diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h b/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h
--- a/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h
@@ -66,6 +66,7 @@
 
 public:
   VPBuilder() = default;
+  VPBuilder(VPBasicBlock *InsertBB) { setInsertPoint(InsertBB); }
 
   /// Clear the insertion point: created instructions will not be inserted into
   /// a block.
@@ -143,6 +144,13 @@
     return createInstruction(Opcode, Operands, DL, Name);
   }
 
+  VPInstruction *createOverflowingOp(unsigned Opcode,
+                                     std::initializer_list<VPValue *> Operands,
+                                     VPRecipeWithIRFlags::WrapFlagsTy WrapFlags,
+                                     DebugLoc DL, const Twine &Name = "") {
+    return tryInsertInstruction(
+        new VPInstruction(Opcode, Operands, WrapFlags, DL, Name));
+  }
   VPValue *createNot(VPValue *Operand, DebugLoc DL, const Twine &Name = "") {
     return createInstruction(VPInstruction::Not, {Operand}, DL, Name);
   }
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -8065,14 +8065,6 @@
     return;
   }
 
-  // If we're using the active lane mask for control flow, then we get the
-  // mask from the active lane mask PHI that is cached in the VPlan.
-  TailFoldingStyle TFStyle = CM.getTailFoldingStyle();
-  if (useActiveLaneMaskForControlFlow(TFStyle)) {
-    BlockMaskCache[Header] = Plan.getActiveLaneMaskPhi();
-    return;
-  }
-
   // Introduce the early-exit compare IV <= BTC to form header block mask.
   // This is used instead of IV < TC because TC may wrap, unlike BTC. Start by
   // constructing the desired canonical IV in the header block as its first
@@ -8086,14 +8078,8 @@
   VPBuilder::InsertPointGuard Guard(Builder);
   Builder.setInsertPoint(HeaderVPBB, NewInsertionPoint);
   VPValue *BlockMask = nullptr;
-  if (useActiveLaneMask(TFStyle)) {
-    VPValue *TC = Plan.getTripCount();
-    BlockMask = Builder.createNaryOp(VPInstruction::ActiveLaneMask, {IV, TC},
-                                     nullptr, "active.lane.mask");
-  } else {
-    VPValue *BTC = Plan.getOrCreateBackedgeTakenCount();
-    BlockMask = Builder.createICmp(CmpInst::ICMP_ULE, IV, BTC);
-  }
+  VPValue *BTC = Plan.getOrCreateBackedgeTakenCount();
+  BlockMask = Builder.createICmp(CmpInst::ICMP_ULE, IV, BTC);
   BlockMaskCache[Header] = BlockMask;
 }
 
@@ -8631,8 +8617,8 @@
 
 // Add the necessary canonical IV and branch recipes required to control the
 // loop.
-static void addCanonicalIVRecipes(VPlan &Plan, Type *IdxTy, DebugLoc DL,
-                                  TailFoldingStyle Style) {
+static void addCanonicalIVRecipes(VPlan &Plan, Type *IdxTy, bool HasNUW,
+                                  DebugLoc DL) {
   Value *StartIdx = ConstantInt::get(IdxTy, 0);
   auto *StartV = Plan.getVPValueOrAddLiveIn(StartIdx);
 
@@ -8644,93 +8630,19 @@
 
   // Add a CanonicalIVIncrement{NUW} VPInstruction to increment the scalar
   // IV by VF * UF.
-  bool HasNUW = Style == TailFoldingStyle::None;
   auto *CanonicalIVIncrement =
       new VPInstruction(VPInstruction::CanonicalIVIncrement, {CanonicalIVPHI},
                         {HasNUW, false}, DL, "index.next");
   CanonicalIVPHI->addOperand(CanonicalIVIncrement);
 
   VPBasicBlock *EB = TopRegion->getExitingBasicBlock();
-  if (useActiveLaneMaskForControlFlow(Style)) {
-    // Create the active lane mask instruction in the vplan preheader.
-    VPBasicBlock *VecPreheader =
-        cast<VPBasicBlock>(Plan.getVectorLoopRegion()->getSinglePredecessor());
-
-    // We can't use StartV directly in the ActiveLaneMask VPInstruction, since
-    // we have to take unrolling into account. Each part needs to start at
-    //   Part * VF
-    auto *CanonicalIVIncrementParts =
-        new VPInstruction(VPInstruction::CanonicalIVIncrementForPart, {StartV},
-                          {HasNUW, false}, DL, "index.part.next");
-    VecPreheader->appendRecipe(CanonicalIVIncrementParts);
-
-    // Create the ActiveLaneMask instruction using the correct start values.
-    VPValue *TC = Plan.getTripCount();
-
-    VPValue *TripCount, *IncrementValue;
-    if (Style == TailFoldingStyle::DataAndControlFlowWithoutRuntimeCheck) {
-      // When avoiding a runtime check, the active.lane.mask inside the loop
-      // uses a modified trip count and the induction variable increment is
-      // done after the active.lane.mask intrinsic is called.
-      auto *TCMinusVF =
-          new VPInstruction(VPInstruction::CalculateTripCountMinusVF, {TC}, DL);
-      VecPreheader->appendRecipe(TCMinusVF);
-      IncrementValue = CanonicalIVPHI;
-      TripCount = TCMinusVF;
-    } else {
-      // When the loop is guarded by a runtime overflow check for the loop
-      // induction variable increment by VF, we can increment the value before
-      // the get.active.lane mask and use the unmodified tripcount.
-      EB->appendRecipe(CanonicalIVIncrement);
-      IncrementValue = CanonicalIVIncrement;
-      TripCount = TC;
-    }
+  EB->appendRecipe(CanonicalIVIncrement);
 
-    auto *EntryALM = new VPInstruction(VPInstruction::ActiveLaneMask,
-                                       {CanonicalIVIncrementParts, TC}, DL,
-                                       "active.lane.mask.entry");
-    VecPreheader->appendRecipe(EntryALM);
-
-    // Now create the ActiveLaneMaskPhi recipe in the main loop using the
-    // preheader ActiveLaneMask instruction.
-    auto *LaneMaskPhi = new VPActiveLaneMaskPHIRecipe(EntryALM, DebugLoc());
-    Header->insert(LaneMaskPhi, Header->getFirstNonPhi());
-
-    // Create the active lane mask for the next iteration of the loop.
-    CanonicalIVIncrementParts =
-        new VPInstruction(VPInstruction::CanonicalIVIncrementForPart,
-                          {IncrementValue}, {HasNUW, false}, DL);
-    EB->appendRecipe(CanonicalIVIncrementParts);
-
-    auto *ALM = new VPInstruction(VPInstruction::ActiveLaneMask,
-                                  {CanonicalIVIncrementParts, TripCount}, DL,
-                                  "active.lane.mask.next");
-    EB->appendRecipe(ALM);
-    LaneMaskPhi->addOperand(ALM);
-
-    if (Style == TailFoldingStyle::DataAndControlFlowWithoutRuntimeCheck) {
-      // Do the increment of the canonical IV after the active.lane.mask, because
-      // that value is still based off %CanonicalIVPHI
-      EB->appendRecipe(CanonicalIVIncrement);
-    }
-
-    // We have to invert the mask here because a true condition means jumping
-    // to the exit block.
-    auto *NotMask = new VPInstruction(VPInstruction::Not, ALM, DL);
-    EB->appendRecipe(NotMask);
-
-    VPInstruction *BranchBack =
-        new VPInstruction(VPInstruction::BranchOnCond, {NotMask}, DL);
-    EB->appendRecipe(BranchBack);
-  } else {
-    EB->appendRecipe(CanonicalIVIncrement);
-
-    // Add the BranchOnCount VPInstruction to the latch.
-    VPInstruction *BranchBack = new VPInstruction(
-        VPInstruction::BranchOnCount,
-        {CanonicalIVIncrement, &Plan.getVectorTripCount()}, DL);
-    EB->appendRecipe(BranchBack);
-  }
+  // Add the BranchOnCount VPInstruction to the latch.
+  VPInstruction *BranchBack =
+      new VPInstruction(VPInstruction::BranchOnCount,
+                        {CanonicalIVIncrement, &Plan.getVectorTripCount()}, DL);
+  EB->appendRecipe(BranchBack);
 }
 
 // Add exit values to \p Plan. VPLiveOuts are added for each LCSSA phi in the
@@ -8817,8 +8729,11 @@
     IVUpdateMayOverflow |= !isIndvarOverflowCheckKnownFalse(&CM, VF);
 
   DebugLoc DL = getDebugLocFromInstOrOperands(Legal->getPrimaryInduction());
-  addCanonicalIVRecipes(*Plan, Legal->getWidestInductionType(), DL,
-                        CM.getTailFoldingStyle(IVUpdateMayOverflow));
+  TailFoldingStyle Style = CM.getTailFoldingStyle(IVUpdateMayOverflow);
+  // When not folding the tail, we know that the induction increment will not
+  // overflow.
+  bool HasNUW = Style == TailFoldingStyle::None;
+  addCanonicalIVRecipes(*Plan, Legal->getWidestInductionType(), HasNUW, DL);
 
   // Proactively create header mask. Masks for other blocks are created on
   // demand.
@@ -8987,6 +8902,15 @@
   if (!VPlanTransforms::adjustFixedOrderRecurrences(*Plan, Builder))
     return nullptr;
 
+  if (useActiveLaneMask(Style)) {
+    // TODO: Move checks to VPlanTransforms::addActiveLaneMask once
+    // TailFoldingStyle is visible there.
+    bool ForControlFlow = useActiveLaneMaskForControlFlow(Style);
+    bool WithoutRuntimeCheck =
+        Style == TailFoldingStyle::DataAndControlFlowWithoutRuntimeCheck;
+    VPlanTransforms::addActiveLaneMask(*Plan, ForControlFlow,
+                                       WithoutRuntimeCheck);
+  }
   return Plan;
 }
 
@@ -9021,8 +8945,11 @@
       Plan->getVectorLoopRegion()->getExitingBasicBlock()->getTerminator();
   Term->eraseFromParent();
 
-  addCanonicalIVRecipes(*Plan, Legal->getWidestInductionType(), DebugLoc(),
-                        CM.getTailFoldingStyle());
+  // Tail folding is not supported for outer loops, so the induction increment
+  // is guaranteed to not wrap.
+  bool HasNUW = true;
+  addCanonicalIVRecipes(*Plan, Legal->getWidestInductionType(), HasNUW,
+                        DebugLoc());
   return Plan;
 }
 
diff --git a/llvm/lib/Transforms/Vectorize/VPlan.h b/llvm/lib/Transforms/Vectorize/VPlan.h
--- a/llvm/lib/Transforms/Vectorize/VPlan.h
+++ b/llvm/lib/Transforms/Vectorize/VPlan.h
@@ -2682,10 +2682,6 @@
     return cast<VPCanonicalIVPHIRecipe>(&*EntryVPBB->begin());
   }
 
-  /// Find and return the VPActiveLaneMaskPHIRecipe from the header - there
-  /// be only one at most. If there isn't one, then return nullptr.
-  VPActiveLaneMaskPHIRecipe *getActiveLaneMaskPhi();
-
   void addLiveOut(PHINode *PN, VPValue *V);
 
   void removeLiveOut(PHINode *PN) {
diff --git a/llvm/lib/Transforms/Vectorize/VPlan.cpp b/llvm/lib/Transforms/Vectorize/VPlan.cpp
--- a/llvm/lib/Transforms/Vectorize/VPlan.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlan.cpp
@@ -718,15 +718,6 @@
   return Plan;
 }
 
-VPActiveLaneMaskPHIRecipe *VPlan::getActiveLaneMaskPhi() {
-  VPBasicBlock *Header = getVectorLoopRegion()->getEntryBasicBlock();
-  for (VPRecipeBase &R : Header->phis()) {
-    if (isa<VPActiveLaneMaskPHIRecipe>(&R))
-      return cast<VPActiveLaneMaskPHIRecipe>(&R);
-  }
-  return nullptr;
-}
-
 void VPlan::prepareToExecute(Value *TripCountV, Value *VectorTripCountV,
                              Value *CanonicalIVStartValue,
                              VPTransformState &State,
diff --git a/llvm/lib/Transforms/Vectorize/VPlanTransforms.h b/llvm/lib/Transforms/Vectorize/VPlanTransforms.h
--- a/llvm/lib/Transforms/Vectorize/VPlanTransforms.h
+++ b/llvm/lib/Transforms/Vectorize/VPlanTransforms.h
@@ -67,6 +67,18 @@
   /// regions until no improvements are remaining.
   static void createAndOptimizeReplicateRegions(VPlan &Plan);
 
