[LV] Don't emit the Vector IV if it is not used.

[SjoerdMeijer]

Summary

The vector induction variable (IV) is created quite early in the pipeline, but may end not being used, and this change avoids emitting the vector IV if that is the case. The scalar IV is splatted into a vector with a code sequence like this:

[[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> undef, i32 [[INDEX]], i32 0
[[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32>
[[BROADCAST_SPLATINSERT]], <4 x i32> undef, <4 x i32> zeroinitializer

We save these instructions to a list where they are being created, and remove them at the end in fixVectorizedLoop where similar fixes and clean ups are performed.

The obvious benefit of this simple admin job is that it makes the LV's output more compact and readable, this unused code can be confusing to look at, and other cleanup passes have to work a little bit less hard.

[Ayal]

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

1890

This doesn't really broadcast when VF<=1 so should be fine?

1921

Would it be possible to avoid generating the undesired broadcasting by wrapping this CreateSplatIV() under an "if (needsVectorInduction(EntryVal))" that checks if any user !shouldScalarizeInstruction(), analogous to needsScalarInduction(EntryVal) above?

Better avoid generating and carrying potential garbage to begin with if it's easy; or potentially augment cse() clean-up at the end.

[SjoerdMeijer]

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

1921

Would it be possible to avoid generating the undesired broadcasting by wrapping this CreateSplatIV() under an "if (needsVectorInduction(EntryVal))" that checks if any user !shouldScalarizeInstruction(), analogous to needsScalarInduction(EntryVal) above?

I agree that this would be nicer, but it looks like needsScalarInduction is an easier case as it simply looks at orginal loop instructions and see if they need to be scalarised. For the possibly new needsVectorInduction variant, I think we would need to look at the uses of the vector IV in the vector code, which hasn't been created yet. And since we need to look at the uses, which is what this patch is doing, I thought doing this afterwards in the fixup routine was a simple and reasonable compromise. For example, I see cases of masked/load stores using the vector IV, and I don't think I have all the information at this point to check all uses.

Better avoid generating and carrying potential garbage to begin with if it's easy; or potentially augment cse() clean-up at the end.

As I wrote above, I am not sure if it is easier or even possible to avoid generating the dead code. But I will have a look again to see if I haven't missed anything. If this is not possible, I understand your preference is to have some form of DCE running here? I thought about that, but wasn't sure if that would be overkill for just removing the vectorIV...

[Ayal]

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

1921

This indeed deserves some cleaning up.

The current decision is to vectorize (vs. scalarize) an IV if it or its update have any immediate user that will be vectorized; see documentation noted below. That decision should be aware that fold-mask will add an immediate vector user to the primary induction; suggest to fix that below.

The claim is that (then), this last default case of widenIntOrFpInduction() where EntryVal is scalarized, should not call CreateSplatIV() at all, as EntryVal must have no vector users.

Note that users first marked vector (!isScalarAfterVectorization; causing IV to be marked vector) may later be found to be isProfitableToScalarize; so IV might end up being vectorized with no vector users. But the converse cannot hold -- an initially marked vector IV cannot later be found isProfitableToScalarize because the latter applies to instructions in predicated blocks only.

An alternative approach, if/when supporting splatting scalar IV's into vectors is desired, may be to introduce them lazily, along with the scalar-to-vector broadcasts of ILV's getOrCreateVectorValue(). Going forward though, all such scalars-to-vector/vector-to-scalars should be modeled explicitly, during VPlan construction, rather than during a recipe's execution.

ILV does employ a self-cleaning cse() post-pass. But going forward, better have things cleaned up in VPlan.

4606

Note the above comment.
If IV has a user that does not remain scalar, IV is not to remain scalar.

4618

Should add here:

// Primary induction will be used to feed a vector compare under fold mask.
if (Ind == Legal->getPrimaryInduction() && foldTailByMasking())
  continue;

[SjoerdMeijer]

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

1921

Thanks Ayal for sharing and explaining this! I am looking into this now.

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

protected:
 
   // Holds the end values for each induction variable. We save the end values
   // so we can later fix-up the external users of the induction variables.
   DenseMap<PHINode *, Value *> IVEndValues;
 
   // Vector of original scalar PHIs whose corresponding widened PHIs need to be
   // fixed up at the end of vector code generation.
   SmallVector<PHINode *, 8> OrigPHIsToFix;
+
+  // When we splat the scalar induction variable into a vector early in the
+  // pipeline, which expands to a sequence of a insertelement, shufflevector
+  // and add instruction, we may end up not using this vector IV. We save these
+  // instructions to this list, so that we can easily clean them up later if it
+  // isn't used.
+  SmallVector<Value *, 4> MaybeDeadVectorIV;
 };
 
 class InnerLoopUnroller : public InnerLoopVectorizer {
 public:
   InnerLoopUnroller(Loop *OrigLoop, PredicatedScalarEvolution &PSE,
                     LoopInfo *LI, DominatorTree *DT,
                     const TargetLibraryInfo *TLI,
                     const TargetTransformInfo *TTI, AssumptionCache *AC,
auto CreateScalarIV = [&](Value *&Step) -> Value * {
     }
     return ScalarIV;
   };
 
   // Create the vector values from the scalar IV, in the absence of creating a
   // vector IV.
   auto CreateSplatIV = [&](Value *ScalarIV, Value *Step) {
     Value *Broadcasted = getBroadcastInstrs(ScalarIV);
+    if (ScalarIV->getNumUses()) {
+      MaybeDeadVectorIV.push_back(*ScalarIV->user_begin());
+      MaybeDeadVectorIV.push_back(Broadcasted);
+    }
     for (unsigned Part = 0; Part < UF; ++Part) {
       Value *EntryPart =
           getStepVector(Broadcasted, VF * Part, Step, ID.getInductionOpcode());
+      MaybeDeadVectorIV.push_back(EntryPart);
       VectorLoopValueMap.setVectorValue(EntryVal, Part, EntryPart);
       if (Trunc)
         addMetadata(EntryPart, Trunc);
       recordVectorLoopValueForInductionCast(ID, EntryVal, EntryPart, Part);
     }
   };
 
   // Now do the actual transformations, and start with creating the step value.
   Value *Step = CreateStepValue(ID.getStep());
   if (VF <= 1) {
     Value *ScalarIV = CreateScalarIV(Step);
     CreateSplatIV(ScalarIV, Step);
     return;
   }
 
   // Determine if we want a scalar version of the induction variable. This is
   // true if the induction variable itself is not widened, or if it has at
   // least one user in the loop that is not widened.
   auto NeedsScalarIV = needsScalarInduction(EntryVal);
   if (!NeedsScalarIV) {
if (!shouldScalarizeInstruction(EntryVal)) {
     buildScalarSteps(ScalarIV, Step, EntryVal, ID);
     return;
   }
 
   // If we haven't yet vectorized the induction variable, splat the scalar
   // induction variable, and build the necessary step vectors.
   // TODO: Don't do it unless the vectorized IV is really required.
   Value *ScalarIV = CreateScalarIV(Step);
   CreateSplatIV(ScalarIV, Step);
   buildScalarSteps(ScalarIV, Step, EntryVal, ID);
 }
 
 Value *InnerLoopVectorizer::getStepVector(Value *Val, int StartIdx, Value *Step,
                                           Instruction::BinaryOps BinOp) {
   // Create and check the types.
   auto *ValVTy = cast<VectorType>(Val->getType());
   int VLen = ValVTy->getNumElements();
Value *InnerLoopVectorizer::getOrCreateTripCount(Loop *L) {
   TripCount = Exp.expandCodeFor(ExitCount, ExitCount->getType(),
                                 L->getLoopPreheader()->getTerminator());
 
   if (TripCount->getType()->isPointerTy())
     TripCount =
         CastInst::CreatePointerCast(TripCount, IdxTy, "exitcount.ptrcnt.to.int",
                                     L->getLoopPreheader()->getTerminator());
 
+
   return TripCount;
 }
 
 Value *InnerLoopVectorizer::getOrCreateVectorTripCount(Loop *L) {
   if (VectorTripCount)
     return VectorTripCount;
 
   Value *TC = getOrCreateTripCount(L);
for (unsigned Part = 0; Part < UF; ++Part) {
         Value *NewI = Inst->getOperand(0);
         Inst->eraseFromParent();
         VectorLoopValueMap.resetVectorValue(KV.first, Part, NewI);
       }
     }
   }
 }
 
+
+// The vector IV consist of an insertelement, shufflevector and add
+// instruction, which are added in this order to the list respectively. Reverse
+// the list so that we first start checking the uses of the add, i.e. the last
+// instruction in this chain.
+static void FixMaybeDeadIV(SmallVector<Value *, 4> &MaybeDead) {
+  for (auto *V : reverse(MaybeDead)) {
+    if (Instruction *I = dyn_cast<Instruction>(V)) {
+      if (I->getNumUses())
+        continue;
+      I->eraseFromParent();
+    }
+  }
+  MaybeDead.clear();
+}
+
 void InnerLoopVectorizer::fixVectorizedLoop() {
   // Insert truncates and extends for any truncated instructions as hints to
   // InstCombine.
   if (VF > 1)
     truncateToMinimalBitwidths();
 
   // Fix widened non-induction PHIs by setting up the PHI operands.
   if (OrigPHIsToFix.size()) {
     assert(EnableVPlanNativePath &&
            "Unexpected non-induction PHIs for fixup in non VPlan-native path");
     fixNonInductionPHIs();
   }
 
+  // Remove the vector IV if it is not used and dead.
+  FixMaybeDeadIV(MaybeDeadVectorIV);
+
   // At this point every instruction in the original loop is widened to a
   // vector form. Now we need to fix the recurrences in the loop. These PHI
   // nodes are currently empty because we did not want to introduce cycles.
   // This is the second stage of vectorizing recurrences.
   fixCrossIterationPHIs();
 
   // Forget the original basic block.
   PSE.getSE()->forgetLoop(OrigLoop);
if (llvm::all_of(Src->users(), [&](User *U) -> bool {
                   isScalarUse(J, Src));
         })) {
       Worklist.insert(Src);
       LLVM_DEBUG(dbgs() << "LV: Found scalar instruction: " << *Src << "\n");
     }
   }
 
   // An induction variable will remain scalar if all users of the induction
   // variable and induction variable update remain scalar.
   for (auto &Induction : Legal->getInductionVars()) {
     auto *Ind = Induction.first;
     auto *IndUpdate = cast<Instruction>(Ind->getIncomingValueForBlock(Latch));
 
     // We already considered pointer induction variables, so there's no reason
     // to look at their users again.
     //
     // TODO: Once we are able to vectorize pointer induction variables we
     //       should no longer skip over them here.
     if (Induction.second.getKind() == InductionDescriptor::IK_PtrInduction)
       continue;
 
     // Determine if all users of the induction variable are scalar after
     // vectorization.
     auto ScalarInd = llvm::all_of(Ind->users(), [&](User *U) -> bool {
       auto *I = cast<Instruction>(U);
       return I == IndUpdate || !TheLoop->contains(I) || Worklist.count(I);
     });
     if (!ScalarInd)
       continue;

llvm/test/Transforms/LoopVectorize/AArch64/extractvalue-no-scalarization-required.ll

 ; CM: LV: Scalar loop costs: 7.
 ; CM: LV: Found an estimated cost of 5 for VF 2 For instruction:   %a = extractvalue { i64, i64 } %sv, 0
 ; CM-NEXT: LV: Found an estimated cost of 5 for VF 2 For instruction:   %b = extractvalue { i64, i64 } %sv, 1
 
 ; Check that the extractvalue operands are actually free in vector code.
 
 ; FORCED-LABEL: vector.body:                                      ; preds = %vector.body, %vector.ph
 ; FORCED-NEXT:    %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
-; FORCED-NEXT:    %broadcast.splatinsert = insertelement <2 x i32> undef, i32 %index, i32 0
-; FORCED-NEXT:    %broadcast.splat = shufflevector <2 x i32> %broadcast.splatinsert, <2 x i32> undef, <2 x i32> zeroinitializer
-; FORCED-NEXT:    %induction = add <2 x i32> %broadcast.splat, <i32 0, i32 1>
 ; FORCED-NEXT:    %0 = add i32 %index, 0
 ; FORCED-NEXT:    %1 = extractvalue { i64, i64 } %sv, 0
 ; FORCED-NEXT:    %2 = extractvalue { i64, i64 } %sv, 0
 ; FORCED-NEXT:    %3 = insertelement <2 x i64> undef, i64 %1, i32 0
 ; FORCED-NEXT:    %4 = insertelement <2 x i64> %3, i64 %2, i32 1
 ; FORCED-NEXT:    %5 = extractvalue { i64, i64 } %sv, 1
 ; FORCED-NEXT:    %6 = extractvalue { i64, i64 } %sv, 1
 ; FORCED-NEXT:    %7 = insertelement <2 x i64> undef, i64 %5, i32 0

 ; CM: LV: Scalar loop costs: 16.
 ; CM: LV: Found an estimated cost of 5 for VF 2 For instruction:   %a = extractvalue { float, float } %sv, 0
 ; CM-NEXT: LV: Found an estimated cost of 5 for VF 2 For instruction:   %b = extractvalue { float, float } %sv, 1
 
