CHECK-NEXT:    vldrwt.u32 q4, [r4], #16
 ; CHECK-NEXT:    subs r3, #4

 ; CHECK-NEXT:    add.w r12, r0, r3, lsl #2
 ; CHECK-NEXT:    adr r0, .LCPI2_0
 ; CHECK-NEXT:    vldrw.u32 q0, [r0]
 ; CHECK-NEXT:    vmov.i32 q1, #0x0
 ; CHECK-NEXT:    movw lr, #1250
 ; CHECK-NEXT:    vmov.i32 q2, #0x3
 ; CHECK-NEXT:    vadd.i32 q0, q0, r1
 ; CHECK-NEXT:    adds r1, r3, #4
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB2_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.32 r3
 ; CHECK-NEXT:    vmov q3, q1
 ; CHECK-NEXT:    vpst
 ; CHECK-NEXT:    vldrwt.u32 q1, [r12], #16
 ; CHECK-NEXT:    subs r3, #4
 ; CHECK-NEXT:    vmul.i32 q1, q1, q2

llvm/test/CodeGen/Thumb2/mve-nounrolledremainder.ll

 ; CHECK-NEXT:  .LBB1_7: @ %vector.ph
 ; CHECK-NEXT:    bic r6, r3, #7
 ; CHECK-NEXT:    movs r5, #1
 ; CHECK-NEXT:    sub.w r7, r6, #8
 ; CHECK-NEXT:    add.w r4, r1, r6, lsl #1
 ; CHECK-NEXT:    add.w r12, r0, r6, lsl #1
 ; CHECK-NEXT:    add.w lr, r5, r7, lsr #3
 ; CHECK-NEXT:    add.w r7, r2, r6, lsl #1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    and r5, r3, #7
 ; CHECK-NEXT:  .LBB1_8: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.u16 q0, [r0], #16
 ; CHECK-NEXT:    vldrh.u16 q1, [r1], #16
 ; CHECK-NEXT:    vadd.f16 q0, q1, q0
 ; CHECK-NEXT:    vstrb.8 q0, [r2], #16
 ; CHECK-NEXT:    le lr, .LBB1_8

llvm/test/CodeGen/Thumb2/mve-postinc-distribute.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+mve.fp %s -o - | FileCheck %s
 
 ; Check some loop postinc's for properly distributed post-incs
 
 define i32 @vaddv(i32* nocapture readonly %data, i32 %N) {
 ; CHECK-LABEL: vaddv:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov lr, r1
 ; CHECK-NEXT:    cmp r1, #1
 ; CHECK-NEXT:    blt .LBB0_4
 ; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    mov r1, r0
 ; CHECK-NEXT:    movs r0, #0
 ; CHECK-NEXT:  .LBB0_2: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r1], #32
 ; CHECK-NEXT:    vaddva.s32 r0, q0
 ; CHECK-NEXT:    vldrw.u32 q0, [r1, #-16]
 ; CHECK-NEXT:    vaddva.s32 r0, q0

 ; CHECK-NEXT:    b .LBB2_6
 ; CHECK-NEXT:  .LBB2_3: @ %vector.ph
 ; CHECK-NEXT:    bic r12, r3, #7
 ; CHECK-NEXT:    movs r5, #1
 ; CHECK-NEXT:    sub.w r6, r12, #8
 ; CHECK-NEXT:    mov r4, r0
 ; CHECK-NEXT:    add.w lr, r5, r6, lsr #3
 ; CHECK-NEXT:    mov r5, r1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    mov r6, r2
 ; CHECK-NEXT:  .LBB2_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r4, #16]
 ; CHECK-NEXT:    vldrw.u32 q1, [r5, #16]
 ; CHECK-NEXT:    vldrw.u32 q2, [r6, #16]
 ; CHECK-NEXT:    vldrw.u32 q3, [r6]
 ; CHECK-NEXT:    vfma.f32 q2, q1, q0
 ; CHECK-NEXT:    vldrw.u32 q0, [r4], #32
 ; CHECK-NEXT:    vldrw.u32 q1, [r5], #32
 ; CHECK-NEXT:    vfma.f32 q3, q1, q0
 ; CHECK-NEXT:    vstrw.32 q3, [r6], #32
 ; CHECK-NEXT:    vstrw.32 q2, [r6, #-16]
 ; CHECK-NEXT:    le lr, .LBB2_4
 ; CHECK-NEXT:  @ %bb.5: @ %middle.block
 ; CHECK-NEXT:    cmp r12, r3
 ; CHECK-NEXT:    it eq
 ; CHECK-NEXT:    popeq {r4, r5, r6, pc}
 ; CHECK-NEXT:  .LBB2_6: @ %for.body.preheader12
 ; CHECK-NEXT:    sub.w lr, r3, r12
 ; CHECK-NEXT:    add.w r0, r0, r12, lsl #2
 ; CHECK-NEXT:    add.w r1, r1, r12, lsl #2
 ; CHECK-NEXT:    add.w r2, r2, r12, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB2_7: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldr s0, [r0]
 ; CHECK-NEXT:    adds r0, #4
 ; CHECK-NEXT:    vldr s2, [r1]
 ; CHECK-NEXT:    adds r1, #4
 ; CHECK-NEXT:    vldr s4, [r2]
 ; CHECK-NEXT:    vfma.f32 s4, s2, s0

llvm/test/CodeGen/Thumb2/mve-postinc-lsr.ll

 ; CHECK-NEXT:    b .LBB0_6
 ; CHECK-NEXT:  .LBB0_3: @ %vector.ph
 ; CHECK-NEXT:    bic r12, r3, #3
 ; CHECK-NEXT:    movs r5, #1
 ; CHECK-NEXT:    sub.w r6, r12, #4
 ; CHECK-NEXT:    mov r4, r0
 ; CHECK-NEXT:    add.w lr, r5, r6, lsr #2
 ; CHECK-NEXT:    mov r5, r1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    mov r6, r2
 ; CHECK-NEXT:  .LBB0_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r4], #16
 ; CHECK-NEXT:    vldrw.u32 q1, [r5], #16
 ; CHECK-NEXT:    vldrw.u32 q2, [r6]
 ; CHECK-NEXT:    vfma.f32 q2, q1, q0
 ; CHECK-NEXT:    vstrb.8 q2, [r6], #16
 ; CHECK-NEXT:    le lr, .LBB0_4
 ; CHECK-NEXT:  @ %bb.5: @ %middle.block
 ; CHECK-NEXT:    cmp r12, r3
 ; CHECK-NEXT:    it eq
 ; CHECK-NEXT:    popeq {r4, r5, r6, pc}
 ; CHECK-NEXT:  .LBB0_6: @ %for.body.preheader12
 ; CHECK-NEXT:    sub.w lr, r3, r12
 ; CHECK-NEXT:    add.w r0, r0, r12, lsl #2
 ; CHECK-NEXT:    add.w r1, r1, r12, lsl #2
 ; CHECK-NEXT:    add.w r2, r2, r12, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB0_7: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldr s0, [r0]
 ; CHECK-NEXT:    adds r0, #4
 ; CHECK-NEXT:    vldr s2, [r1]
 ; CHECK-NEXT:    adds r1, #4
 ; CHECK-NEXT:    vldr s4, [r2]
 ; CHECK-NEXT:    vfma.f32 s4, s2, s0

 ; CHECK-NEXT:    add.w r12, r3, #3
 ; CHECK-NEXT:    mov.w lr, #1
 ; CHECK-NEXT:    bic r12, r12, #3
 ; CHECK-NEXT:    adr r4, .LCPI1_0
 ; CHECK-NEXT:    sub.w r12, r12, #4
 ; CHECK-NEXT:    vldrw.u32 q0, [r4]
 ; CHECK-NEXT:    add.w lr, lr, r12, lsr #2
 ; CHECK-NEXT:    sub.w r12, r3, #1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    movs r3, #0
 ; CHECK-NEXT:    vdup.32 q1, r12
 ; CHECK-NEXT:  .LBB1_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vdup.32 q2, r3
 ; CHECK-NEXT:    adds r3, #4
 ; CHECK-NEXT:    vorr q2, q2, q0
 ; CHECK-NEXT:    vpttt.u32 cs, q1, q2

llvm/test/CodeGen/Thumb2/mve-pred-threshold.ll

 ; CHECK-NEXT:    popeq {r7, pc}
 ; CHECK-NEXT:  .LBB0_1: @ %vector.ph
 ; CHECK-NEXT:    mvn r3, #3
 ; CHECK-NEXT:    add.w r1, r3, r1, lsl #2
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    add.w lr, r3, r1, lsr #2
 ; CHECK-NEXT:    rsbs r1, r2, #0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB0_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q1, [r0]
 ; CHECK-NEXT:    vpte.s32 ge, q1, r2
 ; CHECK-NEXT:    vcmpt.s32 le, q1, r1
 ; CHECK-NEXT:    vstrwe.32 q0, [r0], #16
 ; CHECK-NEXT:    le lr, .LBB0_2
 ; CHECK-NEXT:  @ %bb.3: @ %for.cond.cleanup

 ; CHECK-NEXT:    popeq {r7, pc}
 ; CHECK-NEXT:  .LBB1_1: @ %vector.ph
 ; CHECK-NEXT:    mvn r3, #7
 ; CHECK-NEXT:    add.w r1, r3, r1, lsl #3
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    add.w lr, r3, r1, lsr #3
 ; CHECK-NEXT:    rsbs r1, r2, #0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB1_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.u16 q1, [r0]
 ; CHECK-NEXT:    vpte.s16 ge, q1, r2
 ; CHECK-NEXT:    vcmpt.s16 le, q1, r1
 ; CHECK-NEXT:    vstrhe.16 q0, [r0], #16
 ; CHECK-NEXT:    le lr, .LBB1_2
 ; CHECK-NEXT:  @ %bb.3: @ %for.cond.cleanup

 ; CHECK-NEXT:    popeq {r7, pc}
 ; CHECK-NEXT:  .LBB2_1: @ %vector.ph
 ; CHECK-NEXT:    mvn r3, #15
 ; CHECK-NEXT:    add.w r1, r3, r1, lsl #4
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    add.w lr, r3, r1, lsr #4
 ; CHECK-NEXT:    rsbs r1, r2, #0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB2_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrb.u8 q1, [r0]
 ; CHECK-NEXT:    vpte.s8 ge, q1, r2
 ; CHECK-NEXT:    vcmpt.s8 le, q1, r1
 ; CHECK-NEXT:    vstrbe.8 q0, [r0], #16
 ; CHECK-NEXT:    le lr, .LBB2_2
 ; CHECK-NEXT:  @ %bb.3: @ %for.cond.cleanup

 ; CHECK-NEXT:    it eq
 ; CHECK-NEXT:    popeq {r7, pc}
 ; CHECK-NEXT:  .LBB3_1: @ %vector.ph
 ; CHECK-NEXT:    mvn r2, #3
 ; CHECK-NEXT:    add.w r1, r2, r1, lsl #2
 ; CHECK-NEXT:    movs r2, #1
 ; CHECK-NEXT:    add.w lr, r2, r1, lsr #2
 ; CHECK-NEXT:    vmov r1, s0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    eor r2, r1, #-2147483648
 ; CHECK-NEXT:  .LBB3_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q1, [r0]
 ; CHECK-NEXT:    vpte.f32 ge, q1, r1
 ; CHECK-NEXT:    vcmpt.f32 le, q1, r2
 ; CHECK-NEXT:    vstrwe.32 q0, [r0], #16

 ; CHECK-NEXT:  .LBB4_1: @ %vector.ph
 ; CHECK-NEXT:    mvn r3, #7
 ; CHECK-NEXT:    add.w r1, r3, r1, lsl #3
 ; CHECK-NEXT:    vmov r2, s0
 ; CHECK-NEXT:    vneg.f16 s0, s0
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r1, lsr #3
 ; CHECK-NEXT:    vmov.f16 r1, s0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:  .LBB4_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.u16 q1, [r0]
 ; CHECK-NEXT:    vpte.f16 ge, q1, r2
 ; CHECK-NEXT:    vcmpt.f16 le, q1, r1
 ; CHECK-NEXT:    vstrhe.16 q0, [r0], #16
 ; CHECK-NEXT:    le lr, .LBB4_2