+  /// Replace (ICMP_ULE, wide canonical IV, backedge-taken-count) checks with an
+  /// (active-lane-mask recipe, wide canonical IV, trip-count). If \p
+  /// UseActiveLaneMaskForControlFlow is true, introduce an
+  /// VPActiveLaneMaskPHIRecipe. If \p DataAndControlFlowWithoutRuntimeCheck is
+  /// true, no minimum-iteration runtime check will be created (during skeleton
+  /// creation) and instead it is handled using active-lane-mask. \p
+  /// DataAndControlFlowWithoutRuntimeCheck implies \p
+  /// UseActiveLaneMaskForControlFlow.
+  static void addActiveLaneMask(VPlan &Plan,
+                                bool UseActiveLaneMaskForControlFlow,
+                                bool DataAndControlFlowWithoutRuntimeCheck);
+
 private:
   /// Remove redundant VPBasicBlocks by merging them into their predecessor if
   /// the predecessor has a single successor.
diff --git a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
--- a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
@@ -16,6 +16,7 @@
 #include "VPlanCFG.h"
 #include "VPlanDominatorTree.h"
 #include "llvm/ADT/PostOrderIterator.h"
+#include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SetVector.h"
 #include "llvm/Analysis/IVDescriptors.h"
 #include "llvm/Analysis/VectorUtils.h"
@@ -855,3 +856,152 @@
   removeRedundantExpandSCEVRecipes(Plan);
   mergeBlocksIntoPredecessors(Plan);
 }
+
+// Add a VPActiveLaneMaskPHIRecipe and related recipes to \p Plan and replace
+// the loop terminator with a branch-on-cond recipe with the negated
+// active-lane-mask as operand. Note that this turns the loop into an
+// uncountable one. Only the existing terminator is replaced, all other existing
+// recipes/users remain unchanged, except for poison-generating flags being
+// dropped from the canonical IV increment. Return the created
+// VPActiveLaneMaskPHIRecipe.
+//
+// The function uses the following definitions:
+//
+//  %TripCount = DataWithControlFlowWithoutRuntimeCheck ?
+//    calculate-trip-count-minus-VF (original TC) : original TC
+//  %IncrementValue = DataWithControlFlowWithoutRuntimeCheck ?
+//     CanonicalIVPhi : CanonicalIVIncrement
+//  %StartV is the canonical induction start value.
+//
+// The function adds the following recipes:
+//
+// vector.ph:
+//   %TripCount = calculate-trip-count-minus-VF (original TC)
+//       [if DataWithControlFlowWithoutRuntimeCheck]
+//   %EntryInc = canonical-iv-increment-for-part %StartV
+//   %EntryALM = active-lane-mask %EntryInc, %TripCount
+//
+// vector.body:
+//   ...
+//   %P = active-lane-mask-phi [ %EntryALM, %vector.ph ], [ %ALM, %vector.body ]
+//   ...
+//   %InLoopInc = canonical-iv-increment-for-part %IncrementValue
+//   %ALM = active-lane-mask %InLoopInc, TripCount
+//   %Negated = Not %ALM
+//   branch-on-cond %Negated
+//
+static VPActiveLaneMaskPHIRecipe *addVPLaneMaskPhiAndUpdateExitBranch(
+    VPlan &Plan, bool DataAndControlFlowWithoutRuntimeCheck) {
+  VPRegionBlock *TopRegion = Plan.getVectorLoopRegion();
+  VPBasicBlock *EB = TopRegion->getExitingBasicBlock();
+  auto *CanonicalIVPHI = Plan.getCanonicalIV();
+  VPValue *StartV = CanonicalIVPHI->getStartValue();
+
+  auto *CanonicalIVIncrement =
+      cast<VPInstruction>(CanonicalIVPHI->getBackedgeValue());
+  // TODO: Check if dropping the flags is needed if
+  // !DataAndControlFlowWithoutRuntimeCheck.
+  CanonicalIVIncrement->dropPoisonGeneratingFlags();
+  DebugLoc DL = CanonicalIVIncrement->getDebugLoc();
+  // We can't use StartV directly in the ActiveLaneMask VPInstruction, since
+  // we have to take unrolling into account. Each part needs to start at
+  //   Part * VF
+  auto *VecPreheader = cast<VPBasicBlock>(TopRegion->getSinglePredecessor());
+  VPBuilder Builder(VecPreheader);
+
+  // Create the ActiveLaneMask instruction using the correct start values.
+  VPValue *TC = Plan.getTripCount();
+
+  VPValue *TripCount, *IncrementValue;
+  if (!DataAndControlFlowWithoutRuntimeCheck) {
+    // When the loop is guarded by a runtime overflow check for the loop
+    // induction variable increment by VF, we can increment the value before
+    // the get.active.lane mask and use the unmodified tripcount.
+    IncrementValue = CanonicalIVIncrement;
+    TripCount = TC;
+  } else {
+    // When avoiding a runtime check, the active.lane.mask inside the loop
+    // uses a modified trip count and the induction variable increment is
+    // done after the active.lane.mask intrinsic is called.
+    IncrementValue = CanonicalIVPHI;
+    TripCount = Builder.createNaryOp(VPInstruction::CalculateTripCountMinusVF,
+                                     {TC}, DL);
+  }
+  auto *EntryIncrement = Builder.createOverflowingOp(
+      VPInstruction::CanonicalIVIncrementForPart, {StartV}, {false, false}, DL,
+      "index.part.next");
+
+  // Create the active lane mask instruction in the VPlan preheader.
+  auto *EntryALM =
+      Builder.createNaryOp(VPInstruction::ActiveLaneMask, {EntryIncrement, TC},
+                           DL, "active.lane.mask.entry");
+
+  // Now create the ActiveLaneMaskPhi recipe in the main loop using the
+  // preheader ActiveLaneMask instruction.
+  auto LaneMaskPhi = new VPActiveLaneMaskPHIRecipe(EntryALM, DebugLoc());
+  LaneMaskPhi->insertAfter(CanonicalIVPHI);
+
+  // Create the active lane mask for the next iteration of the loop before the
+  // original terminator.
+  VPRecipeBase *OriginalTerminator = EB->getTerminator();
+  Builder.setInsertPoint(OriginalTerminator);
+  auto *InLoopIncrement =
+      Builder.createOverflowingOp(VPInstruction::CanonicalIVIncrementForPart,
+                                  {IncrementValue}, {false, false}, DL);
+  auto *ALM = Builder.createNaryOp(VPInstruction::ActiveLaneMask,
+                                   {InLoopIncrement, TripCount}, DL,
+                                   "active.lane.mask.next");
+  LaneMaskPhi->addOperand(ALM);
+
+  // Replace the original terminator with BranchOnCond. We have to invert the
+  // mask here because a true condition means jumping to the exit block.
+  auto *NotMask = Builder.createNot(ALM, DL);
+  Builder.createNaryOp(VPInstruction::BranchOnCond, {NotMask}, DL);
+  OriginalTerminator->eraseFromParent();
+  return LaneMaskPhi;
+}
+
+void VPlanTransforms::addActiveLaneMask(
+    VPlan &Plan, bool UseActiveLaneMaskForControlFlow,
+    bool DataAndControlFlowWithoutRuntimeCheck) {
+  assert(!DataAndControlFlowWithoutRuntimeCheck ||
+         UseActiveLaneMaskForControlFlow &&
+             "DataAndControlFlowWithoutRuntimeCheck implies "
+             "UseActiveLaneMaskForControlFlow");
+
+  auto FoundWidenCanonicalIVUser =
+      find_if(Plan.getCanonicalIV()->users(),
+              [](VPUser *U) { return isa<VPWidenCanonicalIVRecipe>(U); });
+  assert(FoundWidenCanonicalIVUser &&
+         "Must have widened canonical IV when tail folding!");
+  auto *WideCanonicalIV =
+      cast<VPWidenCanonicalIVRecipe>(*FoundWidenCanonicalIVUser);
+  VPRecipeBase *LaneMask;
+  if (UseActiveLaneMaskForControlFlow) {
+    LaneMask = addVPLaneMaskPhiAndUpdateExitBranch(
+        Plan, DataAndControlFlowWithoutRuntimeCheck);
+  } else {
+    LaneMask = new VPInstruction(VPInstruction::ActiveLaneMask,
+                                 {WideCanonicalIV, Plan.getTripCount()},
+                                 nullptr, "active.lane.mask");
+    LaneMask->insertAfter(WideCanonicalIV);
+  }
+
+  // Walk users of WideCanonicalIV and replace all compares of the form
+  // (ICMP_ULE, WideCanonicalIV, backedge-taken-count) with an
+  // active-lane-mask.
+  VPValue *BTC = Plan.getOrCreateBackedgeTakenCount();
+  for (VPUser *U : SmallVector<VPUser *>(WideCanonicalIV->users())) {
+    auto *CompareToReplace = dyn_cast<VPInstruction>(U);
+    if (!CompareToReplace ||
+        CompareToReplace->getOpcode() != Instruction::ICmp ||
+        CompareToReplace->getPredicate() != CmpInst::ICMP_ULE ||
+        CompareToReplace->getOperand(1) != BTC)
+      continue;
+
+    assert(CompareToReplace->getOperand(0) == WideCanonicalIV &&
+           "WidenCanonicalIV must be the first operand of the compare");
+    CompareToReplace->replaceAllUsesWith(LaneMask->getVPSingleValue());
+    CompareToReplace->eraseFromParent();
+  }
+}
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-strict-fadd.ll b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-strict-fadd.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-strict-fadd.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-strict-fadd.ll
@@ -153,10 +153,10 @@
 ; CHECK-ORDERED-TF-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 8 x float> @llvm.masked.load.nxv8f32.p0(ptr [[TMP12]], i32 4, <vscale x 8 x i1> [[ACTIVE_LANE_MASK]], <vscale x 8 x float> poison)
 ; CHECK-ORDERED-TF-NEXT:    [[TMP13:%.*]] = select <vscale x 8 x i1> [[ACTIVE_LANE_MASK]], <vscale x 8 x float> [[WIDE_MASKED_LOAD]], <vscale x 8 x float> shufflevector (<vscale x 8 x float> insertelement (<vscale x 8 x float> poison, float -0.000000e+00, i64 0), <vscale x 8 x float> poison, <vscale x 8 x i32> zeroinitializer)
 ; CHECK-ORDERED-TF-NEXT:    [[TMP14]] = call float @llvm.vector.reduce.fadd.nxv8f32(float [[VEC_PHI]], <vscale x 8 x float> [[TMP13]])
-; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[INDEX]], i64 [[TMP9]])
 ; CHECK-ORDERED-TF-NEXT:    [[TMP15:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-ORDERED-TF-NEXT:    [[TMP16:%.*]] = mul i64 [[TMP15]], 8
 ; CHECK-ORDERED-TF-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP16]]
+; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[INDEX]], i64 [[TMP9]])
 ; CHECK-ORDERED-TF-NEXT:    [[TMP17:%.*]] = xor <vscale x 8 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 8 x i1> insertelement (<vscale x 8 x i1> poison, i1 true, i64 0), <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer)
 ; CHECK-ORDERED-TF-NEXT:    [[TMP18:%.*]] = extractelement <vscale x 8 x i1> [[TMP17]], i32 0
 ; CHECK-ORDERED-TF-NEXT:    br i1 [[TMP18]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
@@ -397,34 +397,34 @@
 ; CHECK-ORDERED-TF-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
 ; CHECK-ORDERED-TF-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
 ; CHECK-ORDERED-TF-NEXT:    [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP6:%.*]] = mul i64 [[TMP5]], 8
-; CHECK-ORDERED-TF-NEXT:    [[INDEX_PART_NEXT:%.*]] = add i64 0, [[TMP6]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP7]], 16
-; CHECK-ORDERED-TF-NEXT:    [[INDEX_PART_NEXT1:%.*]] = add i64 0, [[TMP8]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP9:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP10:%.*]] = mul i64 [[TMP9]], 24
-; CHECK-ORDERED-TF-NEXT:    [[INDEX_PART_NEXT2:%.*]] = add i64 0, [[TMP10]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP11:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP12:%.*]] = mul i64 [[TMP11]], 32
-; CHECK-ORDERED-TF-NEXT:    [[TMP13:%.*]] = sub i64 [[N]], [[TMP12]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP14:%.*]] = icmp ugt i64 [[N]], [[TMP12]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP15:%.*]] = select i1 [[TMP14]], i64 [[TMP13]], i64 0
-; CHECK-ORDERED-TF-NEXT:    [[TMP16:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP17:%.*]] = mul i64 [[TMP16]], 32
-; CHECK-ORDERED-TF-NEXT:    [[TMP18:%.*]] = sub i64 [[N]], [[TMP17]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP19:%.*]] = icmp ugt i64 [[N]], [[TMP17]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP20:%.*]] = select i1 [[TMP19]], i64 [[TMP18]], i64 0
-; CHECK-ORDERED-TF-NEXT:    [[TMP21:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP22:%.*]] = mul i64 [[TMP21]], 32
-; CHECK-ORDERED-TF-NEXT:    [[TMP23:%.*]] = sub i64 [[N]], [[TMP22]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP24:%.*]] = icmp ugt i64 [[N]], [[TMP22]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP25:%.*]] = select i1 [[TMP24]], i64 [[TMP23]], i64 0
-; CHECK-ORDERED-TF-NEXT:    [[TMP26:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP27:%.*]] = mul i64 [[TMP26]], 32
-; CHECK-ORDERED-TF-NEXT:    [[TMP28:%.*]] = sub i64 [[N]], [[TMP27]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP29:%.*]] = icmp ugt i64 [[N]], [[TMP27]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP30:%.*]] = select i1 [[TMP29]], i64 [[TMP28]], i64 0
+; CHECK-ORDERED-TF-NEXT:    [[TMP6:%.*]] = mul i64 [[TMP5]], 32
+; CHECK-ORDERED-TF-NEXT:    [[TMP7:%.*]] = sub i64 [[N]], [[TMP6]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP8:%.*]] = icmp ugt i64 [[N]], [[TMP6]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP9:%.*]] = select i1 [[TMP8]], i64 [[TMP7]], i64 0
+; CHECK-ORDERED-TF-NEXT:    [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP11:%.*]] = mul i64 [[TMP10]], 32
+; CHECK-ORDERED-TF-NEXT:    [[TMP12:%.*]] = sub i64 [[N]], [[TMP11]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP13:%.*]] = icmp ugt i64 [[N]], [[TMP11]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP14:%.*]] = select i1 [[TMP13]], i64 [[TMP12]], i64 0
+; CHECK-ORDERED-TF-NEXT:    [[TMP15:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP16:%.*]] = mul i64 [[TMP15]], 32
+; CHECK-ORDERED-TF-NEXT:    [[TMP17:%.*]] = sub i64 [[N]], [[TMP16]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP18:%.*]] = icmp ugt i64 [[N]], [[TMP16]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP19:%.*]] = select i1 [[TMP18]], i64 [[TMP17]], i64 0
+; CHECK-ORDERED-TF-NEXT:    [[TMP20:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP21:%.*]] = mul i64 [[TMP20]], 32
+; CHECK-ORDERED-TF-NEXT:    [[TMP22:%.*]] = sub i64 [[N]], [[TMP21]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP23:%.*]] = icmp ugt i64 [[N]], [[TMP21]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP24:%.*]] = select i1 [[TMP23]], i64 [[TMP22]], i64 0
+; CHECK-ORDERED-TF-NEXT:    [[TMP25:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP26:%.*]] = mul i64 [[TMP25]], 8
+; CHECK-ORDERED-TF-NEXT:    [[INDEX_PART_NEXT:%.*]] = add i64 0, [[TMP26]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP27:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP28:%.*]] = mul i64 [[TMP27]], 16
+; CHECK-ORDERED-TF-NEXT:    [[INDEX_PART_NEXT1:%.*]] = add i64 0, [[TMP28]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP29:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP30:%.*]] = mul i64 [[TMP29]], 24
+; CHECK-ORDERED-TF-NEXT:    [[INDEX_PART_NEXT2:%.*]] = add i64 0, [[TMP30]]
 ; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 0, i64 [[N]])
 ; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_ENTRY3:%.*]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[INDEX_PART_NEXT]], i64 [[N]])
 ; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_ENTRY4:%.*]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[INDEX_PART_NEXT1]], i64 [[N]])
@@ -480,21 +480,21 @@
 ; CHECK-ORDERED-TF-NEXT:    [[TMP67:%.*]] = select <vscale x 8 x i1> [[ACTIVE_LANE_MASK8]], <vscale x 8 x float> [[WIDE_MASKED_LOAD11]], <vscale x 8 x float> shufflevector (<vscale x 8 x float> insertelement (<vscale x 8 x float> poison, float -0.000000e+00, i64 0), <vscale x 8 x float> poison, <vscale x 8 x i32> zeroinitializer)
 ; CHECK-ORDERED-TF-NEXT:    [[TMP68]] = call float @llvm.vector.reduce.fadd.nxv8f32(float [[TMP66]], <vscale x 8 x float> [[TMP67]])
 ; CHECK-ORDERED-TF-NEXT:    [[TMP69:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP70:%.*]] = mul i64 [[TMP69]], 8
-; CHECK-ORDERED-TF-NEXT:    [[TMP71:%.*]] = add i64 [[INDEX]], [[TMP70]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP72:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP73:%.*]] = mul i64 [[TMP72]], 16
-; CHECK-ORDERED-TF-NEXT:    [[TMP74:%.*]] = add i64 [[INDEX]], [[TMP73]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP75:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP76:%.*]] = mul i64 [[TMP75]], 24
-; CHECK-ORDERED-TF-NEXT:    [[TMP77:%.*]] = add i64 [[INDEX]], [[TMP76]]
-; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[INDEX]], i64 [[TMP15]])
-; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT12]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[TMP71]], i64 [[TMP20]])
-; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT13]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[TMP74]], i64 [[TMP25]])
-; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT14]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[TMP77]], i64 [[TMP30]])
-; CHECK-ORDERED-TF-NEXT:    [[TMP78:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP79:%.*]] = mul i64 [[TMP78]], 32
-; CHECK-ORDERED-TF-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP79]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP70:%.*]] = mul i64 [[TMP69]], 32
+; CHECK-ORDERED-TF-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP70]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP71:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP72:%.*]] = mul i64 [[TMP71]], 8
+; CHECK-ORDERED-TF-NEXT:    [[TMP73:%.*]] = add i64 [[INDEX]], [[TMP72]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP74:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP75:%.*]] = mul i64 [[TMP74]], 16
+; CHECK-ORDERED-TF-NEXT:    [[TMP76:%.*]] = add i64 [[INDEX]], [[TMP75]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP77:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP78:%.*]] = mul i64 [[TMP77]], 24
+; CHECK-ORDERED-TF-NEXT:    [[TMP79:%.*]] = add i64 [[INDEX]], [[TMP78]]
+; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[INDEX]], i64 [[TMP9]])
+; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT12]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[TMP73]], i64 [[TMP14]])
+; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT13]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[TMP76]], i64 [[TMP19]])
+; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT14]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[TMP79]], i64 [[TMP24]])
 ; CHECK-ORDERED-TF-NEXT:    [[TMP80:%.*]] = xor <vscale x 8 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 8 x i1> insertelement (<vscale x 8 x i1> poison, i1 true, i64 0), <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer)
 ; CHECK-ORDERED-TF-NEXT:    [[TMP81:%.*]] = xor <vscale x 8 x i1> [[ACTIVE_LANE_MASK_NEXT12]], shufflevector (<vscale x 8 x i1> insertelement (<vscale x 8 x i1> poison, i1 true, i64 0), <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer)
 ; CHECK-ORDERED-TF-NEXT:    [[TMP82:%.*]] = xor <vscale x 8 x i1> [[ACTIVE_LANE_MASK_NEXT13]], shufflevector (<vscale x 8 x i1> insertelement (<vscale x 8 x i1> poison, i1 true, i64 0), <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer)
@@ -755,10 +755,10 @@
 ; CHECK-ORDERED-TF-NEXT:    [[TMP19]] = call float @llvm.vector.reduce.fadd.nxv4f32(float [[VEC_PHI]], <vscale x 4 x float> [[TMP18]])
 ; CHECK-ORDERED-TF-NEXT:    [[TMP20:%.*]] = select <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x float> [[TMP16]], <vscale x 4 x float> shufflevector (<vscale x 4 x float> insertelement (<vscale x 4 x float> poison, float -0.000000e+00, i64 0), <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-ORDERED-TF-NEXT:    [[TMP21]] = call float @llvm.vector.reduce.fadd.nxv4f32(float [[VEC_PHI1]], <vscale x 4 x float> [[TMP20]])
-; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX]], i64 [[TMP12]])
 ; CHECK-ORDERED-TF-NEXT:    [[TMP22:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-ORDERED-TF-NEXT:    [[TMP23:%.*]] = mul i64 [[TMP22]], 4
 ; CHECK-ORDERED-TF-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP23]]
+; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX]], i64 [[TMP12]])
 ; CHECK-ORDERED-TF-NEXT:    [[TMP24:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-ORDERED-TF-NEXT:    [[TMP25:%.*]] = extractelement <vscale x 4 x i1> [[TMP24]], i32 0
 ; CHECK-ORDERED-TF-NEXT:    br i1 [[TMP25]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
@@ -1012,10 +1012,10 @@
 ; CHECK-ORDERED-TF-NEXT:    [[TMP16:%.*]] = fadd <vscale x 4 x float> [[WIDE_MASKED_LOAD]], [[WIDE_MASKED_LOAD1]]
 ; CHECK-ORDERED-TF-NEXT:    [[TMP17:%.*]] = select <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x float> [[TMP16]], <vscale x 4 x float> shufflevector (<vscale x 4 x float> insertelement (<vscale x 4 x float> poison, float -0.000000e+00, i64 0), <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-ORDERED-TF-NEXT:    [[TMP18]] = call float @llvm.vector.reduce.fadd.nxv4f32(float [[VEC_PHI]], <vscale x 4 x float> [[TMP17]])
-; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX]], i64 [[TMP10]])
 ; CHECK-ORDERED-TF-NEXT:    [[TMP19:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-ORDERED-TF-NEXT:    [[TMP20:%.*]] = mul i64 [[TMP19]], 4
 ; CHECK-ORDERED-TF-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP20]]
+; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX]], i64 [[TMP10]])
 ; CHECK-ORDERED-TF-NEXT:    [[TMP21:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-ORDERED-TF-NEXT:    [[TMP22:%.*]] = extractelement <vscale x 4 x i1> [[TMP21]], i32 0
 ; CHECK-ORDERED-TF-NEXT:    br i1 [[TMP22]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
@@ -1258,10 +1258,10 @@
 ; CHECK-ORDERED-TF-NEXT:    [[TMP19:%.*]] = or <vscale x 4 x i1> [[TMP15]], [[TMP18]]
 ; CHECK-ORDERED-TF-NEXT:    [[TMP20:%.*]] = select <vscale x 4 x i1> [[TMP19]], <vscale x 4 x float> [[PREDPHI]], <vscale x 4 x float> shufflevector (<vscale x 4 x float> insertelement (<vscale x 4 x float> poison, float -0.000000e+00, i64 0), <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-ORDERED-TF-NEXT:    [[TMP21]] = call float @llvm.vector.reduce.fadd.nxv4f32(float [[VEC_PHI]], <vscale x 4 x float> [[TMP20]])
-; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX]], i64 [[TMP9]])
 ; CHECK-ORDERED-TF-NEXT:    [[TMP22:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-ORDERED-TF-NEXT:    [[TMP23:%.*]] = mul i64 [[TMP22]], 4
 ; CHECK-ORDERED-TF-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP23]]
+; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX]], i64 [[TMP9]])
 ; CHECK-ORDERED-TF-NEXT:    [[TMP24:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-ORDERED-TF-NEXT:    [[TMP25:%.*]] = extractelement <vscale x 4 x i1> [[TMP24]], i32 0
 ; CHECK-ORDERED-TF-NEXT:    br i1 [[TMP25]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
@@ -1709,34 +1709,34 @@
 ; CHECK-ORDERED-TF-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
 ; CHECK-ORDERED-TF-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
 ; CHECK-ORDERED-TF-NEXT:    [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP6:%.*]] = mul i64 [[TMP5]], 8
-; CHECK-ORDERED-TF-NEXT:    [[INDEX_PART_NEXT:%.*]] = add i64 0, [[TMP6]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP7]], 16
-; CHECK-ORDERED-TF-NEXT:    [[INDEX_PART_NEXT1:%.*]] = add i64 0, [[TMP8]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP9:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP10:%.*]] = mul i64 [[TMP9]], 24
-; CHECK-ORDERED-TF-NEXT:    [[INDEX_PART_NEXT2:%.*]] = add i64 0, [[TMP10]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP11:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP12:%.*]] = mul i64 [[TMP11]], 32
-; CHECK-ORDERED-TF-NEXT:    [[TMP13:%.*]] = sub i64 [[N]], [[TMP12]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP14:%.*]] = icmp ugt i64 [[N]], [[TMP12]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP15:%.*]] = select i1 [[TMP14]], i64 [[TMP13]], i64 0
-; CHECK-ORDERED-TF-NEXT:    [[TMP16:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP17:%.*]] = mul i64 [[TMP16]], 32
-; CHECK-ORDERED-TF-NEXT:    [[TMP18:%.*]] = sub i64 [[N]], [[TMP17]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP19:%.*]] = icmp ugt i64 [[N]], [[TMP17]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP20:%.*]] = select i1 [[TMP19]], i64 [[TMP18]], i64 0
-; CHECK-ORDERED-TF-NEXT:    [[TMP21:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP22:%.*]] = mul i64 [[TMP21]], 32
-; CHECK-ORDERED-TF-NEXT:    [[TMP23:%.*]] = sub i64 [[N]], [[TMP22]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP24:%.*]] = icmp ugt i64 [[N]], [[TMP22]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP25:%.*]] = select i1 [[TMP24]], i64 [[TMP23]], i64 0
-; CHECK-ORDERED-TF-NEXT:    [[TMP26:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP27:%.*]] = mul i64 [[TMP26]], 32
-; CHECK-ORDERED-TF-NEXT:    [[TMP28:%.*]] = sub i64 [[N]], [[TMP27]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP29:%.*]] = icmp ugt i64 [[N]], [[TMP27]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP30:%.*]] = select i1 [[TMP29]], i64 [[TMP28]], i64 0
+; CHECK-ORDERED-TF-NEXT:    [[TMP6:%.*]] = mul i64 [[TMP5]], 32
+; CHECK-ORDERED-TF-NEXT:    [[TMP7:%.*]] = sub i64 [[N]], [[TMP6]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP8:%.*]] = icmp ugt i64 [[N]], [[TMP6]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP9:%.*]] = select i1 [[TMP8]], i64 [[TMP7]], i64 0
+; CHECK-ORDERED-TF-NEXT:    [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP11:%.*]] = mul i64 [[TMP10]], 32
+; CHECK-ORDERED-TF-NEXT:    [[TMP12:%.*]] = sub i64 [[N]], [[TMP11]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP13:%.*]] = icmp ugt i64 [[N]], [[TMP11]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP14:%.*]] = select i1 [[TMP13]], i64 [[TMP12]], i64 0
+; CHECK-ORDERED-TF-NEXT:    [[TMP15:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP16:%.*]] = mul i64 [[TMP15]], 32
+; CHECK-ORDERED-TF-NEXT:    [[TMP17:%.*]] = sub i64 [[N]], [[TMP16]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP18:%.*]] = icmp ugt i64 [[N]], [[TMP16]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP19:%.*]] = select i1 [[TMP18]], i64 [[TMP17]], i64 0
+; CHECK-ORDERED-TF-NEXT:    [[TMP20:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP21:%.*]] = mul i64 [[TMP20]], 32
+; CHECK-ORDERED-TF-NEXT:    [[TMP22:%.*]] = sub i64 [[N]], [[TMP21]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP23:%.*]] = icmp ugt i64 [[N]], [[TMP21]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP24:%.*]] = select i1 [[TMP23]], i64 [[TMP22]], i64 0
+; CHECK-ORDERED-TF-NEXT:    [[TMP25:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP26:%.*]] = mul i64 [[TMP25]], 8
+; CHECK-ORDERED-TF-NEXT:    [[INDEX_PART_NEXT:%.*]] = add i64 0, [[TMP26]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP27:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP28:%.*]] = mul i64 [[TMP27]], 16
+; CHECK-ORDERED-TF-NEXT:    [[INDEX_PART_NEXT1:%.*]] = add i64 0, [[TMP28]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP29:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP30:%.*]] = mul i64 [[TMP29]], 24
+; CHECK-ORDERED-TF-NEXT:    [[INDEX_PART_NEXT2:%.*]] = add i64 0, [[TMP30]]
 ; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 0, i64 [[N]])
 ; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_ENTRY3:%.*]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[INDEX_PART_NEXT]], i64 [[N]])
 ; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_ENTRY4:%.*]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[INDEX_PART_NEXT1]], i64 [[N]])
@@ -1814,21 +1814,21 @@
 ; CHECK-ORDERED-TF-NEXT:    [[TMP85:%.*]] = select <vscale x 8 x i1> [[ACTIVE_LANE_MASK8]], <vscale x 8 x float> [[TMP78]], <vscale x 8 x float> shufflevector (<vscale x 8 x float> insertelement (<vscale x 8 x float> poison, float -0.000000e+00, i64 0), <vscale x 8 x float> poison, <vscale x 8 x i32> zeroinitializer)
 ; CHECK-ORDERED-TF-NEXT:    [[TMP86]] = call float @llvm.vector.reduce.fadd.nxv8f32(float [[TMP84]], <vscale x 8 x float> [[TMP85]])
 ; CHECK-ORDERED-TF-NEXT:    [[TMP87:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP88:%.*]] = mul i64 [[TMP87]], 8
-; CHECK-ORDERED-TF-NEXT:    [[TMP89:%.*]] = add i64 [[INDEX]], [[TMP88]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP90:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP91:%.*]] = mul i64 [[TMP90]], 16
-; CHECK-ORDERED-TF-NEXT:    [[TMP92:%.*]] = add i64 [[INDEX]], [[TMP91]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP93:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP94:%.*]] = mul i64 [[TMP93]], 24
-; CHECK-ORDERED-TF-NEXT:    [[TMP95:%.*]] = add i64 [[INDEX]], [[TMP94]]
-; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[INDEX]], i64 [[TMP15]])
-; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT16]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[TMP89]], i64 [[TMP20]])
-; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT17]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[TMP92]], i64 [[TMP25]])
-; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT18]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[TMP95]], i64 [[TMP30]])
-; CHECK-ORDERED-TF-NEXT:    [[TMP96:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP97:%.*]] = mul i64 [[TMP96]], 32
-; CHECK-ORDERED-TF-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP97]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP88:%.*]] = mul i64 [[TMP87]], 32
+; CHECK-ORDERED-TF-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP88]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP89:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP90:%.*]] = mul i64 [[TMP89]], 8
+; CHECK-ORDERED-TF-NEXT:    [[TMP91:%.*]] = add i64 [[INDEX]], [[TMP90]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP92:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP93:%.*]] = mul i64 [[TMP92]], 16
+; CHECK-ORDERED-TF-NEXT:    [[TMP94:%.*]] = add i64 [[INDEX]], [[TMP93]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP95:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP96:%.*]] = mul i64 [[TMP95]], 24
+; CHECK-ORDERED-TF-NEXT:    [[TMP97:%.*]] = add i64 [[INDEX]], [[TMP96]]
+; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[INDEX]], i64 [[TMP9]])
+; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT16]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[TMP91]], i64 [[TMP14]])
+; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT17]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[TMP94]], i64 [[TMP19]])
+; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT18]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[TMP97]], i64 [[TMP24]])
 ; CHECK-ORDERED-TF-NEXT:    [[TMP98:%.*]] = xor <vscale x 8 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 8 x i1> insertelement (<vscale x 8 x i1> poison, i1 true, i64 0), <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer)
 ; CHECK-ORDERED-TF-NEXT:    [[TMP99:%.*]] = xor <vscale x 8 x i1> [[ACTIVE_LANE_MASK_NEXT16]], shufflevector (<vscale x 8 x i1> insertelement (<vscale x 8 x i1> poison, i1 true, i64 0), <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer)
 ; CHECK-ORDERED-TF-NEXT:    [[TMP100:%.*]] = xor <vscale x 8 x i1> [[ACTIVE_LANE_MASK_NEXT17]], shufflevector (<vscale x 8 x i1> insertelement (<vscale x 8 x i1> poison, i1 true, i64 0), <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer)
@@ -2123,34 +2123,34 @@
 ; CHECK-ORDERED-TF-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
 ; CHECK-ORDERED-TF-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
 ; CHECK-ORDERED-TF-NEXT:    [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP6:%.*]] = mul i64 [[TMP5]], 8
-; CHECK-ORDERED-TF-NEXT:    [[INDEX_PART_NEXT:%.*]] = add i64 0, [[TMP6]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP7]], 16
-; CHECK-ORDERED-TF-NEXT:    [[INDEX_PART_NEXT1:%.*]] = add i64 0, [[TMP8]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP9:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP10:%.*]] = mul i64 [[TMP9]], 24
-; CHECK-ORDERED-TF-NEXT:    [[INDEX_PART_NEXT2:%.*]] = add i64 0, [[TMP10]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP11:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP12:%.*]] = mul i64 [[TMP11]], 32
-; CHECK-ORDERED-TF-NEXT:    [[TMP13:%.*]] = sub i64 [[N]], [[TMP12]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP14:%.*]] = icmp ugt i64 [[N]], [[TMP12]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP15:%.*]] = select i1 [[TMP14]], i64 [[TMP13]], i64 0
-; CHECK-ORDERED-TF-NEXT:    [[TMP16:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP17:%.*]] = mul i64 [[TMP16]], 32
-; CHECK-ORDERED-TF-NEXT:    [[TMP18:%.*]] = sub i64 [[N]], [[TMP17]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP19:%.*]] = icmp ugt i64 [[N]], [[TMP17]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP20:%.*]] = select i1 [[TMP19]], i64 [[TMP18]], i64 0
-; CHECK-ORDERED-TF-NEXT:    [[TMP21:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP22:%.*]] = mul i64 [[TMP21]], 32
-; CHECK-ORDERED-TF-NEXT:    [[TMP23:%.*]] = sub i64 [[N]], [[TMP22]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP24:%.*]] = icmp ugt i64 [[N]], [[TMP22]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP25:%.*]] = select i1 [[TMP24]], i64 [[TMP23]], i64 0
-; CHECK-ORDERED-TF-NEXT:    [[TMP26:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP27:%.*]] = mul i64 [[TMP26]], 32
-; CHECK-ORDERED-TF-NEXT:    [[TMP28:%.*]] = sub i64 [[N]], [[TMP27]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP29:%.*]] = icmp ugt i64 [[N]], [[TMP27]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP30:%.*]] = select i1 [[TMP29]], i64 [[TMP28]], i64 0
+; CHECK-ORDERED-TF-NEXT:    [[TMP6:%.*]] = mul i64 [[TMP5]], 32
+; CHECK-ORDERED-TF-NEXT:    [[TMP7:%.*]] = sub i64 [[N]], [[TMP6]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP8:%.*]] = icmp ugt i64 [[N]], [[TMP6]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP9:%.*]] = select i1 [[TMP8]], i64 [[TMP7]], i64 0
+; CHECK-ORDERED-TF-NEXT:    [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP11:%.*]] = mul i64 [[TMP10]], 32
+; CHECK-ORDERED-TF-NEXT:    [[TMP12:%.*]] = sub i64 [[N]], [[TMP11]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP13:%.*]] = icmp ugt i64 [[N]], [[TMP11]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP14:%.*]] = select i1 [[TMP13]], i64 [[TMP12]], i64 0
+; CHECK-ORDERED-TF-NEXT:    [[TMP15:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP16:%.*]] = mul i64 [[TMP15]], 32
+; CHECK-ORDERED-TF-NEXT:    [[TMP17:%.*]] = sub i64 [[N]], [[TMP16]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP18:%.*]] = icmp ugt i64 [[N]], [[TMP16]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP19:%.*]] = select i1 [[TMP18]], i64 [[TMP17]], i64 0
+; CHECK-ORDERED-TF-NEXT:    [[TMP20:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP21:%.*]] = mul i64 [[TMP20]], 32
+; CHECK-ORDERED-TF-NEXT:    [[TMP22:%.*]] = sub i64 [[N]], [[TMP21]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP23:%.*]] = icmp ugt i64 [[N]], [[TMP21]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP24:%.*]] = select i1 [[TMP23]], i64 [[TMP22]], i64 0
+; CHECK-ORDERED-TF-NEXT:    [[TMP25:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP26:%.*]] = mul i64 [[TMP25]], 8
+; CHECK-ORDERED-TF-NEXT:    [[INDEX_PART_NEXT:%.*]] = add i64 0, [[TMP26]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP27:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP28:%.*]] = mul i64 [[TMP27]], 16
+; CHECK-ORDERED-TF-NEXT:    [[INDEX_PART_NEXT1:%.*]] = add i64 0, [[TMP28]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP29:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP30:%.*]] = mul i64 [[TMP29]], 24
+; CHECK-ORDERED-TF-NEXT:    [[INDEX_PART_NEXT2:%.*]] = add i64 0, [[TMP30]]
 ; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 0, i64 [[N]])
 ; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_ENTRY3:%.*]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[INDEX_PART_NEXT]], i64 [[N]])
 ; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_ENTRY4:%.*]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[INDEX_PART_NEXT1]], i64 [[N]])
@@ -2228,21 +2228,21 @@
 ; CHECK-ORDERED-TF-NEXT:    [[TMP85:%.*]] = select nnan <vscale x 8 x i1> [[ACTIVE_LANE_MASK8]], <vscale x 8 x float> [[TMP78]], <vscale x 8 x float> shufflevector (<vscale x 8 x float> insertelement (<vscale x 8 x float> poison, float -0.000000e+00, i64 0), <vscale x 8 x float> poison, <vscale x 8 x i32> zeroinitializer)