 ; FORCED-LABEL: define void @test_getVectorCallCost
 
 ; FORCED-LABEL: vector.body:                                      ; preds = %vector.body, %vector.ph
 ; FORCED-NEXT:    %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
-; FORCED-NEXT:    %broadcast.splatinsert = insertelement <2 x i32> undef, i32 %index, i32 0
-; FORCED-NEXT:    %broadcast.splat = shufflevector <2 x i32> %broadcast.splatinsert, <2 x i32> undef, <2 x i32> zeroinitializer
-; FORCED-NEXT:    %induction = add <2 x i32> %broadcast.splat, <i32 0, i32 1>
 ; FORCED-NEXT:    %0 = add i32 %index, 0
 ; FORCED-NEXT:    %1 = extractvalue { float, float } %sv, 0
 ; FORCED-NEXT:    %2 = extractvalue { float, float } %sv, 0
 ; FORCED-NEXT:    %3 = insertelement <2 x float> undef, float %1, i32 0
 ; FORCED-NEXT:    %4 = insertelement <2 x float> %3, float %2, i32 1
 ; FORCED-NEXT:    %5 = extractvalue { float, float } %sv, 1
 ; FORCED-NEXT:    %6 = extractvalue { float, float } %sv, 1
 ; FORCED-NEXT:    %7 = insertelement <2 x float> undef, float %5, i32 0

llvm/test/Transforms/LoopVectorize/AArch64/pr36032.ll

 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP1]], 4
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP1]], [[N_MOD_VF]]
 ; CHECK-NEXT:    [[IND_END:%.*]] = add i64 [[TMP0]], [[N_VEC]]
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = add i64 [[TMP0]], [[INDEX]]
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[OFFSET_IDX]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
-; CHECK-NEXT:    [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3>
 ; CHECK-NEXT:    [[TMP17:%.*]] = add i64 [[OFFSET_IDX]], 0
 ; CHECK-NEXT:    [[OFFSET_IDX4:%.*]] = add i64 [[TMP0]], [[INDEX]]
 ; CHECK-NEXT:    [[TMP18:%.*]] = trunc i64 [[OFFSET_IDX4]] to i32
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT5:%.*]] = insertelement <4 x i32> undef, i32 [[TMP18]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT6:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT5]], <4 x i32> undef, <4 x i32> zeroinitializer
-; CHECK-NEXT:    [[INDUCTION7:%.*]] = add <4 x i32> [[BROADCAST_SPLAT6]], <i32 0, i32 1, i32 2, i32 3>
 ; CHECK-NEXT:    [[TMP19:%.*]] = add i32 [[TMP18]], 0
 ; CHECK-NEXT:    [[TMP20:%.*]] = add i32 [[CONV]], [[TMP19]]
 ; CHECK-NEXT:    [[TMP21:%.*]] = zext i32 [[TMP20]] to i64
 ; CHECK-NEXT:    [[TMP22:%.*]] = getelementptr inbounds [6 x i8], [6 x i8]* @c, i64 0, i64 [[TMP21]]
 ; CHECK-NEXT:    [[TMP23:%.*]] = getelementptr inbounds i8, i8* [[TMP22]], i32 0
 ; CHECK-NEXT:    [[TMP24:%.*]] = bitcast i8* [[TMP23]] to <4 x i8>*
 ; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i8>, <4 x i8>* [[TMP24]], align 1, !alias.scope !0
 ; CHECK-NEXT:    [[TMP25:%.*]] = getelementptr inbounds i8, i8* [[CALL]], i64 [[TMP17]]

llvm/test/Transforms/LoopVectorize/ARM/sphinx.ll

 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i32 [[T]], 2
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i32 [[T]], [[N_MOD_VF]]
 ; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <2 x double> zeroinitializer, double [[CONV114]], i32 0
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <2 x double> [ [[TMP0]], [[VECTOR_PH]] ], [ [[TMP16:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <2 x i32> undef, i32 [[INDEX]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <2 x i32> [[BROADCAST_SPLATINSERT]], <2 x i32> undef, <2 x i32> zeroinitializer
-; CHECK-NEXT:    [[INDUCTION:%.*]] = add <2 x i32> [[BROADCAST_SPLAT]], <i32 0, i32 1>
 ; CHECK-NEXT:    [[TMP1:%.*]] = add i32 [[INDEX]], 0
 ; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds float, float* [[X:%.*]], i32 [[TMP1]]
 ; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds float, float* [[TMP2]], i32 0
 ; CHECK-NEXT:    [[TMP4:%.*]] = bitcast float* [[TMP3]] to <2 x float>*
 ; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <2 x float>, <2 x float>* [[TMP4]], align 4
 ; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds float, float* [[T4]], i32 [[TMP1]]
 ; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds float, float* [[TMP5]], i32 0
 ; CHECK-NEXT:    [[TMP7:%.*]] = bitcast float* [[TMP6]] to <2 x float>*

llvm/test/Transforms/LoopVectorize/X86/constant-fold.ll

 ; CHECK-LABEL: @f1(
 ; CHECK-NEXT:  bb1:
 ; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = trunc i32 [[INDEX]] to i16
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <2 x i16> undef, i16 [[OFFSET_IDX]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <2 x i16> [[BROADCAST_SPLATINSERT]], <2 x i16> undef, <2 x i32> zeroinitializer
-; CHECK-NEXT:    [[INDUCTION:%.*]] = add <2 x i16> [[BROADCAST_SPLAT]], <i16 0, i16 1>
 ; CHECK-NEXT:    [[TMP0:%.*]] = add i16 [[OFFSET_IDX]], 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = sext i16 [[TMP0]] to i64
 ; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr [2 x i16*], [2 x i16*]* @b, i16 0, i64 [[TMP1]]
 ; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr i16*, i16** [[TMP2]], i32 0
 ; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i16** [[TMP3]] to <2 x i16*>*
 ; CHECK-NEXT:    store <2 x i16*> <i16* getelementptr inbounds ([1 x %rec8], [1 x %rec8]* @a, i32 0, i32 0, i32 0), i16* getelementptr inbounds ([1 x %rec8], [1 x %rec8]* @a, i32 0, i32 0, i32 0)>, <2 x i16*>* [[TMP4]], align 8
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 2
 ; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[INDEX_NEXT]], 2

llvm/test/Transforms/LoopVectorize/X86/imprecise-through-phis.ll

 ; AVX-LABEL: @sumIfVector(
 ; AVX-NEXT:  entry:
 ; AVX-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; AVX:       vector.ph:
 ; AVX-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; AVX:       vector.body:
 ; AVX-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; AVX-NEXT:    [[VEC_PHI:%.*]] = phi <4 x double> [ zeroinitializer, [[VECTOR_PH]] ], [ [[PREDPHI:%.*]], [[VECTOR_BODY]] ]
-; AVX-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> undef, i32 [[INDEX]], i32 0
-; AVX-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> undef, <4 x i32> zeroinitializer
-; AVX-NEXT:    [[INDUCTION:%.*]] = add <4 x i32> [[BROADCAST_SPLAT]], <i32 0, i32 1, i32 2, i32 3>
 ; AVX-NEXT:    [[TMP0:%.*]] = add i32 [[INDEX]], 0
 ; AVX-NEXT:    [[TMP1:%.*]] = getelementptr double, double* [[ARR:%.*]], i32 [[TMP0]]
 ; AVX-NEXT:    [[TMP2:%.*]] = getelementptr double, double* [[TMP1]], i32 0
 ; AVX-NEXT:    [[TMP3:%.*]] = bitcast double* [[TMP2]] to <4 x double>*
 ; AVX-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x double>, <4 x double>* [[TMP3]], align 8
 ; AVX-NEXT:    [[TMP4:%.*]] = fcmp fast une <4 x double> [[WIDE_LOAD]], <double 4.200000e+01, double 4.200000e+01, double 4.200000e+01, double 4.200000e+01>
 ; AVX-NEXT:    [[TMP5:%.*]] = fadd fast <4 x double> [[VEC_PHI]], [[WIDE_LOAD]]
 ; AVX-NEXT:    [[TMP6:%.*]] = xor <4 x i1> [[TMP4]], <i1 true, i1 true, i1 true, i1 true>

llvm/test/Transforms/LoopVectorize/X86/load-deref-pred.ll

 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP80:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI4:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP81:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI5:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP82:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI6:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP83:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
-; CHECK-NEXT:    [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3>
-; CHECK-NEXT:    [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 4, i64 5, i64 6, i64 7>
-; CHECK-NEXT:    [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 8, i64 9, i64 10, i64 11>
-; CHECK-NEXT:    [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 12, i64 13, i64 14, i64 15>
 ; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 1
 ; CHECK-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 2
 ; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 3
 ; CHECK-NEXT:    [[TMP4:%.*]] = add i64 [[INDEX]], 4
 ; CHECK-NEXT:    [[TMP5:%.*]] = add i64 [[INDEX]], 5
 ; CHECK-NEXT:    [[TMP6:%.*]] = add i64 [[INDEX]], 6
 ; CHECK-NEXT:    [[TMP7:%.*]] = add i64 [[INDEX]], 7

 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP100:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI4:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP101:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI5:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP102:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI6:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP103:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
-; CHECK-NEXT:    [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3>
-; CHECK-NEXT:    [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 4, i64 5, i64 6, i64 7>
-; CHECK-NEXT:    [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 8, i64 9, i64 10, i64 11>
-; CHECK-NEXT:    [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 12, i64 13, i64 14, i64 15>
 ; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 1
 ; CHECK-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 2
 ; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 3
 ; CHECK-NEXT:    [[TMP4:%.*]] = add i64 [[INDEX]], 4
 ; CHECK-NEXT:    [[TMP5:%.*]] = add i64 [[INDEX]], 5
 ; CHECK-NEXT:    [[TMP6:%.*]] = add i64 [[INDEX]], 6
 ; CHECK-NEXT:    [[TMP7:%.*]] = add i64 [[INDEX]], 7

 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_LOAD_CONTINUE36:%.*]] ]
 ; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP180:%.*]], [[PRED_LOAD_CONTINUE36]] ]
 ; CHECK-NEXT:    [[VEC_PHI4:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP181:%.*]], [[PRED_LOAD_CONTINUE36]] ]
 ; CHECK-NEXT:    [[VEC_PHI5:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP182:%.*]], [[PRED_LOAD_CONTINUE36]] ]
 ; CHECK-NEXT:    [[VEC_PHI6:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP183:%.*]], [[PRED_LOAD_CONTINUE36]] ]
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
-; CHECK-NEXT:    [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3>
-; CHECK-NEXT:    [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 4, i64 5, i64 6, i64 7>
-; CHECK-NEXT:    [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 8, i64 9, i64 10, i64 11>
-; CHECK-NEXT:    [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 12, i64 13, i64 14, i64 15>
 ; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 1
 ; CHECK-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 2
 ; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 3
 ; CHECK-NEXT:    [[TMP4:%.*]] = add i64 [[INDEX]], 4
 ; CHECK-NEXT:    [[TMP5:%.*]] = add i64 [[INDEX]], 5
 ; CHECK-NEXT:    [[TMP6:%.*]] = add i64 [[INDEX]], 6
 ; CHECK-NEXT:    [[TMP7:%.*]] = add i64 [[INDEX]], 7

 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP0]], [[N_MOD_VF]]
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP81:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI4:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP82:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI5:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP83:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI6:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP84:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
-; CHECK-NEXT:    [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3>
-; CHECK-NEXT:    [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 4, i64 5, i64 6, i64 7>
-; CHECK-NEXT:    [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 8, i64 9, i64 10, i64 11>
-; CHECK-NEXT:    [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 12, i64 13, i64 14, i64 15>
 ; CHECK-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 0
 ; CHECK-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 1
 ; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 2
 ; CHECK-NEXT:    [[TMP4:%.*]] = add i64 [[INDEX]], 3
 ; CHECK-NEXT:    [[TMP5:%.*]] = add i64 [[INDEX]], 4
 ; CHECK-NEXT:    [[TMP6:%.*]] = add i64 [[INDEX]], 5
 ; CHECK-NEXT:    [[TMP7:%.*]] = add i64 [[INDEX]], 6
 ; CHECK-NEXT:    [[TMP8:%.*]] = add i64 [[INDEX]], 7

 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP80:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI4:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP81:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI5:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP82:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI6:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP83:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = add i64 1024, [[INDEX]]
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[OFFSET_IDX]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
-; CHECK-NEXT:    [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3>
-; CHECK-NEXT:    [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 4, i64 5, i64 6, i64 7>
-; CHECK-NEXT:    [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 8, i64 9, i64 10, i64 11>
-; CHECK-NEXT:    [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 12, i64 13, i64 14, i64 15>
 ; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[OFFSET_IDX]], 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = add i64 [[OFFSET_IDX]], 1
 ; CHECK-NEXT:    [[TMP2:%.*]] = add i64 [[OFFSET_IDX]], 2
 ; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[OFFSET_IDX]], 3
 ; CHECK-NEXT:    [[TMP4:%.*]] = add i64 [[OFFSET_IDX]], 4
 ; CHECK-NEXT:    [[TMP5:%.*]] = add i64 [[OFFSET_IDX]], 5
 ; CHECK-NEXT:    [[TMP6:%.*]] = add i64 [[OFFSET_IDX]], 6
 ; CHECK-NEXT:    [[TMP7:%.*]] = add i64 [[OFFSET_IDX]], 7

 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_LOAD_CONTINUE36:%.*]] ]
 ; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP148:%.*]], [[PRED_LOAD_CONTINUE36]] ]
 ; CHECK-NEXT:    [[VEC_PHI4:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP149:%.*]], [[PRED_LOAD_CONTINUE36]] ]
 ; CHECK-NEXT:    [[VEC_PHI5:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP150:%.*]], [[PRED_LOAD_CONTINUE36]] ]
 ; CHECK-NEXT:    [[VEC_PHI6:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP151:%.*]], [[PRED_LOAD_CONTINUE36]] ]
 ; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = mul i64 [[INDEX]], 2
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[OFFSET_IDX]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
-; CHECK-NEXT:    [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 2, i64 4, i64 6>
-; CHECK-NEXT:    [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 8, i64 10, i64 12, i64 14>
-; CHECK-NEXT:    [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 16, i64 18, i64 20, i64 22>
-; CHECK-NEXT:    [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 24, i64 26, i64 28, i64 30>
 ; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[OFFSET_IDX]], 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = add i64 [[OFFSET_IDX]], 2
 ; CHECK-NEXT:    [[TMP2:%.*]] = add i64 [[OFFSET_IDX]], 4
 ; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[OFFSET_IDX]], 6
 ; CHECK-NEXT:    [[TMP4:%.*]] = add i64 [[OFFSET_IDX]], 8
 ; CHECK-NEXT:    [[TMP5:%.*]] = add i64 [[OFFSET_IDX]], 10
 ; CHECK-NEXT:    [[TMP6:%.*]] = add i64 [[OFFSET_IDX]], 12
 ; CHECK-NEXT:    [[TMP7:%.*]] = add i64 [[OFFSET_IDX]], 14

 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP80:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI4:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP81:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI5:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP82:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI6:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP83:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
-; CHECK-NEXT:    [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3>
-; CHECK-NEXT:    [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 4, i64 5, i64 6, i64 7>
-; CHECK-NEXT:    [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 8, i64 9, i64 10, i64 11>
-; CHECK-NEXT:    [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 12, i64 13, i64 14, i64 15>
 ; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 1
 ; CHECK-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 2
 ; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 3
 ; CHECK-NEXT:    [[TMP4:%.*]] = add i64 [[INDEX]], 4
 ; CHECK-NEXT:    [[TMP5:%.*]] = add i64 [[INDEX]], 5
 ; CHECK-NEXT:    [[TMP6:%.*]] = add i64 [[INDEX]], 6
 ; CHECK-NEXT:    [[TMP7:%.*]] = add i64 [[INDEX]], 7

 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP80:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI4:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP81:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI5:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP82:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI6:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP83:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
-; CHECK-NEXT:    [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3>
-; CHECK-NEXT:    [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 4, i64 5, i64 6, i64 7>
-; CHECK-NEXT:    [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 8, i64 9, i64 10, i64 11>
-; CHECK-NEXT:    [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 12, i64 13, i64 14, i64 15>
 ; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 1
 ; CHECK-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 2
 ; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 3
 ; CHECK-NEXT:    [[TMP4:%.*]] = add i64 [[INDEX]], 4
 ; CHECK-NEXT:    [[TMP5:%.*]] = add i64 [[INDEX]], 5
 ; CHECK-NEXT:    [[TMP6:%.*]] = add i64 [[INDEX]], 6
 ; CHECK-NEXT:    [[TMP7:%.*]] = add i64 [[INDEX]], 7

 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP80:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI4:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP81:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI5:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP82:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI6:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP83:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
-; CHECK-NEXT:    [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3>
-; CHECK-NEXT:    [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 4, i64 5, i64 6, i64 7>
-; CHECK-NEXT:    [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 8, i64 9, i64 10, i64 11>
-; CHECK-NEXT:    [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 12, i64 13, i64 14, i64 15>
 ; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 1
 ; CHECK-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 2
 ; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 3
 ; CHECK-NEXT:    [[TMP4:%.*]] = add i64 [[INDEX]], 4
 ; CHECK-NEXT:    [[TMP5:%.*]] = add i64 [[INDEX]], 5
 ; CHECK-NEXT:    [[TMP6:%.*]] = add i64 [[INDEX]], 6
 ; CHECK-NEXT:    [[TMP7:%.*]] = add i64 [[INDEX]], 7

llvm/test/Transforms/LoopVectorize/X86/masked_load_store.ll

 ; AVX1-NEXT:    [[FOUND_CONFLICT11:%.*]] = and i1 [[BOUND09]], [[BOUND110]]
 ; AVX1-NEXT:    [[CONFLICT_RDX:%.*]] = or i1 [[FOUND_CONFLICT]], [[FOUND_CONFLICT11]]
 ; AVX1-NEXT:    [[MEMCHECK_CONFLICT:%.*]] = and i1 [[CONFLICT_RDX]], true
 ; AVX1-NEXT:    br i1 [[MEMCHECK_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
 ; AVX1:       vector.ph:
 ; AVX1-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; AVX1:       vector.body:
 ; AVX1-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; AVX1-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[INDEX]], i32 0
-; AVX1-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer
-; AVX1-NEXT:    [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
 ; AVX1-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; AVX1-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP0]]
 ; AVX1-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i32 0
 ; AVX1-NEXT:    [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <8 x i32>*
 ; AVX1-NEXT:    [[WIDE_LOAD:%.*]] = load <8 x i32>, <8 x i32>* [[TMP3]], align 4, !alias.scope !0
 ; AVX1-NEXT:    [[TMP4:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD]], <i32 100, i32 100, i32 100, i32 100, i32 100, i32 100, i32 100, i32 100>
 ; AVX1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP0]]
 ; AVX1-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[TMP5]], i32 0

 ; AVX2-NEXT:    [[FOUND_CONFLICT11:%.*]] = and i1 [[BOUND09]], [[BOUND110]]
 ; AVX2-NEXT:    [[CONFLICT_RDX:%.*]] = or i1 [[FOUND_CONFLICT]], [[FOUND_CONFLICT11]]
 ; AVX2-NEXT:    [[MEMCHECK_CONFLICT:%.*]] = and i1 [[CONFLICT_RDX]], true
 ; AVX2-NEXT:    br i1 [[MEMCHECK_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
 ; AVX2:       vector.ph:
 ; AVX2-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; AVX2:       vector.body:
 ; AVX2-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; AVX2-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[INDEX]], i32 0
-; AVX2-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer
-; AVX2-NEXT:    [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
-; AVX2-NEXT:    [[INDUCTION12:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 8, i64 9, i64 10, i64 11, i64 12, i64 13, i64 14, i64 15>
-; AVX2-NEXT:    [[INDUCTION13:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 16, i64 17, i64 18, i64 19, i64 20, i64 21, i64 22, i64 23>
-; AVX2-NEXT:    [[INDUCTION14:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 24, i64 25, i64 26, i64 27, i64 28, i64 29, i64 30, i64 31>
 ; AVX2-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; AVX2-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 8
 ; AVX2-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 16
 ; AVX2-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 24
 ; AVX2-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP0]]
 ; AVX2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP1]]
 ; AVX2-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP2]]
 ; AVX2-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP3]]

 ; AVX512-NEXT:    [[FOUND_CONFLICT11:%.*]] = and i1 [[BOUND09]], [[BOUND110]]
 ; AVX512-NEXT:    [[CONFLICT_RDX:%.*]] = or i1 [[FOUND_CONFLICT]], [[FOUND_CONFLICT11]]
 ; AVX512-NEXT:    [[MEMCHECK_CONFLICT:%.*]] = and i1 [[CONFLICT_RDX]], true
 ; AVX512-NEXT:    br i1 [[MEMCHECK_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
 ; AVX512:       vector.ph:
 ; AVX512-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; AVX512:       vector.body:
 ; AVX512-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; AVX512-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <16 x i64> undef, i64 [[INDEX]], i32 0
-; AVX512-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <16 x i64> [[BROADCAST_SPLATINSERT]], <16 x i64> undef, <16 x i32> zeroinitializer
-; AVX512-NEXT:    [[INDUCTION:%.*]] = add <16 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11, i64 12, i64 13, i64 14, i64 15>
-; AVX512-NEXT:    [[INDUCTION12:%.*]] = add <16 x i64> [[BROADCAST_SPLAT]], <i64 16, i64 17, i64 18, i64 19, i64 20, i64 21, i64 22, i64 23, i64 24, i64 25, i64 26, i64 27, i64 28, i64 29, i64 30, i64 31>
-; AVX512-NEXT:    [[INDUCTION13:%.*]] = add <16 x i64> [[BROADCAST_SPLAT]], <i64 32, i64 33, i64 34, i64 35, i64 36, i64 37, i64 38, i64 39, i64 40, i64 41, i64 42, i64 43, i64 44, i64 45, i64 46, i64 47>
-; AVX512-NEXT:    [[INDUCTION14:%.*]] = add <16 x i64> [[BROADCAST_SPLAT]], <i64 48, i64 49, i64 50, i64 51, i64 52, i64 53, i64 54, i64 55, i64 56, i64 57, i64 58, i64 59, i64 60, i64 61, i64 62, i64 63>
 ; AVX512-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; AVX512-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 16
 ; AVX512-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 32
 ; AVX512-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 48
 ; AVX512-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP0]]
 ; AVX512-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP1]]
 ; AVX512-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP2]]
 ; AVX512-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP3]]

 ; AVX1-NEXT:    [[FOUND_CONFLICT11:%.*]] = and i1 [[BOUND09]], [[BOUND110]]
 ; AVX1-NEXT:    [[CONFLICT_RDX:%.*]] = or i1 [[FOUND_CONFLICT]], [[FOUND_CONFLICT11]]
 ; AVX1-NEXT:    [[MEMCHECK_CONFLICT:%.*]] = and i1 [[CONFLICT_RDX]], true
 ; AVX1-NEXT:    br i1 [[MEMCHECK_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
 ; AVX1:       vector.ph:
 ; AVX1-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; AVX1:       vector.body:
 ; AVX1-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; AVX1-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[INDEX]], i32 0
-; AVX1-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer
-; AVX1-NEXT:    [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
 ; AVX1-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; AVX1-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[TRIGGER]], i64 [[TMP0]]
 ; AVX1-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[TMP1]], i32 0
 ; AVX1-NEXT:    [[TMP3:%.*]] = bitcast i32 addrspace(1)* [[TMP2]] to <8 x i32> addrspace(1)*
 ; AVX1-NEXT:    [[WIDE_LOAD:%.*]] = load <8 x i32>, <8 x i32> addrspace(1)* [[TMP3]], align 4, !alias.scope !11
 ; AVX1-NEXT:    [[TMP4:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD]], <i32 100, i32 100, i32 100, i32 100, i32 100, i32 100, i32 100, i32 100>
 ; AVX1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[B]], i64 [[TMP0]]
 ; AVX1-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[TMP5]], i32 0

 ; AVX2-NEXT:    [[FOUND_CONFLICT11:%.*]] = and i1 [[BOUND09]], [[BOUND110]]
 ; AVX2-NEXT:    [[CONFLICT_RDX:%.*]] = or i1 [[FOUND_CONFLICT]], [[FOUND_CONFLICT11]]
 ; AVX2-NEXT:    [[MEMCHECK_CONFLICT:%.*]] = and i1 [[CONFLICT_RDX]], true
 ; AVX2-NEXT:    br i1 [[MEMCHECK_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
 ; AVX2:       vector.ph:
 ; AVX2-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; AVX2:       vector.body:
 ; AVX2-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; AVX2-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[INDEX]], i32 0
-; AVX2-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer
-; AVX2-NEXT:    [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
-; AVX2-NEXT:    [[INDUCTION12:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 8, i64 9, i64 10, i64 11, i64 12, i64 13, i64 14, i64 15>
-; AVX2-NEXT:    [[INDUCTION13:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 16, i64 17, i64 18, i64 19, i64 20, i64 21, i64 22, i64 23>
-; AVX2-NEXT:    [[INDUCTION14:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 24, i64 25, i64 26, i64 27, i64 28, i64 29, i64 30, i64 31>
 ; AVX2-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; AVX2-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 8
 ; AVX2-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 16
 ; AVX2-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 24
 ; AVX2-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[TRIGGER]], i64 [[TMP0]]
 ; AVX2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[TRIGGER]], i64 [[TMP1]]
 ; AVX2-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[TRIGGER]], i64 [[TMP2]]
 ; AVX2-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[TRIGGER]], i64 [[TMP3]]

 ; AVX512-NEXT:    [[FOUND_CONFLICT11:%.*]] = and i1 [[BOUND09]], [[BOUND110]]
 ; AVX512-NEXT:    [[CONFLICT_RDX:%.*]] = or i1 [[FOUND_CONFLICT]], [[FOUND_CONFLICT11]]
 ; AVX512-NEXT:    [[MEMCHECK_CONFLICT:%.*]] = and i1 [[CONFLICT_RDX]], true
 ; AVX512-NEXT:    br i1 [[MEMCHECK_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
 ; AVX512:       vector.ph:
 ; AVX512-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; AVX512:       vector.body:
 ; AVX512-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; AVX512-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <16 x i64> undef, i64 [[INDEX]], i32 0
-; AVX512-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <16 x i64> [[BROADCAST_SPLATINSERT]], <16 x i64> undef, <16 x i32> zeroinitializer
-; AVX512-NEXT:    [[INDUCTION:%.*]] = add <16 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11, i64 12, i64 13, i64 14, i64 15>
-; AVX512-NEXT:    [[INDUCTION12:%.*]] = add <16 x i64> [[BROADCAST_SPLAT]], <i64 16, i64 17, i64 18, i64 19, i64 20, i64 21, i64 22, i64 23, i64 24, i64 25, i64 26, i64 27, i64 28, i64 29, i64 30, i64 31>
-; AVX512-NEXT:    [[INDUCTION13:%.*]] = add <16 x i64> [[BROADCAST_SPLAT]], <i64 32, i64 33, i64 34, i64 35, i64 36, i64 37, i64 38, i64 39, i64 40, i64 41, i64 42, i64 43, i64 44, i64 45, i64 46, i64 47>
-; AVX512-NEXT:    [[INDUCTION14:%.*]] = add <16 x i64> [[BROADCAST_SPLAT]], <i64 48, i64 49, i64 50, i64 51, i64 52, i64 53, i64 54, i64 55, i64 56, i64 57, i64 58, i64 59, i64 60, i64 61, i64 62, i64 63>
 ; AVX512-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; AVX512-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 16
 ; AVX512-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 32
 ; AVX512-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 48
 ; AVX512-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[TRIGGER]], i64 [[TMP0]]
 ; AVX512-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[TRIGGER]], i64 [[TMP1]]
 ; AVX512-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[TRIGGER]], i64 [[TMP2]]
 ; AVX512-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[TRIGGER]], i64 [[TMP3]]

 ; AVX1-NEXT:    [[FOUND_CONFLICT11:%.*]] = and i1 [[BOUND09]], [[BOUND110]]
 ; AVX1-NEXT:    [[CONFLICT_RDX:%.*]] = or i1 [[FOUND_CONFLICT]], [[FOUND_CONFLICT11]]
 ; AVX1-NEXT:    [[MEMCHECK_CONFLICT:%.*]] = and i1 [[CONFLICT_RDX]], true
 ; AVX1-NEXT:    br i1 [[MEMCHECK_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
 ; AVX1:       vector.ph:
 ; AVX1-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; AVX1:       vector.body:
 ; AVX1-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; AVX1-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[INDEX]], i32 0
-; AVX1-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer
-; AVX1-NEXT:    [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
 ; AVX1-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; AVX1-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP0]]
 ; AVX1-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i32 0
 ; AVX1-NEXT:    [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <8 x i32>*
 ; AVX1-NEXT:    [[WIDE_LOAD:%.*]] = load <8 x i32>, <8 x i32>* [[TMP3]], align 4, !alias.scope !21
 ; AVX1-NEXT:    [[TMP4:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD]], <i32 100, i32 100, i32 100, i32 100, i32 100, i32 100, i32 100, i32 100>
 ; AVX1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds float, float* [[B]], i64 [[TMP0]]
 ; AVX1-NEXT:    [[TMP6:%.*]] = getelementptr inbounds float, float* [[TMP5]], i32 0

 ; AVX2-NEXT:    [[FOUND_CONFLICT11:%.*]] = and i1 [[BOUND09]], [[BOUND110]]
 ; AVX2-NEXT:    [[CONFLICT_RDX:%.*]] = or i1 [[FOUND_CONFLICT]], [[FOUND_CONFLICT11]]
 ; AVX2-NEXT:    [[MEMCHECK_CONFLICT:%.*]] = and i1 [[CONFLICT_RDX]], true
 ; AVX2-NEXT:    br i1 [[MEMCHECK_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
 ; AVX2:       vector.ph:
 ; AVX2-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; AVX2:       vector.body:
 ; AVX2-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; AVX2-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[INDEX]], i32 0
-; AVX2-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer
-; AVX2-NEXT:    [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
-; AVX2-NEXT:    [[INDUCTION12:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 8, i64 9, i64 10, i64 11, i64 12, i64 13, i64 14, i64 15>
-; AVX2-NEXT:    [[INDUCTION13:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 16, i64 17, i64 18, i64 19, i64 20, i64 21, i64 22, i64 23>
-; AVX2-NEXT:    [[INDUCTION14:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 24, i64 25, i64 26, i64 27, i64 28, i64 29, i64 30, i64 31>
 ; AVX2-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; AVX2-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 8
 ; AVX2-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 16
 ; AVX2-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 24
 ; AVX2-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP0]]
 ; AVX2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP1]]
 ; AVX2-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP2]]
 ; AVX2-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP3]]

 ; AVX512-NEXT:    [[FOUND_CONFLICT11:%.*]] = and i1 [[BOUND09]], [[BOUND110]]
 ; AVX512-NEXT:    [[CONFLICT_RDX:%.*]] = or i1 [[FOUND_CONFLICT]], [[FOUND_CONFLICT11]]
 ; AVX512-NEXT:    [[MEMCHECK_CONFLICT:%.*]] = and i1 [[CONFLICT_RDX]], true
 ; AVX512-NEXT:    br i1 [[MEMCHECK_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
 ; AVX512:       vector.ph:
 ; AVX512-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; AVX512:       vector.body:
 ; AVX512-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; AVX512-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <16 x i64> undef, i64 [[INDEX]], i32 0
-; AVX512-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <16 x i64> [[BROADCAST_SPLATINSERT]], <16 x i64> undef, <16 x i32> zeroinitializer
-; AVX512-NEXT:    [[INDUCTION:%.*]] = add <16 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11, i64 12, i64 13, i64 14, i64 15>
-; AVX512-NEXT:    [[INDUCTION12:%.*]] = add <16 x i64> [[BROADCAST_SPLAT]], <i64 16, i64 17, i64 18, i64 19, i64 20, i64 21, i64 22, i64 23, i64 24, i64 25, i64 26, i64 27, i64 28, i64 29, i64 30, i64 31>
-; AVX512-NEXT:    [[INDUCTION13:%.*]] = add <16 x i64> [[BROADCAST_SPLAT]], <i64 32, i64 33, i64 34, i64 35, i64 36, i64 37, i64 38, i64 39, i64 40, i64 41, i64 42, i64 43, i64 44, i64 45, i64 46, i64 47>
-; AVX512-NEXT:    [[INDUCTION14:%.*]] = add <16 x i64> [[BROADCAST_SPLAT]], <i64 48, i64 49, i64 50, i64 51, i64 52, i64 53, i64 54, i64 55, i64 56, i64 57, i64 58, i64 59, i64 60, i64 61, i64 62, i64 63>
 ; AVX512-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; AVX512-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 16
 ; AVX512-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 32
 ; AVX512-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 48
 ; AVX512-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP0]]
 ; AVX512-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP1]]
 ; AVX512-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP2]]
 ; AVX512-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP3]]

 ; AVX-NEXT:    [[FOUND_CONFLICT11:%.*]] = and i1 [[BOUND09]], [[BOUND110]]
 ; AVX-NEXT:    [[CONFLICT_RDX:%.*]] = or i1 [[FOUND_CONFLICT]], [[FOUND_CONFLICT11]]
 ; AVX-NEXT:    [[MEMCHECK_CONFLICT:%.*]] = and i1 [[CONFLICT_RDX]], true
 ; AVX-NEXT:    br i1 [[MEMCHECK_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
 ; AVX:       vector.ph:
 ; AVX-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; AVX:       vector.body:
 ; AVX-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; AVX-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0
-; AVX-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
-; AVX-NEXT:    [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3>
-; AVX-NEXT:    [[INDUCTION12:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 4, i64 5, i64 6, i64 7>
-; AVX-NEXT:    [[INDUCTION13:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 8, i64 9, i64 10, i64 11>
-; AVX-NEXT:    [[INDUCTION14:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 12, i64 13, i64 14, i64 15>
 ; AVX-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; AVX-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 4
 ; AVX-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 8
 ; AVX-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 12
 ; AVX-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP0]]
 ; AVX-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP1]]
 ; AVX-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP2]]
 ; AVX-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP3]]

 ; AVX512-NEXT:    [[FOUND_CONFLICT11:%.*]] = and i1 [[BOUND09]], [[BOUND110]]
 ; AVX512-NEXT:    [[CONFLICT_RDX:%.*]] = or i1 [[FOUND_CONFLICT]], [[FOUND_CONFLICT11]]
 ; AVX512-NEXT:    [[MEMCHECK_CONFLICT:%.*]] = and i1 [[CONFLICT_RDX]], true
 ; AVX512-NEXT:    br i1 [[MEMCHECK_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
 ; AVX512:       vector.ph:
 ; AVX512-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; AVX512:       vector.body:
 ; AVX512-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; AVX512-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[INDEX]], i32 0
-; AVX512-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer
-; AVX512-NEXT:    [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
-; AVX512-NEXT:    [[INDUCTION12:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 8, i64 9, i64 10, i64 11, i64 12, i64 13, i64 14, i64 15>
-; AVX512-NEXT:    [[INDUCTION13:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 16, i64 17, i64 18, i64 19, i64 20, i64 21, i64 22, i64 23>
-; AVX512-NEXT:    [[INDUCTION14:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 24, i64 25, i64 26, i64 27, i64 28, i64 29, i64 30, i64 31>
 ; AVX512-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; AVX512-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 8
 ; AVX512-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 16
 ; AVX512-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 24
 ; AVX512-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP0]]
 ; AVX512-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP1]]
 ; AVX512-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP2]]
 ; AVX512-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP3]]

 ; AVX2-NEXT:    [[CONFLICT_RDX:%.*]] = or i1 [[FOUND_CONFLICT]], [[FOUND_CONFLICT11]]
 ; AVX2-NEXT:    [[MEMCHECK_CONFLICT:%.*]] = and i1 [[CONFLICT_RDX]], true
 ; AVX2-NEXT:    br i1 [[MEMCHECK_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
 ; AVX2:       vector.ph:
 ; AVX2-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; AVX2:       vector.body:
 ; AVX2-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; AVX2-NEXT:    [[OFFSET_IDX:%.*]] = sub i64 4095, [[INDEX]]
-; AVX2-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[OFFSET_IDX]], i32 0
-; AVX2-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
-; AVX2-NEXT:    [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 -1, i64 -2, i64 -3>
-; AVX2-NEXT:    [[INDUCTION12:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 -4, i64 -5, i64 -6, i64 -7>
-; AVX2-NEXT:    [[INDUCTION13:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 -8, i64 -9, i64 -10, i64 -11>
-; AVX2-NEXT:    [[INDUCTION14:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 -12, i64 -13, i64 -14, i64 -15>
 ; AVX2-NEXT:    [[TMP0:%.*]] = add i64 [[OFFSET_IDX]], 0
 ; AVX2-NEXT:    [[TMP1:%.*]] = add i64 [[OFFSET_IDX]], -4
 ; AVX2-NEXT:    [[TMP2:%.*]] = add i64 [[OFFSET_IDX]], -8
 ; AVX2-NEXT:    [[TMP3:%.*]] = add i64 [[OFFSET_IDX]], -12
 ; AVX2-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP0]]
 ; AVX2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP1]]
 ; AVX2-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP2]]
 ; AVX2-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP3]]

 ; AVX512-NEXT:    [[CONFLICT_RDX:%.*]] = or i1 [[FOUND_CONFLICT]], [[FOUND_CONFLICT11]]
 ; AVX512-NEXT:    [[MEMCHECK_CONFLICT:%.*]] = and i1 [[CONFLICT_RDX]], true
 ; AVX512-NEXT:    br i1 [[MEMCHECK_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
 ; AVX512:       vector.ph:
 ; AVX512-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; AVX512:       vector.body:
 ; AVX512-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; AVX512-NEXT:    [[OFFSET_IDX:%.*]] = sub i64 4095, [[INDEX]]
-; AVX512-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[OFFSET_IDX]], i32 0
-; AVX512-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer
-; AVX512-NEXT:    [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 -1, i64 -2, i64 -3, i64 -4, i64 -5, i64 -6, i64 -7>
-; AVX512-NEXT:    [[INDUCTION12:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 -8, i64 -9, i64 -10, i64 -11, i64 -12, i64 -13, i64 -14, i64 -15>
-; AVX512-NEXT:    [[INDUCTION13:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 -16, i64 -17, i64 -18, i64 -19, i64 -20, i64 -21, i64 -22, i64 -23>
-; AVX512-NEXT:    [[INDUCTION14:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 -24, i64 -25, i64 -26, i64 -27, i64 -28, i64 -29, i64 -30, i64 -31>
 ; AVX512-NEXT:    [[TMP0:%.*]] = add i64 [[OFFSET_IDX]], 0
 ; AVX512-NEXT:    [[TMP1:%.*]] = add i64 [[OFFSET_IDX]], -8
 ; AVX512-NEXT:    [[TMP2:%.*]] = add i64 [[OFFSET_IDX]], -16
 ; AVX512-NEXT:    [[TMP3:%.*]] = add i64 [[OFFSET_IDX]], -24
 ; AVX512-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP0]]
 ; AVX512-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP1]]
 ; AVX512-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP2]]
 ; AVX512-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP3]]

 ; AVX1-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[WIDE_TRIP_COUNT]], 16
 ; AVX1-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; AVX1:       vector.ph:
 ; AVX1-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[WIDE_TRIP_COUNT]], 16
 ; AVX1-NEXT:    [[N_VEC:%.*]] = sub i64 [[WIDE_TRIP_COUNT]], [[N_MOD_VF]]
 ; AVX1-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; AVX1:       vector.body:
 ; AVX1-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; AVX1-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0
-; AVX1-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
-; AVX1-NEXT:    [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3>
-; AVX1-NEXT:    [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 4, i64 5, i64 6, i64 7>
-; AVX1-NEXT:    [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 8, i64 9, i64 10, i64 11>
-; AVX1-NEXT:    [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 12, i64 13, i64 14, i64 15>
 ; AVX1-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; AVX1-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 4
 ; AVX1-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 8
 ; AVX1-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 12
 ; AVX1-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i8, i8* [[TRIGGER:%.*]], i64 [[TMP0]]
 ; AVX1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i8, i8* [[TRIGGER]], i64 [[TMP1]]
 ; AVX1-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i8, i8* [[TRIGGER]], i64 [[TMP2]]
 ; AVX1-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i8, i8* [[TRIGGER]], i64 [[TMP3]]