 ; CHECK-NEXT:    popeq {r7, pc}
 ; CHECK-NEXT:  .LBB5_1: @ %vector.ph
 ; CHECK-NEXT:    mvn r3, #3
 ; CHECK-NEXT:    add.w r1, r3, r1, lsl #2
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    add.w lr, r3, r1, lsr #2
 ; CHECK-NEXT:    rsbs r1, r2, #0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB5_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q1, [r0]
 ; CHECK-NEXT:    vpte.s32 ge, q1, r2
 ; CHECK-NEXT:    vcmpt.s32 le, q1, r1
 ; CHECK-NEXT:    vstrwe.32 q0, [r0], #16
 ; CHECK-NEXT:    le lr, .LBB5_2
 ; CHECK-NEXT:  @ %bb.3: @ %for.cond.cleanup

 ; CHECK-NEXT:    popeq {r7, pc}
 ; CHECK-NEXT:  .LBB6_1: @ %vector.ph
 ; CHECK-NEXT:    mvn r3, #7
 ; CHECK-NEXT:    add.w r1, r3, r1, lsl #3
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    add.w lr, r3, r1, lsr #3
 ; CHECK-NEXT:    rsbs r1, r2, #0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB6_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.u16 q1, [r0]
 ; CHECK-NEXT:    vpte.s16 ge, q1, r2
 ; CHECK-NEXT:    vcmpt.s16 le, q1, r1
 ; CHECK-NEXT:    vstrhe.16 q0, [r0], #16
 ; CHECK-NEXT:    le lr, .LBB6_2
 ; CHECK-NEXT:  @ %bb.3: @ %for.cond.cleanup

 ; CHECK-NEXT:    popeq {r7, pc}
 ; CHECK-NEXT:  .LBB7_1: @ %vector.ph
 ; CHECK-NEXT:    mvn r3, #15
 ; CHECK-NEXT:    add.w r1, r3, r1, lsl #4
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    add.w lr, r3, r1, lsr #4
 ; CHECK-NEXT:    rsbs r1, r2, #0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB7_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrb.u8 q1, [r0]
 ; CHECK-NEXT:    vpte.s8 ge, q1, r2
 ; CHECK-NEXT:    vcmpt.s8 le, q1, r1
 ; CHECK-NEXT:    vstrbe.8 q0, [r0], #16
 ; CHECK-NEXT:    le lr, .LBB7_2
 ; CHECK-NEXT:  @ %bb.3: @ %for.cond.cleanup

 ; CHECK-NEXT:    it eq
 ; CHECK-NEXT:    popeq {r7, pc}
 ; CHECK-NEXT:  .LBB8_1: @ %vector.ph
 ; CHECK-NEXT:    mvn r2, #3
 ; CHECK-NEXT:    add.w r1, r2, r1, lsl #2
 ; CHECK-NEXT:    movs r2, #1
 ; CHECK-NEXT:    add.w lr, r2, r1, lsr #2
 ; CHECK-NEXT:    vmov r1, s0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    eor r2, r1, #-2147483648
 ; CHECK-NEXT:  .LBB8_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q1, [r0]
 ; CHECK-NEXT:    vpte.f32 ge, q1, r1
 ; CHECK-NEXT:    vcmpt.f32 le, q1, r2
 ; CHECK-NEXT:    vstrwe.32 q0, [r0], #16

 ; CHECK-NEXT:  .LBB9_1: @ %vector.ph
 ; CHECK-NEXT:    mvn r3, #7
 ; CHECK-NEXT:    add.w r1, r3, r1, lsl #3
 ; CHECK-NEXT:    vmov r2, s0
 ; CHECK-NEXT:    vneg.f16 s0, s0
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r1, lsr #3
 ; CHECK-NEXT:    vmov.f16 r1, s0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:  .LBB9_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.u16 q1, [r0]
 ; CHECK-NEXT:    vpte.f16 ge, q1, r2
 ; CHECK-NEXT:    vcmpt.f16 le, q1, r1
 ; CHECK-NEXT:    vstrhe.16 q0, [r0], #16
 ; CHECK-NEXT:    le lr, .LBB9_2

llvm/test/CodeGen/Thumb2/mve-satmul-loops.ll

 ; CHECK-NEXT:    subs r7, r3, #2
 ; CHECK-NEXT:    movs r6, #1
 ; CHECK-NEXT:    adr r4, .LCPI0_0
 ; CHECK-NEXT:    str r3, [sp] @ 4-byte Spill
 ; CHECK-NEXT:    add.w lr, r6, r7, lsr #1
 ; CHECK-NEXT:    add.w r11, r2, r3, lsl #2
 ; CHECK-NEXT:    add.w r10, r1, r3, lsl #2
 ; CHECK-NEXT:    add.w r12, r0, r3, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q0, [r4]
 ; CHECK-NEXT:    vmvn.i32 q1, #0x80000000
 ; CHECK-NEXT:  .LBB0_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldrd r5, r4, [r0]
 ; CHECK-NEXT:    mov.w r3, #-1
 ; CHECK-NEXT:    ldrd r8, r7, [r1]
 ; CHECK-NEXT:    adds r0, #8

 ; CHECK-NEXT:    le lr, .LBB0_4
 ; CHECK-NEXT:  @ %bb.5: @ %middle.block
 ; CHECK-NEXT:    ldrd r7, r3, [sp] @ 8-byte Folded Reload
 ; CHECK-NEXT:    cmp r7, r3
 ; CHECK-NEXT:    beq .LBB0_8
 ; CHECK-NEXT:  .LBB0_6: @ %for.body.preheader
 ; CHECK-NEXT:    sub.w lr, r3, r7
 ; CHECK-NEXT:    mov.w r0, #-1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    mov.w r1, #-2147483648
 ; CHECK-NEXT:    mvn r2, #-2147483648
 ; CHECK-NEXT:  .LBB0_7: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldr r3, [r12], #4
 ; CHECK-NEXT:    ldr r4, [r10], #4
 ; CHECK-NEXT:    smull r4, r3, r4, r3
 ; CHECK-NEXT:    asrl r4, r3, #31

 ; CHECK-NEXT:    movs r6, #1
 ; CHECK-NEXT:    vldrw.u32 q0, [r4]
 ; CHECK-NEXT:    adr r4, .LCPI1_1
 ; CHECK-NEXT:    add.w lr, r6, r7, lsr #2
 ; CHECK-NEXT:    str r3, [sp] @ 4-byte Spill
 ; CHECK-NEXT:    add.w r11, r2, r3, lsl #2
 ; CHECK-NEXT:    add.w r9, r1, r3, lsl #2
 ; CHECK-NEXT:    add.w r12, r0, r3, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q1, [r4]
 ; CHECK-NEXT:  .LBB1_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q3, [r1], #16
 ; CHECK-NEXT:    vldrw.u32 q2, [r0], #16
 ; CHECK-NEXT:    str r2, [sp, #12] @ 4-byte Spill
 ; CHECK-NEXT:    mov.w r2, #-1
 ; CHECK-NEXT:    vmov.f32 s16, s10

 ; CHECK-NEXT:    le lr, .LBB1_4
 ; CHECK-NEXT:  @ %bb.5: @ %middle.block
 ; CHECK-NEXT:    ldrd r7, r3, [sp] @ 8-byte Folded Reload
 ; CHECK-NEXT:    cmp r7, r3
 ; CHECK-NEXT:    beq .LBB1_8
 ; CHECK-NEXT:  .LBB1_6: @ %for.body.preheader21
 ; CHECK-NEXT:    sub.w lr, r3, r7
 ; CHECK-NEXT:    mov.w r0, #-1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    mov.w r3, #-2147483648
 ; CHECK-NEXT:    mvn r2, #-2147483648
 ; CHECK-NEXT:  .LBB1_7: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldr r1, [r12], #4
 ; CHECK-NEXT:    ldr r4, [r9], #4
 ; CHECK-NEXT:    smull r4, r1, r4, r1
 ; CHECK-NEXT:    asrl r4, r1, #31

 ; CHECK-NEXT:    adr r4, .LCPI2_1
 ; CHECK-NEXT:    subs r7, #4
 ; CHECK-NEXT:    adr r5, .LCPI2_2
 ; CHECK-NEXT:    vldrw.u32 q2, [r4]
 ; CHECK-NEXT:    vldrw.u32 q3, [r5]
 ; CHECK-NEXT:    add.w lr, r6, r7, lsr #2
 ; CHECK-NEXT:    adr r6, .LCPI2_0
 ; CHECK-NEXT:    subs r7, r3, #1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q0, [r6]
 ; CHECK-NEXT:    mov.w r9, #0
 ; CHECK-NEXT:    vdup.32 q1, r7
 ; CHECK-NEXT:    mov.w r12, #-1
 ; CHECK-NEXT:    mvn r8, #-2147483648
 ; CHECK-NEXT:    vstrw.32 q0, [sp] @ 16-byte Spill
 ; CHECK-NEXT:  .LBB2_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1

 ; CHECK-NEXT:    bic r5, r3, #1
 ; CHECK-NEXT:    movs r6, #1
 ; CHECK-NEXT:    subs r7, r5, #2
 ; CHECK-NEXT:    str r5, [sp] @ 4-byte Spill
 ; CHECK-NEXT:    add.w r8, r2, r5, lsl #2
 ; CHECK-NEXT:    add.w r11, r1, r5, lsl #2
 ; CHECK-NEXT:    add.w lr, r6, r7, lsr #1
 ; CHECK-NEXT:    add.w r12, r0, r5, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB3_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldrd r4, r7, [r0]
 ; CHECK-NEXT:    adds r0, #8
 ; CHECK-NEXT:    ldrd r5, r10, [r1]
 ; CHECK-NEXT:    adds r1, #8
 ; CHECK-NEXT:    umull r4, r5, r5, r4
 ; CHECK-NEXT:    lsrl r4, r5, #31

 ; CHECK-NEXT:    adds r2, #8
 ; CHECK-NEXT:    le lr, .LBB3_4
 ; CHECK-NEXT:  @ %bb.5: @ %middle.block
 ; CHECK-NEXT:    ldr r7, [sp] @ 4-byte Reload
 ; CHECK-NEXT:    cmp r7, r3
 ; CHECK-NEXT:    beq .LBB3_8
 ; CHECK-NEXT:  .LBB3_6: @ %for.body.preheader
 ; CHECK-NEXT:    sub.w lr, r3, r7
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB3_7: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldr r0, [r12], #4
 ; CHECK-NEXT:    ldr r1, [r11], #4
 ; CHECK-NEXT:    umull r0, r1, r1, r0
 ; CHECK-NEXT:    lsrl r0, r1, #31
 ; CHECK-NEXT:    subs.w r2, r0, #-1
 ; CHECK-NEXT:    sbcs r1, r1, #0

 ; CHECK-NEXT:  .LBB4_3: @ %vector.ph
 ; CHECK-NEXT:    bic r8, r3, #3
 ; CHECK-NEXT:    movs r6, #1
 ; CHECK-NEXT:    sub.w r7, r8, #4
 ; CHECK-NEXT:    add.w r10, r2, r8, lsl #2
 ; CHECK-NEXT:    add.w r9, r1, r8, lsl #2
 ; CHECK-NEXT:    add.w lr, r6, r7, lsr #2
 ; CHECK-NEXT:    add.w r12, r0, r8, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB4_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r0], #16
 ; CHECK-NEXT:    vldrw.u32 q2, [r1], #16
 ; CHECK-NEXT:    vmov.f32 s4, s2
 ; CHECK-NEXT:    vmov.f32 s12, s10
 ; CHECK-NEXT:    vmov.f32 s6, s3
 ; CHECK-NEXT:    vmov.f32 s14, s11

 ; CHECK-NEXT:    vmov.f32 s3, s6
 ; CHECK-NEXT:    vstrb.8 q0, [r2], #16
 ; CHECK-NEXT:    le lr, .LBB4_4
 ; CHECK-NEXT:  @ %bb.5: @ %middle.block
 ; CHECK-NEXT:    cmp r8, r3
 ; CHECK-NEXT:    beq .LBB4_8
 ; CHECK-NEXT:  .LBB4_6: @ %for.body.preheader21
 ; CHECK-NEXT:    sub.w lr, r3, r8
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB4_7: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldr r0, [r12], #4
 ; CHECK-NEXT:    ldr r1, [r9], #4
 ; CHECK-NEXT:    umull r0, r1, r1, r0
 ; CHECK-NEXT:    lsrl r0, r1, #31
 ; CHECK-NEXT:    subs.w r2, r0, #-1
 ; CHECK-NEXT:    sbcs r1, r1, #0

 ; CHECK-NEXT:  .LBB5_3: @ %vector.ph
 ; CHECK-NEXT:    bic r5, r3, #3
 ; CHECK-NEXT:    movs r4, #1
 ; CHECK-NEXT:    subs r6, r5, #4
 ; CHECK-NEXT:    add.w r12, r0, r5, lsl #1
 ; CHECK-NEXT:    add.w lr, r4, r6, lsr #2
 ; CHECK-NEXT:    add.w r4, r2, r5, lsl #1
 ; CHECK-NEXT:    add.w r6, r1, r5, lsl #1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB5_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.s32 q0, [r0], #8
 ; CHECK-NEXT:    vldrh.s32 q1, [r1], #8
 ; CHECK-NEXT:    vmul.i32 q0, q1, q0
 ; CHECK-NEXT:    vqshrnb.s32 q0, q0, #15
 ; CHECK-NEXT:    vstrh.32 q0, [r2], #8
 ; CHECK-NEXT:    le lr, .LBB5_4
 ; CHECK-NEXT:  @ %bb.5: @ %middle.block
 ; CHECK-NEXT:    cmp r5, r3
 ; CHECK-NEXT:    it eq
 ; CHECK-NEXT:    popeq {r4, r5, r6, pc}
 ; CHECK-NEXT:  .LBB5_6: @ %for.body.preheader21
 ; CHECK-NEXT:    sub.w lr, r3, r5
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB5_7: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldrsh r0, [r12], #2
 ; CHECK-NEXT:    ldrsh r1, [r6], #2
 ; CHECK-NEXT:    muls r0, r1, r0
 ; CHECK-NEXT:    ssat r0, #16, r0, asr #15
 ; CHECK-NEXT:    strh r0, [r4], #2
 ; CHECK-NEXT:    le lr, .LBB5_7

 ; CHECK-NEXT:  .LBB6_3: @ %vector.ph
 ; CHECK-NEXT:    bic r5, r3, #7
 ; CHECK-NEXT:    movs r4, #1
 ; CHECK-NEXT:    sub.w r6, r5, #8
 ; CHECK-NEXT:    add.w r12, r0, r5, lsl #1
 ; CHECK-NEXT:    add.w lr, r4, r6, lsr #3
 ; CHECK-NEXT:    add.w r4, r2, r5, lsl #1
 ; CHECK-NEXT:    add.w r6, r1, r5, lsl #1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB6_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.s32 q0, [r0, #8]
 ; CHECK-NEXT:    vldrh.s32 q1, [r1, #8]
 ; CHECK-NEXT:    vmul.i32 q0, q1, q0
 ; CHECK-NEXT:    vldrh.s32 q1, [r1], #16
 ; CHECK-NEXT:    vqshrnb.s32 q0, q0, #15
 ; CHECK-NEXT:    vstrh.32 q0, [r2, #8]
 ; CHECK-NEXT:    vldrh.s32 q0, [r0], #16
 ; CHECK-NEXT:    vmul.i32 q0, q1, q0
 ; CHECK-NEXT:    vqshrnb.s32 q0, q0, #15
 ; CHECK-NEXT:    vstrh.32 q0, [r2], #16
 ; CHECK-NEXT:    le lr, .LBB6_4
 ; CHECK-NEXT:  @ %bb.5: @ %middle.block
 ; CHECK-NEXT:    cmp r5, r3
 ; CHECK-NEXT:    it eq
 ; CHECK-NEXT:    popeq {r4, r5, r6, pc}
 ; CHECK-NEXT:  .LBB6_6: @ %for.body.preheader21
 ; CHECK-NEXT:    sub.w lr, r3, r5
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB6_7: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldrsh r0, [r12], #2
 ; CHECK-NEXT:    ldrsh r1, [r6], #2
 ; CHECK-NEXT:    muls r0, r1, r0
 ; CHECK-NEXT:    ssat r0, #16, r0, asr #15
 ; CHECK-NEXT:    strh r0, [r4], #2
 ; CHECK-NEXT:    le lr, .LBB6_7

 ; CHECK-NEXT:  .LBB7_3: @ %vector.ph
 ; CHECK-NEXT:    bic r5, r3, #7
 ; CHECK-NEXT:    movs r4, #1
 ; CHECK-NEXT:    sub.w r6, r5, #8
 ; CHECK-NEXT:    add.w r12, r0, r5, lsl #1
 ; CHECK-NEXT:    add.w lr, r4, r6, lsr #3
 ; CHECK-NEXT:    add.w r4, r2, r5, lsl #1
 ; CHECK-NEXT:    add.w r6, r1, r5, lsl #1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB7_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.u16 q0, [r0], #16
 ; CHECK-NEXT:    vldrh.u16 q1, [r1], #16
 ; CHECK-NEXT:    vmullt.s16 q2, q1, q0
 ; CHECK-NEXT:    vmullb.s16 q0, q1, q0
 ; CHECK-NEXT:    vqshrnb.s32 q0, q0, #15
 ; CHECK-NEXT:    vqshrnt.s32 q0, q2, #15
 ; CHECK-NEXT:    vstrb.8 q0, [r2], #16
 ; CHECK-NEXT:    le lr, .LBB7_4
 ; CHECK-NEXT:  @ %bb.5: @ %middle.block
 ; CHECK-NEXT:    cmp r5, r3
 ; CHECK-NEXT:    it eq
 ; CHECK-NEXT:    popeq {r4, r5, r6, pc}
 ; CHECK-NEXT:  .LBB7_6: @ %for.body.preheader21
 ; CHECK-NEXT:    sub.w lr, r3, r5
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB7_7: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldrsh r0, [r12], #2
 ; CHECK-NEXT:    ldrsh r1, [r6], #2
 ; CHECK-NEXT:    muls r0, r1, r0
 ; CHECK-NEXT:    ssat r0, #16, r0, asr #15
 ; CHECK-NEXT:    strh r0, [r4], #2
 ; CHECK-NEXT:    le lr, .LBB7_7

 ; CHECK-NEXT:    add.w r12, r3, #3
 ; CHECK-NEXT:    mov.w lr, #1
 ; CHECK-NEXT:    bic r12, r12, #3
 ; CHECK-NEXT:    adr r4, .LCPI8_0
 ; CHECK-NEXT:    sub.w r12, r12, #4
 ; CHECK-NEXT:    vldrw.u32 q0, [r4]
 ; CHECK-NEXT:    add.w lr, lr, r12, lsr #2
 ; CHECK-NEXT:    sub.w r12, r3, #1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    movs r3, #0
 ; CHECK-NEXT:    vdup.32 q1, r12
 ; CHECK-NEXT:  .LBB8_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vdup.32 q2, r3
 ; CHECK-NEXT:    adds r3, #4
 ; CHECK-NEXT:    vorr q2, q2, q0
 ; CHECK-NEXT:    vptt.u32 cs, q1, q2

 ; CHECK-NEXT:    bic r12, r12, #7
 ; CHECK-NEXT:    mov.w lr, #1
 ; CHECK-NEXT:    sub.w r12, r12, #8
 ; CHECK-NEXT:    vldrw.u32 q0, [r4]
 ; CHECK-NEXT:    adr r4, .LCPI9_1
 ; CHECK-NEXT:    movs r5, #0
 ; CHECK-NEXT:    add.w lr, lr, r12, lsr #3
 ; CHECK-NEXT:    sub.w r12, r3, #1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q4, [r4]
 ; CHECK-NEXT:    vdup.32 q1, r12
 ; CHECK-NEXT:    vmov.i8 q2, #0x0
 ; CHECK-NEXT:    vmov.i8 q3, #0xff
 ; CHECK-NEXT:    vstrw.32 q0, [sp] @ 16-byte Spill
 ; CHECK-NEXT:  .LBB9_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [sp] @ 16-byte Reload

 ; CHECK-NEXT:    bic r12, r12, #7
 ; CHECK-NEXT:    mov.w lr, #1
 ; CHECK-NEXT:    sub.w r12, r12, #8
 ; CHECK-NEXT:    vldrw.u32 q0, [r4]
 ; CHECK-NEXT:    adr r4, .LCPI10_1
 ; CHECK-NEXT:    vmov.i8 q2, #0x0
 ; CHECK-NEXT:    add.w lr, lr, r12, lsr #3
 ; CHECK-NEXT:    sub.w r12, r3, #1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q4, [r4]
 ; CHECK-NEXT:    movs r3, #0
 ; CHECK-NEXT:    vdup.32 q1, r12
 ; CHECK-NEXT:    vmov.i8 q3, #0xff
 ; CHECK-NEXT:  .LBB10_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vdup.32 q6, r3
 ; CHECK-NEXT:    adds r3, #8

 ; CHECK-NEXT:  .LBB11_3: @ %vector.ph
 ; CHECK-NEXT:    bic r5, r3, #3
 ; CHECK-NEXT:    movs r4, #1
 ; CHECK-NEXT:    subs r6, r5, #4
 ; CHECK-NEXT:    add.w r12, r0, r5, lsl #1
 ; CHECK-NEXT:    add.w lr, r4, r6, lsr #2
 ; CHECK-NEXT:    add.w r4, r2, r5, lsl #1
 ; CHECK-NEXT:    add.w r6, r1, r5, lsl #1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB11_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.u32 q0, [r0], #8
 ; CHECK-NEXT:    vldrh.u32 q1, [r1], #8
 ; CHECK-NEXT:    vmul.i32 q0, q1, q0
 ; CHECK-NEXT:    vqshrnb.u32 q0, q0, #15
 ; CHECK-NEXT:    vstrh.32 q0, [r2], #8
 ; CHECK-NEXT:    le lr, .LBB11_4
 ; CHECK-NEXT:  @ %bb.5: @ %middle.block
 ; CHECK-NEXT:    cmp r5, r3
 ; CHECK-NEXT:    it eq
 ; CHECK-NEXT:    popeq {r4, r5, r6, pc}
 ; CHECK-NEXT:  .LBB11_6: @ %for.body.preheader21
 ; CHECK-NEXT:    sub.w lr, r3, r5
 ; CHECK-NEXT:    movw r0, #65535
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB11_7: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldrh r1, [r12], #2
 ; CHECK-NEXT:    ldrh r2, [r6], #2
 ; CHECK-NEXT:    muls r1, r2, r1
 ; CHECK-NEXT:    lsrs r2, r1, #15
 ; CHECK-NEXT:    cmp r2, r0
 ; CHECK-NEXT:    movw r2, #65535

 ; CHECK-NEXT:  .LBB12_3: @ %vector.ph
 ; CHECK-NEXT:    bic r5, r3, #7
 ; CHECK-NEXT:    movs r4, #1
 ; CHECK-NEXT:    sub.w r6, r5, #8
 ; CHECK-NEXT:    add.w r12, r0, r5, lsl #1
 ; CHECK-NEXT:    add.w lr, r4, r6, lsr #3
 ; CHECK-NEXT:    add.w r4, r2, r5, lsl #1
 ; CHECK-NEXT:    add.w r6, r1, r5, lsl #1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB12_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.u32 q0, [r0, #8]
 ; CHECK-NEXT:    vldrh.u32 q1, [r1, #8]
 ; CHECK-NEXT:    vmul.i32 q0, q1, q0
 ; CHECK-NEXT:    vldrh.u32 q1, [r1], #16
 ; CHECK-NEXT:    vqshrnb.u32 q0, q0, #15
 ; CHECK-NEXT:    vstrh.32 q0, [r2, #8]
 ; CHECK-NEXT:    vldrh.u32 q0, [r0], #16
 ; CHECK-NEXT:    vmul.i32 q0, q1, q0
 ; CHECK-NEXT:    vqshrnb.u32 q0, q0, #15
 ; CHECK-NEXT:    vstrh.32 q0, [r2], #16
 ; CHECK-NEXT:    le lr, .LBB12_4
 ; CHECK-NEXT:  @ %bb.5: @ %middle.block
 ; CHECK-NEXT:    cmp r5, r3
 ; CHECK-NEXT:    it eq
 ; CHECK-NEXT:    popeq {r4, r5, r6, pc}
 ; CHECK-NEXT:  .LBB12_6: @ %for.body.preheader21
 ; CHECK-NEXT:    sub.w lr, r3, r5
 ; CHECK-NEXT:    movw r0, #65535
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB12_7: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldrh r1, [r12], #2
 ; CHECK-NEXT:    ldrh r2, [r6], #2
 ; CHECK-NEXT:    muls r1, r2, r1
 ; CHECK-NEXT:    lsrs r2, r1, #15
 ; CHECK-NEXT:    cmp r2, r0
 ; CHECK-NEXT:    movw r2, #65535

 ; CHECK-NEXT:    movs r4, #1
 ; CHECK-NEXT:    subs r6, r5, #4
 ; CHECK-NEXT:    add.w r12, r0, r5
 ; CHECK-NEXT:    vmvn.i32 q0, #0x7f
 ; CHECK-NEXT:    vmov.i32 q1, #0x7f
 ; CHECK-NEXT:    add.w lr, r4, r6, lsr #2
 ; CHECK-NEXT:    adds r4, r2, r5
 ; CHECK-NEXT:    adds r6, r1, r5
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB13_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrb.s32 q2, [r0], #4
 ; CHECK-NEXT:    vldrb.s32 q3, [r1], #4
 ; CHECK-NEXT:    vmul.i32 q2, q3, q2
 ; CHECK-NEXT:    vshr.s32 q2, q2, #7
 ; CHECK-NEXT:    vmax.s32 q2, q2, q0
 ; CHECK-NEXT:    vmin.s32 q2, q2, q1
 ; CHECK-NEXT:    vstrb.32 q2, [r2], #4
 ; CHECK-NEXT:    le lr, .LBB13_4
 ; CHECK-NEXT:  @ %bb.5: @ %middle.block
 ; CHECK-NEXT:    cmp r5, r3
 ; CHECK-NEXT:    it eq
 ; CHECK-NEXT:    popeq {r4, r5, r6, pc}
 ; CHECK-NEXT:  .LBB13_6: @ %for.body.preheader21
 ; CHECK-NEXT:    sub.w lr, r3, r5
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB13_7: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldrsb r0, [r12], #1
 ; CHECK-NEXT:    ldrsb r1, [r6], #1
 ; CHECK-NEXT:    muls r0, r1, r0
 ; CHECK-NEXT:    ssat r0, #8, r0, asr #7
 ; CHECK-NEXT:    strb r0, [r4], #1
 ; CHECK-NEXT:    le lr, .LBB13_7

 ; CHECK-NEXT:  .LBB14_3: @ %vector.ph
 ; CHECK-NEXT:    bic r5, r3, #7
 ; CHECK-NEXT:    movs r4, #1
 ; CHECK-NEXT:    sub.w r6, r5, #8
 ; CHECK-NEXT:    add.w r12, r0, r5
 ; CHECK-NEXT:    add.w lr, r4, r6, lsr #3
 ; CHECK-NEXT:    adds r4, r2, r5
 ; CHECK-NEXT:    adds r6, r1, r5
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB14_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrb.s16 q0, [r0], #8
 ; CHECK-NEXT:    vldrb.s16 q1, [r1], #8
 ; CHECK-NEXT:    vmul.i16 q0, q1, q0
 ; CHECK-NEXT:    vqshrnb.s16 q0, q0, #7
 ; CHECK-NEXT:    vstrb.16 q0, [r2], #8
 ; CHECK-NEXT:    le lr, .LBB14_4
 ; CHECK-NEXT:  @ %bb.5: @ %middle.block
 ; CHECK-NEXT:    cmp r5, r3
 ; CHECK-NEXT:    it eq
 ; CHECK-NEXT:    popeq {r4, r5, r6, pc}
 ; CHECK-NEXT:  .LBB14_6: @ %for.body.preheader23
 ; CHECK-NEXT:    sub.w lr, r3, r5
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB14_7: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldrsb r0, [r12], #1
 ; CHECK-NEXT:    ldrsb r1, [r6], #1
 ; CHECK-NEXT:    muls r0, r1, r0
 ; CHECK-NEXT:    ssat r0, #8, r0, asr #7
 ; CHECK-NEXT:    strb r0, [r4], #1
 ; CHECK-NEXT:    le lr, .LBB14_7

 ; CHECK-NEXT:  .LBB15_3: @ %vector.ph
 ; CHECK-NEXT:    bic r5, r3, #15
 ; CHECK-NEXT:    movs r4, #1
 ; CHECK-NEXT:    sub.w r6, r5, #16
 ; CHECK-NEXT:    add.w r12, r0, r5
 ; CHECK-NEXT:    add.w lr, r4, r6, lsr #4
 ; CHECK-NEXT:    adds r4, r2, r5
 ; CHECK-NEXT:    adds r6, r1, r5
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB15_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrb.s16 q0, [r0, #8]
 ; CHECK-NEXT:    vldrb.s16 q1, [r1, #8]
 ; CHECK-NEXT:    vmul.i16 q0, q1, q0
 ; CHECK-NEXT:    vldrb.s16 q1, [r1], #16
 ; CHECK-NEXT:    vqshrnb.s16 q0, q0, #7
 ; CHECK-NEXT:    vstrb.16 q0, [r2, #8]
 ; CHECK-NEXT:    vldrb.s16 q0, [r0], #16
 ; CHECK-NEXT:    vmul.i16 q0, q1, q0
 ; CHECK-NEXT:    vqshrnb.s16 q0, q0, #7
 ; CHECK-NEXT:    vstrb.16 q0, [r2], #16
 ; CHECK-NEXT:    le lr, .LBB15_4
 ; CHECK-NEXT:  @ %bb.5: @ %middle.block
 ; CHECK-NEXT:    cmp r5, r3
 ; CHECK-NEXT:    it eq
 ; CHECK-NEXT:    popeq {r4, r5, r6, pc}
 ; CHECK-NEXT:  .LBB15_6: @ %for.body.preheader23
 ; CHECK-NEXT:    sub.w lr, r3, r5
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB15_7: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldrsb r0, [r12], #1
 ; CHECK-NEXT:    ldrsb r1, [r6], #1
 ; CHECK-NEXT:    muls r0, r1, r0
 ; CHECK-NEXT:    ssat r0, #8, r0, asr #7
 ; CHECK-NEXT:    strb r0, [r4], #1
 ; CHECK-NEXT:    le lr, .LBB15_7

 ; CHECK-NEXT:  .LBB16_3: @ %vector.ph
 ; CHECK-NEXT:    bic r5, r3, #15
 ; CHECK-NEXT:    movs r4, #1
 ; CHECK-NEXT:    sub.w r6, r5, #16
 ; CHECK-NEXT:    add.w r12, r0, r5
 ; CHECK-NEXT:    add.w lr, r4, r6, lsr #4
 ; CHECK-NEXT:    adds r4, r2, r5
 ; CHECK-NEXT:    adds r6, r1, r5
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB16_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrb.u8 q0, [r0], #16
 ; CHECK-NEXT:    vldrb.u8 q1, [r1], #16
 ; CHECK-NEXT:    vmullt.s8 q2, q1, q0
 ; CHECK-NEXT:    vmullb.s8 q0, q1, q0
 ; CHECK-NEXT:    vqshrnb.s16 q0, q0, #7
 ; CHECK-NEXT:    vqshrnt.s16 q0, q2, #7
 ; CHECK-NEXT:    vstrb.8 q0, [r2], #16
 ; CHECK-NEXT:    le lr, .LBB16_4
 ; CHECK-NEXT:  @ %bb.5: @ %middle.block
 ; CHECK-NEXT:    cmp r5, r3
 ; CHECK-NEXT:    it eq
 ; CHECK-NEXT:    popeq {r4, r5, r6, pc}
 ; CHECK-NEXT:  .LBB16_6: @ %for.body.preheader23
 ; CHECK-NEXT:    sub.w lr, r3, r5
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB16_7: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldrsb r0, [r12], #1
 ; CHECK-NEXT:    ldrsb r1, [r6], #1
 ; CHECK-NEXT:    muls r0, r1, r0
 ; CHECK-NEXT:    ssat r0, #8, r0, asr #7
 ; CHECK-NEXT:    strb r0, [r4], #1
 ; CHECK-NEXT:    le lr, .LBB16_7

 ; CHECK-NEXT:    bic r12, r12, #7
 ; CHECK-NEXT:    mov.w lr, #1
 ; CHECK-NEXT:    sub.w r12, r12, #8
 ; CHECK-NEXT:    vldrw.u32 q0, [r4]
 ; CHECK-NEXT:    adr r4, .LCPI17_1
 ; CHECK-NEXT:    vmov.i8 q2, #0x0
 ; CHECK-NEXT:    add.w lr, lr, r12, lsr #3
 ; CHECK-NEXT:    sub.w r12, r3, #1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vldrw.u32 q4, [r4]
 ; CHECK-NEXT:    movs r3, #0
 ; CHECK-NEXT:    vdup.32 q1, r12
 ; CHECK-NEXT:    vmov.i8 q3, #0xff
 ; CHECK-NEXT:  .LBB17_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vdup.32 q6, r3
 ; CHECK-NEXT:    adds r3, #8

 ; CHECK-NEXT:    bic r12, r12, #15
 ; CHECK-NEXT:    vldrw.u32 q0, [r4]
 ; CHECK-NEXT:    sub.w r12, r12, #16
 ; CHECK-NEXT:    mov.w lr, #1
 ; CHECK-NEXT:    adr r4, .LCPI18_1
 ; CHECK-NEXT:    vmov.i8 q2, #0x0
 ; CHECK-NEXT:    add.w lr, lr, r12, lsr #4
 ; CHECK-NEXT:    sub.w r12, r3, #1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vstrw.32 q0, [sp, #32] @ 16-byte Spill
 ; CHECK-NEXT:    vldrw.u32 q0, [r4]
 ; CHECK-NEXT:    adr r4, .LCPI18_2
 ; CHECK-NEXT:    movs r3, #0
 ; CHECK-NEXT:    vdup.32 q1, r12
 ; CHECK-NEXT:    vstrw.32 q0, [sp, #16] @ 16-byte Spill
 ; CHECK-NEXT:    vldrw.u32 q0, [r4]
 ; CHECK-NEXT:    adr r4, .LCPI18_3

 ; CHECK-NEXT:    bic r12, r12, #15
 ; CHECK-NEXT:    vldrw.u32 q0, [r4]
 ; CHECK-NEXT:    sub.w r12, r12, #16
 ; CHECK-NEXT:    mov.w lr, #1
 ; CHECK-NEXT:    adr r4, .LCPI19_1
 ; CHECK-NEXT:    vmov.i8 q2, #0x0
 ; CHECK-NEXT:    add.w lr, lr, r12, lsr #4
 ; CHECK-NEXT:    sub.w r12, r3, #1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vstrw.32 q0, [sp, #32] @ 16-byte Spill
 ; CHECK-NEXT:    vldrw.u32 q0, [r4]
 ; CHECK-NEXT:    adr r4, .LCPI19_2
 ; CHECK-NEXT:    movs r3, #0
 ; CHECK-NEXT:    vdup.32 q1, r12
 ; CHECK-NEXT:    vstrw.32 q0, [sp, #16] @ 16-byte Spill
 ; CHECK-NEXT:    vldrw.u32 q0, [r4]
 ; CHECK-NEXT:    adr r4, .LCPI19_3

 ; CHECK-NEXT:  .LBB20_3: @ %vector.ph
 ; CHECK-NEXT:    bic r5, r3, #7
 ; CHECK-NEXT:    movs r4, #1
 ; CHECK-NEXT:    sub.w r6, r5, #8
 ; CHECK-NEXT:    add.w r12, r0, r5
 ; CHECK-NEXT:    add.w lr, r4, r6, lsr #3
 ; CHECK-NEXT:    adds r4, r2, r5
 ; CHECK-NEXT:    adds r6, r1, r5
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB20_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrb.u16 q0, [r0], #8
 ; CHECK-NEXT:    vldrb.u16 q1, [r1], #8
 ; CHECK-NEXT:    vmul.i16 q0, q1, q0
 ; CHECK-NEXT:    vqshrnb.u16 q0, q0, #7
 ; CHECK-NEXT:    vstrb.16 q0, [r2], #8
 ; CHECK-NEXT:    le lr, .LBB20_4
 ; CHECK-NEXT:  @ %bb.5: @ %middle.block
 ; CHECK-NEXT:    cmp r5, r3
 ; CHECK-NEXT:    it eq
 ; CHECK-NEXT:    popeq {r4, r5, r6, pc}
 ; CHECK-NEXT:  .LBB20_6: @ %for.body.preheader23
 ; CHECK-NEXT:    sub.w lr, r3, r5
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB20_7: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldrb r0, [r12], #1
 ; CHECK-NEXT:    ldrb r1, [r6], #1
 ; CHECK-NEXT:    muls r0, r1, r0
 ; CHECK-NEXT:    lsrs r1, r0, #7
 ; CHECK-NEXT:    cmp r1, #255
 ; CHECK-NEXT:    mov.w r1, #255

 ; CHECK-NEXT:  .LBB21_3: @ %vector.ph
 ; CHECK-NEXT:    bic r5, r3, #15
 ; CHECK-NEXT:    movs r4, #1
 ; CHECK-NEXT:    sub.w r6, r5, #16
 ; CHECK-NEXT:    add.w r12, r0, r5
 ; CHECK-NEXT:    add.w lr, r4, r6, lsr #4
 ; CHECK-NEXT:    adds r4, r2, r5
 ; CHECK-NEXT:    adds r6, r1, r5
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB21_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrb.u16 q0, [r0, #8]
 ; CHECK-NEXT:    vldrb.u16 q1, [r1, #8]
 ; CHECK-NEXT:    vmul.i16 q0, q1, q0
 ; CHECK-NEXT:    vldrb.u16 q1, [r1], #16
 ; CHECK-NEXT:    vqshrnb.u16 q0, q0, #7
 ; CHECK-NEXT:    vmovlb.u8 q0, q0
 ; CHECK-NEXT:    vstrb.16 q0, [r2, #8]
 ; CHECK-NEXT:    vldrb.u16 q0, [r0], #16
 ; CHECK-NEXT:    vmul.i16 q0, q1, q0
 ; CHECK-NEXT:    vqshrnb.u16 q0, q0, #7
 ; CHECK-NEXT:    vmovlb.u8 q0, q0
 ; CHECK-NEXT:    vstrb.16 q0, [r2], #16
 ; CHECK-NEXT:    le lr, .LBB21_4
 ; CHECK-NEXT:  @ %bb.5: @ %middle.block
 ; CHECK-NEXT:    cmp r5, r3
 ; CHECK-NEXT:    it eq
 ; CHECK-NEXT:    popeq {r4, r5, r6, pc}
 ; CHECK-NEXT:  .LBB21_6: @ %for.body.preheader23
 ; CHECK-NEXT:    sub.w lr, r3, r5
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB21_7: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldrb r0, [r12], #1
 ; CHECK-NEXT:    ldrb r1, [r6], #1
 ; CHECK-NEXT:    muls r0, r1, r0
 ; CHECK-NEXT:    lsrs r1, r0, #7
 ; CHECK-NEXT:    cmp r1, #255
 ; CHECK-NEXT:    mov.w r1, #255

llvm/test/CodeGen/Thumb2/mve-shifts-scalar.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -O3 -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+mve %s --verify-machineinstrs -o - | FileCheck %s
 
 define dso_local arm_aapcs_vfpcc void @sink_shl_i32(i32* nocapture readonly %in, i32* noalias nocapture %out, i32 %shift, i32 %N) {
 ; CHECK-LABEL: sink_shl_i32:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    bic r3, r3, #3
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB0_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r0], #16
 ; CHECK-NEXT:    vshl.u32 q0, r2
 ; CHECK-NEXT:    vstrb.8 q0, [r1], #16
 ; CHECK-NEXT:    le lr, .LBB0_1
 ; CHECK-NEXT:  @ %bb.2: @ %exit
 ; CHECK-NEXT:    pop {r7, pc}

 ; CHECK-LABEL: sink_shl_i16:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    bic r3, r3, #3
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB1_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r0], #8
 ; CHECK-NEXT:    vshl.u16 q0, r2
 ; CHECK-NEXT:    vstrb.8 q0, [r1], #8
 ; CHECK-NEXT:    le lr, .LBB1_1
 ; CHECK-NEXT:  @ %bb.2: @ %exit
 ; CHECK-NEXT:    pop {r7, pc}

 ; CHECK-LABEL: sink_shl_i8:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    bic r3, r3, #3
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB2_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r0], #4
 ; CHECK-NEXT:    vshl.u8 q0, r2
 ; CHECK-NEXT:    vstrb.8 q0, [r1], #4
 ; CHECK-NEXT:    le lr, .LBB2_1
 ; CHECK-NEXT:  @ %bb.2: @ %exit
 ; CHECK-NEXT:    pop {r7, pc}

 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    bic r3, r3, #3
 ; CHECK-NEXT:    rsbs r2, r2, #0
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB3_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r0], #16
 ; CHECK-NEXT:    vshl.u32 q0, r2
 ; CHECK-NEXT:    vstrb.8 q0, [r1], #16
 ; CHECK-NEXT:    le lr, .LBB3_1
 ; CHECK-NEXT:  @ %bb.2: @ %exit
 ; CHECK-NEXT:    pop {r7, pc}

 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    bic r3, r3, #3
 ; CHECK-NEXT:    rsbs r2, r2, #0
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB4_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r0], #8
 ; CHECK-NEXT:    vshl.u16 q0, r2
 ; CHECK-NEXT:    vstrb.8 q0, [r1], #8
 ; CHECK-NEXT:    le lr, .LBB4_1
 ; CHECK-NEXT:  @ %bb.2: @ %exit
 ; CHECK-NEXT:    pop {r7, pc}

 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    bic r3, r3, #3
 ; CHECK-NEXT:    rsbs r2, r2, #0
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB5_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r0], #4
 ; CHECK-NEXT:    vshl.u8 q0, r2
 ; CHECK-NEXT:    vstrb.8 q0, [r1], #4
 ; CHECK-NEXT:    le lr, .LBB5_1
 ; CHECK-NEXT:  @ %bb.2: @ %exit
 ; CHECK-NEXT:    pop {r7, pc}

 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    bic r3, r3, #3
 ; CHECK-NEXT:    rsbs r2, r2, #0
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB6_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r0], #16
 ; CHECK-NEXT:    vshl.s32 q0, r2
 ; CHECK-NEXT:    vstrb.8 q0, [r1], #16
 ; CHECK-NEXT:    le lr, .LBB6_1
 ; CHECK-NEXT:  @ %bb.2: @ %exit
 ; CHECK-NEXT:    pop {r7, pc}

 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    bic r3, r3, #3
 ; CHECK-NEXT:    rsbs r2, r2, #0
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB7_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r0], #8
 ; CHECK-NEXT:    vshl.s16 q0, r2
 ; CHECK-NEXT:    vstrb.8 q0, [r1], #8
 ; CHECK-NEXT:    le lr, .LBB7_1
 ; CHECK-NEXT:  @ %bb.2: @ %exit
 ; CHECK-NEXT:    pop {r7, pc}

 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    bic r3, r3, #3
 ; CHECK-NEXT:    rsbs r2, r2, #0
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB8_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r0], #4
 ; CHECK-NEXT:    vshl.s8 q0, r2
 ; CHECK-NEXT:    vstrb.8 q0, [r1], #4
 ; CHECK-NEXT:    le lr, .LBB8_1
 ; CHECK-NEXT:  @ %bb.2: @ %exit
 ; CHECK-NEXT:    pop {r7, pc}

llvm/test/CodeGen/Thumb2/mve-vabdus.ll

 }
 
 define void @vabd_loop_s8(i8* nocapture readonly %x, i8* nocapture readonly %y, i8* noalias nocapture %z, i32 %n) {
 ; CHECK-LABEL: vabd_loop_s8:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #64
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB6_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrb.s32 q0, [r1, #12]
 ; CHECK-NEXT:    vldrb.s32 q1, [r0, #12]
 ; CHECK-NEXT:    vsub.i32 q0, q1, q0
 ; CHECK-NEXT:    vldrb.s32 q1, [r0, #8]
 ; CHECK-NEXT:    vabs.s32 q0, q0
 ; CHECK-NEXT:    vstrb.32 q0, [r2, #12]

 }
 
 define void @vabd_loop_s16(i16* nocapture readonly %x, i16* nocapture readonly %y, i16* noalias nocapture %z, i32 %n) {
 ; CHECK-LABEL: vabd_loop_s16:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #128
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB7_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.s32 q0, [r1, #8]
 ; CHECK-NEXT:    vldrh.s32 q1, [r0, #8]
 ; CHECK-NEXT:    vsub.i32 q0, q1, q0
 ; CHECK-NEXT:    vldrh.s32 q1, [r0], #16
 ; CHECK-NEXT:    vabs.s32 q0, q0
 ; CHECK-NEXT:    vstrh.32 q0, [r2, #8]

 ; CHECK-NEXT:    .save {r4, r5, r6, r7, r8, r9, r10, r11, lr}
 ; CHECK-NEXT:    push.w {r4, r5, r6, r7, r8, r9, r10, r11, lr}
 ; CHECK-NEXT:    .pad #4
 ; CHECK-NEXT:    sub sp, #4
 ; CHECK-NEXT:    .vsave {d8, d9}
 ; CHECK-NEXT:    vpush {d8, d9}
 ; CHECK-NEXT:    mov.w lr, #256
 ; CHECK-NEXT:    mov.w r12, #1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:  .LBB8_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q1, [r0], #16
 ; CHECK-NEXT:    vldrw.u32 q2, [r1], #16
 ; CHECK-NEXT:    vmov.f32 s12, s4
 ; CHECK-NEXT:    vmov.f32 s16, s8
 ; CHECK-NEXT:    vmov.f32 s14, s5

 }
 
 define void @vabd_loop_u8(i8* nocapture readonly %x, i8* nocapture readonly %y, i8* noalias nocapture %z, i32 %n) {
 ; CHECK-LABEL: vabd_loop_u8:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #64
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB9_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrb.u32 q0, [r1, #12]
 ; CHECK-NEXT:    vldrb.u32 q1, [r0, #12]
 ; CHECK-NEXT:    vsub.i32 q0, q1, q0
 ; CHECK-NEXT:    vldrb.u32 q1, [r0, #8]
 ; CHECK-NEXT:    vabs.s32 q0, q0
 ; CHECK-NEXT:    vstrb.32 q0, [r2, #12]

 }
 
 define void @vabd_loop_u16(i16* nocapture readonly %x, i16* nocapture readonly %y, i16* noalias nocapture %z, i32 %n) {
 ; CHECK-LABEL: vabd_loop_u16:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #128
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB10_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.u32 q0, [r1, #8]
 ; CHECK-NEXT:    vldrh.u32 q1, [r0, #8]
 ; CHECK-NEXT:    vsub.i32 q0, q1, q0
 ; CHECK-NEXT:    vldrh.u32 q1, [r0], #16
 ; CHECK-NEXT:    vabs.s32 q0, q0
 ; CHECK-NEXT:    vstrh.32 q0, [r2, #8]

 ; CHECK-NEXT:    .save {r4, r5, r6, r7, r8, r9, r10, r11, lr}
 ; CHECK-NEXT:    push.w {r4, r5, r6, r7, r8, r9, r10, r11, lr}
 ; CHECK-NEXT:    .pad #4
 ; CHECK-NEXT:    sub sp, #4
 ; CHECK-NEXT:    .vsave {d8, d9, d10, d11}
 ; CHECK-NEXT:    vpush {d8, d9, d10, d11}
 ; CHECK-NEXT:    mov.w lr, #256
 ; CHECK-NEXT:    vmov.i64 q0, #0xffffffff
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vmov.i32 q1, #0x0
 ; CHECK-NEXT:  .LBB11_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q2, [r1], #16
 ; CHECK-NEXT:    vmov.f32 s12, s8
 ; CHECK-NEXT:    vmov.f32 s14, s9
 ; CHECK-NEXT:    vand q4, q3, q0
 ; CHECK-NEXT:    vldrw.u32 q3, [r0], #16

llvm/test/CodeGen/Thumb2/mve-vecreduce-loops.ll

 ; CHECK-NEXT:    movs r0, #0
 ; CHECK-NEXT:    b .LBB0_9
 ; CHECK-NEXT:  .LBB0_4: @ %vector.ph
 ; CHECK-NEXT:    bic r3, r1, #3
 ; CHECK-NEXT:    movs r2, #1
 ; CHECK-NEXT:    subs r0, r3, #4
 ; CHECK-NEXT:    add.w lr, r2, r0, lsr #2
 ; CHECK-NEXT:    movs r0, #0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    mov r2, r12
 ; CHECK-NEXT:  .LBB0_5: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r2], #16
 ; CHECK-NEXT:    vaddva.u32 r0, q0
 ; CHECK-NEXT:    le lr, .LBB0_5
 ; CHECK-NEXT:  @ %bb.6: @ %middle.block
 ; CHECK-NEXT:    cmp r3, r1
 ; CHECK-NEXT:    it eq
 ; CHECK-NEXT:    popeq {r7, pc}
 ; CHECK-NEXT:  .LBB0_7: @ %for.body.preheader1
 ; CHECK-NEXT:    sub.w lr, r1, r3
 ; CHECK-NEXT:    add.w r2, r12, r3, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB0_8: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldr r1, [r2], #4
 ; CHECK-NEXT:    add r0, r1
 ; CHECK-NEXT:    le lr, .LBB0_8
 ; CHECK-NEXT:  .LBB0_9: @ %for.cond.cleanup
 ; CHECK-NEXT:    pop {r7, pc}
 entry:

 ; CHECK-NEXT:    mov.w r12, #0
 ; CHECK-NEXT:    b .LBB1_6
 ; CHECK-NEXT:  .LBB1_3: @ %vector.ph
 ; CHECK-NEXT:    bic r12, r1, #3
 ; CHECK-NEXT:    vmov.i32 q0, #0x1
 ; CHECK-NEXT:    sub.w r3, r12, #4
 ; CHECK-NEXT:    add.w lr, r2, r3, lsr #2
 ; CHECK-NEXT:    mov r2, r0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB1_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q1, [r2], #16
 ; CHECK-NEXT:    vmul.i32 q0, q1, q0
 ; CHECK-NEXT:    le lr, .LBB1_4
 ; CHECK-NEXT:  @ %bb.5: @ %middle.block
 ; CHECK-NEXT:    vmov r2, s3
 ; CHECK-NEXT:    cmp r12, r1
 ; CHECK-NEXT:    vmov r3, s2
 ; CHECK-NEXT:    mul lr, r3, r2
 ; CHECK-NEXT:    vmov r3, s1
 ; CHECK-NEXT:    vmov r2, s0
 ; CHECK-NEXT:    mul r2, r3, r2
 ; CHECK-NEXT:    mul r2, r2, lr
 ; CHECK-NEXT:    beq .LBB1_8
 ; CHECK-NEXT:  .LBB1_6: @ %for.body.preheader1
 ; CHECK-NEXT:    sub.w lr, r1, r12
 ; CHECK-NEXT:    add.w r0, r0, r12, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB1_7: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldr r1, [r0], #4
 ; CHECK-NEXT:    muls r2, r1, r2
 ; CHECK-NEXT:    le lr, .LBB1_7
 ; CHECK-NEXT:  .LBB1_8: @ %for.cond.cleanup
 ; CHECK-NEXT:    mov r0, r2
 ; CHECK-NEXT:    pop {r7, pc}

 ; CHECK-NEXT:    b .LBB2_9
 ; CHECK-NEXT:  .LBB2_4: @ %vector.ph
 ; CHECK-NEXT:    bic r3, r1, #3
 ; CHECK-NEXT:    movs r2, #1
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    vmov.i8 q0, #0xff
 ; CHECK-NEXT:    add.w lr, r2, r12, lsr #2
 ; CHECK-NEXT:    mov r2, r0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB2_5: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q1, [r2], #16
 ; CHECK-NEXT:    vand q0, q1, q0
 ; CHECK-NEXT:    le lr, .LBB2_5
 ; CHECK-NEXT:  @ %bb.6: @ %middle.block
 ; CHECK-NEXT:    vmov r12, s3
 ; CHECK-NEXT:    cmp r3, r1
 ; CHECK-NEXT:    vmov r2, s2
 ; CHECK-NEXT:    vmov lr, s1
 ; CHECK-NEXT:    and.w r12, r12, r2
 ; CHECK-NEXT:    vmov r2, s0
 ; CHECK-NEXT:    and.w r2, r2, lr
 ; CHECK-NEXT:    and.w r2, r2, r12
 ; CHECK-NEXT:    beq .LBB2_9
 ; CHECK-NEXT:  .LBB2_7: @ %for.body.preheader1
 ; CHECK-NEXT:    sub.w lr, r1, r3
 ; CHECK-NEXT:    add.w r0, r0, r3, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB2_8: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldr r1, [r0], #4
 ; CHECK-NEXT:    ands r2, r1
 ; CHECK-NEXT:    le lr, .LBB2_8
 ; CHECK-NEXT:  .LBB2_9: @ %for.cond.cleanup
 ; CHECK-NEXT:    mov r0, r2
 ; CHECK-NEXT:    pop {r7, pc}

 ; CHECK-NEXT:    b .LBB3_9
 ; CHECK-NEXT:  .LBB3_4: @ %vector.ph
 ; CHECK-NEXT:    bic r3, r1, #3
 ; CHECK-NEXT:    movs r2, #1
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    add.w lr, r2, r12, lsr #2
 ; CHECK-NEXT:    mov r2, r0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB3_5: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q1, [r2], #16
 ; CHECK-NEXT:    vorr q0, q1, q0
 ; CHECK-NEXT:    le lr, .LBB3_5
 ; CHECK-NEXT:  @ %bb.6: @ %middle.block
 ; CHECK-NEXT:    vmov r12, s3
 ; CHECK-NEXT:    cmp r3, r1
 ; CHECK-NEXT:    vmov r2, s2
 ; CHECK-NEXT:    vmov lr, s1
 ; CHECK-NEXT:    orr.w r12, r12, r2
 ; CHECK-NEXT:    vmov r2, s0
 ; CHECK-NEXT:    orr.w r2, r2, lr
 ; CHECK-NEXT:    orr.w r2, r2, r12
 ; CHECK-NEXT:    beq .LBB3_9
 ; CHECK-NEXT:  .LBB3_7: @ %for.body.preheader1
 ; CHECK-NEXT:    sub.w lr, r1, r3
 ; CHECK-NEXT:    add.w r0, r0, r3, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB3_8: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldr r1, [r0], #4
 ; CHECK-NEXT:    orrs r2, r1
 ; CHECK-NEXT:    le lr, .LBB3_8
 ; CHECK-NEXT:  .LBB3_9: @ %for.cond.cleanup
 ; CHECK-NEXT:    mov r0, r2
 ; CHECK-NEXT:    pop {r7, pc}

 ; CHECK-NEXT:    b .LBB4_9
 ; CHECK-NEXT:  .LBB4_4: @ %vector.ph
 ; CHECK-NEXT:    bic r3, r1, #3
 ; CHECK-NEXT:    movs r2, #1
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    add.w lr, r2, r12, lsr #2
 ; CHECK-NEXT:    mov r2, r0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB4_5: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q1, [r2], #16
 ; CHECK-NEXT:    veor q0, q1, q0
 ; CHECK-NEXT:    le lr, .LBB4_5
 ; CHECK-NEXT:  @ %bb.6: @ %middle.block
 ; CHECK-NEXT:    vmov r12, s3
 ; CHECK-NEXT:    cmp r3, r1
 ; CHECK-NEXT:    vmov r2, s2
 ; CHECK-NEXT:    vmov lr, s1
 ; CHECK-NEXT:    eor.w r12, r12, r2
 ; CHECK-NEXT:    vmov r2, s0
 ; CHECK-NEXT:    eor.w r2, r2, lr
 ; CHECK-NEXT:    eor.w r2, r2, r12
 ; CHECK-NEXT:    beq .LBB4_9
 ; CHECK-NEXT:  .LBB4_7: @ %for.body.preheader1
 ; CHECK-NEXT:    sub.w lr, r1, r3
 ; CHECK-NEXT:    add.w r0, r0, r3, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB4_8: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldr r1, [r0], #4
 ; CHECK-NEXT:    eors r2, r1
 ; CHECK-NEXT:    le lr, .LBB4_8
 ; CHECK-NEXT:  .LBB4_9: @ %for.cond.cleanup
 ; CHECK-NEXT:    mov r0, r2
 ; CHECK-NEXT:    pop {r7, pc}

 ; CHECK-NEXT:    b .LBB5_9
 ; CHECK-NEXT:  .LBB5_4: @ %vector.ph
 ; CHECK-NEXT:    bic r2, r1, #3
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    sub.w r12, r2, #4
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
 ; CHECK-NEXT:    mov r3, r0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB5_5: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q1, [r3], #16
 ; CHECK-NEXT:    vadd.f32 q0, q1, q0
 ; CHECK-NEXT:    le lr, .LBB5_5
 ; CHECK-NEXT:  @ %bb.6: @ %middle.block
 ; CHECK-NEXT:    vadd.f32 s4, s2, s3
 ; CHECK-NEXT:    cmp r2, r1
 ; CHECK-NEXT:    vadd.f32 s0, s0, s1
 ; CHECK-NEXT:    vadd.f32 s0, s0, s4
 ; CHECK-NEXT:    beq .LBB5_9
 ; CHECK-NEXT:  .LBB5_7: @ %for.body.preheader1
 ; CHECK-NEXT:    sub.w lr, r1, r2
 ; CHECK-NEXT:    add.w r0, r0, r2, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB5_8: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldr s2, [r0]
 ; CHECK-NEXT:    adds r0, #4
 ; CHECK-NEXT:    vadd.f32 s0, s2, s0
 ; CHECK-NEXT:    le lr, .LBB5_8
 ; CHECK-NEXT:  .LBB5_9: @ %for.cond.cleanup
 ; CHECK-NEXT:    vmov r0, s0

 ; CHECK-NEXT:    b .LBB6_9
 ; CHECK-NEXT:  .LBB6_4: @ %vector.ph
 ; CHECK-NEXT:    bic r2, r1, #3
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    sub.w r12, r2, #4
 ; CHECK-NEXT:    vmov.f32 q0, #1.000000e+00
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
 ; CHECK-NEXT:    mov r3, r0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB6_5: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q1, [r3], #16
 ; CHECK-NEXT:    vmul.f32 q0, q1, q0
 ; CHECK-NEXT:    le lr, .LBB6_5
 ; CHECK-NEXT:  @ %bb.6: @ %middle.block
 ; CHECK-NEXT:    vmul.f32 s4, s2, s3
 ; CHECK-NEXT:    cmp r2, r1
 ; CHECK-NEXT:    vmul.f32 s0, s0, s1
 ; CHECK-NEXT:    vmul.f32 s0, s0, s4
 ; CHECK-NEXT:    beq .LBB6_9
 ; CHECK-NEXT:  .LBB6_7: @ %for.body.preheader1
 ; CHECK-NEXT:    sub.w lr, r1, r2
 ; CHECK-NEXT:    add.w r0, r0, r2, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB6_8: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldr s2, [r0]
 ; CHECK-NEXT:    adds r0, #4
 ; CHECK-NEXT:    vmul.f32 s0, s2, s0
 ; CHECK-NEXT:    le lr, .LBB6_8
 ; CHECK-NEXT:  .LBB6_9: @ %for.cond.cleanup
 ; CHECK-NEXT:    vmov r0, s0

 ; CHECK-NEXT:    b .LBB7_9
 ; CHECK-NEXT:  .LBB7_4: @ %vector.ph
 ; CHECK-NEXT:    bic r3, r1, #3
 ; CHECK-NEXT:    movs r2, #1
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    vmvn.i32 q0, #0x80000000
 ; CHECK-NEXT:    add.w lr, r2, r12, lsr #2
 ; CHECK-NEXT:    mov r2, r0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB7_5: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q1, [r2], #16
 ; CHECK-NEXT:    vmin.s32 q0, q0, q1
 ; CHECK-NEXT:    le lr, .LBB7_5
 ; CHECK-NEXT:  @ %bb.6: @ %middle.block
 ; CHECK-NEXT:    mvn r2, #-2147483648
 ; CHECK-NEXT:    cmp r3, r1
 ; CHECK-NEXT:    vminv.s32 r2, q0
 ; CHECK-NEXT:    beq .LBB7_9
 ; CHECK-NEXT:  .LBB7_7: @ %for.body.preheader1
 ; CHECK-NEXT:    sub.w lr, r1, r3
 ; CHECK-NEXT:    add.w r0, r0, r3, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB7_8: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldr r1, [r0], #4
 ; CHECK-NEXT:    cmp r2, r1
 ; CHECK-NEXT:    csel r2, r2, r1, lt
 ; CHECK-NEXT:    le lr, .LBB7_8
 ; CHECK-NEXT:  .LBB7_9: @ %for.cond.cleanup
 ; CHECK-NEXT:    mov r0, r2

 ; CHECK-NEXT:    mvn r0, #-2147483648
 ; CHECK-NEXT:    b .LBB8_9
 ; CHECK-NEXT:  .LBB8_4: @ %vector.ph
 ; CHECK-NEXT:    bic r3, r1, #3
 ; CHECK-NEXT:    movs r2, #1
 ; CHECK-NEXT:    subs r0, r3, #4
 ; CHECK-NEXT:    add.w lr, r2, r0, lsr #2
 ; CHECK-NEXT:    mvn r0, #-2147483648
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    mov r2, r12
 ; CHECK-NEXT:  .LBB8_5: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r2], #16
 ; CHECK-NEXT:    vminv.s32 r0, q0
 ; CHECK-NEXT:    le lr, .LBB8_5
 ; CHECK-NEXT:  @ %bb.6: @ %middle.block
 ; CHECK-NEXT:    cmp r3, r1
 ; CHECK-NEXT:    it eq
 ; CHECK-NEXT:    popeq {r7, pc}
 ; CHECK-NEXT:  .LBB8_7: @ %for.body.preheader1
 ; CHECK-NEXT:    sub.w lr, r1, r3
 ; CHECK-NEXT:    add.w r2, r12, r3, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB8_8: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldr r1, [r2], #4
 ; CHECK-NEXT:    cmp r0, r1
 ; CHECK-NEXT:    csel r0, r0, r1, lt
 ; CHECK-NEXT:    le lr, .LBB8_8
 ; CHECK-NEXT:  .LBB8_9: @ %for.cond.cleanup
 ; CHECK-NEXT:    pop {r7, pc}

 ; CHECK-NEXT:    b .LBB9_9
 ; CHECK-NEXT:  .LBB9_4: @ %vector.ph
 ; CHECK-NEXT:    bic r3, r1, #3
 ; CHECK-NEXT:    movs r2, #1
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    vmov.i32 q0, #0x80000000
 ; CHECK-NEXT:    add.w lr, r2, r12, lsr #2
 ; CHECK-NEXT:    mov r2, r0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB9_5: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q1, [r2], #16
 ; CHECK-NEXT:    vmax.s32 q0, q0, q1
 ; CHECK-NEXT:    le lr, .LBB9_5
 ; CHECK-NEXT:  @ %bb.6: @ %middle.block
 ; CHECK-NEXT:    mov.w r2, #-2147483648
 ; CHECK-NEXT:    cmp r3, r1
 ; CHECK-NEXT:    vmaxv.s32 r2, q0
 ; CHECK-NEXT:    beq .LBB9_9
 ; CHECK-NEXT:  .LBB9_7: @ %for.body.preheader1
 ; CHECK-NEXT:    sub.w lr, r1, r3
 ; CHECK-NEXT:    add.w r0, r0, r3, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB9_8: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldr r1, [r0], #4
 ; CHECK-NEXT:    cmp r2, r1
 ; CHECK-NEXT:    csel r2, r2, r1, gt
 ; CHECK-NEXT:    le lr, .LBB9_8
 ; CHECK-NEXT:  .LBB9_9: @ %for.cond.cleanup
 ; CHECK-NEXT:    mov r0, r2

 ; CHECK-NEXT:    mov.w r0, #-2147483648
 ; CHECK-NEXT:    b .LBB10_9
 ; CHECK-NEXT:  .LBB10_4: @ %vector.ph
 ; CHECK-NEXT:    bic r3, r1, #3
 ; CHECK-NEXT:    movs r2, #1
 ; CHECK-NEXT:    subs r0, r3, #4
 ; CHECK-NEXT:    add.w lr, r2, r0, lsr #2
 ; CHECK-NEXT:    mov.w r0, #-2147483648
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    mov r2, r12
 ; CHECK-NEXT:  .LBB10_5: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r2], #16
 ; CHECK-NEXT:    vmaxv.s32 r0, q0
 ; CHECK-NEXT:    le lr, .LBB10_5
 ; CHECK-NEXT:  @ %bb.6: @ %middle.block
 ; CHECK-NEXT:    cmp r3, r1
 ; CHECK-NEXT:    it eq
 ; CHECK-NEXT:    popeq {r7, pc}
 ; CHECK-NEXT:  .LBB10_7: @ %for.body.preheader1
 ; CHECK-NEXT:    sub.w lr, r1, r3
 ; CHECK-NEXT:    add.w r2, r12, r3, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB10_8: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldr r1, [r2], #4
 ; CHECK-NEXT:    cmp r0, r1
 ; CHECK-NEXT:    csel r0, r0, r1, gt
 ; CHECK-NEXT:    le lr, .LBB10_8
 ; CHECK-NEXT:  .LBB10_9: @ %for.cond.cleanup
 ; CHECK-NEXT:    pop {r7, pc}

 ; CHECK-NEXT:    b .LBB11_9
 ; CHECK-NEXT:  .LBB11_4: @ %vector.ph
 ; CHECK-NEXT:    bic r3, r1, #3
 ; CHECK-NEXT:    movs r2, #1
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    vmov.i8 q0, #0xff
 ; CHECK-NEXT:    add.w lr, r2, r12, lsr #2
 ; CHECK-NEXT:    mov r2, r0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB11_5: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q1, [r2], #16
 ; CHECK-NEXT:    vmin.u32 q0, q0, q1
 ; CHECK-NEXT:    le lr, .LBB11_5
 ; CHECK-NEXT:  @ %bb.6: @ %middle.block
 ; CHECK-NEXT:    mov.w r2, #-1
 ; CHECK-NEXT:    cmp r3, r1
 ; CHECK-NEXT:    vminv.u32 r2, q0
 ; CHECK-NEXT:    beq .LBB11_9
 ; CHECK-NEXT:  .LBB11_7: @ %for.body.preheader1
 ; CHECK-NEXT:    sub.w lr, r1, r3
 ; CHECK-NEXT:    add.w r0, r0, r3, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB11_8: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldr r1, [r0], #4
 ; CHECK-NEXT:    cmp r2, r1
 ; CHECK-NEXT:    csel r2, r2, r1, lo
 ; CHECK-NEXT:    le lr, .LBB11_8
 ; CHECK-NEXT:  .LBB11_9: @ %for.cond.cleanup
 ; CHECK-NEXT:    mov r0, r2

 ; CHECK-NEXT:    mov.w r0, #-1
 ; CHECK-NEXT:    b .LBB12_9
 ; CHECK-NEXT:  .LBB12_4: @ %vector.ph
 ; CHECK-NEXT:    bic r3, r1, #3
 ; CHECK-NEXT:    movs r2, #1
 ; CHECK-NEXT:    subs r0, r3, #4
 ; CHECK-NEXT:    add.w lr, r2, r0, lsr #2
 ; CHECK-NEXT:    mov.w r0, #-1
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    mov r2, r12
 ; CHECK-NEXT:  .LBB12_5: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r2], #16
 ; CHECK-NEXT:    vminv.u32 r0, q0
 ; CHECK-NEXT:    le lr, .LBB12_5
 ; CHECK-NEXT:  @ %bb.6: @ %middle.block
 ; CHECK-NEXT:    cmp r3, r1
 ; CHECK-NEXT:    it eq
 ; CHECK-NEXT:    popeq {r7, pc}
 ; CHECK-NEXT:  .LBB12_7: @ %for.body.preheader1
 ; CHECK-NEXT:    sub.w lr, r1, r3
 ; CHECK-NEXT:    add.w r2, r12, r3, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB12_8: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldr r1, [r2], #4
 ; CHECK-NEXT:    cmp r0, r1
 ; CHECK-NEXT:    csel r0, r0, r1, hi
 ; CHECK-NEXT:    le lr, .LBB12_8
 ; CHECK-NEXT:  .LBB12_9: @ %for.cond.cleanup
 ; CHECK-NEXT:    pop {r7, pc}

 ; CHECK-NEXT:    b .LBB13_9
 ; CHECK-NEXT:  .LBB13_4: @ %vector.ph
 ; CHECK-NEXT:    bic r3, r1, #3
 ; CHECK-NEXT:    movs r2, #1
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    add.w lr, r2, r12, lsr #2
 ; CHECK-NEXT:    mov r2, r0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB13_5: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q1, [r2], #16
 ; CHECK-NEXT:    vmax.u32 q0, q0, q1
 ; CHECK-NEXT:    le lr, .LBB13_5
 ; CHECK-NEXT:  @ %bb.6: @ %middle.block
 ; CHECK-NEXT:    movs r2, #0
 ; CHECK-NEXT:    cmp r3, r1
 ; CHECK-NEXT:    vmaxv.u32 r2, q0
 ; CHECK-NEXT:    beq .LBB13_9
 ; CHECK-NEXT:  .LBB13_7: @ %for.body.preheader1
 ; CHECK-NEXT:    sub.w lr, r1, r3
 ; CHECK-NEXT:    add.w r0, r0, r3, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB13_8: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldr r1, [r0], #4
 ; CHECK-NEXT:    cmp r2, r1
 ; CHECK-NEXT:    csel r2, r2, r1, hi
 ; CHECK-NEXT:    le lr, .LBB13_8
 ; CHECK-NEXT:  .LBB13_9: @ %for.cond.cleanup
 ; CHECK-NEXT:    mov r0, r2

 ; CHECK-NEXT:    movs r0, #0
 ; CHECK-NEXT:    b .LBB14_9
 ; CHECK-NEXT:  .LBB14_4: @ %vector.ph
 ; CHECK-NEXT:    bic r3, r1, #3
 ; CHECK-NEXT:    movs r2, #1
 ; CHECK-NEXT:    subs r0, r3, #4
 ; CHECK-NEXT:    add.w lr, r2, r0, lsr #2
 ; CHECK-NEXT:    movs r0, #0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    mov r2, r12
 ; CHECK-NEXT:  .LBB14_5: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r2], #16
 ; CHECK-NEXT:    vmaxv.u32 r0, q0
 ; CHECK-NEXT:    le lr, .LBB14_5
 ; CHECK-NEXT:  @ %bb.6: @ %middle.block
 ; CHECK-NEXT:    cmp r3, r1
 ; CHECK-NEXT:    it eq
 ; CHECK-NEXT:    popeq {r7, pc}
 ; CHECK-NEXT:  .LBB14_7: @ %for.body.preheader1
 ; CHECK-NEXT:    sub.w lr, r1, r3
 ; CHECK-NEXT:    add.w r2, r12, r3, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB14_8: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldr r1, [r2], #4
 ; CHECK-NEXT:    cmp r0, r1
 ; CHECK-NEXT:    csel r0, r0, r1, hi
 ; CHECK-NEXT:    le lr, .LBB14_8
 ; CHECK-NEXT:  .LBB14_9: @ %for.cond.cleanup
 ; CHECK-NEXT:    pop {r7, pc}

 ; CHECK-NEXT:    b .LBB15_9
 ; CHECK-NEXT:  .LBB15_4: @ %vector.ph
 ; CHECK-NEXT:    bic r2, r1, #3
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    sub.w r12, r2, #4
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
 ; CHECK-NEXT:    mov r3, r0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB15_5: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q1, [r3], #16
 ; CHECK-NEXT:    vcmp.f32 lt, q0, q1
 ; CHECK-NEXT:    vpsel q0, q0, q1
 ; CHECK-NEXT:    le lr, .LBB15_5
 ; CHECK-NEXT:  @ %bb.6: @ %middle.block
 ; CHECK-NEXT:    vminnm.f32 s4, s2, s3
 ; CHECK-NEXT:    vminnm.f32 s0, s0, s1
 ; CHECK-NEXT:    vminnm.f32 s0, s0, s4
 ; CHECK-NEXT:    cmp r2, r1
 ; CHECK-NEXT:    beq .LBB15_9
 ; CHECK-NEXT:  .LBB15_7: @ %for.body.preheader1
 ; CHECK-NEXT:    sub.w lr, r1, r2
 ; CHECK-NEXT:    add.w r0, r0, r2, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB15_8: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldmia r0!, {s2}
 ; CHECK-NEXT:    vcmp.f32 s0, s2
 ; CHECK-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-NEXT:    vselge.f32 s0, s2, s0
 ; CHECK-NEXT:    le lr, .LBB15_8
 ; CHECK-NEXT:  .LBB15_9: @ %for.cond.cleanup

 ; CHECK-NEXT:    b .LBB16_9
 ; CHECK-NEXT:  .LBB16_4: @ %vector.ph
 ; CHECK-NEXT:    bic r2, r1, #3
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    sub.w r12, r2, #4
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
 ; CHECK-NEXT:    mov r3, r0
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB16_5: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q1, [r3], #16
 ; CHECK-NEXT:    vcmp.f32 lt, q1, q0
 ; CHECK-NEXT:    vpsel q0, q0, q1
 ; CHECK-NEXT:    le lr, .LBB16_5
 ; CHECK-NEXT:  @ %bb.6: @ %middle.block
 ; CHECK-NEXT:    vmaxnm.f32 s4, s2, s3
 ; CHECK-NEXT:    vmaxnm.f32 s0, s0, s1
 ; CHECK-NEXT:    vmaxnm.f32 s0, s0, s4
 ; CHECK-NEXT:    cmp r2, r1
 ; CHECK-NEXT:    beq .LBB16_9
 ; CHECK-NEXT:  .LBB16_7: @ %for.body.preheader1
 ; CHECK-NEXT:    sub.w lr, r1, r2
 ; CHECK-NEXT:    add.w r0, r0, r2, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB16_8: @ %for.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldmia r0!, {s2}
 ; CHECK-NEXT:    vcmp.f32 s2, s0
 ; CHECK-NEXT:    vmrs APSR_nzcv, fpscr
 ; CHECK-NEXT:    vselge.f32 s0, s2, s0
 ; CHECK-NEXT:    le lr, .LBB16_8
 ; CHECK-NEXT:  .LBB16_9: @ %for.cond.cleanup

llvm/test/CodeGen/Thumb2/mve-vldshuffle.ll

 ; CHECK-NEXT:    bhi .LBB0_9
 ; CHECK-NEXT:  @ %bb.3: @ %vector.ph
 ; CHECK-NEXT:    bic r4, r2, #7
 ; CHECK-NEXT:    movs r5, #1
 ; CHECK-NEXT:    sub.w r3, r4, #8
 ; CHECK-NEXT:    add.w r12, r1, r4, lsl #1
 ; CHECK-NEXT:    add.w lr, r5, r3, lsr #3
 ; CHECK-NEXT:    add.w r3, r0, r4, lsl #2
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    and r5, r2, #7
 ; CHECK-NEXT:  .LBB0_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vld20.16 {q0, q1}, [r0]
 ; CHECK-NEXT:    vld21.16 {q0, q1}, [r0]!
 ; CHECK-NEXT:    vmul.f16 q2, q0, q0
 ; CHECK-NEXT:    vfma.f16 q2, q1, q1
 ; CHECK-NEXT:    vstrb.8 q2, [r1], #16

 ; CHECK-NEXT:    bhi .LBB1_9
 ; CHECK-NEXT:  @ %bb.3: @ %vector.ph
 ; CHECK-NEXT:    bic r4, r2, #3
 ; CHECK-NEXT:    movs r5, #1
 ; CHECK-NEXT:    subs r3, r4, #4
 ; CHECK-NEXT:    add.w r12, r1, r4, lsl #2
 ; CHECK-NEXT:    add.w lr, r5, r3, lsr #2
 ; CHECK-NEXT:    add.w r3, r0, r4, lsl #3
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    and r5, r2, #3
 ; CHECK-NEXT:  .LBB1_4: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vld20.32 {q0, q1}, [r0]
 ; CHECK-NEXT:    vld21.32 {q0, q1}, [r0]!
 ; CHECK-NEXT:    vmul.f32 q2, q0, q0
 ; CHECK-NEXT:    vfma.f32 q2, q1, q1
 ; CHECK-NEXT:    vstrb.8 q2, [r1], #16

llvm/test/CodeGen/Thumb2/mve-vldst4.ll

 ; CHECK-NEXT:    beq.w .LBB0_3
 ; CHECK-NEXT:  @ %bb.1: @ %vector.ph
 ; CHECK-NEXT:    mvn r3, #7
 ; CHECK-NEXT:    ldr r5, [sp, #160]
 ; CHECK-NEXT:    and.w r3, r3, r12, lsr #2
 ; CHECK-NEXT:    sub.w r12, r3, #8
 ; CHECK-NEXT:    movs r3, #1
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #3
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB0_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.u16 q5, [r0, #32]
 ; CHECK-NEXT:    vldrh.u16 q3, [r0, #48]
 ; CHECK-NEXT:    vldrh.u16 q7, [r0], #64
 ; CHECK-NEXT:    vmov r2, s20
 ; CHECK-NEXT:    vmovx.f16 s8, s12
 ; CHECK-NEXT:    vmov.16 q0[4], r2

llvm/test/CodeGen/Thumb2/mve-vqdmulh.ll

 
 
 define void @vqdmulh_loop_i8(i8* nocapture readonly %x, i8* nocapture readonly %y, i8* noalias nocapture %z, i32 %n) local_unnamed_addr #0 {
 ; CHECK-LABEL: vqdmulh_loop_i8:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #64
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB8_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrb.u8 q0, [r0], #16
 ; CHECK-NEXT:    vldrb.u8 q1, [r1], #16
 ; CHECK-NEXT:    vqdmulh.s8 q0, q1, q0
 ; CHECK-NEXT:    vstrb.8 q0, [r2], #16
 ; CHECK-NEXT:    le lr, .LBB8_1
 ; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup

 }
 
 define void @vqdmulh_loop_i16(i16* nocapture readonly %x, i16* nocapture readonly %y, i16* noalias nocapture %z, i32 %n) {
 ; CHECK-LABEL: vqdmulh_loop_i16:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #128
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB9_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrh.u16 q0, [r0], #16
 ; CHECK-NEXT:    vldrh.u16 q1, [r1], #16
 ; CHECK-NEXT:    vqdmulh.s16 q0, q1, q0
 ; CHECK-NEXT:    vstrb.8 q0, [r2], #16
 ; CHECK-NEXT:    le lr, .LBB9_1
 ; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup

 }
 
 define void @vqdmulh_loop_i32(i32* nocapture readonly %x, i32* nocapture readonly %y, i32* noalias nocapture %z, i32 %n) {
 ; CHECK-LABEL: vqdmulh_loop_i32:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    mov.w lr, #256
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB10_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [r0], #16
 ; CHECK-NEXT:    vldrw.u32 q1, [r1], #16
 ; CHECK-NEXT:    vqdmulh.s32 q0, q1, q0
 ; CHECK-NEXT:    vstrb.8 q0, [r2], #16
 ; CHECK-NEXT:    le lr, .LBB10_1
 ; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup

llvm/test/Transforms/HardwareLoops/ARM/calls-codegen.ll

 ; RUN: llc -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+lob,+mve.fp -disable-arm-loloops=true %s -o - | FileCheck %s --check-prefix=DISABLED
 ; RUN: llc -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+lob,+mve.fp %s -o - | FileCheck %s
 
 ; DISABLED-NOT: dls lr,
 
 ; CHECK-LABEL: test_target_specific:
 ; CHECK:        mov.w lr, #50
-; CHECK:        dls lr, lr
+; CHECK-NOT:    dls lr, lr
 ; CHECK-NOT:    mov lr,
 ; CHECK:      [[LOOP_HEADER:\.LBB[0-9_]+]]:
 ; CHECK:        le lr, [[LOOP_HEADER]]
 ; CHECK-NOT:    b .
 ; CHECK:      @ %exit
 
 define i32 @test_target_specific(i32* %a, i32* %b) {
 entry:
loop:
   %cmp = icmp ne i32 %count.next, 100
   br i1 %cmp, label %loop, label %exit
 exit:
   ret i32 %res
 }
 
 ; CHECK-LABEL: test_fabs:
 ; CHECK:        mov.w lr, #100
-; CHECK:        dls lr, lr
+; CHECK-NOT:    dls lr, lr
 ; CHECK-NOT:    mov lr,
 ; CHECK:      [[LOOP_HEADER:\.LBB[0-9_]+]]:
 ; CHECK-NOT:    bl
 ; CHECK:        le lr, [[LOOP_HEADER]]
 ; CHECK-NOT:    b .
 ; CHECK:      @ %exit
 
 define float @test_fabs(float* %a) {

llvm/test/Transforms/HardwareLoops/ARM/simple-do.ll

 ; CHECK: while.body:
 ; CHECK:   [[REM:%[^ ]+]] = phi i32 [ [[START]], %while.body.lr.ph ], [ [[LOOP_DEC:%[^ ]+]], %while.body ]
 ; CHECK:   [[LOOP_DEC]] = call i32 @llvm.loop.decrement.reg.i32(i32 [[REM]], i32 1)
 ; CHECK:   [[CMP:%[^ ]+]] = icmp ne i32 [[LOOP_DEC]], 0
 ; CHECK:   br i1 [[CMP]], label %while.body, label %while.end.loopexit
 
 ; CHECK-LLC:      do_inc2:
 ; CHECK-LLC-NOT:    mov lr,
-; CHECK-LLC:        dls lr, {{.*}}
+; CHECK-LLC:        add.w lr,
+; CHECK-LLC-NOT:    dls lr,
 ; CHECK-LLC-NOT:    mov lr,
 ; CHECK-LLC:      [[LOOP_HEADER:\.LBB[0-9._]+]]:
 ; CHECK-LLC:        le lr, [[LOOP_HEADER]]
 
 define i32 @do_inc2(i32 %n) {
 entry:
   %cmp7 = icmp sgt i32 %n, 0
   br i1 %cmp7, label %while.body.lr.ph, label %while.end

 
 ; CHECK: [[REM:%[^ ]+]] = phi i32 [ [[START]], %while.body.lr.ph ], [ [[LOOP_DEC:%[^ ]+]], %while.body ]
 ; CHECK: [[LOOP_DEC]] = call i32 @llvm.loop.decrement.reg.i32(i32 [[REM]], i32 1)
 ; CHECK: [[CMP:%[^ ]+]] = icmp ne i32 [[LOOP_DEC]], 0
 ; CHECK: br i1 [[CMP]], label %while.body, label %while.end.loopexit
 
 ; CHECK-LLC:      do_dec2
 ; CHECK-LLC-NOT:    mov lr,
-; CHECK-LLC:        dls lr, {{.*}}
+; CHECK-LLC:        add.w lr,
+; CHECK-LLC-NOT:    dls lr,
 ; CHECK-LLC-NOT:    mov lr,
 ; CHECK-LLC:      [[LOOP_HEADER:\.LBB[0-9_]+]]:
 ; CHECK-LLC:        le lr, [[LOOP_HEADER]]
 ; CHECK-LLC-NOT:    b .
 define i32 @do_dec2(i32 %n) {
 entry:
   %cmp6 = icmp sgt i32 %n, 0
   br i1 %cmp6, label %while.body.lr.ph, label %while.end

llvm/test/Transforms/HardwareLoops/ARM/structure.ll

 ; CHECK: call i32 @llvm.start.loop.iterations.i32(i32 %N)
 ; CHECK: call i32 @llvm.loop.decrement.reg.i32(
 
 ; CHECK-UNROLL-LABEL: unroll_dec_int:
 ; CHECK-UNROLL:         wls lr, {{.*}}, [[PROLOGUE_EXIT:.LBB[0-9_]+]]
 ; CHECK-UNROLL-NEXT: [[PROLOGUE:.LBB[0-9_]+]]:
 ; CHECK-UNROLL:         le lr, [[PROLOGUE]]
 ; CHECK-UNROLL-NEXT: [[PROLOGUE_EXIT:.LBB[0-9_]+]]:
-; CHECK-UNROLL:         dls lr, lr
 ; CHECK-UNROLL:      [[BODY:.LBB[0-9_]+]]:
 ; CHECK-UNROLL:         le lr, [[BODY]]
 ; CHECK-UNROLL-NOT:     b
 ; CHECK-UNROLL:         pop
 define void @unroll_dec_int(i32* nocapture %a, i32* nocapture readonly %b, i32* nocapture readonly %c, i32 %N) {
 entry:
   %cmp8 = icmp sgt i32 %N, 0
   br i1 %cmp8, label %for.body, label %for.cond.cleanup