 ; CHECK-ORDERED-TF-NEXT:    [[TMP86]] = call nnan float @llvm.vector.reduce.fadd.nxv8f32(float [[TMP84]], <vscale x 8 x float> [[TMP85]])
 ; CHECK-ORDERED-TF-NEXT:    [[TMP87:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP88:%.*]] = mul i64 [[TMP87]], 8
-; CHECK-ORDERED-TF-NEXT:    [[TMP89:%.*]] = add i64 [[INDEX]], [[TMP88]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP90:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP91:%.*]] = mul i64 [[TMP90]], 16
-; CHECK-ORDERED-TF-NEXT:    [[TMP92:%.*]] = add i64 [[INDEX]], [[TMP91]]
-; CHECK-ORDERED-TF-NEXT:    [[TMP93:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP94:%.*]] = mul i64 [[TMP93]], 24
-; CHECK-ORDERED-TF-NEXT:    [[TMP95:%.*]] = add i64 [[INDEX]], [[TMP94]]
-; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[INDEX]], i64 [[TMP15]])
-; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT16]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[TMP89]], i64 [[TMP20]])
-; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT17]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[TMP92]], i64 [[TMP25]])
-; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT18]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[TMP95]], i64 [[TMP30]])
-; CHECK-ORDERED-TF-NEXT:    [[TMP96:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-ORDERED-TF-NEXT:    [[TMP97:%.*]] = mul i64 [[TMP96]], 32
-; CHECK-ORDERED-TF-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP97]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP88:%.*]] = mul i64 [[TMP87]], 32
+; CHECK-ORDERED-TF-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP88]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP89:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP90:%.*]] = mul i64 [[TMP89]], 8
+; CHECK-ORDERED-TF-NEXT:    [[TMP91:%.*]] = add i64 [[INDEX]], [[TMP90]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP92:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP93:%.*]] = mul i64 [[TMP92]], 16
+; CHECK-ORDERED-TF-NEXT:    [[TMP94:%.*]] = add i64 [[INDEX]], [[TMP93]]
+; CHECK-ORDERED-TF-NEXT:    [[TMP95:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-ORDERED-TF-NEXT:    [[TMP96:%.*]] = mul i64 [[TMP95]], 24
+; CHECK-ORDERED-TF-NEXT:    [[TMP97:%.*]] = add i64 [[INDEX]], [[TMP96]]
+; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[INDEX]], i64 [[TMP9]])
+; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT16]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[TMP91]], i64 [[TMP14]])
+; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT17]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[TMP94]], i64 [[TMP19]])
+; CHECK-ORDERED-TF-NEXT:    [[ACTIVE_LANE_MASK_NEXT18]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[TMP97]], i64 [[TMP24]])
 ; CHECK-ORDERED-TF-NEXT:    [[TMP98:%.*]] = xor <vscale x 8 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 8 x i1> insertelement (<vscale x 8 x i1> poison, i1 true, i64 0), <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer)
 ; CHECK-ORDERED-TF-NEXT:    [[TMP99:%.*]] = xor <vscale x 8 x i1> [[ACTIVE_LANE_MASK_NEXT16]], shufflevector (<vscale x 8 x i1> insertelement (<vscale x 8 x i1> poison, i1 true, i64 0), <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer)
 ; CHECK-ORDERED-TF-NEXT:    [[TMP100:%.*]] = xor <vscale x 8 x i1> [[ACTIVE_LANE_MASK_NEXT17]], shufflevector (<vscale x 8 x i1> insertelement (<vscale x 8 x i1> poison, i1 true, i64 0), <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer)
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-interleaved-masked-accesses.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-interleaved-masked-accesses.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-interleaved-masked-accesses.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-interleaved-masked-accesses.ll
@@ -146,10 +146,10 @@
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[INTERLEAVED_VEC:%.*]] = call <vscale x 32 x i8> @llvm.experimental.vector.interleave2.nxv32i8(<vscale x 16 x i8> [[TMP14]], <vscale x 16 x i8> [[TMP15]])
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[INTERLEAVED_MASK1:%.*]] = call <vscale x 32 x i1> @llvm.experimental.vector.interleave2.nxv32i1(<vscale x 16 x i1> [[TMP10]], <vscale x 16 x i1> [[TMP10]])
 ; PREDICATED_TAIL_FOLDING-NEXT:    call void @llvm.masked.store.nxv32i8.p0(<vscale x 32 x i8> [[INTERLEAVED_VEC]], ptr [[TMP18]], i32 1, <vscale x 32 x i1> [[INTERLEAVED_MASK1]])
-; PREDICATED_TAIL_FOLDING-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 [[INDEX]], i32 [[TMP2]])
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP19:%.*]] = call i32 @llvm.vscale.i32()
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP20:%.*]] = shl i32 [[TMP19]], 4
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], [[TMP20]]
+; PREDICATED_TAIL_FOLDING-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 [[INDEX]], i32 [[TMP2]])
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 16 x i32> [[VEC_IND]], [[DOTSPLAT]]
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP21:%.*]] = extractelement <vscale x 16 x i1> [[ACTIVE_LANE_MASK_NEXT]], i64 0
 ; PREDICATED_TAIL_FOLDING-NEXT:    br i1 [[TMP21]], label [[VECTOR_BODY]], label [[MIDDLE_BLOCK:%.*]], !llvm.loop [[LOOP0:![0-9]+]]
@@ -312,10 +312,10 @@
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP12:%.*]] = getelementptr inbounds i8, ptr [[Q]], <vscale x 16 x i64> [[TMP11]]
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP13:%.*]] = select <vscale x 16 x i1> [[ACTIVE_LANE_MASK]], <vscale x 16 x i1> [[TMP9]], <vscale x 16 x i1> zeroinitializer
 ; PREDICATED_TAIL_FOLDING-NEXT:    call void @llvm.masked.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8> shufflevector (<vscale x 16 x i8> insertelement (<vscale x 16 x i8> poison, i8 2, i64 0), <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer), <vscale x 16 x ptr> [[TMP12]], i32 1, <vscale x 16 x i1> [[TMP13]])
-; PREDICATED_TAIL_FOLDING-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 [[INDEX]], i32 [[TMP2]])
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP14:%.*]] = call i32 @llvm.vscale.i32()
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP15:%.*]] = shl i32 [[TMP14]], 4
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], [[TMP15]]
+; PREDICATED_TAIL_FOLDING-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 [[INDEX]], i32 [[TMP2]])
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 16 x i32> [[VEC_IND]], [[DOTSPLAT]]
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP16:%.*]] = extractelement <vscale x 16 x i1> [[ACTIVE_LANE_MASK_NEXT]], i64 0
 ; PREDICATED_TAIL_FOLDING-NEXT:    br i1 [[TMP16]], label [[VECTOR_BODY]], label [[MIDDLE_BLOCK:%.*]], !llvm.loop [[LOOP4:![0-9]+]]
@@ -487,10 +487,10 @@
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP14:%.*]] = getelementptr inbounds i8, ptr [[Q]], <vscale x 16 x i64> [[TMP13]]
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP15:%.*]] = select <vscale x 16 x i1> [[ACTIVE_LANE_MASK]], <vscale x 16 x i1> [[TMP11]], <vscale x 16 x i1> zeroinitializer
 ; PREDICATED_TAIL_FOLDING-NEXT:    call void @llvm.masked.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8> shufflevector (<vscale x 16 x i8> insertelement (<vscale x 16 x i8> poison, i8 2, i64 0), <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer), <vscale x 16 x ptr> [[TMP14]], i32 1, <vscale x 16 x i1> [[TMP15]])
-; PREDICATED_TAIL_FOLDING-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 [[INDEX]], i32 [[TMP2]])
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP16:%.*]] = call i32 @llvm.vscale.i32()
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP17:%.*]] = shl i32 [[TMP16]], 4
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], [[TMP17]]
+; PREDICATED_TAIL_FOLDING-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 [[INDEX]], i32 [[TMP2]])
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 16 x i32> [[VEC_IND]], [[DOTSPLAT]]
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP18:%.*]] = extractelement <vscale x 16 x i1> [[ACTIVE_LANE_MASK_NEXT]], i64 0
 ; PREDICATED_TAIL_FOLDING-NEXT:    br i1 [[TMP18]], label [[VECTOR_BODY]], label [[MIDDLE_BLOCK:%.*]], !llvm.loop [[LOOP6:![0-9]+]]
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-forced.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-forced.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-forced.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-forced.ll
@@ -17,8 +17,8 @@
 ; VPLANS-NEXT: No successors
 ; VPLANS-EMPTY:
 ; VPLANS-NEXT: vector.ph:
-; VPLANS-NEXT:   EMIT vp<[[VF:%[0-9]+]]> = VF * Part + ir<0>
 ; VPLANS-NEXT:   EMIT vp<[[NEWTC:%[0-9]+]]> = TC > VF ? TC - VF : 0 vp<[[TC]]>
+; VPLANS-NEXT:   EMIT vp<[[VF:%[0-9]+]]> = VF * Part + ir<0>
 ; VPLANS-NEXT:   EMIT vp<[[LANEMASK_ENTRY:%[0-9]+]]> = active lane mask vp<[[VF]]>, vp<[[TC]]>
 ; VPLANS-NEXT: Successor(s): vector loop
 ; VPLANS-EMPTY:
@@ -29,9 +29,9 @@
 ; VPLANS-NEXT:     vp<[[STEP:%[0-9]+]]>    = SCALAR-STEPS vp<[[INDV]]>, ir<1>
 ; VPLANS-NEXT:     CLONE ir<%gep> = getelementptr ir<%ptr>, vp<[[STEP]]>
 ; VPLANS-NEXT:     WIDEN store ir<%gep>, ir<%val>, vp<[[LANEMASK_PHI]]>
+; VPLANS-NEXT:     EMIT vp<[[INDV_UPDATE:%[0-9]+]]> = VF * UF + vp<[[INDV]]>
 ; VPLANS-NEXT:     EMIT vp<[[INC:%[0-9]+]]> = VF * Part + vp<[[INDV]]>
 ; VPLANS-NEXT:     EMIT vp<[[LANEMASK_LOOP]]> = active lane mask vp<[[INC]]>, vp<[[NEWTC]]>
-; VPLANS-NEXT:     EMIT vp<[[INDV_UPDATE:%[0-9]+]]> = VF * UF + vp<[[INDV]]>
 ; VPLANS-NEXT:     EMIT vp<[[NOT:%[0-9]+]]> = not vp<[[LANEMASK_LOOP]]>
 ; VPLANS-NEXT:     EMIT branch-on-cond vp<[[NOT]]>
 ; VPLANS-NEXT:   No successors
@@ -67,10 +67,10 @@
 ; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr i32, ptr [[PTR:%.*]], i64 [[TMP10]]
 ; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr i32, ptr [[TMP11]], i32 0
 ; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0(<vscale x 4 x i32> [[BROADCAST_SPLAT]], ptr [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
 ; CHECK-NEXT:    [[TMP13:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP14:%.*]] = mul i64 [[TMP13]], 4
 ; CHECK-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP14]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
 ; CHECK-NEXT:    [[TMP15:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP16:%.*]] = extractelement <vscale x 4 x i1> [[TMP15]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP16]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-overflow-checks.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-overflow-checks.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-overflow-checks.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-overflow-checks.ll
@@ -89,10 +89,10 @@
 ; CHECK-NEXT:    [[TMP4:%.*]] = add nsw <vscale x 4 x i32> [[WIDE_MASKED_LOAD]], shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 42, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, ptr [[DST:%.*]], i64 [[INDEX]]
 ; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0(<vscale x 4 x i32> [[TMP4]], ptr [[TMP5]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX]], i64 [[TMP2]])
 ; CHECK-NEXT:    [[TMP6:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP7:%.*]] = shl nuw nsw i64 [[TMP6]], 2
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP7]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX]], i64 [[TMP2]])
 ; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], i64 0
 ; CHECK-NEXT:    br i1 [[TMP8]], label [[VECTOR_BODY]], label [[MIDDLE_BLOCK:%.*]], !llvm.loop [[LOOP4:![0-9]+]]
 ; CHECK:       middle.block:
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-reductions.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-reductions.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-reductions.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-reductions.ll
@@ -37,10 +37,10 @@
 ; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0(ptr [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> poison)
 ; CHECK-NEXT:    [[TMP13:%.*]] = add <vscale x 4 x i32> [[VEC_PHI]], [[WIDE_MASKED_LOAD]]
 ; CHECK-NEXT:    [[TMP14]] = select <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> [[TMP13]], <vscale x 4 x i32> [[VEC_PHI]]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
 ; CHECK-NEXT:    [[TMP15:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP16:%.*]] = mul i64 [[TMP15]], 4
 ; CHECK-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP16]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
 ; CHECK-NEXT:    [[TMP17:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP18:%.*]] = extractelement <vscale x 4 x i1> [[TMP17]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP18]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
@@ -95,10 +95,10 @@
 ; CHECK-IN-LOOP-NEXT:    [[TMP13:%.*]] = select <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> [[WIDE_MASKED_LOAD]], <vscale x 4 x i32> zeroinitializer
 ; CHECK-IN-LOOP-NEXT:    [[TMP14:%.*]] = call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> [[TMP13]])
 ; CHECK-IN-LOOP-NEXT:    [[TMP15]] = add i32 [[TMP14]], [[VEC_PHI]]
-; CHECK-IN-LOOP-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
 ; CHECK-IN-LOOP-NEXT:    [[TMP16:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-IN-LOOP-NEXT:    [[TMP17:%.*]] = mul i64 [[TMP16]], 4
 ; CHECK-IN-LOOP-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP17]]
+; CHECK-IN-LOOP-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
 ; CHECK-IN-LOOP-NEXT:    [[TMP18:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-IN-LOOP-NEXT:    [[TMP19:%.*]] = extractelement <vscale x 4 x i1> [[TMP18]], i32 0
 ; CHECK-IN-LOOP-NEXT:    br i1 [[TMP19]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
@@ -169,10 +169,10 @@
 ; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x float> @llvm.masked.load.nxv4f32.p0(ptr [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x float> poison)
 ; CHECK-NEXT:    [[TMP13:%.*]] = select <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x float> shufflevector (<vscale x 4 x float> insertelement (<vscale x 4 x float> poison, float -0.000000e+00, i64 0), <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP14]] = call float @llvm.vector.reduce.fadd.nxv4f32(float [[VEC_PHI]], <vscale x 4 x float> [[TMP13]])
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
 ; CHECK-NEXT:    [[TMP15:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP16:%.*]] = mul i64 [[TMP15]], 4
 ; CHECK-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP16]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
 ; CHECK-NEXT:    [[TMP17:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP18:%.*]] = extractelement <vscale x 4 x i1> [[TMP17]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP18]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
@@ -225,10 +225,10 @@
 ; CHECK-IN-LOOP-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x float> @llvm.masked.load.nxv4f32.p0(ptr [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x float> poison)
 ; CHECK-IN-LOOP-NEXT:    [[TMP13:%.*]] = select <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x float> shufflevector (<vscale x 4 x float> insertelement (<vscale x 4 x float> poison, float -0.000000e+00, i64 0), <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-IN-LOOP-NEXT:    [[TMP14]] = call float @llvm.vector.reduce.fadd.nxv4f32(float [[VEC_PHI]], <vscale x 4 x float> [[TMP13]])
-; CHECK-IN-LOOP-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
 ; CHECK-IN-LOOP-NEXT:    [[TMP15:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-IN-LOOP-NEXT:    [[TMP16:%.*]] = mul i64 [[TMP15]], 4
 ; CHECK-IN-LOOP-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP16]]
+; CHECK-IN-LOOP-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
 ; CHECK-IN-LOOP-NEXT:    [[TMP17:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-IN-LOOP-NEXT:    [[TMP18:%.*]] = extractelement <vscale x 4 x i1> [[TMP17]], i32 0
 ; CHECK-IN-LOOP-NEXT:    br i1 [[TMP18]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
@@ -306,10 +306,10 @@
 ; CHECK-NEXT:    [[TMP19:%.*]] = select <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i1> [[TMP18]], <vscale x 4 x i1> zeroinitializer
 ; CHECK-NEXT:    [[PREDPHI:%.*]] = select <vscale x 4 x i1> [[TMP15]], <vscale x 4 x i32> [[TMP17]], <vscale x 4 x i32> [[VEC_PHI]]
 ; CHECK-NEXT:    [[TMP20]] = select <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> [[PREDPHI]], <vscale x 4 x i32> [[VEC_PHI]]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX]], i64 [[TMP9]])
 ; CHECK-NEXT:    [[TMP21:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP22:%.*]] = mul i64 [[TMP21]], 4
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP22]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX]], i64 [[TMP9]])
 ; CHECK-NEXT:    [[TMP23:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP24:%.*]] = extractelement <vscale x 4 x i1> [[TMP23]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP24]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
@@ -376,10 +376,10 @@
 ; CHECK-IN-LOOP-NEXT:    [[TMP17:%.*]] = select <vscale x 4 x i1> [[TMP15]], <vscale x 4 x i32> [[WIDE_MASKED_LOAD1]], <vscale x 4 x i32> zeroinitializer
 ; CHECK-IN-LOOP-NEXT:    [[TMP18:%.*]] = call i32 @llvm.vector.reduce.xor.nxv4i32(<vscale x 4 x i32> [[TMP17]])
 ; CHECK-IN-LOOP-NEXT:    [[TMP19]] = xor i32 [[TMP18]], [[VEC_PHI]]
-; CHECK-IN-LOOP-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX]], i64 [[TMP9]])
 ; CHECK-IN-LOOP-NEXT:    [[TMP20:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-IN-LOOP-NEXT:    [[TMP21:%.*]] = mul i64 [[TMP20]], 4
 ; CHECK-IN-LOOP-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP21]]
+; CHECK-IN-LOOP-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX]], i64 [[TMP9]])
 ; CHECK-IN-LOOP-NEXT:    [[TMP22:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-IN-LOOP-NEXT:    [[TMP23:%.*]] = extractelement <vscale x 4 x i1> [[TMP22]], i32 0
 ; CHECK-IN-LOOP-NEXT:    br i1 [[TMP23]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-unroll.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-unroll.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-unroll.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-unroll.ll
@@ -19,34 +19,34 @@
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
 ; CHECK-NEXT:    [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP6:%.*]] = mul i64 [[TMP5]], 4
-; CHECK-NEXT:    [[INDEX_PART_NEXT:%.*]] = add i64 0, [[TMP6]]
-; CHECK-NEXT:    [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP7]], 8
-; CHECK-NEXT:    [[INDEX_PART_NEXT1:%.*]] = add i64 0, [[TMP8]]
-; CHECK-NEXT:    [[TMP9:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP10:%.*]] = mul i64 [[TMP9]], 12
-; CHECK-NEXT:    [[INDEX_PART_NEXT2:%.*]] = add i64 0, [[TMP10]]
-; CHECK-NEXT:    [[TMP11:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP12:%.*]] = mul i64 [[TMP11]], 16
-; CHECK-NEXT:    [[TMP13:%.*]] = sub i64 [[UMAX]], [[TMP12]]
-; CHECK-NEXT:    [[TMP14:%.*]] = icmp ugt i64 [[UMAX]], [[TMP12]]
-; CHECK-NEXT:    [[TMP15:%.*]] = select i1 [[TMP14]], i64 [[TMP13]], i64 0
-; CHECK-NEXT:    [[TMP16:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP17:%.*]] = mul i64 [[TMP16]], 16
-; CHECK-NEXT:    [[TMP18:%.*]] = sub i64 [[UMAX]], [[TMP17]]
-; CHECK-NEXT:    [[TMP19:%.*]] = icmp ugt i64 [[UMAX]], [[TMP17]]
-; CHECK-NEXT:    [[TMP20:%.*]] = select i1 [[TMP19]], i64 [[TMP18]], i64 0
-; CHECK-NEXT:    [[TMP21:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP22:%.*]] = mul i64 [[TMP21]], 16
-; CHECK-NEXT:    [[TMP23:%.*]] = sub i64 [[UMAX]], [[TMP22]]
-; CHECK-NEXT:    [[TMP24:%.*]] = icmp ugt i64 [[UMAX]], [[TMP22]]
-; CHECK-NEXT:    [[TMP25:%.*]] = select i1 [[TMP24]], i64 [[TMP23]], i64 0
-; CHECK-NEXT:    [[TMP26:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP27:%.*]] = mul i64 [[TMP26]], 16
-; CHECK-NEXT:    [[TMP28:%.*]] = sub i64 [[UMAX]], [[TMP27]]
-; CHECK-NEXT:    [[TMP29:%.*]] = icmp ugt i64 [[UMAX]], [[TMP27]]
-; CHECK-NEXT:    [[TMP30:%.*]] = select i1 [[TMP29]], i64 [[TMP28]], i64 0
+; CHECK-NEXT:    [[TMP6:%.*]] = mul i64 [[TMP5]], 16
+; CHECK-NEXT:    [[TMP7:%.*]] = sub i64 [[UMAX]], [[TMP6]]
+; CHECK-NEXT:    [[TMP8:%.*]] = icmp ugt i64 [[UMAX]], [[TMP6]]
+; CHECK-NEXT:    [[TMP9:%.*]] = select i1 [[TMP8]], i64 [[TMP7]], i64 0
+; CHECK-NEXT:    [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP11:%.*]] = mul i64 [[TMP10]], 16
+; CHECK-NEXT:    [[TMP12:%.*]] = sub i64 [[UMAX]], [[TMP11]]
+; CHECK-NEXT:    [[TMP13:%.*]] = icmp ugt i64 [[UMAX]], [[TMP11]]
+; CHECK-NEXT:    [[TMP14:%.*]] = select i1 [[TMP13]], i64 [[TMP12]], i64 0
+; CHECK-NEXT:    [[TMP15:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP16:%.*]] = mul i64 [[TMP15]], 16
+; CHECK-NEXT:    [[TMP17:%.*]] = sub i64 [[UMAX]], [[TMP16]]
+; CHECK-NEXT:    [[TMP18:%.*]] = icmp ugt i64 [[UMAX]], [[TMP16]]
+; CHECK-NEXT:    [[TMP19:%.*]] = select i1 [[TMP18]], i64 [[TMP17]], i64 0
+; CHECK-NEXT:    [[TMP20:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP21:%.*]] = mul i64 [[TMP20]], 16
+; CHECK-NEXT:    [[TMP22:%.*]] = sub i64 [[UMAX]], [[TMP21]]
+; CHECK-NEXT:    [[TMP23:%.*]] = icmp ugt i64 [[UMAX]], [[TMP21]]
+; CHECK-NEXT:    [[TMP24:%.*]] = select i1 [[TMP23]], i64 [[TMP22]], i64 0
+; CHECK-NEXT:    [[TMP25:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP26:%.*]] = mul i64 [[TMP25]], 4
+; CHECK-NEXT:    [[INDEX_PART_NEXT:%.*]] = add i64 0, [[TMP26]]
+; CHECK-NEXT:    [[TMP27:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP28:%.*]] = mul i64 [[TMP27]], 8
+; CHECK-NEXT:    [[INDEX_PART_NEXT1:%.*]] = add i64 0, [[TMP28]]
+; CHECK-NEXT:    [[TMP29:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP30:%.*]] = mul i64 [[TMP29]], 12
+; CHECK-NEXT:    [[INDEX_PART_NEXT2:%.*]] = add i64 0, [[TMP30]]
 ; CHECK-NEXT:    [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[UMAX]])
 ; CHECK-NEXT:    [[ACTIVE_LANE_MASK_ENTRY3:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_PART_NEXT]], i64 [[UMAX]])
 ; CHECK-NEXT:    [[ACTIVE_LANE_MASK_ENTRY4:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_PART_NEXT1]], i64 [[UMAX]])
@@ -55,11 +55,11 @@
 ; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i32> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
-; CHECK-NEXT:    [[INDEX6:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT13:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[INDEX6:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT10:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK7:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY3]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT10:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK8:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY4]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT11:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK9:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY5]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT12:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK7:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY3]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT11:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK8:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY4]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT12:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK9:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY5]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT13:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP31:%.*]] = add i64 [[INDEX6]], 0
 ; CHECK-NEXT:    [[TMP32:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP33:%.*]] = mul i64 [[TMP32]], 4
@@ -95,25 +95,25 @@
 ; CHECK-NEXT:    [[TMP60:%.*]] = getelementptr i32, ptr [[TMP47]], i64 [[TMP59]]
 ; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0(<vscale x 4 x i32> [[BROADCAST_SPLAT]], ptr [[TMP60]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK9]])
 ; CHECK-NEXT:    [[TMP61:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP62:%.*]] = mul i64 [[TMP61]], 4
-; CHECK-NEXT:    [[TMP63:%.*]] = add i64 [[INDEX6]], [[TMP62]]
-; CHECK-NEXT:    [[TMP64:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP65:%.*]] = mul i64 [[TMP64]], 8
-; CHECK-NEXT:    [[TMP66:%.*]] = add i64 [[INDEX6]], [[TMP65]]
-; CHECK-NEXT:    [[TMP67:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP68:%.*]] = mul i64 [[TMP67]], 12
-; CHECK-NEXT:    [[TMP69:%.*]] = add i64 [[INDEX6]], [[TMP68]]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX6]], i64 [[TMP15]])
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT10]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[TMP63]], i64 [[TMP20]])
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT11]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[TMP66]], i64 [[TMP25]])
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT12]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[TMP69]], i64 [[TMP30]])
-; CHECK-NEXT:    [[TMP70:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP71:%.*]] = mul i64 [[TMP70]], 16
-; CHECK-NEXT:    [[INDEX_NEXT13]] = add i64 [[INDEX6]], [[TMP71]]
+; CHECK-NEXT:    [[TMP62:%.*]] = mul i64 [[TMP61]], 16
+; CHECK-NEXT:    [[INDEX_NEXT10]] = add i64 [[INDEX6]], [[TMP62]]
+; CHECK-NEXT:    [[TMP63:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP64:%.*]] = mul i64 [[TMP63]], 4
+; CHECK-NEXT:    [[TMP65:%.*]] = add i64 [[INDEX6]], [[TMP64]]
+; CHECK-NEXT:    [[TMP66:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP67:%.*]] = mul i64 [[TMP66]], 8
+; CHECK-NEXT:    [[TMP68:%.*]] = add i64 [[INDEX6]], [[TMP67]]
+; CHECK-NEXT:    [[TMP69:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP70:%.*]] = mul i64 [[TMP69]], 12
+; CHECK-NEXT:    [[TMP71:%.*]] = add i64 [[INDEX6]], [[TMP70]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX6]], i64 [[TMP9]])
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT11]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[TMP65]], i64 [[TMP14]])
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT12]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[TMP68]], i64 [[TMP19]])
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT13]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[TMP71]], i64 [[TMP24]])
 ; CHECK-NEXT:    [[TMP72:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
-; CHECK-NEXT:    [[TMP73:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT10]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
-; CHECK-NEXT:    [[TMP74:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT11]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
-; CHECK-NEXT:    [[TMP75:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT12]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT:    [[TMP73:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT11]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT:    [[TMP74:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT12]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT:    [[TMP75:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT13]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP76:%.*]] = extractelement <vscale x 4 x i1> [[TMP72]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP76]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
 ; CHECK:       middle.block:
@@ -161,34 +161,34 @@
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
 ; CHECK-NEXT:    [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP6:%.*]] = mul i64 [[TMP5]], 4
-; CHECK-NEXT:    [[INDEX_PART_NEXT:%.*]] = add i64 0, [[TMP6]]
-; CHECK-NEXT:    [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP7]], 8
-; CHECK-NEXT:    [[INDEX_PART_NEXT1:%.*]] = add i64 0, [[TMP8]]
-; CHECK-NEXT:    [[TMP9:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP10:%.*]] = mul i64 [[TMP9]], 12
-; CHECK-NEXT:    [[INDEX_PART_NEXT2:%.*]] = add i64 0, [[TMP10]]
-; CHECK-NEXT:    [[TMP11:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP12:%.*]] = mul i64 [[TMP11]], 16
-; CHECK-NEXT:    [[TMP13:%.*]] = sub i64 [[UMAX]], [[TMP12]]
-; CHECK-NEXT:    [[TMP14:%.*]] = icmp ugt i64 [[UMAX]], [[TMP12]]
-; CHECK-NEXT:    [[TMP15:%.*]] = select i1 [[TMP14]], i64 [[TMP13]], i64 0
-; CHECK-NEXT:    [[TMP16:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP17:%.*]] = mul i64 [[TMP16]], 16
-; CHECK-NEXT:    [[TMP18:%.*]] = sub i64 [[UMAX]], [[TMP17]]
-; CHECK-NEXT:    [[TMP19:%.*]] = icmp ugt i64 [[UMAX]], [[TMP17]]
-; CHECK-NEXT:    [[TMP20:%.*]] = select i1 [[TMP19]], i64 [[TMP18]], i64 0
-; CHECK-NEXT:    [[TMP21:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP22:%.*]] = mul i64 [[TMP21]], 16
-; CHECK-NEXT:    [[TMP23:%.*]] = sub i64 [[UMAX]], [[TMP22]]
-; CHECK-NEXT:    [[TMP24:%.*]] = icmp ugt i64 [[UMAX]], [[TMP22]]
-; CHECK-NEXT:    [[TMP25:%.*]] = select i1 [[TMP24]], i64 [[TMP23]], i64 0
-; CHECK-NEXT:    [[TMP26:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP27:%.*]] = mul i64 [[TMP26]], 16
-; CHECK-NEXT:    [[TMP28:%.*]] = sub i64 [[UMAX]], [[TMP27]]
-; CHECK-NEXT:    [[TMP29:%.*]] = icmp ugt i64 [[UMAX]], [[TMP27]]
-; CHECK-NEXT:    [[TMP30:%.*]] = select i1 [[TMP29]], i64 [[TMP28]], i64 0
+; CHECK-NEXT:    [[TMP6:%.*]] = mul i64 [[TMP5]], 16
+; CHECK-NEXT:    [[TMP7:%.*]] = sub i64 [[UMAX]], [[TMP6]]
+; CHECK-NEXT:    [[TMP8:%.*]] = icmp ugt i64 [[UMAX]], [[TMP6]]
+; CHECK-NEXT:    [[TMP9:%.*]] = select i1 [[TMP8]], i64 [[TMP7]], i64 0
+; CHECK-NEXT:    [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP11:%.*]] = mul i64 [[TMP10]], 16
+; CHECK-NEXT:    [[TMP12:%.*]] = sub i64 [[UMAX]], [[TMP11]]
+; CHECK-NEXT:    [[TMP13:%.*]] = icmp ugt i64 [[UMAX]], [[TMP11]]
+; CHECK-NEXT:    [[TMP14:%.*]] = select i1 [[TMP13]], i64 [[TMP12]], i64 0
+; CHECK-NEXT:    [[TMP15:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP16:%.*]] = mul i64 [[TMP15]], 16
+; CHECK-NEXT:    [[TMP17:%.*]] = sub i64 [[UMAX]], [[TMP16]]
+; CHECK-NEXT:    [[TMP18:%.*]] = icmp ugt i64 [[UMAX]], [[TMP16]]
+; CHECK-NEXT:    [[TMP19:%.*]] = select i1 [[TMP18]], i64 [[TMP17]], i64 0
+; CHECK-NEXT:    [[TMP20:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP21:%.*]] = mul i64 [[TMP20]], 16
+; CHECK-NEXT:    [[TMP22:%.*]] = sub i64 [[UMAX]], [[TMP21]]
+; CHECK-NEXT:    [[TMP23:%.*]] = icmp ugt i64 [[UMAX]], [[TMP21]]
+; CHECK-NEXT:    [[TMP24:%.*]] = select i1 [[TMP23]], i64 [[TMP22]], i64 0
+; CHECK-NEXT:    [[TMP25:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP26:%.*]] = mul i64 [[TMP25]], 4
+; CHECK-NEXT:    [[INDEX_PART_NEXT:%.*]] = add i64 0, [[TMP26]]
+; CHECK-NEXT:    [[TMP27:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP28:%.*]] = mul i64 [[TMP27]], 8
+; CHECK-NEXT:    [[INDEX_PART_NEXT1:%.*]] = add i64 0, [[TMP28]]
+; CHECK-NEXT:    [[TMP29:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP30:%.*]] = mul i64 [[TMP29]], 12
+; CHECK-NEXT:    [[INDEX_PART_NEXT2:%.*]] = add i64 0, [[TMP30]]
 ; CHECK-NEXT:    [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[UMAX]])
 ; CHECK-NEXT:    [[ACTIVE_LANE_MASK_ENTRY3:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_PART_NEXT]], i64 [[UMAX]])
 ; CHECK-NEXT:    [[ACTIVE_LANE_MASK_ENTRY4:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_PART_NEXT1]], i64 [[UMAX]])
@@ -197,11 +197,11 @@
 ; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i32> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
-; CHECK-NEXT:    [[INDEX6:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT16:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[INDEX6:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT13:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK7:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY3]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT13:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK8:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY4]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT14:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK9:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY5]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT15:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK7:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY3]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT14:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK8:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY4]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT15:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK9:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY5]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT16:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP31:%.*]] = add i64 [[INDEX6]], 0
 ; CHECK-NEXT:    [[TMP32:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP33:%.*]] = mul i64 [[TMP32]], 4
@@ -263,25 +263,25 @@
 ; CHECK-NEXT:    [[TMP82:%.*]] = getelementptr i32, ptr [[TMP65]], i64 [[TMP81]]
 ; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0(<vscale x 4 x i32> [[BROADCAST_SPLAT]], ptr [[TMP82]], i32 4, <vscale x 4 x i1> [[TMP72]])
 ; CHECK-NEXT:    [[TMP83:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP84:%.*]] = mul i64 [[TMP83]], 4
-; CHECK-NEXT:    [[TMP85:%.*]] = add i64 [[INDEX6]], [[TMP84]]
-; CHECK-NEXT:    [[TMP86:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP87:%.*]] = mul i64 [[TMP86]], 8
-; CHECK-NEXT:    [[TMP88:%.*]] = add i64 [[INDEX6]], [[TMP87]]
-; CHECK-NEXT:    [[TMP89:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP90:%.*]] = mul i64 [[TMP89]], 12
-; CHECK-NEXT:    [[TMP91:%.*]] = add i64 [[INDEX6]], [[TMP90]]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX6]], i64 [[TMP15]])
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT13]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[TMP85]], i64 [[TMP20]])
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT14]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[TMP88]], i64 [[TMP25]])
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT15]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[TMP91]], i64 [[TMP30]])
-; CHECK-NEXT:    [[TMP92:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP93:%.*]] = mul i64 [[TMP92]], 16
-; CHECK-NEXT:    [[INDEX_NEXT16]] = add i64 [[INDEX6]], [[TMP93]]
+; CHECK-NEXT:    [[TMP84:%.*]] = mul i64 [[TMP83]], 16
+; CHECK-NEXT:    [[INDEX_NEXT13]] = add i64 [[INDEX6]], [[TMP84]]
+; CHECK-NEXT:    [[TMP85:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP86:%.*]] = mul i64 [[TMP85]], 4
+; CHECK-NEXT:    [[TMP87:%.*]] = add i64 [[INDEX6]], [[TMP86]]
+; CHECK-NEXT:    [[TMP88:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP89:%.*]] = mul i64 [[TMP88]], 8
+; CHECK-NEXT:    [[TMP90:%.*]] = add i64 [[INDEX6]], [[TMP89]]
+; CHECK-NEXT:    [[TMP91:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP92:%.*]] = mul i64 [[TMP91]], 12
+; CHECK-NEXT:    [[TMP93:%.*]] = add i64 [[INDEX6]], [[TMP92]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX6]], i64 [[TMP9]])
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT14]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[TMP87]], i64 [[TMP14]])
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT15]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[TMP90]], i64 [[TMP19]])
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT16]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[TMP93]], i64 [[TMP24]])
 ; CHECK-NEXT:    [[TMP94:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
-; CHECK-NEXT:    [[TMP95:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT13]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
-; CHECK-NEXT:    [[TMP96:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT14]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
-; CHECK-NEXT:    [[TMP97:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT15]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT:    [[TMP95:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT14]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT:    [[TMP96:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT15]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT:    [[TMP97:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT16]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP98:%.*]] = extractelement <vscale x 4 x i1> [[TMP94]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP98]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
 ; CHECK:       middle.block:
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding.ll
@@ -34,10 +34,10 @@
 ; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr i32, ptr [[PTR:%.*]], i64 [[TMP10]]
 ; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr i32, ptr [[TMP11]], i32 0
 ; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0(<vscale x 4 x i32> [[BROADCAST_SPLAT]], ptr [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
 ; CHECK-NEXT:    [[TMP13:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP14:%.*]] = mul i64 [[TMP13]], 4
 ; CHECK-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP14]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
 ; CHECK-NEXT:    [[TMP15:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP16:%.*]] = extractelement <vscale x 4 x i1> [[TMP15]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP16]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
@@ -95,8 +95,8 @@
 ; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr i32, ptr [[PTR:%.*]], i64 [[TMP3]]
 ; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr i32, ptr [[TMP4]], i32 0
 ; CHECK-NEXT:    call void @llvm.masked.store.v4i32.p0(<4 x i32> [[BROADCAST_SPLAT]], ptr [[TMP5]], i32 4, <4 x i1> [[ACTIVE_LANE_MASK]])
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 [[INDEX1]], i64 [[TMP2]])
 ; CHECK-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], 4
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 [[INDEX1]], i64 [[TMP2]])
 ; CHECK-NEXT:    [[TMP6:%.*]] = xor <4 x i1> [[ACTIVE_LANE_MASK_NEXT]], <i1 true, i1 true, i1 true, i1 true>
 ; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <4 x i1> [[TMP6]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
@@ -162,10 +162,10 @@
 ; CHECK-NEXT:    [[TMP13:%.*]] = getelementptr i32, ptr [[DST:%.*]], i64 [[TMP10]]
 ; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr i32, ptr [[TMP13]], i32 0
 ; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0(<vscale x 4 x i32> [[WIDE_MASKED_LOAD]], ptr [[TMP14]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
 ; CHECK-NEXT:    [[TMP15:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP16:%.*]] = mul i64 [[TMP15]], 4
 ; CHECK-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP16]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
 ; CHECK-NEXT:    [[TMP17:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP18:%.*]] = extractelement <vscale x 4 x i1> [[TMP17]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP18]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
@@ -246,10 +246,10 @@
 ; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0(<vscale x 4 x ptr> [[TMP19]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> poison)
 ; CHECK-NEXT:    [[TMP20:%.*]] = getelementptr i32, ptr [[DST:%.*]], <vscale x 4 x i64> [[VEC_IND]]
 ; CHECK-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> [[WIDE_MASKED_GATHER]], <vscale x 4 x ptr> [[TMP20]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP12]])
 ; CHECK-NEXT:    [[TMP21:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP22:%.*]] = mul i64 [[TMP21]], 4
 ; CHECK-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP22]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP12]])
 ; CHECK-NEXT:    [[TMP23:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 4 x i64> [[VEC_IND]], [[DOTSPLAT]]
 ; CHECK-NEXT:    [[TMP24:%.*]] = extractelement <vscale x 4 x i1> [[TMP23]], i32 0
@@ -321,10 +321,10 @@
 ; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0(<vscale x 4 x ptr> [[TMP13]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> poison)
 ; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr i32, ptr [[DST:%.*]], <vscale x 4 x i32> [[WIDE_MASKED_LOAD]]
 ; CHECK-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> [[WIDE_MASKED_GATHER]], <vscale x 4 x ptr> [[TMP14]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
 ; CHECK-NEXT:    [[TMP15:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP16:%.*]] = mul i64 [[TMP15]], 4
 ; CHECK-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP16]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
 ; CHECK-NEXT:    [[TMP17:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP18:%.*]] = extractelement <vscale x 4 x i1> [[TMP17]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP18]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
@@ -399,10 +399,10 @@
 ; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr inbounds i32, ptr [[DST:%.*]], i64 [[TMP10]]
 ; CHECK-NEXT:    [[TMP13:%.*]] = getelementptr inbounds i32, ptr [[TMP12]], i32 0
 ; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0(<vscale x 4 x i32> [[BROADCAST_SPLAT]], ptr [[TMP13]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX]], i64 [[TMP9]])
 ; CHECK-NEXT:    [[TMP14:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP15:%.*]] = mul i64 [[TMP14]], 4
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP15]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX]], i64 [[TMP9]])
 ; CHECK-NEXT:    [[TMP16:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP17:%.*]] = extractelement <vscale x 4 x i1> [[TMP16]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP17]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
@@ -483,10 +483,10 @@
 ; CHECK-NEXT:    [[TMP18:%.*]] = or <vscale x 4 x i1> [[TMP15]], [[TMP16]]
 ; CHECK-NEXT:    [[TMP19:%.*]] = getelementptr inbounds i32, ptr [[TMP17]], i32 0
 ; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0(<vscale x 4 x i32> [[PREDPHI]], ptr [[TMP19]], i32 4, <vscale x 4 x i1> [[TMP18]])
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
 ; CHECK-NEXT:    [[TMP20:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP21:%.*]] = mul i64 [[TMP20]], 4
 ; CHECK-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP21]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
 ; CHECK-NEXT:    [[TMP22:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP23:%.*]] = extractelement <vscale x 4 x i1> [[TMP22]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP23]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP14:![0-9]+]]
@@ -574,10 +574,10 @@
 ; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr inbounds i32, ptr [[TMP11]], i32 0
 ; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0(ptr [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> poison)
 ; CHECK-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> [[WIDE_MASKED_LOAD]], <vscale x 4 x ptr> [[BROADCAST_SPLAT]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX]], i64 [[TMP9]])
 ; CHECK-NEXT:    [[TMP13:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP14:%.*]] = mul i64 [[TMP13]], 4
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP14]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX]], i64 [[TMP9]])
 ; CHECK-NEXT:    [[TMP15:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP16:%.*]] = extractelement <vscale x 4 x i1> [[TMP15]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP16]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP16:![0-9]+]]
@@ -648,10 +648,10 @@
 ; CHECK-NEXT:    [[WIDE_MASKED_LOAD2:%.*]] = call <vscale x 4 x float> @llvm.masked.load.nxv4f32.p0(ptr [[TMP14]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x float> poison)
 ; CHECK-NEXT:    [[TMP15:%.*]] = fdiv <vscale x 4 x float> [[WIDE_MASKED_LOAD]], [[WIDE_MASKED_LOAD2]]
 ; CHECK-NEXT:    call void @llvm.masked.store.nxv4f32.p0(<vscale x 4 x float> [[TMP15]], ptr [[TMP14]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
 ; CHECK-NEXT:    [[TMP16:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP17:%.*]] = mul i64 [[TMP16]], 4
 ; CHECK-NEXT:    [[INDEX_NEXT3]] = add i64 [[INDEX1]], [[TMP17]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
 ; CHECK-NEXT:    [[TMP18:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP19:%.*]] = extractelement <vscale x 4 x i1> [[TMP18]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP19]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP18:![0-9]+]]
@@ -729,10 +729,10 @@
 ; CHECK-NEXT:    [[TMP15:%.*]] = select <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> [[WIDE_MASKED_LOAD2]], <vscale x 4 x i32> shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP16:%.*]] = udiv <vscale x 4 x i32> [[WIDE_MASKED_LOAD]], [[TMP15]]
 ; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0(<vscale x 4 x i32> [[TMP16]], ptr [[TMP14]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
 ; CHECK-NEXT:    [[TMP17:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP18:%.*]] = mul i64 [[TMP17]], 4
 ; CHECK-NEXT:    [[INDEX_NEXT3]] = add i64 [[INDEX1]], [[TMP18]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
 ; CHECK-NEXT:    [[TMP19:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP20:%.*]] = extractelement <vscale x 4 x i1> [[TMP19]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP20]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP20:![0-9]+]]
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/tail-fold-uniform-memops.ll b/llvm/test/Transforms/LoopVectorize/AArch64/tail-fold-uniform-memops.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/tail-fold-uniform-memops.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/tail-fold-uniform-memops.ll
@@ -25,8 +25,8 @@
 ; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, ptr %dst, i64 [[TMP3]]
 ; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i32, ptr [[TMP6]], i32 0
 ; CHECK-NEXT:    call void @llvm.masked.store.v4i32.p0(<4 x i32> [[TMP5]], ptr [[TMP7]], i32 4, <4 x i1> [[ACTIVE_LANE_MASK]])
-; CHECK-NEXT:    [[NEXT_ACTIVE_LANE_MASK]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 [[IDX]], i64 [[N2]])
 ; CHECK-NEXT:    [[IDX_NEXT]] = add i64 [[IDX]], 4
+; CHECK-NEXT:    [[NEXT_ACTIVE_LANE_MASK]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 [[IDX]], i64 [[N2]])
 ; CHECK-NEXT:    [[NOT_ACTIVE_LANE_MASK:%.*]] = xor <4 x i1> [[NEXT_ACTIVE_LANE_MASK]], <i1 true, i1 true, i1 true, i1 true>
 ; CHECK-NEXT:    [[FIRST_LANE_SET:%.*]] = extractelement <4 x i1> [[NOT_ACTIVE_LANE_MASK]], i32 0
 ; CHECK-NEXT:    br i1 [[FIRST_LANE_SET]], label %middle.block, label %vector.body
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/tail-folding-styles.ll b/llvm/test/Transforms/LoopVectorize/AArch64/tail-folding-styles.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/tail-folding-styles.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/tail-folding-styles.ll
@@ -233,10 +233,10 @@
 ; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[TMP11:%.*]] = getelementptr i32, ptr [[PTR:%.*]], i64 [[TMP10]]
 ; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[TMP12:%.*]] = getelementptr i32, ptr [[TMP11]], i32 0
 ; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0(<vscale x 4 x i32> [[BROADCAST_SPLAT]], ptr [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
-; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
 ; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[TMP13:%.*]] = call i64 @llvm.vscale.i64()
 ; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[TMP14:%.*]] = mul i64 [[TMP13]], 4
 ; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP14]]
+; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
 ; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[TMP15:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[TMP16:%.*]] = extractelement <vscale x 4 x i1> [[TMP15]], i32 0
 ; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    br i1 [[TMP16]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]