 ; AVX2-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[WIDE_TRIP_COUNT]], 16
 ; AVX2-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; AVX2:       vector.ph:
 ; AVX2-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[WIDE_TRIP_COUNT]], 16
 ; AVX2-NEXT:    [[N_VEC:%.*]] = sub i64 [[WIDE_TRIP_COUNT]], [[N_MOD_VF]]
 ; AVX2-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; AVX2:       vector.body:
 ; AVX2-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; AVX2-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0
-; AVX2-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
-; AVX2-NEXT:    [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3>
-; AVX2-NEXT:    [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 4, i64 5, i64 6, i64 7>
-; AVX2-NEXT:    [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 8, i64 9, i64 10, i64 11>
-; AVX2-NEXT:    [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 12, i64 13, i64 14, i64 15>
 ; AVX2-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; AVX2-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 4
 ; AVX2-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 8
 ; AVX2-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 12
 ; AVX2-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i8, i8* [[TRIGGER:%.*]], i64 [[TMP0]]
 ; AVX2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i8, i8* [[TRIGGER]], i64 [[TMP1]]
 ; AVX2-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i8, i8* [[TRIGGER]], i64 [[TMP2]]
 ; AVX2-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i8, i8* [[TRIGGER]], i64 [[TMP3]]

 ; AVX512-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[WIDE_TRIP_COUNT]], 32
 ; AVX512-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; AVX512:       vector.ph:
 ; AVX512-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[WIDE_TRIP_COUNT]], 32
 ; AVX512-NEXT:    [[N_VEC:%.*]] = sub i64 [[WIDE_TRIP_COUNT]], [[N_MOD_VF]]
 ; AVX512-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; AVX512:       vector.body:
 ; AVX512-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; AVX512-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[INDEX]], i32 0
-; AVX512-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer
-; AVX512-NEXT:    [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
-; AVX512-NEXT:    [[INDUCTION1:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 8, i64 9, i64 10, i64 11, i64 12, i64 13, i64 14, i64 15>
-; AVX512-NEXT:    [[INDUCTION2:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 16, i64 17, i64 18, i64 19, i64 20, i64 21, i64 22, i64 23>
-; AVX512-NEXT:    [[INDUCTION3:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 24, i64 25, i64 26, i64 27, i64 28, i64 29, i64 30, i64 31>
 ; AVX512-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; AVX512-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 8
 ; AVX512-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 16
 ; AVX512-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 24
 ; AVX512-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i8, i8* [[TRIGGER:%.*]], i64 [[TMP0]]
 ; AVX512-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i8, i8* [[TRIGGER]], i64 [[TMP1]]
 ; AVX512-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i8, i8* [[TRIGGER]], i64 [[TMP2]]
 ; AVX512-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i8, i8* [[TRIGGER]], i64 [[TMP3]]

 ; AVX1-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[WIDE_TRIP_COUNT]], 16
 ; AVX1-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; AVX1:       vector.ph:
 ; AVX1-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[WIDE_TRIP_COUNT]], 16
 ; AVX1-NEXT:    [[N_VEC:%.*]] = sub i64 [[WIDE_TRIP_COUNT]], [[N_MOD_VF]]
 ; AVX1-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; AVX1:       vector.body:
 ; AVX1-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; AVX1-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0
-; AVX1-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
-; AVX1-NEXT:    [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3>
-; AVX1-NEXT:    [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 4, i64 5, i64 6, i64 7>
-; AVX1-NEXT:    [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 8, i64 9, i64 10, i64 11>
-; AVX1-NEXT:    [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 12, i64 13, i64 14, i64 15>
 ; AVX1-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; AVX1-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 4
 ; AVX1-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 8
 ; AVX1-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 12
 ; AVX1-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i8, i8* [[TRIGGER:%.*]], i64 [[TMP0]]
 ; AVX1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i8, i8* [[TRIGGER]], i64 [[TMP1]]
 ; AVX1-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i8, i8* [[TRIGGER]], i64 [[TMP2]]
 ; AVX1-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i8, i8* [[TRIGGER]], i64 [[TMP3]]

 ; AVX2-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[WIDE_TRIP_COUNT]], 16
 ; AVX2-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; AVX2:       vector.ph:
 ; AVX2-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[WIDE_TRIP_COUNT]], 16
 ; AVX2-NEXT:    [[N_VEC:%.*]] = sub i64 [[WIDE_TRIP_COUNT]], [[N_MOD_VF]]
 ; AVX2-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; AVX2:       vector.body:
 ; AVX2-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; AVX2-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0
-; AVX2-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
-; AVX2-NEXT:    [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3>
-; AVX2-NEXT:    [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 4, i64 5, i64 6, i64 7>
-; AVX2-NEXT:    [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 8, i64 9, i64 10, i64 11>
-; AVX2-NEXT:    [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 12, i64 13, i64 14, i64 15>
 ; AVX2-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; AVX2-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 4
 ; AVX2-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 8
 ; AVX2-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 12
 ; AVX2-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i8, i8* [[TRIGGER:%.*]], i64 [[TMP0]]
 ; AVX2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i8, i8* [[TRIGGER]], i64 [[TMP1]]
 ; AVX2-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i8, i8* [[TRIGGER]], i64 [[TMP2]]
 ; AVX2-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i8, i8* [[TRIGGER]], i64 [[TMP3]]

 ; AVX512-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[WIDE_TRIP_COUNT]], 32
 ; AVX512-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; AVX512:       vector.ph:
 ; AVX512-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[WIDE_TRIP_COUNT]], 32
 ; AVX512-NEXT:    [[N_VEC:%.*]] = sub i64 [[WIDE_TRIP_COUNT]], [[N_MOD_VF]]
 ; AVX512-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; AVX512:       vector.body:
 ; AVX512-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; AVX512-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[INDEX]], i32 0
-; AVX512-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer
-; AVX512-NEXT:    [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
-; AVX512-NEXT:    [[INDUCTION1:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 8, i64 9, i64 10, i64 11, i64 12, i64 13, i64 14, i64 15>
-; AVX512-NEXT:    [[INDUCTION2:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 16, i64 17, i64 18, i64 19, i64 20, i64 21, i64 22, i64 23>
-; AVX512-NEXT:    [[INDUCTION3:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 24, i64 25, i64 26, i64 27, i64 28, i64 29, i64 30, i64 31>
 ; AVX512-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; AVX512-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 8
 ; AVX512-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 16
 ; AVX512-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 24
 ; AVX512-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i8, i8* [[TRIGGER:%.*]], i64 [[TMP0]]
 ; AVX512-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i8, i8* [[TRIGGER]], i64 [[TMP1]]
 ; AVX512-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i8, i8* [[TRIGGER]], i64 [[TMP2]]
 ; AVX512-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i8, i8* [[TRIGGER]], i64 [[TMP3]]

llvm/test/Transforms/LoopVectorize/X86/metadata-enable.ll

 ; O1VEC2-NEXT:  entry:
 ; O1VEC2-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; O1VEC2:       vector.ph:
 ; O1VEC2-NEXT:    [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0
 ; O1VEC2-NEXT:    [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT1]], <4 x i32> undef, <4 x i32> zeroinitializer
 ; O1VEC2-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; O1VEC2:       vector.body:
 ; O1VEC2-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; O1VEC2-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0
-; O1VEC2-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
-; O1VEC2-NEXT:    [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3>
 ; O1VEC2-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; O1VEC2-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[TMP0]]
 ; O1VEC2-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i32 0
 ; O1VEC2-NEXT:    [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <4 x i32>*
 ; O1VEC2-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP3]], align 4
 ; O1VEC2-NEXT:    [[TMP4:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT2]]
 ; O1VEC2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[TMP0]]
 ; O1VEC2-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[TMP5]], i32 0

 ; OzVEC2-NEXT:  entry:
 ; OzVEC2-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; OzVEC2:       vector.ph:
 ; OzVEC2-NEXT:    [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0
 ; OzVEC2-NEXT:    [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT1]], <4 x i32> undef, <4 x i32> zeroinitializer
 ; OzVEC2-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; OzVEC2:       vector.body:
 ; OzVEC2-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; OzVEC2-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0
-; OzVEC2-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
-; OzVEC2-NEXT:    [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3>
 ; OzVEC2-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; OzVEC2-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[TMP0]]
 ; OzVEC2-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i32 0
 ; OzVEC2-NEXT:    [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <4 x i32>*
 ; OzVEC2-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP3]], align 4
 ; OzVEC2-NEXT:    [[TMP4:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT2]]
 ; OzVEC2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[TMP0]]
 ; OzVEC2-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[TMP5]], i32 0

llvm/test/Transforms/LoopVectorize/X86/pr35432.ll

 ; CHECK-NEXT:    br i1 [[CMP63]], label [[FOR_BODY8_LR_PH:%.*]], label [[FOR_INC9]]
 ; CHECK:       for.body8.lr.ph:
 ; CHECK-NEXT:    [[CONV3:%.*]] = trunc i32 [[STOREMERGE_IN9]] to i8
 ; CHECK-NEXT:    [[DOTPROMOTED:%.*]] = load i32, i32* getelementptr inbounds ([192 x [192 x i32]], [192 x [192 x i32]]* @a, i64 0, i64 0, i64 0), align 16
 ; CHECK-NEXT:    [[TMP3:%.*]] = add i8 [[CONV3]], -1
 ; CHECK-NEXT:    [[TMP4:%.*]] = zext i8 [[TMP3]] to i32
 ; CHECK-NEXT:    [[TMP5:%.*]] = add i32 [[TMP4]], 1
 ; CHECK-NEXT:    [[TMP6:%.*]] = icmp ult i32 [[TMP2]], [[TMP4]]
-; CHECK-NEXT:    [[UMAX:%.*]] = select i1 [[TMP6]], i32 [[TMP2]], i32 [[TMP4]]
-; CHECK-NEXT:    [[TMP7:%.*]] = sub i32 [[TMP5]], [[UMAX]]
+; CHECK-NEXT:    [[UMIN:%.*]] = select i1 [[TMP6]], i32 [[TMP2]], i32 [[TMP4]]
+; CHECK-NEXT:    [[TMP7:%.*]] = sub i32 [[TMP5]], [[UMIN]]
 ; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[TMP7]], 8
 ; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
 ; CHECK:       vector.scevcheck:
 ; CHECK-NEXT:    [[TMP8:%.*]] = add i8 [[CONV3]], -1
 ; CHECK-NEXT:    [[TMP9:%.*]] = zext i8 [[TMP8]] to i32
 ; CHECK-NEXT:    [[TMP10:%.*]] = icmp ult i32 [[TMP2]], [[TMP9]]
-; CHECK-NEXT:    [[UMAX1:%.*]] = select i1 [[TMP10]], i32 [[TMP2]], i32 [[TMP9]]
-; CHECK-NEXT:    [[TMP11:%.*]] = sub i32 [[TMP9]], [[UMAX1]]
+; CHECK-NEXT:    [[UMIN1:%.*]] = select i1 [[TMP10]], i32 [[TMP2]], i32 [[TMP9]]
+; CHECK-NEXT:    [[TMP11:%.*]] = sub i32 [[TMP9]], [[UMIN1]]
 ; CHECK-NEXT:    [[TMP12:%.*]] = trunc i32 [[TMP11]] to i8
 ; CHECK-NEXT:    [[MUL:%.*]] = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 1, i8 [[TMP12]])
 ; CHECK-NEXT:    [[MUL_RESULT:%.*]] = extractvalue { i8, i1 } [[MUL]], 0
 ; CHECK-NEXT:    [[MUL_OVERFLOW:%.*]] = extractvalue { i8, i1 } [[MUL]], 1
 ; CHECK-NEXT:    [[TMP13:%.*]] = add i8 [[TMP8]], [[MUL_RESULT]]
 ; CHECK-NEXT:    [[TMP14:%.*]] = sub i8 [[TMP8]], [[MUL_RESULT]]
 ; CHECK-NEXT:    [[TMP15:%.*]] = icmp ugt i8 [[TMP14]], [[TMP8]]
 ; CHECK-NEXT:    [[TMP16:%.*]] = icmp ult i8 [[TMP13]], [[TMP8]]

 ; CHECK-NEXT:    [[TMP22:%.*]] = insertelement <4 x i32> zeroinitializer, i32 [[DOTPROMOTED]], i32 0
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ [[TMP22]], [[VECTOR_PH]] ], [ [[TMP26:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI2:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP27:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP23:%.*]] = trunc i32 [[INDEX]] to i8
 ; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = sub i8 [[CONV3]], [[TMP23]]
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i8> undef, i8 [[OFFSET_IDX]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i8> [[BROADCAST_SPLATINSERT]], <4 x i8> undef, <4 x i32> zeroinitializer
-; CHECK-NEXT:    [[INDUCTION:%.*]] = add <4 x i8> [[BROADCAST_SPLAT]], <i8 0, i8 -1, i8 -2, i8 -3>
-; CHECK-NEXT:    [[INDUCTION3:%.*]] = add <4 x i8> [[BROADCAST_SPLAT]], <i8 -4, i8 -5, i8 -6, i8 -7>
 ; CHECK-NEXT:    [[TMP24:%.*]] = add i8 [[OFFSET_IDX]], 0
 ; CHECK-NEXT:    [[TMP25:%.*]] = add i8 [[OFFSET_IDX]], -4
 ; CHECK-NEXT:    [[TMP26]] = add <4 x i32> [[VEC_PHI]], <i32 1, i32 1, i32 1, i32 1>
 ; CHECK-NEXT:    [[TMP27]] = add <4 x i32> [[VEC_PHI2]], <i32 1, i32 1, i32 1, i32 1>
 ; CHECK-NEXT:    [[TMP28:%.*]] = add i8 [[TMP24]], -1
 ; CHECK-NEXT:    [[TMP29:%.*]] = add i8 [[TMP25]], -1
 ; CHECK-NEXT:    [[TMP30:%.*]] = zext i8 [[TMP28]] to i32
 ; CHECK-NEXT:    [[TMP31:%.*]] = zext i8 [[TMP29]] to i32

llvm/test/Transforms/LoopVectorize/X86/pr36524.ll

 ; RUN: opt -S -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 < %s | FileCheck %s
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128-ni:1"
 
 define void @foo() {
 ; CHECK-LABEL: @foo(
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH:%.*]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY:%.*]] ]
 ; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 2, i64 3, i64 4, i64 5>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = add i64 2, [[INDEX]]
 ; CHECK-NEXT:    [[TMP7:%.*]] = add i64 [[OFFSET_IDX]], 0
 ; CHECK-NEXT:    [[TMP8:%.*]] = add i64 [[OFFSET_IDX]], 1
 ; CHECK-NEXT:    [[TMP9:%.*]] = add i64 [[OFFSET_IDX]], 2
 ; CHECK-NEXT:    [[TMP10:%.*]] = add i64 [[OFFSET_IDX]], 3
 ; CHECK-NEXT:    [[OFFSET_IDX1:%.*]] = add i64 2, [[INDEX]]
 ; CHECK-NEXT:    [[TMP11:%.*]] = trunc i64 [[OFFSET_IDX1]] to i32
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> undef, i32 [[TMP11]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> undef, <4 x i32> zeroinitializer
-; CHECK-NEXT:    [[INDUCTION:%.*]] = add <4 x i32> [[BROADCAST_SPLAT]], <i32 0, i32 1, i32 2, i32 3>
 ; CHECK-NEXT:    [[TMP12:%.*]] = add i32 [[TMP11]], 0
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
 ; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
 ; CHECK-NEXT:    [[TMP13:%.*]] = icmp eq i64 [[INDEX_NEXT]], 80
 ; CHECK-NEXT:    br i1 [[TMP13]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !0
 ;
 entry:
   br label %loop

llvm/test/Transforms/LoopVectorize/X86/strided_load_cost.ll

 ; CHECK-NEXT:    [[IDXPROM:%.*]] = sext i32 [[I:%.*]] to i64
 ; CHECK-NEXT:    [[IDXPROM5:%.*]] = sext i32 [[J:%.*]] to i64
 ; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP21:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
-; CHECK-NEXT:    [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3>
 ; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 1
 ; CHECK-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 2
 ; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 3
 ; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [100 x i32], [100 x i32]* [[DATA:%.*]], i64 [[IDXPROM]], i64 [[TMP0]]
 ; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 0
 ; CHECK-NEXT:    [[TMP6:%.*]] = bitcast i32* [[TMP5]] to <4 x i32>*
 ; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP6]], align 4, !tbaa !1

llvm/test/Transforms/LoopVectorize/X86/vect.omp.force.small-tc.ll

 define void @vectorized(float* noalias nocapture %A, float* noalias nocapture readonly %B) {
 ; CHECK-LABEL: @vectorized(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[INDEX]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer
-; CHECK-NEXT:    [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
 ; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds float, float* [[B:%.*]], i64 [[TMP0]]
 ; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds float, float* [[TMP1]], i32 0
 ; CHECK-NEXT:    [[TMP3:%.*]] = bitcast float* [[TMP2]] to <8 x float>*
-; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <8 x float>, <8 x float>* [[TMP3]], align 4
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <8 x float>, <8 x float>* [[TMP3]], align 4, !llvm.access.group !0
 ; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds float, float* [[A:%.*]], i64 [[TMP0]]
 ; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds float, float* [[TMP4]], i32 0
 ; CHECK-NEXT:    [[TMP6:%.*]] = bitcast float* [[TMP5]] to <8 x float>*
-; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <8 x float>, <8 x float>* [[TMP6]], align 4
+; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <8 x float>, <8 x float>* [[TMP6]], align 4, !llvm.access.group !0
 ; CHECK-NEXT:    [[TMP7:%.*]] = fadd fast <8 x float> [[WIDE_LOAD]], [[WIDE_LOAD1]]
 ; CHECK-NEXT:    [[TMP8:%.*]] = bitcast float* [[TMP5]] to <8 x float>*
-; CHECK-NEXT:    store <8 x float> [[TMP7]], <8 x float>* [[TMP8]], align 4
+; CHECK-NEXT:    store <8 x float> [[TMP7]], <8 x float>* [[TMP8]], align 4, !llvm.access.group !0
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 8
 ; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT]], 16
 ; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !1
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 20, 16
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 16, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]

 ; CHECK-NEXT:    [[TMP4:%.*]] = bitcast float* [[TMP3]] to <8 x float>*
 ; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* [[TMP4]], i32 4, <8 x i1> [[TMP2]], <8 x float> undef), !llvm.access.group !6
 ; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds float, float* [[A:%.*]], i64 [[TMP0]]
 ; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds float, float* [[TMP5]], i32 0
 ; CHECK-NEXT:    [[TMP7:%.*]] = bitcast float* [[TMP6]] to <8 x float>*
 ; CHECK-NEXT:    [[WIDE_MASKED_LOAD1:%.*]] = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* [[TMP7]], i32 4, <8 x i1> [[TMP2]], <8 x float> undef), !llvm.access.group !6
 ; CHECK-NEXT:    [[TMP8:%.*]] = fadd fast <8 x float> [[WIDE_MASKED_LOAD]], [[WIDE_MASKED_LOAD1]]
 ; CHECK-NEXT:    [[TMP9:%.*]] = bitcast float* [[TMP6]] to <8 x float>*
-; CHECK-NEXT:    call void @llvm.masked.store.v8f32.p0v8f32(<8 x float> [[TMP8]], <8 x float>* [[TMP9]], i32 4, <8 x i1> [[TMP2]])
+; CHECK-NEXT:    call void @llvm.masked.store.v8f32.p0v8f32(<8 x float> [[TMP8]], <8 x float>* [[TMP9]], i32 4, <8 x i1> [[TMP2]]), !llvm.access.group !6
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 8
 ; CHECK-NEXT:    [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], 24
 ; CHECK-NEXT:    br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !7
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 24, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds float, float* [[B]], i64 [[INDVARS_IV]]
+; CHECK-NEXT:    [[TMP11:%.*]] = load float, float* [[ARRAYIDX]], align 4, !llvm.access.group !6
+; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[INDVARS_IV]]
+; CHECK-NEXT:    [[TMP12:%.*]] = load float, float* [[ARRAYIDX2]], align 4, !llvm.access.group !6
+; CHECK-NEXT:    [[ADD:%.*]] = fadd fast float [[TMP11]], [[TMP12]]
+; CHECK-NEXT:    store float [[ADD]], float* [[ARRAYIDX2]], align 4, !llvm.access.group !6
+; CHECK-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 20
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop !9
 ; CHECK:       for.end:
 ; CHECK-NEXT:    ret void
 ;
 entry:
   br label %for.body
 
 for.body:
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]

 define void @vectorized2(float* noalias nocapture %A, float* noalias nocapture readonly %B) {
 ; CHECK-LABEL: @vectorized2(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[INDEX]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer
-; CHECK-NEXT:    [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
 ; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds float, float* [[B:%.*]], i64 [[TMP0]]
 ; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds float, float* [[TMP1]], i32 0
 ; CHECK-NEXT:    [[TMP3:%.*]] = bitcast float* [[TMP2]] to <8 x float>*
-; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <8 x float>, <8 x float>* [[TMP3]], align 4
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <8 x float>, <8 x float>* [[TMP3]], align 4, !llvm.access.group !6
 ; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds float, float* [[A:%.*]], i64 [[TMP0]]
 ; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds float, float* [[TMP4]], i32 0
 ; CHECK-NEXT:    [[TMP6:%.*]] = bitcast float* [[TMP5]] to <8 x float>*
-; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <8 x float>, <8 x float>* [[TMP6]], align 4
+; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <8 x float>, <8 x float>* [[TMP6]], align 4, !llvm.access.group !6
 ; CHECK-NEXT:    [[TMP7:%.*]] = fadd fast <8 x float> [[WIDE_LOAD]], [[WIDE_LOAD1]]
 ; CHECK-NEXT:    [[TMP8:%.*]] = bitcast float* [[TMP5]] to <8 x float>*
-; CHECK-NEXT:    store <8 x float> [[TMP7]], <8 x float>* [[TMP8]], align 4
+; CHECK-NEXT:    store <8 x float> [[TMP7]], <8 x float>* [[TMP8]], align 4, !llvm.access.group !6
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 8
 ; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT]], 16
 ; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !10
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 16, 16
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 16, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]

llvm/test/Transforms/LoopVectorize/fcmp-vectorize.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -S %s | FileCheck %s
 
 ; Avoid crashing while trying to vectorize fcmp that can be folded to vector of
 ; i1 true.
 define void @test1() {
-; CHECK-LABEL: test1(
-; CHECK-LABEL: vector.body:
-; CHECK-NEXT:    %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
-; CHECK-NEXT:    %broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
-; CHECK:         %induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
-; CHECK:         %index.next = add i32 %index, 4
-
+; CHECK-LABEL: @test1(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK:       vector.ph:
+; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[INDEX]], 0
+; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp eq i32 [[INDEX_NEXT]], 144
+; CHECK-NEXT:    br i1 [[TMP1]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !0
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 144, 144
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ 144, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK:       loop:
+; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IVNEXT:%.*]], [[LOOP]] ]
+; CHECK-NEXT:    [[FCMP:%.*]] = fcmp uno float 0.000000e+00, 0.000000e+00
+; CHECK-NEXT:    [[IVNEXT]] = add nsw i32 [[IV]], 1
+; CHECK-NEXT:    [[CND:%.*]] = icmp sgt i32 [[IV]], 142
+; CHECK-NEXT:    br i1 [[CND]], label [[EXIT]], label [[LOOP]], !llvm.loop !2
+; CHECK:       exit:
+; CHECK-NEXT:    ret void
+;
 entry:
   br label %loop
 
 loop:                                              ; preds = %loop, %entry
   %iv = phi i32 [ 0, %entry ], [ %ivnext, %loop ]
   %fcmp = fcmp uno float 0.000000e+00, 0.000000e+00
   %ivnext = add nsw i32 %iv, 1
   %cnd = icmp sgt i32 %iv, 142
   br i1 %cnd, label %exit, label %loop
 
 exit:                                              ; preds = %loop
   ret void
 }

llvm/test/Transforms/LoopVectorize/first-order-recurrence-complex.ll

 ; CHECK-NEXT:   %broadcast.splat2 = shufflevector <4 x i32> %broadcast.splatinsert1, <4 x i32> undef, <4 x i32> zeroinitializer
 ; CHECK-NEXT:   %vector.recur.init = insertelement <4 x i32> undef, i32 %.pre, i32 3
 ; CHECK-NEXT:    br label %vector.body
 
 ; CHECK-LABEL: vector.body:
 ; CHECK-NEXT:   %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
 ; CHECK-NEXT:   %vector.recur = phi <4 x i32> [ %vector.recur.init, %vector.ph ], [ %wide.load, %vector.body ]
 ; CHECK-NEXT:   %offset.idx = add i64 1, %index
-; CHECK-NEXT:   %broadcast.splatinsert = insertelement <4 x i64> undef, i64 %offset.idx, i32 0
-; CHECK-NEXT:   %broadcast.splat = shufflevector <4 x i64> %broadcast.splatinsert, <4 x i64> undef, <4 x i32> zeroinitializer
-; CHECK-NEXT:   %induction = add <4 x i64> %broadcast.splat, <i64 0, i64 1, i64 2, i64 3>
 ; CHECK-NEXT:   %0 = add i64 %offset.idx, 0
 ; CHECK-NEXT:   %1 = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 %0
 ; CHECK-NEXT:   %2 = getelementptr inbounds i32, i32* %1, i32 0
 ; CHECK-NEXT:   %3 = bitcast i32* %2 to <4 x i32>*
 ; CHECK-NEXT:   %wide.load = load <4 x i32>, <4 x i32>* %3, align 4
 ; CHECK-NEXT:   %4 = shufflevector <4 x i32> %vector.recur, <4 x i32> %wide.load, <4 x i32> <i32 3, i32 4, i32 5, i32 6>
 ; CHECK-NEXT:   %5 = add <4 x i32> %4, %broadcast.splat2
 ; CHECK-NEXT:   %6 = add <4 x i32> %5, %wide.load

 ; CHECK-NEXT:   %broadcast.splat2 = shufflevector <4 x i32> %broadcast.splatinsert1, <4 x i32> undef, <4 x i32> zeroinitializer
 ; CHECK-NEXT:   %vector.recur.init = insertelement <4 x i32> undef, i32 %.pre, i32 3
 ; CHECK-NEXT:    br label %vector.body
 
 ; CHECK-LABEL: vector.body:
 ; CHECK-NEXT:   %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
 ; CHECK-NEXT:   %vector.recur = phi <4 x i32> [ %vector.recur.init, %vector.ph ], [ %wide.load, %vector.body ]
 ; CHECK-NEXT:   %offset.idx = add i64 1, %index
-; CHECK-NEXT:   %broadcast.splatinsert = insertelement <4 x i64> undef, i64 %offset.idx, i32 0
-; CHECK-NEXT:   %broadcast.splat = shufflevector <4 x i64> %broadcast.splatinsert, <4 x i64> undef, <4 x i32> zeroinitializer
-; CHECK-NEXT:   %induction = add <4 x i64> %broadcast.splat, <i64 0, i64 1, i64 2, i64 3>
 ; CHECK-NEXT:   %0 = add i64 %offset.idx, 0
 ; CHECK-NEXT:   %1 = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 %0
 ; CHECK-NEXT:   %2 = getelementptr inbounds i32, i32* %1, i32 0
 ; CHECK-NEXT:   %3 = bitcast i32* %2 to <4 x i32>*
 ; CHECK-NEXT:   %wide.load = load <4 x i32>, <4 x i32>* %3, align 4
 ; CHECK-NEXT:   %4 = shufflevector <4 x i32> %vector.recur, <4 x i32> %wide.load, <4 x i32> <i32 3, i32 4, i32 5, i32 6>
 ; CHECK-NEXT:   %5 = sdiv <4 x i32> %4, %broadcast.splat2
 ; CHECK-NEXT:   %6 = add <4 x i32> %5, %wide.load

llvm/test/Transforms/LoopVectorize/float-minmax-instruction-flag.ll

 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[MINMAX_IDENT_SPLATINSERT:%.*]] = insertelement <4 x float> undef, float [[T]], i32 0
 ; CHECK-NEXT:    [[MINMAX_IDENT_SPLAT:%.*]] = shufflevector <4 x float> [[MINMAX_IDENT_SPLATINSERT]], <4 x float> undef, <4 x i32> zeroinitializer
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x float> [ [[MINMAX_IDENT_SPLAT]], [[VECTOR_PH]] ], [ [[TMP6:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = add i64 1, [[INDEX]]
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[OFFSET_IDX]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
-; CHECK-NEXT:    [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3>
 ; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[OFFSET_IDX]], 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr float, float* [[ARG]], i64 [[TMP0]]
 ; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr float, float* [[TMP1]], i32 0
 ; CHECK-NEXT:    [[TMP3:%.*]] = bitcast float* [[TMP2]] to <4 x float>*
 ; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x float>, <4 x float>* [[TMP3]], align 4
 ; CHECK-NEXT:    [[TMP4:%.*]] = fcmp olt <4 x float> [[VEC_PHI]], [[WIDE_LOAD]]
 ; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x i1> [[TMP4]], i32 0
 ; CHECK-NEXT:    [[TMP6]] = select <4 x i1> [[TMP4]], <4 x float> [[VEC_PHI]], <4 x float> [[WIDE_LOAD]]

llvm/test/Transforms/LoopVectorize/if-pred-stores.ll

 ; UNROLL-NOSIMPLIFY:       for.end:
 ; UNROLL-NOSIMPLIFY-NEXT:    ret i32 0
 ;
 ; VEC-LABEL: @test(
 ; VEC-NEXT:  entry:
 ; VEC-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; VEC:       vector.body:
 ; VEC-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE2:%.*]] ]
-; VEC-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <2 x i64> undef, i64 [[INDEX]], i32 0
-; VEC-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <2 x i64> [[BROADCAST_SPLATINSERT]], <2 x i64> undef, <2 x i32> zeroinitializer
-; VEC-NEXT:    [[INDUCTION:%.*]] = add <2 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1>
 ; VEC-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; VEC-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[F:%.*]], i64 [[TMP0]]
 ; VEC-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i32 0
 ; VEC-NEXT:    [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <2 x i32>*
 ; VEC-NEXT:    [[WIDE_LOAD:%.*]] = load <2 x i32>, <2 x i32>* [[TMP3]], align 4
 ; VEC-NEXT:    [[TMP4:%.*]] = icmp sgt <2 x i32> [[WIDE_LOAD]], <i32 100, i32 100>
 ; VEC-NEXT:    [[TMP5:%.*]] = extractelement <2 x i1> [[TMP4]], i32 0
 ; VEC-NEXT:    br i1 [[TMP5]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]

 ; UNROLL-NOSIMPLIFY-NEXT:    br label [[PRED_STORE_CONTINUE4]]
 ; UNROLL-NOSIMPLIFY:       pred.store.continue4:
 ; UNROLL-NOSIMPLIFY-NEXT:    [[TMP4:%.*]] = add i32 [[VEC_PHI]], 1
 ; UNROLL-NOSIMPLIFY-NEXT:    [[TMP5:%.*]] = add i32 [[VEC_PHI2]], 1
 ; UNROLL-NOSIMPLIFY-NEXT:    [[PREDPHI]] = select i1 undef, i32 [[VEC_PHI]], i32 [[TMP4]]
 ; UNROLL-NOSIMPLIFY-NEXT:    [[PREDPHI5]] = select i1 undef, i32 [[VEC_PHI2]], i32 [[TMP5]]
 ; UNROLL-NOSIMPLIFY-NEXT:    [[OFFSET_IDX6:%.*]] = add i64 undef, [[INDEX]]
 ; UNROLL-NOSIMPLIFY-NEXT:    [[TMP6:%.*]] = trunc i64 [[OFFSET_IDX6]] to i32
-; UNROLL-NOSIMPLIFY-NEXT:    [[INDUCTION7:%.*]] = add i32 [[TMP6]], 0
-; UNROLL-NOSIMPLIFY-NEXT:    [[INDUCTION8:%.*]] = add i32 [[TMP6]], 1
 ; UNROLL-NOSIMPLIFY-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 2
 ; UNROLL-NOSIMPLIFY-NEXT:    [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], 0
 ; UNROLL-NOSIMPLIFY-NEXT:    br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !3
 ; UNROLL-NOSIMPLIFY:       middle.block:
 ; UNROLL-NOSIMPLIFY-NEXT:    [[BIN_RDX:%.*]] = add i32 [[PREDPHI5]], [[PREDPHI]]
 ; UNROLL-NOSIMPLIFY-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1, 0
 ; UNROLL-NOSIMPLIFY-NEXT:    br i1 [[CMP_N]], label [[FOR_INC26_LOOPEXIT:%.*]], label [[SCALAR_PH]]
 ; UNROLL-NOSIMPLIFY:       scalar.ph:

 ;
 define void @minimal_bit_widths(i1 %c) {
 ; UNROLL-LABEL: @minimal_bit_widths(
 ; UNROLL-NEXT:  entry:
 ; UNROLL-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; UNROLL:       vector.body:
 ; UNROLL-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE6:%.*]] ]
 ; UNROLL-NEXT:    [[OFFSET_IDX:%.*]] = sub i64 undef, [[INDEX]]
-; UNROLL-NEXT:    [[INDUCTION3:%.*]] = add i64 [[OFFSET_IDX]], 0
-; UNROLL-NEXT:    [[INDUCTION4:%.*]] = add i64 [[OFFSET_IDX]], -1
 ; UNROLL-NEXT:    br i1 [[C:%.*]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE6]]
 ; UNROLL:       pred.store.if:
 ; UNROLL-NEXT:    [[INDUCTION:%.*]] = add i64 [[INDEX]], 0
 ; UNROLL-NEXT:    [[TMP0:%.*]] = getelementptr i8, i8* undef, i64 [[INDUCTION]]
 ; UNROLL-NEXT:    [[TMP1:%.*]] = load i8, i8* [[TMP0]], align 1
 ; UNROLL-NEXT:    [[TMP2:%.*]] = zext i8 [[TMP1]] to i32
 ; UNROLL-NEXT:    [[TMP3:%.*]] = trunc i32 [[TMP2]] to i8
 ; UNROLL-NEXT:    store i8 [[TMP3]], i8* [[TMP0]], align 1

 ; UNROLL-NOSIMPLIFY-LABEL: @minimal_bit_widths(
 ; UNROLL-NOSIMPLIFY-NEXT:  entry:
 ; UNROLL-NOSIMPLIFY-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; UNROLL-NOSIMPLIFY:       vector.ph:
 ; UNROLL-NOSIMPLIFY-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; UNROLL-NOSIMPLIFY:       vector.body:
 ; UNROLL-NOSIMPLIFY-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE6:%.*]] ]
 ; UNROLL-NOSIMPLIFY-NEXT:    [[OFFSET_IDX:%.*]] = sub i64 undef, [[INDEX]]
-; UNROLL-NOSIMPLIFY-NEXT:    [[INDUCTION3:%.*]] = add i64 [[OFFSET_IDX]], 0
-; UNROLL-NOSIMPLIFY-NEXT:    [[INDUCTION4:%.*]] = add i64 [[OFFSET_IDX]], -1
 ; UNROLL-NOSIMPLIFY-NEXT:    br i1 [[C:%.*]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
 ; UNROLL-NOSIMPLIFY:       pred.store.if:
 ; UNROLL-NOSIMPLIFY-NEXT:    [[INDUCTION:%.*]] = add i64 [[INDEX]], 0
 ; UNROLL-NOSIMPLIFY-NEXT:    [[TMP0:%.*]] = getelementptr i8, i8* undef, i64 [[INDUCTION]]
 ; UNROLL-NOSIMPLIFY-NEXT:    [[TMP1:%.*]] = load i8, i8* [[TMP0]], align 1
 ; UNROLL-NOSIMPLIFY-NEXT:    [[TMP2:%.*]] = zext i8 [[TMP1]] to i32
 ; UNROLL-NOSIMPLIFY-NEXT:    [[TMP3:%.*]] = trunc i32 [[TMP2]] to i8
 ; UNROLL-NOSIMPLIFY-NEXT:    store i8 [[TMP3]], i8* [[TMP0]], align 1

 ;
 ; VEC-LABEL: @minimal_bit_widths(
 ; VEC-NEXT:  entry:
 ; VEC-NEXT:    [[BROADCAST_SPLATINSERT5:%.*]] = insertelement <2 x i1> undef, i1 [[C:%.*]], i32 0
 ; VEC-NEXT:    [[BROADCAST_SPLAT6:%.*]] = shufflevector <2 x i1> [[BROADCAST_SPLATINSERT5]], <2 x i1> undef, <2 x i32> zeroinitializer
 ; VEC-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; VEC:       vector.body:
 ; VEC-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE8:%.*]] ]
-; VEC-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <2 x i64> undef, i64 [[INDEX]], i32 0
-; VEC-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <2 x i64> [[BROADCAST_SPLATINSERT]], <2 x i64> undef, <2 x i32> zeroinitializer
-; VEC-NEXT:    [[INDUCTION:%.*]] = add <2 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1>
 ; VEC-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; VEC-NEXT:    [[OFFSET_IDX:%.*]] = sub i64 undef, [[INDEX]]
-; VEC-NEXT:    [[BROADCAST_SPLATINSERT2:%.*]] = insertelement <2 x i64> undef, i64 [[OFFSET_IDX]], i32 0
-; VEC-NEXT:    [[BROADCAST_SPLAT3:%.*]] = shufflevector <2 x i64> [[BROADCAST_SPLATINSERT2]], <2 x i64> undef, <2 x i32> zeroinitializer
-; VEC-NEXT:    [[INDUCTION4:%.*]] = add <2 x i64> [[BROADCAST_SPLAT3]], <i64 0, i64 -1>
 ; VEC-NEXT:    [[TMP1:%.*]] = add i64 [[OFFSET_IDX]], 0
 ; VEC-NEXT:    [[TMP2:%.*]] = getelementptr i8, i8* undef, i64 [[TMP0]]
 ; VEC-NEXT:    [[TMP3:%.*]] = getelementptr i8, i8* [[TMP2]], i32 0
 ; VEC-NEXT:    [[TMP4:%.*]] = bitcast i8* [[TMP3]] to <2 x i8>*
 ; VEC-NEXT:    [[WIDE_LOAD:%.*]] = load <2 x i8>, <2 x i8>* [[TMP4]], align 1
 ; VEC-NEXT:    [[TMP5:%.*]] = extractelement <2 x i1> [[BROADCAST_SPLAT6]], i32 0
 ; VEC-NEXT:    br i1 [[TMP5]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
 ; VEC:       pred.store.if:

llvm/test/Transforms/LoopVectorize/multiple-strides-vectorization.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -loop-vectorize -force-vector-width=4 -S < %s | FileCheck %s
 
 ; This is the test case from PR26314.
 ; When we were retrying dependence checking with memchecks only,
 ; the loop-invariant access in the inner loop was incorrectly determined to be wrapping
 ; because it was not strided in the inner loop.
 ; Improved wrapping detection allows vectorization in the following case.
 
 ; #define Z 32
 ; typedef struct s {
 ;       int v1[Z];
 ;       int v2[Z];
 ;       int v3[Z][Z];
 ; } s;
 ;
 ; void slow_function (s* const obj, int z) {
 ;    for (int j=0; j<Z; j++) {
 ;        for (int k=0; k<z; k++) {
 ;            int x = obj->v1[k] + obj->v2[j];
 ;            obj->v3[j][k] += x;
 ;        }
 ;    }
 ; }
 
-; CHECK-LABEL: Test
-; CHECK: <4 x i64>
-; CHECK: <4 x i32>, <4 x i32>
-; CHECK: !{!"llvm.loop.isvectorized", i32 1}
-
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 
 %struct.s = type { [32 x i32], [32 x i32], [32 x [32 x i32]] }
 
 define void @Test(%struct.s* nocapture %obj, i64 %z) #0 {
+; CHECK-LABEL: @Test(
+; CHECK-NEXT:    [[OBJ4:%.*]] = bitcast %struct.s* [[OBJ:%.*]] to i8*
+; CHECK-NEXT:    [[SCEVGEP5:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.s* [[OBJ]], i64 0, i32 0, i64 [[Z:%.*]]
+; CHECK-NEXT:    [[SCEVGEP56:%.*]] = bitcast i32* [[SCEVGEP5]] to i8*
+; CHECK-NEXT:    br label [[DOTOUTER_PREHEADER:%.*]]
+; CHECK:       .outer.preheader:
+; CHECK-NEXT:    [[I:%.*]] = phi i64 [ 0, [[TMP0:%.*]] ], [ [[I_NEXT:%.*]], [[DOTOUTER:%.*]] ]
+; CHECK-NEXT:    [[SCEVGEP:%.*]] = getelementptr [[STRUCT_S]], %struct.s* [[OBJ]], i64 0, i32 2, i64 [[I]], i64 0
+; CHECK-NEXT:    [[SCEVGEP1:%.*]] = bitcast i32* [[SCEVGEP]] to i8*
+; CHECK-NEXT:    [[SCEVGEP2:%.*]] = getelementptr [[STRUCT_S]], %struct.s* [[OBJ]], i64 0, i32 2, i64 [[I]], i64 [[Z]]
+; CHECK-NEXT:    [[SCEVGEP23:%.*]] = bitcast i32* [[SCEVGEP2]] to i8*
+; CHECK-NEXT:    [[SCEVGEP7:%.*]] = getelementptr [[STRUCT_S]], %struct.s* [[OBJ]], i64 0, i32 1, i64 [[I]]
+; CHECK-NEXT:    [[SCEVGEP78:%.*]] = bitcast i32* [[SCEVGEP7]] to i8*
+; CHECK-NEXT:    [[UGLYGEP:%.*]] = getelementptr i8, i8* [[SCEVGEP78]], i64 1
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.s* [[OBJ]], i64 0, i32 1, i64 [[I]]
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[Z]], 4
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_MEMCHECK:%.*]]
+; CHECK:       vector.memcheck:
+; CHECK-NEXT:    [[BOUND0:%.*]] = icmp ult i8* [[SCEVGEP1]], [[SCEVGEP56]]
+; CHECK-NEXT:    [[BOUND1:%.*]] = icmp ult i8* [[OBJ4]], [[SCEVGEP23]]
+; CHECK-NEXT:    [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
+; CHECK-NEXT:    [[BC:%.*]] = bitcast i32* [[TMP1]] to i8*
+; CHECK-NEXT:    [[BOUND09:%.*]] = icmp ult i8* [[SCEVGEP1]], [[UGLYGEP]]
+; CHECK-NEXT:    [[BOUND110:%.*]] = icmp ult i8* [[BC]], [[SCEVGEP23]]
+; CHECK-NEXT:    [[FOUND_CONFLICT11:%.*]] = and i1 [[BOUND09]], [[BOUND110]]
+; CHECK-NEXT:    [[CONFLICT_RDX:%.*]] = or i1 [[FOUND_CONFLICT]], [[FOUND_CONFLICT11]]
+; CHECK-NEXT:    [[MEMCHECK_CONFLICT:%.*]] = and i1 [[CONFLICT_RDX]], true
+; CHECK-NEXT:    br i1 [[MEMCHECK_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
+; CHECK:       vector.ph:
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[Z]], 4
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[Z]], [[N_MOD_VF]]
+; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 0
+; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.s* [[OBJ]], i64 0, i32 0, i64 [[TMP2]]
+; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, i32* [[TMP3]], i32 0
+; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i32* [[TMP4]] to <4 x i32>*
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP5]], align 4, !alias.scope !0
+; CHECK-NEXT:    [[TMP6:%.*]] = load i32, i32* [[TMP1]], !alias.scope !3
+; CHECK-NEXT:    [[TMP7:%.*]] = load i32, i32* [[TMP1]], !alias.scope !3
+; CHECK-NEXT:    [[TMP8:%.*]] = load i32, i32* [[TMP1]], !alias.scope !3
+; CHECK-NEXT:    [[TMP9:%.*]] = load i32, i32* [[TMP1]], !alias.scope !3
+; CHECK-NEXT:    [[TMP10:%.*]] = insertelement <4 x i32> undef, i32 [[TMP6]], i32 0
+; CHECK-NEXT:    [[TMP11:%.*]] = insertelement <4 x i32> [[TMP10]], i32 [[TMP7]], i32 1
+; CHECK-NEXT:    [[TMP12:%.*]] = insertelement <4 x i32> [[TMP11]], i32 [[TMP8]], i32 2
+; CHECK-NEXT:    [[TMP13:%.*]] = insertelement <4 x i32> [[TMP12]], i32 [[TMP9]], i32 3
+; CHECK-NEXT:    [[TMP14:%.*]] = add nsw <4 x i32> [[TMP13]], [[WIDE_LOAD]]
+; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.s* [[OBJ]], i64 0, i32 2, i64 [[I]], i64 [[TMP2]]
+; CHECK-NEXT:    [[TMP16:%.*]] = getelementptr inbounds i32, i32* [[TMP15]], i32 0
+; CHECK-NEXT:    [[TMP17:%.*]] = bitcast i32* [[TMP16]] to <4 x i32>*
+; CHECK-NEXT:    [[WIDE_LOAD12:%.*]] = load <4 x i32>, <4 x i32>* [[TMP17]], align 4, !alias.scope !5, !noalias !7
+; CHECK-NEXT:    [[TMP18:%.*]] = add nsw <4 x i32> [[TMP14]], [[WIDE_LOAD12]]
+; CHECK-NEXT:    [[TMP19:%.*]] = bitcast i32* [[TMP16]] to <4 x i32>*
+; CHECK-NEXT:    store <4 x i32> [[TMP18]], <4 x i32>* [[TMP19]], align 4, !alias.scope !5, !noalias !7
+; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
+; CHECK-NEXT:    [[TMP20:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP20]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !8
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[Z]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[DOTOUTER]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[DOTOUTER_PREHEADER]] ], [ 0, [[VECTOR_MEMCHECK]] ]
+; CHECK-NEXT:    br label [[DOTINNER:%.*]]
+; CHECK:       .exit:
+; CHECK-NEXT:    ret void
+; CHECK:       .outer:
+; CHECK-NEXT:    [[I_NEXT]] = add nuw nsw i64 [[I]], 1
+; CHECK-NEXT:    [[EXITCOND_OUTER:%.*]] = icmp eq i64 [[I_NEXT]], 32
+; CHECK-NEXT:    br i1 [[EXITCOND_OUTER]], label [[DOTEXIT:%.*]], label [[DOTOUTER_PREHEADER]]
+; CHECK:       .inner:
+; CHECK-NEXT:    [[J:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[J_NEXT:%.*]], [[DOTINNER]] ]
+; CHECK-NEXT:    [[TMP21:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.s* [[OBJ]], i64 0, i32 0, i64 [[J]]
+; CHECK-NEXT:    [[TMP22:%.*]] = load i32, i32* [[TMP21]]
+; CHECK-NEXT:    [[TMP23:%.*]] = load i32, i32* [[TMP1]]
+; CHECK-NEXT:    [[TMP24:%.*]] = add nsw i32 [[TMP23]], [[TMP22]]
+; CHECK-NEXT:    [[TMP25:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.s* [[OBJ]], i64 0, i32 2, i64 [[I]], i64 [[J]]
+; CHECK-NEXT:    [[TMP26:%.*]] = load i32, i32* [[TMP25]]
+; CHECK-NEXT:    [[TMP27:%.*]] = add nsw i32 [[TMP24]], [[TMP26]]
+; CHECK-NEXT:    store i32 [[TMP27]], i32* [[TMP25]]
+; CHECK-NEXT:    [[J_NEXT]] = add nuw nsw i64 [[J]], 1
+; CHECK-NEXT:    [[EXITCOND_INNER:%.*]] = icmp eq i64 [[J_NEXT]], [[Z]]
+; CHECK-NEXT:    br i1 [[EXITCOND_INNER]], label [[DOTOUTER]], label [[DOTINNER]], !llvm.loop !10
+;
   br label %.outer.preheader
 
 
 .outer.preheader:
   %i = phi i64 [ 0, %0 ], [ %i.next, %.outer ]
   %1 = getelementptr inbounds %struct.s, %struct.s* %obj, i64 0, i32 1, i64 %i
   br label %.inner
 
 .exit:
   ret void
- 
 .outer:
   %i.next = add nuw nsw i64 %i, 1
   %exitcond.outer = icmp eq i64 %i.next, 32
   br i1 %exitcond.outer, label %.exit, label %.outer.preheader
 
 .inner:
   %j = phi i64 [ 0, %.outer.preheader ], [ %j.next, %.inner ]
   %2 = getelementptr inbounds %struct.s, %struct.s* %obj, i64 0, i32 0, i64 %j
   %3 = load i32, i32* %2
   %4 = load i32, i32* %1
   %5 = add nsw i32 %4, %3
   %6 = getelementptr inbounds %struct.s, %struct.s* %obj, i64 0, i32 2, i64 %i, i64 %j
   %7 = load i32, i32* %6
   %8 = add nsw i32 %5, %7
-  store i32 %8, i32* %6  
+  store i32 %8, i32* %6
   %j.next = add nuw nsw i64 %j, 1
   %exitcond.inner = icmp eq i64 %j.next, %z
   br i1 %exitcond.inner, label %.outer, label %.inner
 }

llvm/test/Transforms/LoopVectorize/pr35773.ll

 
 ; CHECK-LABEL: @doit1(
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[MAIN_IV:%.*]] = phi i32 [ 0, [[VECTOR_PH:%.*]] ], [ [[MAIN_IV_NEXT:%.*]], [[VECTOR_BODY:%.*]] ]
 ; CHECK-NEXT:    [[I8_IV:%.*]] = phi <4 x i8> [ zeroinitializer, [[VECTOR_PH]] ], [ [[I8_IV_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[I32_IV:%.*]] = phi <4 x i32> [ <i32 0, i32 9, i32 18, i32 27>, [[VECTOR_PH]] ], [ [[I32_IV_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[IV_FROM_TRUNC:%.*]] = phi <4 x i8> [ <i8 0, i8 9, i8 18, i8 27>, [[VECTOR_PH]] ], [ [[IV_FROM_TRUNC_NEXT:%.*]], [[VECTOR_BODY]] ]
 
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> undef, i32 [[MAIN_IV]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> undef, <4 x i32> zeroinitializer
-; CHECK-NEXT:    [[INDUCTION:%.*]] = add <4 x i32> [[BROADCAST_SPLAT]], <i32 0, i32 1, i32 2, i32 3>
 ; CHECK-NEXT:    [[TMP7:%.*]] = add i32 [[MAIN_IV]], 0
 
 ; CHECK-NEXT:    [[I8_IV_NEXT]] = add <4 x i8> [[I8_IV]], [[IV_FROM_TRUNC]]
 
 ; CHECK-NEXT:    [[MAIN_IV_NEXT]] = add i32 [[MAIN_IV]], 4
 ; CHECK-NEXT:    [[I32_IV_NEXT]] = add <4 x i32> [[I32_IV]], <i32 36, i32 36, i32 36, i32 36>
 ; CHECK-NEXT:    [[IV_FROM_TRUNC_NEXT]] = add <4 x i8> [[IV_FROM_TRUNC]], <i8 36, i8 36, i8 36, i8 36>
 ; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i32 [[MAIN_IV_NEXT]], 16

llvm/test/Transforms/LoopVectorize/pr44488-predication.ll

 ; RUN: opt < %s -force-vector-width=2 -force-vector-interleave=1 -loop-vectorize -S | FileCheck %s
 
 ; Test case for PR44488. Checks that the correct predicates are created for
 ; branches where true and false successors are equal. See the checks involving
 ; CMP1 and CMP2.
 
 @v_38 = global i16 12061, align 1
 @v_39 = global i16 11333, align 1
 
 define i16 @test_true_and_false_branch_equal() {
 ; CHECK-LABEL: @test_true_and_false_branch_equal(
 ; CHECK-LABEL: vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, %vector.ph ], [ [[INDEX_NEXT:%.*]], [[PRED_SREM_CONTINUE2:%.*]] ]
 ; CHECK-NEXT:    [[TMP0:%.*]] = trunc i32 [[INDEX]] to i16
 ; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = add i16 99, [[TMP0]]
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <2 x i16> undef, i16 [[OFFSET_IDX]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <2 x i16> [[BROADCAST_SPLATINSERT]], <2 x i16> undef, <2 x i32> zeroinitializer
-; CHECK-NEXT:    [[INDUCTION:%.*]] = add <2 x i16> [[BROADCAST_SPLAT]], <i16 0, i16 1>
 ; CHECK-NEXT:    [[TMP1:%.*]] = add i16 [[OFFSET_IDX]], 0
 ; CHECK-NEXT:    [[TMP2:%.*]] = load i16, i16* @v_38, align 1
 ; CHECK-NEXT:    [[TMP3:%.*]] = load i16, i16* @v_38, align 1
 ; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <2 x i16> undef, i16 [[TMP2]], i32 0
 ; CHECK-NEXT:    [[TMP5:%.*]] = insertelement <2 x i16> [[TMP4]], i16 [[TMP3]], i32 1
 ; CHECK-NEXT:    [[CMP1:%.*]] = icmp eq <2 x i16> [[TMP5]], <i16 32767, i16 32767>
 ; CHECK-NEXT:    [[CMP2:%.*]] = icmp eq <2 x i16> [[TMP5]], zeroinitializer
 ; CHECK-NEXT:    [[NOT_CMP2:%.*]] = xor <2 x i1> [[CMP2]], <i1 true, i1 true>

llvm/test/Transforms/LoopVectorize/vector-intrinsic-call-cost.ll

 ; RUN: opt -S -loop-vectorize -force-vector-width=4 %s | FileCheck %s
 
 ; CHECK-LABEL: @test_fshl
 ; CHECK-LABEL: vector.body:
 ; CHECK-NEXT:    %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
-; CHECK-NEXT:    %broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
-; CHECK-NEXT:    %broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
-; CHECK-NEXT:    %induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
 ; CHECK-NEXT:    %0 = add i32 %index, 0
 ; CHECK-NEXT:    %1 = call <4 x i16> @llvm.fshl.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i16> <i16 15, i16 15, i16 15, i16 15>)
 ; CHECK-NEXT:    %index.next = add i32 %index, 4
 ; CHECK-NEXT:    %2 = icmp eq i32 %index.next, %n.vec
 ; CHECK-NEXT:     br i1 %2, label %middle.block, label %vector.body, !llvm.loop !0
 ;
 define void @test_fshl(i32 %width) {
 entry: