[LV] Don't apply "TinyTripCountVectorThreshold" for loops with compile time known TC.

[ebrevnov]

Summary

When trip count is not known at compile time, there are additional overhead to make sure it's safe to perform next VF iterations. Thus, if vector loop is skipped at runtime then such vectorization is unprofitable. When trip count is known to be small enough there is high chance to get into such situation. Currently, LV is not able to properly cost model in this case since it doesn't account for cost of the epilog loop. Instead "short trip count" heuristic is employed.

While "short trip count" heuristic  makes sense in general (at least for current state) it can be slightly lifted up when trip count is compile time known constant. In   this case it's known at compile time how many vector iterations will be executed and there is no implied overhead by trip count checks as well.  Cost modeling is simple as well, if one vector iteration costs less than one scalar iteration multiple VF then vectorization is profitable.

Note: One may say, that "short trip count" heuristic is the needed to reduce code size in assumption that short trip count loops can't be performance critical. That statement turns out to be false in many cases (for example, nested loops) and should not be driving factor.

[ebrevnov]

Ping

[ebrevnov]

PING!

[dmgreen]

llvm/test/Transforms/LoopVectorize/ARM/mve-known-trip-count.ll

7 ↗

(On Diff #394187)

I don't think we want this - it is worse. At least that is what my benchmarks suggest.

That was the point of D101726. 1 vector + 1 masked vector iteration when unrolled was worse than 5 scalar because of the overheads of vector instructions. 1 vector + 1 scalar will be in the same boat.

[fhahn]

llvm/test/Transforms/LoopVectorize/ARM/mve-known-trip-count.ll

7 ↗

(On Diff #394187)

I also think we would probably need to make this target/CPU dependent. We also have some AArch64 CPUs where usually at least 2 vector iterations are needed to make the vector code profitable if there is a scalar tail.

[ebrevnov]

Rebase + fix problem for platforms which prefer tail folding over scalar epilogue.

[ebrevnov]

Thanks for feedback!
The problem with mve-known-trip-count.ll was caused by 2 things 1) Outdated code base 2) Bug in the implementation caused to skip "preferPredicateOverEpilogue" check and as a result scalar epilogue have been selected. Now both items are fixed mve-known-trip-count.ll works as previously (cost model says vectorization with tail folding is not profitable).

In order to fix above two items (and not introduce new ones) I had to restructure the code responsible for scalar epilog lowering. This restructuring is now parent for this one and in WIP state. While I believe proposed restructuring is a good thing regardless this change I would like to postpone polishing it until we have an agreement on this one.

[david-arm]

Adding @dtemirbulatov since he was the author of the original patch that introduced getMinTripCountTailFoldingThreshold.

[paulwalker-arm]

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

9851–9866

I don't quite understand this change. The whole point of getMinTripCountTailFoldingThreshold() was to give targets control over this behaviour based on their understanding how the cost model has been implemented.

Admittedly this was in part due to the immaturity of the cost modelling but this change essentially removes that flexibility to the point where there's no value in keeping getMinTripCountTailFoldingThreshold()?

If your previous patches improve the cost model in this regard then I'd rather getMinTripCountTailFoldingThreshold() be removed. That said, @dtemirbulatov can you help here in ascertaining if this option is still required based on this new patch series?

[ebrevnov]

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

9851–9866

I think you are missing one thing. Currently we allow vectorization of short trip count loops if there is no run-time overhead and the tail can be folded only. Introduction of getMinTripCountTailFoldingThreshold put additional limitations on vectorization of such loops. This change enables vectorization of short trip count loops with scalar epilogue ONLY If trip count is compile time constant. getMinTripCountTailFoldingThreshold is still applicable if we decide to vectorize by folding the tail.

In other words, this change enables exactly the same way of vectorization for loops with small constant trip count as for loops with unknown or large trip count.

It's a question whether getMinTripCountTailFoldingThreshold threshold should be taken into account if it's decided to fold the tail at step 5) for short trip count loop. Possibly yes... I think this is your original concern, right?

[ebrevnov]

Ping!

[lebedev.ri]

I think the effect this patch has is not well understood, and the description is not informative enough to understand it.
I would perhaps recommend formatting the desired behavior change as a truth table.

[dmgreen]

I tried running the original benchmarks again with this patch series, it still sees the same decrease in performance I'm afraid. If it was a small change it would be understandable, we accidentally end up on the wrong side of the scalar cost and choose to vectorize where we shouldn't. But the new code is 40% slower than the scalar version, so it's quite a difference. I haven't had a chance to look into the costs it produces, there is a chance we are underestimating the cost of predication or overestimating the cost of scalar. At worst, providing getMinTripCountTailFoldingThreshold works like it should we can always put a limit on the tripcount, providing we can find a decent minimum that works in general for MVE.

The vectorizer doesn't really do any cost modelling for the setup cost, past some obvious things like runtime checks. Due the the pass pipeline, it is usually expected that many low-trip-count loops are unrolled prior to vectorization, and we SLP them instead. D135971 looks like it changes a lot of code in an area that has caused an amount of trouble in the past. We know that the Vectorizer current needs to commit to tail folding vs not tail folding too early. It would be better to have that option as part of the vplan, allowing predicated and non-predicated patters to be costed against one another. I'm not sure I follow D135971 enough to understand the ramifications of those changes.

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

9851–9866

Are you assuming that the loop will be unrolled after vectorization, and that unrolling will leave no extra overhead? Scalable vector loops cannot (currently) be unrolled.

[ebrevnov]

Make sure MinTripCountTailFoldingThreshold is honord even for loops with short compile tine known TC.

[ebrevnov]

In D115713#3898587, @dmgreen wrote:

I tried running the original benchmarks again with this patch series, it still sees the same decrease in performance I'm afraid. If it was a small change it would be understandable, we accidentally end up on the wrong side of the scalar cost and choose to vectorize where we shouldn't. But the new code is 40% slower than the scalar version, so it's quite a difference. I haven't had a chance to look into the costs it produces, there is a chance we are underestimating the cost of predication or overestimating the cost of scalar. At worst, providing getMinTripCountTailFoldingThreshold works like it should we can always put a limit on the tripcount, providing we can find a decent minimum that works in general for MVE.

It sounds like current cost model works really bad for this case and it's essentially the reason why getMinTripCountTailFoldingThreshold had been introduced. If this is the case would you mind trying updated version and see if it helps. Otherwise, I'd probably need a test case I could analyze.

The vectorizer doesn't really do any cost modelling for the setup cost, past some obvious things like runtime checks. Due the the pass pipeline, it is usually expected that many low-trip-count loops are unrolled prior to vectorization, and we SLP them instead. D135971 looks like it changes a lot of code in an area that has caused an amount of trouble in the past. We know that the Vectorizer current needs to commit to tail folding vs not tail folding too early. It would be better to have that option as part of the vplan, allowing predicated and non-predicated patters to be costed against one another. I'm not sure I follow D135971 enough to understand the ramifications of those changes.

I understand the problem you describe here. D135971 has nothing to do with it. It's an NFC. None of tests change their behavior. Main motivation is to simplify unnecessary complicated implementation because I struggled how to push new functionality in it.

[ebrevnov]

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

9851–9866

Actually no. Even if we keep vector loop which runs just 1 or 2 iterations I don't see any additional overhead comparing to scalar loop. At least not on IR level. Is there any overhead specific to MVE not visible on IR level?

[dmgreen]

I've been taking a look at the example that is getting a lot worse. There are certainly some issues with the code generation being non-optimal, but even after a lot of optimizations it looks like it will always be worse than the scalar version. There is a lot of predications and fairly efficient scalar instructions like BFI, which makes accurate cost modelling difficult. There's a lot of setup and spilling too, which is going to hurt for small trip counts. I think for MVE it would make sense to have a way for the target to put a limit on the minumum trip count.

I think @fhahn also mentioned that he had some AArch64 examples where the same is true. I'm not sure in general where this would be useful. The vectorizers handing of small trip count loops is not amazing, considering that many such loops will already have been fully unrolled. It doesn't come up a huge amount and a lot of the cost modelling currently assumes any extra setup costs will be dominated by the loop.

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

9851–9866

The getMinTripCountTailFoldingThreshold was added for SVE, it is not (currently) used in MVE.

There will be a certain amount of overhead just from having a second loop, let alone all the extra overhead from the gubbins around it. https://godbolt.org/z/s8xEf7d6K. None of that is particularly MVE specific though, although as it is designed for small energy-efficient cores it may feel the overheads more than other architectures.

[ebrevnov]

In D115713#3910792, @dmgreen wrote:

I've been taking a look at the example that is getting a lot worse. There are certainly some issues with the code generation being non-optimal, but even after a lot of optimizations it looks like it will always be worse than the scalar version. There is a lot of predications and fairly efficient scalar instructions like BFI, which makes accurate cost modelling difficult.

I would like to understand you case better. Let's take current non optimality of code generation out of the consideration. Is it a problem of inaccurate cost estimation for some particular instructions or not taking overhead which comes with the vectorization into account?

There's a lot of setup and spilling too, which is going to hurt for small trip counts.

Does this setup/spilling happens inside the main vector loop or outside? Is this reflected on IR level or low level (maybe even hardware specific)?

I think for MVE it would make sense to have a way for the target to put a limit on the minumum trip count.

IMHO, this may be an option only if we find out that this is something specific to MVE. Anyway, it looks like a workaround (hopefully temporary :-)) until a better support is there.

I think @fhahn also mentioned that he had some AArch64 examples where the same is true. I'm not sure in general where this would be useful. The vectorizers handing of small trip count loops is not amazing, considering that many such loops will already have been fully unrolled.

Until I'm missing something looks like currently LV comes before Unroller&SLP which makes perfect sense to me. Anyway, I wouldn't stick to any specific pass ordering as LLVM is an infrastructure for building custom compilers. LV should do its job as good as it can. If it can prove that vectorization is beneficial it should do it (until we have an infrastructure to take dependencies between different passes into account).

It doesn't come up a huge amount and a lot of the cost modelling currently assumes any extra setup costs will be dominated by the loop.

[ebrevnov]

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

9851–9866

It looks like, in this specific example, vector cost of the main vector loop being estimated as 2x lower than scalar one is pretty much accurate. The problem is that extra cost coming from horizontal reduction after main vector loop is not taken into account. This is something that definitely should be fixed before we can move on in this direction. Essentially, this problem is a major blocking factor to enable short TC loops vectorization in general case (not only compile time known TC).

PS: I wonder if your problematic case on MVE is something similar to this or not?

[lebedev.ri]

In D115713#3911820, @ebrevnov wrote:

In D115713#3910792, @dmgreen wrote:

I think @fhahn also mentioned that he had some AArch64 examples where the same is true. I'm not sure in general where this would be useful. The vectorizers handing of small trip count loops is not amazing, considering that many such loops will already have been fully unrolled.

Until I'm missing something looks like currently LV comes before Unroller&SLP which makes perfect sense to me. Anyway, I wouldn't stick to any specific pass ordering as LLVM is an infrastructure for building custom compilers. LV should do its job as good as it can. If it can prove that vectorization is beneficial it should do it (until we have an infrastructure to take dependencies between different passes into account).

(Unfortunately?) full loop unrolling happens before LV.
I personally think that once LV has outer loop vectorization, that should be considered a bug that should be resolved.

[ebrevnov]

Avoid vectorization if there is reduction/recurrence induced overhead

[ebrevnov]

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

9851–9866

I've update the patch to avoid vectorization in such cases. Please take a look.

[dmgreen]

Avoid vectorization if there is reduction/recurrence induced overhead

For some architectures like MVE and AArch64 the reduction cost might well be cheap. Non-zero but also not huge. It can depend on the reduction. Have you considered the cost of constants and splats too, that the vectorizer will currently hoist into the preheader? The costmodel functions might also sometimes return cheaper costs for certain shuffles and gathers under the assumption that loop invariant parts can be hoisted.

I've tried to get an example of the case that is getting worse for MVE in rG662b5f18467e. It might be a bit over-reduced, but hopefully it still shows the same problems. The original I can't share, I'm afraid.

@fhahn did you have an example of cases where you had seen AArch64 getting worse? Is it covered by reductions or is it more general?

[lebedev.ri]

This review may be stuck/dead, consider abandoning if no longer relevant.
Removing myself as reviewer in attempt to clean dashboard.

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

 // for predication.
 Optional<ScalarEpilogueLowering> getScalarEpilogueLowering(
     Function *F, Loop *L, LoopVectorizeHints &Hints, ProfileSummaryInfo *PSI,
     BlockFrequencyInfo *BFI, TargetTransformInfo *TTI, TargetLibraryInfo *TLI,
     AssumptionCache *AC, LoopInfo *LI, PredicatedScalarEvolution &PSE,
     DominatorTree *DT, LoopVectorizationLegality &LVL,
     InterleavedAccessInfo *IAI, OptimizationRemarkEmitter *ORE) {
   auto &SE = *PSE.getSE();
+  auto PreferPredicate =
+      TTI->preferPredicateOverEpilogue(L, LI, SE, *AC, TLI, DT, &LVL, IAI);
 
   // 1) OptSize takes precedence over all other options, i.e. if this is set,
   // don't look at hints or options, and don't request a scalar epilogue.
   // (For PGSO, as shouldOptimizeForSize isn't currently accessible from
   // LoopAccessInfo (due to code dependency and not being able to reliably get
   // PSI/BFI from a loop analysis under NPM), we cannot suppress the collection
   // of strides in LoopAccessInfo::analyzeLoop() and vectorize without
   // versioning when the vectorization is forced, unlike hasOptSize. So revert
if (ExpectedTC && *ExpectedTC < TinyTripCountVectorThreshold) {
     if (Hints.getForce() == LoopVectorizeHints::FK_Enabled)
       LLVM_DEBUG(dbgs() << " But vectorizing was explicitly forced.\n");
     else {
       if (runtimeChecksRequired(LVL, PSE, ORE, L)) {
         LLVM_DEBUG(dbgs() << "LV: Not allowing scalar epilogue due to low trip "
                           << "count.\n");
         return None;
       }
+      // If trip count is known compile time constant there is no any extra
+      // overhead from vectorization with scalar epilogue. Let cost model to
+      // decide on profitability in that case.
+      auto TC = SE.getSmallConstantTripCount(L);
+      if (TC == 0 || PreferPredicate) {
         if (*ExpectedTC <= TTI->getMinTripCountTailFoldingThreshold()) {
           LLVM_DEBUG(dbgs() << "But the target considers the trip count too "
                                "small to consider vectorizing.\n");
           reportVectorizationFailure(
               "The trip count is below the minimal threshold value.",
               "loop trip count is too low, avoiding vectorization",
               "LowTripCount", ORE, L);
           return None;
         }
         return CM_SEL_PredicateOrDontVectorize;
       }
     }
+  }
 
   // 5) if the TTI hook indicates this is profitable, request predication.
-  if (TTI->preferPredicateOverEpilogue(L, LI, SE, *AC, TLI, DT, &LVL, IAI))
+  if (PreferPredicate)
     return CM_SEL_PredicateElseScalar;
 
   return CM_SEL_Allowed;
 }
 
 Value *VPTransformState::get(VPValue *Def, unsigned Part) {
   // If Values have been set for this Def return the one relevant for \p Part.
   if (hasVectorValue(Def, Part))

llvm/test/Transforms/LoopVectorize/AArch64/sve-low-trip-count.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -loop-vectorize -S < %s | FileCheck %s
 
 target triple = "aarch64-unknown-linux-gnu"
 
 define void @trip7_i64(i64* noalias nocapture noundef %dst, i64* noalias nocapture noundef readonly %src) #0 {
 ; CHECK-LABEL: @trip7_i64(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 7, [[TMP1]]
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK:       vector.ph:
+; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 2
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 7, [[TMP3]]
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 7, [[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:         [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 2 x i1> [ {{%.*}}, %vector.ph ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], %vector.body ]
-; CHECK:         {{%.*}} = call <vscale x 2 x i64> @llvm.masked.load.nxv2i64.p0nxv2i64(<vscale x 2 x i64>* {{%.*}}, i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i64> poison)
-; CHECK:         {{%.*}} = call <vscale x 2 x i64> @llvm.masked.load.nxv2i64.p0nxv2i64(<vscale x 2 x i64>* {{%.*}}, i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i64> poison)
-; CHECK:         call void @llvm.masked.store.nxv2i64.p0nxv2i64(<vscale x 2 x i64> {{%.*}}, <vscale x 2 x i64>* {{%.*}}, i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
-; CHECK:         [[VSCALE:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[VF:%.*]] = mul i64 [[VSCALE]], 2
-; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[VF]]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX_NEXT]], i64 7)
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NOT:%.*]] = xor <vscale x 2 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i32 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer)
-; CHECK-NEXT:    [[COND:%.*]] = extractelement <vscale x 2 x i1> [[ACTIVE_LANE_MASK_NOT]], i32 0
-; CHECK-NEXT:    br i1 [[COND]], label %middle.block, label %vector.body
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP4:%.*]] = add i64 [[INDEX]], 0
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i64, i64* [[SRC:%.*]], i64 [[TMP4]]
+; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i64, i64* [[TMP5]], i32 0
+; CHECK-NEXT:    [[TMP7:%.*]] = bitcast i64* [[TMP6]] to <vscale x 2 x i64>*
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 2 x i64>, <vscale x 2 x i64>* [[TMP7]], align 8
+; CHECK-NEXT:    [[TMP8:%.*]] = shl nsw <vscale x 2 x i64> [[WIDE_LOAD]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 1, i32 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
+; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i64, i64* [[DST:%.*]], i64 [[TMP4]]
+; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i64, i64* [[TMP9]], i32 0
+; CHECK-NEXT:    [[TMP11:%.*]] = bitcast i64* [[TMP10]] to <vscale x 2 x i64>*
+; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <vscale x 2 x i64>, <vscale x 2 x i64>* [[TMP11]], align 8
+; CHECK-NEXT:    [[TMP12:%.*]] = add nsw <vscale x 2 x i64> [[WIDE_LOAD1]], [[TMP8]]
+; CHECK-NEXT:    [[TMP13:%.*]] = bitcast i64* [[TMP10]] to <vscale x 2 x i64>*
+; CHECK-NEXT:    store <vscale x 2 x i64> [[TMP12]], <vscale x 2 x i64>* [[TMP13]], align 8
+; CHECK-NEXT:    [[TMP14:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP15:%.*]] = mul i64 [[TMP14]], 2
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP15]]
+; CHECK-NEXT:    [[TMP16:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP16]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 7, [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[I_06:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, i64* [[SRC]], i64 [[I_06]]
+; CHECK-NEXT:    [[TMP17:%.*]] = load i64, i64* [[ARRAYIDX]], align 8
+; CHECK-NEXT:    [[MUL:%.*]] = shl nsw i64 [[TMP17]], 1
+; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i64, i64* [[DST]], i64 [[I_06]]
+; CHECK-NEXT:    [[TMP18:%.*]] = load i64, i64* [[ARRAYIDX1]], align 8
+; CHECK-NEXT:    [[ADD:%.*]] = add nsw i64 [[TMP18]], [[MUL]]
+; CHECK-NEXT:    store i64 [[ADD]], i64* [[ARRAYIDX1]], align 8
+; CHECK-NEXT:    [[INC]] = add nuw nsw i64 [[I_06]], 1
+; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], 7
+; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP2:![0-9]+]]
+; CHECK:       for.end:
+; CHECK-NEXT:    ret void
 ;
 entry:
   br label %for.body
 
 for.body:                                         ; preds = %entry, %for.body
   %i.06 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
   %arrayidx = getelementptr inbounds i64, i64* %src, i64 %i.06
   %0 = load i64, i64* %arrayidx, align 8
   %mul = shl nsw i64 %0, 1
   %arrayidx1 = getelementptr inbounds i64, i64* %dst, i64 %i.06
   %1 = load i64, i64* %arrayidx1, align 8
   %add = add nsw i64 %1, %mul
   store i64 %add, i64* %arrayidx1, align 8
   %inc = add nuw nsw i64 %i.06, 1
   %exitcond.not = icmp eq i64 %inc, 7
   br i1 %exitcond.not, label %for.end, label %for.body
 
 for.end:                                          ; preds = %for.body
   ret void
 }
 
 define void @trip5_i8(i8* noalias nocapture noundef %dst, i8* noalias nocapture noundef readonly %src) #0 {
 ; CHECK-LABEL: @trip5_i8(
 ; 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:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i8, i8* [[SRC:%.*]], i64 [[TMP0]]
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i8, i8* [[TMP1]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i8* [[TMP2]] to <4 x i8>*
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i8>, <4 x i8>* [[TMP3]], align 1
+; CHECK-NEXT:    [[TMP4:%.*]] = shl <4 x i8> [[WIDE_LOAD]], <i8 1, i8 1, i8 1, i8 1>
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i8, i8* [[DST:%.*]], i64 [[TMP0]]
+; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i8, i8* [[TMP5]], i32 0
+; CHECK-NEXT:    [[TMP7:%.*]] = bitcast i8* [[TMP6]] to <4 x i8>*
+; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <4 x i8>, <4 x i8>* [[TMP7]], align 1
+; CHECK-NEXT:    [[TMP8:%.*]] = add <4 x i8> [[TMP4]], [[WIDE_LOAD1]]
+; CHECK-NEXT:    [[TMP9:%.*]] = bitcast i8* [[TMP6]] to <4 x i8>*
+; CHECK-NEXT:    store <4 x i8> [[TMP8]], <4 x i8>* [[TMP9]], align 1
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
+; CHECK-NEXT:    [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], 4
+; CHECK-NEXT:    br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 5, 4
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 4, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
-; CHECK-NEXT:    [[I_08:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
-; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, i8* [[SRC:%.*]], i64 [[I_08]]
-; CHECK-NEXT:    [[TMP0:%.*]] = load i8, i8* [[ARRAYIDX]], align 1
-; CHECK-NEXT:    [[MUL:%.*]] = shl i8 [[TMP0]], 1
-; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, i8* [[DST:%.*]], i64 [[I_08]]
-; CHECK-NEXT:    [[TMP1:%.*]] = load i8, i8* [[ARRAYIDX1]], align 1
-; CHECK-NEXT:    [[ADD:%.*]] = add i8 [[MUL]], [[TMP1]]
+; CHECK-NEXT:    [[I_08:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 [[I_08]]
+; CHECK-NEXT:    [[TMP11:%.*]] = load i8, i8* [[ARRAYIDX]], align 1
+; CHECK-NEXT:    [[MUL:%.*]] = shl i8 [[TMP11]], 1
+; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 [[I_08]]
+; CHECK-NEXT:    [[TMP12:%.*]] = load i8, i8* [[ARRAYIDX1]], align 1
+; CHECK-NEXT:    [[ADD:%.*]] = add i8 [[MUL]], [[TMP12]]
 ; CHECK-NEXT:    store i8 [[ADD]], i8* [[ARRAYIDX1]], align 1
 ; CHECK-NEXT:    [[INC]] = add nuw nsw i64 [[I_08]], 1
 ; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], 5
-; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END:%.*]], label [[FOR_BODY]]
+; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
 ; CHECK:       for.end:
 ; CHECK-NEXT:    ret void
 ;
 entry:
   br label %for.body
 
 for.body:                                         ; preds = %entry, %for.body
   %i.08 = phi i64 [ 0, %entry ], [ %inc, %for.body ]

llvm/test/Transforms/LoopVectorize/RISCV/low-trip-count.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -loop-vectorize -riscv-v-vector-bits-min=128 -scalable-vectorization=on -force-target-instruction-cost=1 -S < %s | FileCheck %s
 
 target triple = "riscv64"
 
 define void @trip5_i8(i8* noalias nocapture noundef %dst, i8* noalias nocapture noundef readonly %src) #0 {
 ; CHECK-LABEL: @trip5_i8(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 8
-; CHECK-NEXT:    [[TMP2:%.*]] = icmp ult i64 -6, [[TMP1]]
-; CHECK-NEXT:    br i1 [[TMP2]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
-; CHECK-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 8
-; CHECK-NEXT:    [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP6:%.*]] = mul i64 [[TMP5]], 8
-; CHECK-NEXT:    [[TMP7:%.*]] = sub i64 [[TMP6]], 1
-; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i64 5, [[TMP7]]
-; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP4]]
-; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[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:    [[TMP8:%.*]] = add i64 [[INDEX]], 0
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[TMP8]], i64 5)
-; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i8, i8* [[SRC:%.*]], i64 [[TMP8]]
-; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i8, i8* [[TMP9]], i32 0
-; CHECK-NEXT:    [[TMP11:%.*]] = bitcast i8* [[TMP10]] to <vscale x 8 x i8>*
-; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 8 x i8> @llvm.masked.load.nxv8i8.p0nxv8i8(<vscale x 8 x i8>* [[TMP11]], i32 1, <vscale x 8 x i1> [[ACTIVE_LANE_MASK]], <vscale x 8 x i8> poison)
-; CHECK-NEXT:    [[TMP12:%.*]] = shl <vscale x 8 x i8> [[WIDE_MASKED_LOAD]], shufflevector (<vscale x 8 x i8> insertelement (<vscale x 8 x i8> poison, i8 1, i32 0), <vscale x 8 x i8> poison, <vscale x 8 x i32> zeroinitializer)
-; CHECK-NEXT:    [[TMP13:%.*]] = getelementptr inbounds i8, i8* [[DST:%.*]], i64 [[TMP8]]
-; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr inbounds i8, i8* [[TMP13]], i32 0
-; CHECK-NEXT:    [[TMP15:%.*]] = bitcast i8* [[TMP14]] to <vscale x 8 x i8>*
-; CHECK-NEXT:    [[WIDE_MASKED_LOAD1:%.*]] = call <vscale x 8 x i8> @llvm.masked.load.nxv8i8.p0nxv8i8(<vscale x 8 x i8>* [[TMP15]], i32 1, <vscale x 8 x i1> [[ACTIVE_LANE_MASK]], <vscale x 8 x i8> poison)
-; CHECK-NEXT:    [[TMP16:%.*]] = add <vscale x 8 x i8> [[TMP12]], [[WIDE_MASKED_LOAD1]]
-; CHECK-NEXT:    [[TMP17:%.*]] = bitcast i8* [[TMP14]] to <vscale x 8 x i8>*
-; CHECK-NEXT:    call void @llvm.masked.store.nxv8i8.p0nxv8i8(<vscale x 8 x i8> [[TMP16]], <vscale x 8 x i8>* [[TMP17]], i32 1, <vscale x 8 x i1> [[ACTIVE_LANE_MASK]])
-; CHECK-NEXT:    [[TMP18:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP19:%.*]] = mul i64 [[TMP18]], 8
-; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP19]]
-; CHECK-NEXT:    br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i8, i8* [[SRC:%.*]], i64 [[TMP0]]
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i8, i8* [[TMP1]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i8* [[TMP2]] to <4 x i8>*
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i8>, <4 x i8>* [[TMP3]], align 1
+; CHECK-NEXT:    [[TMP4:%.*]] = shl <4 x i8> [[WIDE_LOAD]], <i8 1, i8 1, i8 1, i8 1>
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i8, i8* [[DST:%.*]], i64 [[TMP0]]
+; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i8, i8* [[TMP5]], i32 0
+; CHECK-NEXT:    [[TMP7:%.*]] = bitcast i8* [[TMP6]] to <4 x i8>*
+; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <4 x i8>, <4 x i8>* [[TMP7]], align 1
+; CHECK-NEXT:    [[TMP8:%.*]] = add <4 x i8> [[TMP4]], [[WIDE_LOAD1]]
+; CHECK-NEXT:    [[TMP9:%.*]] = bitcast i8* [[TMP6]] to <4 x i8>*
+; CHECK-NEXT:    store <4 x i8> [[TMP8]], <4 x i8>* [[TMP9]], align 1
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
+; CHECK-NEXT:    [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], 4
+; CHECK-NEXT:    br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
 ; CHECK:       middle.block:
-; CHECK-NEXT:    br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 5, 4
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
-; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 4, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[I_08:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
 ; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 [[I_08]]
-; CHECK-NEXT:    [[TMP20:%.*]] = load i8, i8* [[ARRAYIDX]], align 1
-; CHECK-NEXT:    [[MUL:%.*]] = shl i8 [[TMP20]], 1
+; CHECK-NEXT:    [[TMP11:%.*]] = load i8, i8* [[ARRAYIDX]], align 1
+; CHECK-NEXT:    [[MUL:%.*]] = shl i8 [[TMP11]], 1
 ; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 [[I_08]]
-; CHECK-NEXT:    [[TMP21:%.*]] = load i8, i8* [[ARRAYIDX1]], align 1
-; CHECK-NEXT:    [[ADD:%.*]] = add i8 [[MUL]], [[TMP21]]
+; CHECK-NEXT:    [[TMP12:%.*]] = load i8, i8* [[ARRAYIDX1]], align 1
+; CHECK-NEXT:    [[ADD:%.*]] = add i8 [[MUL]], [[TMP12]]
 ; CHECK-NEXT:    store i8 [[ADD]], i8* [[ARRAYIDX1]], align 1
 ; CHECK-NEXT:    [[INC]] = add nuw nsw i64 [[I_08]], 1
 ; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], 5
 ; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP2:![0-9]+]]
 ; CHECK:       for.end:
 ; CHECK-NEXT:    ret void
 ;
 entry:

llvm/test/Transforms/LoopVectorize/SystemZ/predicated-first-order-recurrence.ll

 
 define void @func_21() {
 ; CHECK-LABEL: @func_21(
 ; 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:%.*]], [[PRED_STORE_CONTINUE4:%.*]] ]
-; CHECK-NEXT:    [[VECTOR_RECUR:%.*]] = phi <2 x i32> [ <i32 poison, i32 0>, [[VECTOR_PH]] ], [ [[TMP12:%.*]], [[PRED_STORE_CONTINUE4]] ]
-; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <2 x i64> [ <i64 0, i64 1>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_STORE_CONTINUE4]] ]
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VECTOR_RECUR:%.*]] = phi <2 x i32> [ <i32 poison, i32 0>, [[VECTOR_PH]] ], [ [[WIDE_LOAD:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
-; CHECK-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 1
-; CHECK-NEXT:    [[TMP2:%.*]] = icmp ule <2 x i64> [[VEC_IND]], <i64 4, i64 4>
-; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <2 x i1> [[TMP2]], i32 0
-; CHECK-NEXT:    br i1 [[TMP3]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]]
-; CHECK:       pred.load.if:
-; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [5 x i32], [5 x i32]* @A, i64 0, i64 [[TMP0]]
-; CHECK-NEXT:    [[TMP5:%.*]] = load i32, i32* [[TMP4]], align 4
-; CHECK-NEXT:    [[TMP6:%.*]] = insertelement <2 x i32> poison, i32 [[TMP5]], i32 0
-; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE]]
-; CHECK:       pred.load.continue:
-; CHECK-NEXT:    [[TMP7:%.*]] = phi <2 x i32> [ poison, [[VECTOR_BODY]] ], [ [[TMP6]], [[PRED_LOAD_IF]] ]
-; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <2 x i1> [[TMP2]], i32 1
-; CHECK-NEXT:    br i1 [[TMP8]], label [[PRED_LOAD_IF1:%.*]], label [[PRED_LOAD_CONTINUE2:%.*]]
-; CHECK:       pred.load.if1:
-; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [5 x i32], [5 x i32]* @A, i64 0, i64 [[TMP1]]
-; CHECK-NEXT:    [[TMP10:%.*]] = load i32, i32* [[TMP9]], align 4
-; CHECK-NEXT:    [[TMP11:%.*]] = insertelement <2 x i32> [[TMP7]], i32 [[TMP10]], i32 1
-; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE2]]
-; CHECK:       pred.load.continue2:
-; CHECK-NEXT:    [[TMP12]] = phi <2 x i32> [ [[TMP7]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP11]], [[PRED_LOAD_IF1]] ]
-; CHECK-NEXT:    [[TMP13:%.*]] = shufflevector <2 x i32> [[VECTOR_RECUR]], <2 x i32> [[TMP12]], <2 x i32> <i32 1, i32 2>
-; CHECK-NEXT:    [[TMP14:%.*]] = extractelement <2 x i1> [[TMP2]], i32 0
-; CHECK-NEXT:    br i1 [[TMP14]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
-; CHECK:       pred.store.if:
-; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds [5 x i32], [5 x i32]* @B, i64 0, i64 [[TMP0]]
-; CHECK-NEXT:    [[TMP16:%.*]] = extractelement <2 x i32> [[TMP13]], i32 0
-; CHECK-NEXT:    store i32 [[TMP16]], i32* [[TMP15]], align 4
-; CHECK-NEXT:    br label [[PRED_STORE_CONTINUE]]
-; CHECK:       pred.store.continue:
-; CHECK-NEXT:    [[TMP17:%.*]] = extractelement <2 x i1> [[TMP2]], i32 1
-; CHECK-NEXT:    br i1 [[TMP17]], label [[PRED_STORE_IF3:%.*]], label [[PRED_STORE_CONTINUE4]]
-; CHECK:       pred.store.if3:
-; CHECK-NEXT:    [[TMP18:%.*]] = getelementptr inbounds [5 x i32], [5 x i32]* @B, i64 0, i64 [[TMP1]]
-; CHECK-NEXT:    [[TMP19:%.*]] = extractelement <2 x i32> [[TMP13]], i32 1
-; CHECK-NEXT:    store i32 [[TMP19]], i32* [[TMP18]], align 4
-; CHECK-NEXT:    br label [[PRED_STORE_CONTINUE4]]
-; CHECK:       pred.store.continue4:
-; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 2
-; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <2 x i64> [[VEC_IND]], <i64 2, i64 2>
-; CHECK-NEXT:    [[TMP20:%.*]] = icmp eq i64 [[INDEX_NEXT]], 6
-; CHECK-NEXT:    br i1 [[TMP20]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP0:!llvm.loop !.*]]
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds [5 x i32], [5 x i32]* @A, i64 0, i64 [[TMP0]]
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <2 x i32>*
+; CHECK-NEXT:    [[WIDE_LOAD]] = load <2 x i32>, <2 x i32>* [[TMP3]], align 4
+; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <2 x i32> [[VECTOR_RECUR]], <2 x i32> [[WIDE_LOAD]], <2 x i32> <i32 1, i32 2>
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [5 x i32], [5 x i32]* @B, i64 0, i64 [[TMP0]]
+; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[TMP5]], i32 0
+; CHECK-NEXT:    [[TMP7:%.*]] = bitcast i32* [[TMP6]] to <2 x i32>*
+; CHECK-NEXT:    store <2 x i32> [[TMP4]], <2 x i32>* [[TMP7]], align 4
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
+; CHECK-NEXT:    [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], 4
+; CHECK-NEXT:    br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
 ; CHECK:       middle.block:
-; CHECK-NEXT:    [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <2 x i32> [[TMP12]], i32 1
-; CHECK-NEXT:    [[VECTOR_RECUR_EXTRACT_FOR_PHI:%.*]] = extractelement <2 x i32> [[TMP12]], i32 0
-; CHECK-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 5, 4
+; CHECK-NEXT:    [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <2 x i32> [[WIDE_LOAD]], i32 1
+; CHECK-NEXT:    [[VECTOR_RECUR_EXTRACT_FOR_PHI:%.*]] = extractelement <2 x i32> [[WIDE_LOAD]], i32 0
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[SCALAR_RECUR_INIT:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[VECTOR_RECUR_EXTRACT]], [[MIDDLE_BLOCK]] ]
-; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 6, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY]] ]
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 4, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY]] ]
 ; CHECK-NEXT:    br label [[LOOP:%.*]]
 ; CHECK:       loop:
 ; CHECK-NEXT:    [[SCALAR_RECUR:%.*]] = phi i32 [ [[SCALAR_RECUR_INIT]], [[SCALAR_PH]] ], [ [[LV:%.*]], [[LOOP]] ]
 ; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[LOOP]] ]
 ; CHECK-NEXT:    [[A_PTR:%.*]] = getelementptr inbounds [5 x i32], [5 x i32]* @A, i64 0, i64 [[INDVARS_IV]]
 ; CHECK-NEXT:    [[LV]] = load i32, i32* [[A_PTR]], align 4
 ; CHECK-NEXT:    [[B_PTR:%.*]] = getelementptr inbounds [5 x i32], [5 x i32]* @B, i64 0, i64 [[INDVARS_IV]]
 ; CHECK-NEXT:    store i32 [[SCALAR_RECUR]], i32* [[B_PTR]], align 4
 ; CHECK-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
 ; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 5
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[EXIT]], label [[LOOP]], [[LOOP2:!llvm.loop !.*]]
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP2:![0-9]+]]
 ; CHECK:       exit:
 ; CHECK-NEXT:    ret void
 ;
 entry:
   br label %loop
 
 loop:                                    ; preds = %loop, %entry
   %rec = phi i32 [ 0, %entry], [ %lv, %loop ]

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

 ; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = trunc i32 [[INDEX]] to i16
 ; 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 nuw i32 [[INDEX]], 2
-; CHECK-NEXT:    br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP0:!llvm.loop !.*]]
+; CHECK-NEXT:    br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 2, 2
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[BB3:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i16 [ 2, [[MIDDLE_BLOCK]] ], [ 0, [[BB1:%.*]] ]
 ; CHECK-NEXT:    br label [[BB2:%.*]]
 ; CHECK:       bb2:
 ; CHECK-NEXT:    [[C_1_0:%.*]] = phi i16 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[_TMP9:%.*]], [[BB2]] ]
 ; CHECK-NEXT:    [[_TMP1:%.*]] = zext i16 0 to i64
 ; CHECK-NEXT:    [[_TMP2:%.*]] = getelementptr [1 x %rec8], [1 x %rec8]* @a, i16 0, i64 [[_TMP1]]
 ; CHECK-NEXT:    [[_TMP4:%.*]] = bitcast %rec8* [[_TMP2]] to i16*
 ; CHECK-NEXT:    [[_TMP6:%.*]] = sext i16 [[C_1_0]] to i64
 ; CHECK-NEXT:    [[_TMP7:%.*]] = getelementptr [2 x i16*], [2 x i16*]* @b, i16 0, i64 [[_TMP6]]
 ; CHECK-NEXT:    store i16* [[_TMP4]], i16** [[_TMP7]], align 8
 ; CHECK-NEXT:    [[_TMP9]] = add nsw i16 [[C_1_0]], 1
 ; CHECK-NEXT:    [[_TMP11:%.*]] = icmp slt i16 [[_TMP9]], 2
-; CHECK-NEXT:    br i1 [[_TMP11]], label [[BB2]], label [[BB3]], [[LOOP2:!llvm.loop !.*]]
+; CHECK-NEXT:    br i1 [[_TMP11]], label [[BB2]], label [[BB3]], !llvm.loop [[LOOP2:![0-9]+]]
 ; CHECK:       bb3:
 ; CHECK-NEXT:    ret void
 ;
 
 bb1:
   br label %bb2
 
 bb2:

llvm/test/Transforms/LoopVectorize/X86/pr31671-consecutive-ptr-uniforms.ll

 ; REQUIRES: asserts
 ; RUN: opt < %s -aa-pipeline=basic-aa -passes=loop-vectorize,instcombine -S -debug-only=loop-vectorize -disable-output -print-after=instcombine 2>&1 | FileCheck %s
-; RUN: opt < %s -loop-vectorize -force-vector-width=2 -S | FileCheck %s -check-prefix=FORCE
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
 ; CHECK-LABEL: PR31671
 ;
 ; Check a pointer in which one of its uses is consecutive-like and another of
 ; its uses is non-consecutive-like. In the test case below, %tmp3 is the
 ; pointer operand of an interleaved load, making it consecutive-like. However,
 ; it is also the pointer operand of a non-interleaved store that will become a
 ; scatter operation. %tmp3 (and the induction variable) should not be marked
 ; uniform-after-vectorization.
 ;
 ; CHECK:       LV: Found uniform instruction: %tmp0 = getelementptr inbounds %data, %data* %d, i64 0, i32 3, i64 %i
 ; CHECK-NOT:   LV: Found uniform instruction: %tmp3 = getelementptr inbounds %data, %data* %d, i64 0, i32 0, i64 %i
 ; CHECK-NOT:   LV: Found uniform instruction: %i = phi i64 [ %i.next, %for.body ], [ 0, %entry ]
 ; CHECK-NOT:   LV: Found uniform instruction: %i.next = add nuw nsw i64 %i, 5
-; CHECK:       define void @PR31671(
+; CHECK-LABEL: @PR31671(
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <16 x float> poison, float %x, i64 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <16 x float> [[BROADCAST_SPLATINSERT]], <16 x float> poison, <16 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_IND:%.*]] = phi <16 x i64> [ <i64 0, i64 5, i64 10, i64 15, i64 20, i64 25, i64 30, i64 35, i64 40, i64 45, i64 50, i64 55, i64 60, i64 65, i64 70, i64 75>, %vector.ph ], [ [[VEC_IND_NEXT:%.*]], %vector.body ]
 ; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = mul i64 [[INDEX]], 5
for.body:
   br i1 %cond, label %for.body, label %for.end
 
 for.end:
   ret void
 }
 
 attributes #0 = { "target-cpu"="knl" }
 
-; CHECK-LABEL: PR40816
-;
-; Check that scalar with predication instructions are not considered uniform
-; after vectorization, because that results in replicating a region instead of
-; having a single instance (out of VF). The predication stems from a tiny count
-; of 3 leading to folding the tail by masking using icmp ule <i, i+1> <= <2, 2>.
-;
-; CHECK:     LV: Found trip count: 3
-; CHECK:     LV: Found uniform instruction:   {{%.*}} = icmp eq i32 {{%.*}}, 0
-; CHECK-NOT: LV: Found uniform instruction:   {{%.*}} = load i32, i32* {{%.*}}, align 1
-; CHECK:     LV: Found not uniform being ScalarWithPredication:  {{%.*}} = load i32, i32* {{%.*}}, align 1
-; CHECK:     LV: Found scalar instruction:   {{%.*}} = getelementptr inbounds [3 x i32], [3 x i32]* @a, i32 0, i32 {{%.*}}
-;
-; FORCE-LABEL: @PR40816(
-; FORCE-NEXT:  entry:
-; FORCE-NEXT:    br i1 false, label {{%.*}}, label [[VECTOR_PH:%.*]]
-; FORCE:       vector.ph:
-; FORCE-NEXT:    br label [[VECTOR_BODY:%.*]]
-; FORCE:       vector.body:
-; FORCE-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_LOAD_CONTINUE4:%.*]] ]
-; FORCE-NEXT:    [[VEC_IND:%.*]] = phi <2 x i32> [ <i32 0, i32 1>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_LOAD_CONTINUE4]] ]
-; FORCE-NEXT:    [[TMP2:%.*]] = icmp ule <2 x i32> [[VEC_IND]], <i32 2, i32 2>
-; FORCE-NEXT:    [[TMP3:%.*]] = extractelement <2 x i1> [[TMP2]], i32 0
-; FORCE-NEXT:    br i1 [[TMP3]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]]
-; FORCE:       pred.load.if:
-; FORCE-NEXT:    [[TMP0:%.*]] = add i32 [[INDEX]], 0
-; FORCE-NEXT:    store i32 [[TMP0]], i32* @b, align 1
-; FORCE-NEXT:    br label [[PRED_LOAD_CONTINUE]]
-; FORCE:       pred.load.continue:
-; FORCE-NEXT:    [[TMP10:%.*]] = extractelement <2 x i1> [[TMP2]], i32 1
-; FORCE-NEXT:    br i1 [[TMP10]], label [[PRED_LOAD_IF3:%.*]], label [[PRED_LOAD_CONTINUE4]]
-; FORCE:       pred.load.if1:
-; FORCE-NEXT:    [[TMP1:%.*]] = add i32 [[INDEX]], 1
-; FORCE-NEXT:    store i32 [[TMP1]], i32* @b, align 1
-; FORCE-NEXT:    br label [[PRED_LOAD_CONTINUE4]]
-; FORCE:       pred.load.continue2:
-; FORCE-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 2
-; FORCE-NEXT:    [[VEC_IND_NEXT]] = add <2 x i32> [[VEC_IND]], <i32 2, i32 2>
-; FORCE-NEXT:    [[TMP15:%.*]] = icmp eq i32 [[INDEX_NEXT]], 4
-; FORCE-NEXT:    br i1 [[TMP15]], label {{%.*}}, label [[VECTOR_BODY]]
-;
-@a = internal constant [3 x i32] [i32 7, i32 7, i32 0], align 1
-@b = external global i32, align 1
-
-define void @PR40816() #1 {
-
-entry:
-  br label %for.body
-
-for.body:                                         ; preds = %for.body, %entry
-  %0 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
-  store i32 %0, i32* @b, align 1
-  %arrayidx1 = getelementptr inbounds [3 x i32], [3 x i32]* @a, i32 0, i32 %0
-  %1 = load i32, i32* %arrayidx1, align 1
-  %cmp2 = icmp eq i32 %1, 0
-  %inc = add nuw nsw i32 %0, 1
-  br i1 %cmp2, label %return, label %for.body
-
-return:                                           ; preds = %for.body
-  ret void
-}
-
-attributes #1 = { "target-cpu"="core2" }

llvm/test/Transforms/LoopVectorize/X86/pr34438.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:    [[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, !llvm.access.group !0
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <8 x float>, <8 x float>* [[TMP3]], align 4, !llvm.access.group [[ACC_GRP0:![0-9]+]]
 ; 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, !llvm.access.group !0
+; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <8 x float>, <8 x float>* [[TMP6]], align 4, !llvm.access.group [[ACC_GRP0]]
 ; 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, !llvm.access.group !0
+; CHECK-NEXT:    store <8 x float> [[TMP7]], <8 x float>* [[TMP8]], align 4, !llvm.access.group [[ACC_GRP0]]
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
-; CHECK-NEXT:    br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP1:!llvm.loop !.*]]
+; CHECK-NEXT:    br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP1:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 8, 8
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 8, [[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:    [[TMP10:%.*]] = load float, float* [[ARRAYIDX]], align 4, !llvm.access.group !0
+; CHECK-NEXT:    [[TMP9:%.*]] = load float, float* [[ARRAYIDX]], align 4, !llvm.access.group [[ACC_GRP0]]
 ; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[INDVARS_IV]]
-; CHECK-NEXT:    [[TMP11:%.*]] = load float, float* [[ARRAYIDX2]], align 4, !llvm.access.group !0
-; CHECK-NEXT:    [[ADD:%.*]] = fadd fast float [[TMP10]], [[TMP11]]
-; CHECK-NEXT:    store float [[ADD]], float* [[ARRAYIDX2]], align 4, !llvm.access.group !0
+; CHECK-NEXT:    [[TMP10:%.*]] = load float, float* [[ARRAYIDX2]], align 4, !llvm.access.group [[ACC_GRP0]]
+; CHECK-NEXT:    [[ADD:%.*]] = fadd fast float [[TMP9]], [[TMP10]]
+; CHECK-NEXT:    store float [[ADD]], float* [[ARRAYIDX2]], align 4, !llvm.access.group [[ACC_GRP0]]
 ; CHECK-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
 ; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 8
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_END]], label [[FOR_BODY]], [[LOOP3:!llvm.loop !.*]]
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
 ; 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 ]

llvm/test/Transforms/LoopVectorize/X86/pr40816-consecutive-ptr-uniforms.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; REQUIRES: asserts
+; RUN: opt < %s -aa-pipeline=basic-aa -passes=loop-vectorize,instcombine -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue -S -debug-only=loop-vectorize -disable-output -print-after=instcombine 2>&1 | FileCheck %s
+; RUN: opt < %s -loop-vectorize -instcombine -S -debug-only=loop-vectorize -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue -disable-output -print-after=instcombine -enable-new-pm=0 2>&1 | FileCheck %s
+; RUN: opt < %s -loop-vectorize -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue -force-vector-width=2 -S | FileCheck %s -check-prefix=FORCE
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+; CHECK-LABEL: PR40816
+;
+; Check that scalar with predication instructions are not considered uniform
+; after vectorization, because that results in replicating a region instead of
+; having a single instance (out of VF). The predication stems from a tiny count
+; of 3 leading to folding the tail by masking using icmp ule <i, i+1> <= <2, 2>.
+;
+; CHECK:     LV: Found trip count: 3
+; CHECK:     LV: Found uniform instruction:   {{%.*}} = icmp eq i32 {{%.*}}, 0
+; CHECK-NOT: LV: Found uniform instruction:   {{%.*}} = load i32, i32* {{%.*}}, align 1
+; CHECK:     LV: Found not uniform being ScalarWithPredication:  {{%.*}} = load i32, i32* {{%.*}}, align 1
+; CHECK:     LV: Found scalar instruction:   {{%.*}} = getelementptr inbounds [3 x i32], [3 x i32]* @a, i32 0, i32 {{%.*}}
+;
+@a = internal constant [3 x i32] [i32 7, i32 7, i32 0], align 1
+@b = external global i32, align 1
+
+define void @PR40816() #1 {
+; CHECK-LABEL: @PR40816(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[TMP0:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
+; CHECK-NEXT:    store i32 [[TMP0]], i32* @b, align 1
+; CHECK-NEXT:    [[CMP2:%.*]] = icmp eq i32 [[TMP0]], 2
+; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[TMP0]], 1
+; CHECK-NEXT:    br i1 [[CMP2]], label [[RETURN:%.*]], label [[FOR_BODY]]
+; CHECK:       return:
+; CHECK-NEXT:    ret void
+;
+; FORCE-LABEL: @PR40816(
+; FORCE-NEXT:  entry:
+; FORCE-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; FORCE:       vector.ph:
+; FORCE-NEXT:    br label [[VECTOR_BODY:%.*]]
+; FORCE:       vector.body:
+; FORCE-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_LOAD_CONTINUE2:%.*]] ]
+; FORCE-NEXT:    [[VEC_IND:%.*]] = phi <2 x i32> [ <i32 0, i32 1>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_LOAD_CONTINUE2]] ]
+; FORCE-NEXT:    [[TMP0:%.*]] = icmp ule <2 x i32> [[VEC_IND]], <i32 2, i32 2>
+; FORCE-NEXT:    [[TMP1:%.*]] = extractelement <2 x i1> [[TMP0]], i32 0
+; FORCE-NEXT:    br i1 [[TMP1]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]]
+; FORCE:       pred.load.if:
+; FORCE-NEXT:    [[TMP2:%.*]] = add i32 [[INDEX]], 0
+; FORCE-NEXT:    store i32 [[TMP2]], i32* @b, align 1
+; FORCE-NEXT:    br label [[PRED_LOAD_CONTINUE]]
+; FORCE:       pred.load.continue:
+; FORCE-NEXT:    [[TMP3:%.*]] = extractelement <2 x i1> [[TMP0]], i32 1
+; FORCE-NEXT:    br i1 [[TMP3]], label [[PRED_LOAD_IF1:%.*]], label [[PRED_LOAD_CONTINUE2]]
+; FORCE:       pred.load.if1:
+; FORCE-NEXT:    [[TMP4:%.*]] = add i32 [[INDEX]], 1
+; FORCE-NEXT:    store i32 [[TMP4]], i32* @b, align 1
+; FORCE-NEXT:    br label [[PRED_LOAD_CONTINUE2]]
+; FORCE:       pred.load.continue2:
+; FORCE-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 2
+; FORCE-NEXT:    [[VEC_IND_NEXT]] = add <2 x i32> [[VEC_IND]], <i32 2, i32 2>
+; FORCE-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[INDEX_NEXT]], 4
+; FORCE-NEXT:    br i1 [[TMP5]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; FORCE:       middle.block:
+; FORCE-NEXT:    br i1 true, label [[RETURN:%.*]], label [[SCALAR_PH]]
+; FORCE:       scalar.ph:
+; FORCE-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ 4, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; FORCE-NEXT:    br label [[FOR_BODY:%.*]]
+; FORCE:       for.body:
+; FORCE-NEXT:    [[TMP6:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
+; FORCE-NEXT:    store i32 [[TMP6]], i32* @b, align 1
+; FORCE-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds [3 x i32], [3 x i32]* @a, i32 0, i32 [[TMP6]]
+; FORCE-NEXT:    [[TMP7:%.*]] = load i32, i32* [[ARRAYIDX1]], align 1
+; FORCE-NEXT:    [[CMP2:%.*]] = icmp eq i32 [[TMP7]], 0
+; FORCE-NEXT:    [[INC]] = add nuw nsw i32 [[TMP6]], 1
+; FORCE-NEXT:    br i1 [[CMP2]], label [[RETURN]], label [[FOR_BODY]], !llvm.loop [[LOOP2:![0-9]+]]
+; FORCE:       return:
+; FORCE-NEXT:    ret void
+;
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %0 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
+  store i32 %0, i32* @b, align 1
+  %arrayidx1 = getelementptr inbounds [3 x i32], [3 x i32]* @a, i32 0, i32 %0
+  %1 = load i32, i32* %arrayidx1, align 1
+  %cmp2 = icmp eq i32 %1, 0
+  %inc = add nuw nsw i32 %0, 1
+  br i1 %cmp2, label %return, label %for.body
+
+return:                                           ; preds = %for.body
+  ret void
+}
+
+attributes #1 = { "target-cpu"="core2" }
+

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

 ; 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, !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, !llvm.access.group !0
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
 ; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT]], 16
-; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP1:!llvm.loop !.*]]
+; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP1:![0-9]+]]
 ; 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:    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:    [[TMP10:%.*]] = load float, float* [[ARRAYIDX]], align 4, !llvm.access.group !0
 ; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[INDVARS_IV]]
 ; CHECK-NEXT:    [[TMP11:%.*]] = load float, float* [[ARRAYIDX2]], align 4, !llvm.access.group !0
 ; CHECK-NEXT:    [[ADD:%.*]] = fadd fast float [[TMP10]], [[TMP11]]
 ; CHECK-NEXT:    store float [[ADD]], float* [[ARRAYIDX2]], align 4, !llvm.access.group !0
 ; 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]], [[LOOP4:!llvm.loop !.*]]
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
 ; 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 ]

 ; CHECK-LABEL: @vectorized1(
 ; 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:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> poison, i64 [[INDEX]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> poison, <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:    [[TMP1:%.*]] = icmp ule <8 x i64> [[INDUCTION]], <i64 19, i64 19, i64 19, i64 19, i64 19, i64 19, i64 19, i64 19>
-; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds float, float* [[B:%.*]], i64 [[TMP0]]
-; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds float, float* [[TMP2]], i32 0
-; 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> [[TMP1]], <8 x float> poison), !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> [[TMP1]], <8 x float> poison), !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> [[TMP1]]), !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]], [[LOOP7:!llvm.loop !.*]]
+; 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, !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, !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, !llvm.access.group !6
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw 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 [[LOOP7:![0-9]+]]
 ; CHECK:       middle.block:
-; CHECK-NEXT:    br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
+; 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 [ 24, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 16, [[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:    [[TMP10:%.*]] = 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:    [[TMP11:%.*]] = load float, float* [[ARRAYIDX2]], align 4, !llvm.access.group !6
+; CHECK-NEXT:    [[ADD:%.*]] = fadd fast float [[TMP10]], [[TMP11]]
 ; 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]], [[LOOP9:!llvm.loop !.*]]
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]]
 ; 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 ]

 ; 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, !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, !llvm.access.group !6
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
 ; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT]], 16
-; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP10:!llvm.loop !.*]]
+; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
 ; 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:%.*]] ]
 ; 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:    [[TMP10:%.*]] = load float, float* [[ARRAYIDX]], align 4, !llvm.access.group !6
 ; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[INDVARS_IV]]
 ; CHECK-NEXT:    [[TMP11:%.*]] = load float, float* [[ARRAYIDX2]], align 4, !llvm.access.group !6
 ; CHECK-NEXT:    [[ADD:%.*]] = fadd fast float [[TMP10]], [[TMP11]]
 ; 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]], 16
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_END]], label [[FOR_BODY]], [[LOOP11:!llvm.loop !.*]]
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP11:![0-9]+]]
 ; 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 ]

llvm/test/Transforms/LoopVectorize/first-order-recurrence-sink-replicate-region.ll

 ; REQUIRES: asserts
-; RUN: opt < %s -passes=loop-vectorize -force-vector-width=2 -force-vector-interleave=1 -force-widen-divrem-via-safe-divisor=0 -disable-output -debug-only=loop-vectorize 2>&1 | FileCheck %s
+; RUN: opt < %s -passes=loop-vectorize -force-vector-width=2 -force-vector-interleave=1 -force-widen-divrem-via-safe-divisor=0 -disable-output -debug-only=loop-vectorize -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue 2>&1 | FileCheck %s
 
 target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
 
 ; Test cases for PR50009, which require sinking a replicate-region due to a
 ; first-order recurrence.
 
 define void @sink_replicate_region_1(i32 %x, i8* %ptr, i32* noalias %dst) optsize {
 ; CHECK-LABEL: sink_replicate_region_1

llvm/test/Transforms/LoopVectorize/icmp-uniforms.ll

for.end:
   ret i32 %tmp4
 }
 
 ; Check for crash exposed by D76992.
 ; CHECK-LABEL: 'test'
 ; CHECK:      VPlan 'Initial VPlan for VF={4},UF>=1' {
 ; CHECK-NEXT: Live-in vp<[[VEC_TC:%.+]]> = vector-trip-count
 ; CHECK-EMPTY:
-; CHECK-NEXT: Live-in vp<[[BTC:%.+]]> = backedge-taken count
-; CHECK-EMPTY:
 ; CHECK-NEXT: vector.ph:
 ; CHECK-NEXT: Successor(s): vector loop
 ; CHECK-EMPTY:
 ; CHECK-NEXT: <x1> vector loop: {
 ; CHECK-NEXT: vector.body:
-; CHECK-NEXT:   EMIT vp<[[CAN_IV:%.+]]> = CANONICAL-INDUCTION
-; CHECK-NEXT:   WIDEN-INDUCTION %iv = phi 0, %iv.next, ir<1>
-; CHECK-NEXT:   vp<[[STEPS:%.+]]> = SCALAR-STEPS vp<[[CAN_IV]]>, ir<0>, ir<1>
-; CHECK-NEXT:   EMIT vp<[[COND:%.+]]> = icmp ule ir<%iv> vp<[[BTC]]>
-; CHECK-NEXT:   WIDEN ir<%cond0> = icmp ult ir<%iv>, ir<13>
-; CHECK-NEXT:   WIDEN-SELECT ir<%s> = select ir<%cond0>, ir<10>, ir<20>
-; CHECK-NEXT: Successor(s): pred.store
-; CHECK-EMPTY:
-; CHECK-NEXT:  <xVFxUF> pred.store: {
-; CHECK-NEXT:    pred.store.entry:
-; CHECK-NEXT:      BRANCH-ON-MASK vp<[[COND]]>
-; CHECK-NEXT:    Successor(s): pred.store.if, pred.store.continue
-; CHECK-EMPTY:
-; CHECK-NEXT:    pred.store.if:
-; CHECK-NEXT:      REPLICATE ir<%gep> = getelementptr ir<%ptr>, vp<[[STEPS]]>
-; CHECK-NEXT:      REPLICATE store ir<%s>, ir<%gep>
-; CHECK-NEXT:    Successor(s): pred.store.continue
-; CHECK-EMPTY:
-; CHECK-NEXT:    pred.store.continue:
-; CHECK-NEXT:    No successors
-; CHECK-NEXT:  }
-; CHECK-NEXT:  Successor(s): loop.0
-; CHECK-EMPTY:
-; CHECK-NEXT: loop.0:
-; CHECK-NEXT:   EMIT vp<[[CAN_IV_NEXT:%.+]]> = VF * UF + vp<[[CAN_IV]]>
-; CHECK-NEXT:   EMIT branch-on-count vp<[[CAN_IV_NEXT]]> vp<[[VEC_TC]]>
-; CHECK-NEXT: No successor
-; CHECK-NEXT: }
+; CHECK-NEXT:    EMIT vp<%2> = CANONICAL-INDUCTION
+; CHECK-NEXT:    WIDEN-INDUCTION %iv = phi 0, %iv.next, ir<1>
+; CHECK-NEXT:    vp<%4>    = SCALAR-STEPS vp<%2>, ir<0>, ir<1>
+; CHECK-NEXT:    WIDEN ir<%cond0> = icmp ult ir<%iv>, ir<13>
+; CHECK-NEXT:    WIDEN-SELECT ir<%s> = select ir<%cond0>, ir<10>, ir<20>
+; CHECK-NEXT:    CLONE ir<%gep> = getelementptr ir<%ptr>, vp<%4>
+; CHECK-NEXT:    WIDEN store ir<%gep>, ir<%s>
+; CHECK-NEXT:    EMIT vp<%8> = VF * UF +(nuw)  vp<%2>
+; CHECK-NEXT:    EMIT branch-on-count  vp<%8> vp<%1>
+; CHECK-NEXT:  No successors
+; CHECK-NEXT: }
 define void @test(i32* %ptr) {
 entry:
   br label %loop
 
 loop:                       ; preds = %loop, %entry
   %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
   %cond0 = icmp ult i64 %iv, 13
   %s = select i1 %cond0, i32 10, i32 20

llvm/test/Transforms/LoopVectorize/pr43166-fold-tail-by-masking.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt < %s -passes=loop-vectorize -force-vector-width=4 -S | FileCheck %s
+; RUN: opt < %s -passes=loop-vectorize -force-vector-width=4 -prefer-predicate-over-epilogue=predicate-dont-vectorize -S | FileCheck %s
+; RUN: opt < %s -loop-vectorize -force-vector-width=4 -prefer-predicate-over-epilogue=predicate-dont-vectorize -S | FileCheck %s
 
 
 ; Test cases below are reduced (and slightly modified) reproducers based on a
 ; problem seen when compiling a C program like this:
 ;
 ;    #include <stdint.h>
 ;    #include <stdio.h>
 ;

llvm/test/Transforms/LoopVectorize/pr45679-fold-tail-by-masking.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt < %s -passes=loop-vectorize -force-vector-width=4 -S | FileCheck %s
-; RUN: opt < %s -passes=loop-vectorize -force-vector-width=2 -force-vector-interleave=2 -S | FileCheck %s -check-prefix=VF2UF2
-; RUN: opt < %s -passes=loop-vectorize -force-vector-width=1 -force-vector-interleave=4 -S | FileCheck %s -check-prefix=VF1UF4
+; RUN: opt < %s -passes=loop-vectorize -force-vector-width=4 -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue -S | FileCheck %s
+; RUN: opt < %s -passes=loop-vectorize -force-vector-width=2 -force-vector-interleave=2 -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue -S | FileCheck %s -check-prefix=VF2UF2
+; RUN: opt < %s -passes=loop-vectorize -force-vector-width=1 -force-vector-interleave=4 -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue -S | FileCheck %s -check-prefix=VF1UF4
 
 target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"
 
 ; Make sure a loop is vectorized correctly with fold-tail when the constant
 ; trip-count is not a multiple of -force-vector-width and/or
 ; -force-vector-interleave, but is a multiple of the internally computed MaxVF;
 ; e.g., when all types are i32 lead to MaxVF=1.
 

llvm/test/Transforms/LoopVectorize/reduction-order.ll

-; RUN: opt -passes='loop-vectorize' -force-vector-width=4 -force-vector-interleave=1 -S < %s 2>&1 | FileCheck %s
+; RUN: opt -passes='loop-vectorize' -force-vector-width=4 -force-vector-interleave=1 -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue -S < %s 2>&1 | FileCheck %s
 
 target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
 
 ; Make sure the selects generated from reduction are always emitted
 ; in deterministic order.
 ; CHECK-LABEL: @foo(
 ; CHECK: vector.body:
 ; CHECK:      [[VEC_PHI_1:%.+]] = phi <4 x i32> [ zeroinitializer, %vector.ph ], [ [[ADD_5:%.+]], %vector.body ]

llvm/test/Transforms/LoopVectorize/tail-folding-vectorization-factor-1.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt < %s  -loop-vectorize -force-vector-interleave=4 -pass-remarks='loop-vectorize' -disable-output -S 2>&1 | FileCheck %s --check-prefix=CHECK-REMARKS
-; RUN: opt < %s  -loop-vectorize -force-vector-interleave=4 -S | FileCheck %s
+; RUN: opt < %s  -loop-vectorize -force-vector-interleave=4 -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue -pass-remarks='loop-vectorize' -disable-output -S 2>&1 | FileCheck %s --check-prefix=CHECK-REMARKS
+; RUN: opt < %s  -loop-vectorize -force-vector-interleave=4 -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue -S | FileCheck %s
 
 ; These tests are to check that fold-tail procedure produces correct scalar code when
 ; loop-vectorization is only unrolling but not vectorizing.
 
 ; CHECK-REMARKS:      remark: {{.*}} interleaved loop (interleaved count: 4)
 ; CHECK-REMARKS-NEXT: remark: {{.*}} interleaved loop (interleaved count: 4)
 ; CHECK-REMARKS-NOT:  remark: {{.*}} vectorized loop
 

llvm/test/Transforms/LoopVectorize/tripcount.ll

 for.end:                                          ; preds = %for.body
   ret i32 0
 }
 
 define i32 @const_low_trip_count() {
 ; Simple loop with constant, small trip count and no profiling info.
 ; CHECK-LABEL: @const_low_trip_count(
 ; 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:    [[TMP1:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP0]]
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i8, i8* [[TMP1]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i8* [[TMP2]] to <2 x i8>*
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <2 x i8>, <2 x i8>* [[TMP3]], align 1
+; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq <2 x i8> [[WIDE_LOAD]], zeroinitializer
+; CHECK-NEXT:    [[TMP5:%.*]] = select <2 x i1> [[TMP4]], <2 x i8> <i8 2, i8 2>, <2 x i8> <i8 1, i8 1>
+; CHECK-NEXT:    [[TMP6:%.*]] = bitcast i8* [[TMP2]] to <2 x i8>*
+; CHECK-NEXT:    store <2 x i8> [[TMP5]], <2 x i8>* [[TMP6]], align 1
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 2
+; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq i32 [[INDEX_NEXT]], 2
+; CHECK-NEXT:    br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]]
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 3, 2
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ 2, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
-; CHECK-NEXT:    [[I_08:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
+; CHECK-NEXT:    [[I_08:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
 ; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[I_08]]
-; CHECK-NEXT:    [[TMP0:%.*]] = load i8, i8* [[ARRAYIDX]], align 1
-; CHECK-NEXT:    [[CMP1:%.*]] = icmp eq i8 [[TMP0]], 0
+; CHECK-NEXT:    [[TMP8:%.*]] = load i8, i8* [[ARRAYIDX]], align 1
+; CHECK-NEXT:    [[CMP1:%.*]] = icmp eq i8 [[TMP8]], 0
 ; CHECK-NEXT:    [[DOT:%.*]] = select i1 [[CMP1]], i8 2, i8 1
 ; CHECK-NEXT:    store i8 [[DOT]], i8* [[ARRAYIDX]], align 1
 ; CHECK-NEXT:    [[INC]] = add nsw i32 [[I_08]], 1
 ; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp slt i32 [[I_08]], 2
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_END:%.*]]
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_END]], !llvm.loop [[LOOP10:![0-9]+]]
 ; CHECK:       for.end:
 ; CHECK-NEXT:    ret i32 0
 ;
 
 entry:
   br label %for.body
 
 for.body:                                         ; preds = %for.body, %entry

 ; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i8* [[TMP2]] to <4 x i8>*
 ; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i8>, <4 x i8>* [[TMP3]], align 1
 ; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq <4 x i8> [[WIDE_LOAD]], zeroinitializer
 ; CHECK-NEXT:    [[TMP5:%.*]] = select <4 x i1> [[TMP4]], <4 x i8> <i8 2, i8 2, i8 2, i8 2>, <4 x i8> <i8 1, i8 1, i8 1, i8 1>
 ; CHECK-NEXT:    [[TMP6:%.*]] = bitcast i8* [[TMP2]] to <4 x i8>*
 ; CHECK-NEXT:    store <4 x i8> [[TMP5]], <4 x i8>* [[TMP6]], align 1
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
 ; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq i32 [[INDEX_NEXT]], 1000
-; CHECK-NEXT:    br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]]
+; CHECK-NEXT:    br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP11:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 1001, 1000
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ 1000, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[I_08:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
 ; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[I_08]]
 ; CHECK-NEXT:    [[TMP8:%.*]] = load i8, i8* [[ARRAYIDX]], align 1
 ; CHECK-NEXT:    [[CMP1:%.*]] = icmp eq i8 [[TMP8]], 0
 ; CHECK-NEXT:    [[DOT:%.*]] = select i1 [[CMP1]], i8 2, i8 1
 ; CHECK-NEXT:    store i8 [[DOT]], i8* [[ARRAYIDX]], align 1
 ; CHECK-NEXT:    [[INC]] = add nsw i32 [[I_08]], 1
 ; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp slt i32 [[I_08]], 1000
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_END]], !llvm.loop [[LOOP10:![0-9]+]]
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_END]], !llvm.loop [[LOOP12:![0-9]+]]
 ; CHECK:       for.end:
 ; CHECK-NEXT:    ret i32 0
 ;
 
 entry:
   br label %for.body
 
 for.body:                                         ; preds = %for.body, %entry

 for.end:                                          ; preds = %for.body
   ret i32 0
 }
 
 define i32 @const_small_trip_count_step() {
 ; Simple loop with static, small trip count and no profiling info.
 ; CHECK-LABEL: @const_small_trip_count_step(
 ; 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:    [[OFFSET_IDX:%.*]] = mul i32 [[INDEX]], 5
+; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[OFFSET_IDX]], 0
+; CHECK-NEXT:    [[TMP1:%.*]] = add i32 [[OFFSET_IDX]], 5
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP0]]
+; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP1]]
+; CHECK-NEXT:    [[TMP4:%.*]] = load i8, i8* [[TMP2]], align 1
+; CHECK-NEXT:    [[TMP5:%.*]] = load i8, i8* [[TMP3]], align 1
+; CHECK-NEXT:    [[TMP6:%.*]] = insertelement <2 x i8> poison, i8 [[TMP4]], i32 0
+; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <2 x i8> [[TMP6]], i8 [[TMP5]], i32 1
+; CHECK-NEXT:    [[TMP8:%.*]] = icmp eq <2 x i8> [[TMP7]], zeroinitializer
+; CHECK-NEXT:    [[TMP9:%.*]] = select <2 x i1> [[TMP8]], <2 x i8> <i8 2, i8 2>, <2 x i8> <i8 1, i8 1>
+; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <2 x i8> [[TMP9]], i32 0
+; CHECK-NEXT:    store i8 [[TMP10]], i8* [[TMP2]], align 1
+; CHECK-NEXT:    [[TMP11:%.*]] = extractelement <2 x i8> [[TMP9]], i32 1
+; CHECK-NEXT:    store i8 [[TMP11]], i8* [[TMP3]], align 1
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 2
+; CHECK-NEXT:    [[TMP12:%.*]] = icmp eq i32 [[INDEX_NEXT]], 2
+; CHECK-NEXT:    br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP13:![0-9]+]]
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 3, 2
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ 10, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
-; CHECK-NEXT:    [[I_08:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
+; CHECK-NEXT:    [[I_08:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
 ; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[I_08]]
-; CHECK-NEXT:    [[TMP0:%.*]] = load i8, i8* [[ARRAYIDX]], align 1
-; CHECK-NEXT:    [[CMP1:%.*]] = icmp eq i8 [[TMP0]], 0
+; CHECK-NEXT:    [[TMP13:%.*]] = load i8, i8* [[ARRAYIDX]], align 1
+; CHECK-NEXT:    [[CMP1:%.*]] = icmp eq i8 [[TMP13]], 0
 ; CHECK-NEXT:    [[DOT:%.*]] = select i1 [[CMP1]], i8 2, i8 1
 ; CHECK-NEXT:    store i8 [[DOT]], i8* [[ARRAYIDX]], align 1
 ; CHECK-NEXT:    [[INC]] = add nsw i32 [[I_08]], 5
 ; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp slt i32 [[I_08]], 10
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_END:%.*]]
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_END]], !llvm.loop [[LOOP14:![0-9]+]]
 ; CHECK:       for.end:
 ; CHECK-NEXT:    ret i32 0
 ;
 
 entry:
   br label %for.body
 
 for.body:                                         ; preds = %for.body, %entry

 ; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i8* [[TMP2]] to <4 x i8>*
 ; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i8>, <4 x i8>* [[TMP3]], align 1
 ; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq <4 x i8> [[WIDE_LOAD]], zeroinitializer
 ; CHECK-NEXT:    [[TMP5:%.*]] = select <4 x i1> [[TMP4]], <4 x i8> <i8 2, i8 2, i8 2, i8 2>, <4 x i8> <i8 1, i8 1, i8 1, i8 1>
 ; CHECK-NEXT:    [[TMP6:%.*]] = bitcast i8* [[TMP2]] to <4 x i8>*
 ; CHECK-NEXT:    store <4 x i8> [[TMP5]], <4 x i8>* [[TMP6]], align 1
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
 ; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq i32 [[INDEX_NEXT]], 1000
-; CHECK-NEXT:    br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP11:![0-9]+]]
+; CHECK-NEXT:    br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP15:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 1001, 1000
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ 1000, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[I_08:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
 ; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[I_08]]
 ; CHECK-NEXT:    [[TMP8:%.*]] = load i8, i8* [[ARRAYIDX]], align 1
 ; CHECK-NEXT:    [[CMP1:%.*]] = icmp eq i8 [[TMP8]], 0
 ; CHECK-NEXT:    [[DOT:%.*]] = select i1 [[CMP1]], i8 2, i8 1
 ; CHECK-NEXT:    store i8 [[DOT]], i8* [[ARRAYIDX]], align 1
 ; CHECK-NEXT:    [[INC]] = add nsw i32 [[I_08]], 1
 ; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp slt i32 [[I_08]], 1000
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_END]], !prof [[PROF0]], !llvm.loop [[LOOP12:![0-9]+]]
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_END]], !prof [[PROF0]], !llvm.loop [[LOOP16:![0-9]+]]
 ; CHECK:       for.end:
 ; CHECK-NEXT:    ret i32 0
 ;
 
 entry:
   br label %for.body
 
 for.body:                                         ; preds = %for.body, %entry

llvm/test/Transforms/LoopVectorize/vplan-sink-scalars-and-merge.ll

 }
 
 ; Make sure we do not sink uniform instructions.
 define void @uniform_gep(i64 %k, i16* noalias %A, i16* noalias %B) {
 ; CHECK-LABEL: LV: Checking a loop in 'uniform_gep'
 ; CHECK:      VPlan 'Initial VPlan for VF={2},UF>=1' {
 ; CHECK-NEXT: Live-in vp<[[VEC_TC:%.+]]> = vector-trip-count
 ; CHECK-EMPTY:
-; CHECK-NEXT: Live-in vp<[[BTC:%.+]]> = backedge-taken count
-; CHECK-EMPTY:
 ; CHECK-NEXT: vector.ph:
 ; CHECK-NEXT: Successor(s): vector loop
 ; CHECK-EMPTY:
 ; CHECK-NEXT: <x1> vector loop: {
 ; CHECK-NEXT: vector.body:
 ; CHECK-NEXT:   EMIT vp<[[CAN_IV:%.+]]> = CANONICAL-INDUCTION
 ; CHECK-NEXT:   WIDEN-INDUCTION %iv = phi 21, %iv.next, ir<1>
 ; CHECK-NEXT:   vp<[[STEPS:%.+]]> = SCALAR-STEPS vp<[[CAN_IV]]>, ir<21>, ir<1>
-; CHECK-NEXT:   EMIT vp<[[WIDE_CAN_IV:%.+]]> = WIDEN-CANONICAL-INDUCTION vp<[[CAN_IV]]>
-; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule vp<[[WIDE_CAN_IV]]> vp<[[BTC]]>
 ; CHECK-NEXT:   CLONE ir<%gep.A.uniform> = getelementptr ir<%A>, ir<0>
 ; CHECK-NEXT:   CLONE ir<%lv> = load ir<%gep.A.uniform>
 ; CHECK-NEXT:   WIDEN ir<%cmp> = icmp ult ir<%iv>, ir<%k>
 ; CHECK-NEXT: Successor(s): loop.then
 ; CHECK-EMPTY:
 ; CHECK-NEXT: loop.then:
 ; CHECK-NEXT:   EMIT vp<[[NOT2:%.+]]> = not ir<%cmp>
-; CHECK-NEXT:   EMIT vp<[[MASK2:%.+]]> = select vp<[[MASK]]> vp<[[NOT2]]> ir<false>
 ; CHECK-NEXT: Successor(s): pred.store
 ; CHECK-EMPTY:
 ; CHECK-NEXT: <xVFxUF> pred.store: {
 ; CHECK-NEXT:   pred.store.entry:
-; CHECK-NEXT:     BRANCH-ON-MASK vp<[[MASK2]]>
+; CHECK-NEXT:     BRANCH-ON-MASK vp<[[NOT2]]>
 ; CHECK-NEXT:   Successor(s): pred.store.if, pred.store.continue
 ; CHECK-EMPTY:
 ; CHECK-NEXT:   pred.store.if:
 ; CHECK-NEXT:     REPLICATE ir<%gep.B> = getelementptr ir<%B>, vp<[[STEPS]]>
 ; CHECK-NEXT:     REPLICATE store ir<%lv>, ir<%gep.B>
 ; CHECK-NEXT:   Successor(s): pred.store.continue
 ; CHECK-EMPTY:
 ; CHECK-NEXT:   pred.store.continue:
 ; CHECK-NEXT:   No successors
 ; CHECK-NEXT: }
 ; CHECK-NEXT: Successor(s): loop.then.0
 ; CHECK-EMPTY:
 ; CHECK-NEXT: loop.then.0:
 ; CHECK-NEXT: Successor(s): loop.latch
 ; CHECK-EMPTY:
 ; CHECK-NEXT: loop.latch:
-; CHECK-NEXT:   EMIT vp<[[CAN_IV_NEXT:%.+]]> = VF * UF + vp<[[CAN_IV]]>
+; CHECK-NEXT:   EMIT vp<[[CAN_IV_NEXT:%.+]]> = VF * UF +(nuw) vp<[[CAN_IV]]>
 ; CHECK-NEXT:   EMIT branch-on-count vp<[[CAN_IV_NEXT]]> vp<[[VEC_TC]]>
 ; CHECK-NEXT: No successors
 ; CHECK-NEXT: }
 ;
 entry:
   br label %loop
 
 loop: