[LV] Scalar Epilogue Lowering. NFC.

[SjoerdMeijer]

Summary

This refactors boolean 'OptForSize' that was passed around in a lot of places
into isScalarEpilogueAllowed, which was already part of the CostModel. This
boolean controls folding of the tail loop, the scalar epilogue, into the main
loop but code-size reasons may not be the only reason to do this. Thus, this is
a first step to generalise this, and hence OptForSize has been renamed to
isScalarEpilogueAllowed.

[Meinersbur]

Generally, the patch looks fine. I'd would prefer if someone who has contributed to VPlan to accept the patch.

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

848 ↗

(On Diff #210538)

[style] Use PascalCase for variable/parameter names.

4677 ↗

(On Diff #210538)

Renaming CantVersionLoopWithOptForSize breaks API: Tools parsing the YAML output might match the string. I wouldn't rename these identifiers without a reason.

4795 ↗

(On Diff #210538)

Using the getter method for the object's own field looks strange. Did you consider directly using IsScalarEpilogueAllowed?

[SjoerdMeijer]

Feedback addressed. Thanks for taking a look!

[hsaito]

Looks to be a good change. Can we add a little more improvement to this patch --- adding more crispness in ORE message?

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

4683 ↗

(On Diff #210790)

I understand that the existing code didn't properly reflect having -Os/-Oz but losing this, where applicable, isn't great. This being a debug message, I won't insist, since "performing code size checks" debug message is already printed.

4752 ↗

(On Diff #210790)

Ideally, this is where we'd like to be crisp about whether the code was actually compiled under Os/Oz or vectorizer itself is forcing no scalar epilogue. If the flag is used, programmer has an option of using pragma or getting rid of the flag. If vectorizer is forcing, the only choice is using pragma.

In order for us to be able to do that, IsScalarEpilogueAllowed, when it is false, should come with reasoning behind it. May want to consider changing it to have enum value instead, e.g., ScalarEpilogueAllowed, ScalarEpilogueNotAllowedOptSize, ScalarEpilogueNotAllowedLowTripLoop.

[SjoerdMeijer]

Thanks for the suggestion: I have generalized isScalarEpilogueAllowed by introducing an enum to model different reasons why it might be allowed or not.

I have reverted most/all changes I made to the debug messages. I will look at that again when I will make actual functional changes in this area, which is as soon as this groundwork lands.

[hsaito]

Just one comment from me.

@Meinersbur, you think your comments are addressed enough?

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

1290 ↗

(On Diff #211088)

IsSomething sounds like a boolean value. Suggest something like ScalarEpilogueStatus, ScalarEpilogueSetting, etc.

[Meinersbur]

In D64916#1599520, @hsaito wrote:

Just one comment from me.

@Meinersbur, you think your comments are addressed enough?

Yes.

[SjoerdMeijer]

Many thanks for reviewing, very much appreciated!

Comments addressed: renamed member IsScalarEpilogueAllowed to ScalarEpilogueStatus

[hsaito]

LGTM

lib/Transforms/Vectorize/LoopVectorizationPlanner.h

public:
   LoopVectorizationPlanner(Loop *L, LoopInfo *LI, const TargetLibraryInfo *TLI,
                            const TargetTransformInfo *TTI,
                            LoopVectorizationLegality *Legal,
                            LoopVectorizationCostModel &CM)
       : OrigLoop(L), LI(LI), TLI(TLI), TTI(TTI), Legal(Legal), CM(CM) {}
 
   /// Plan how to best vectorize, return the best VF and its cost, or None if
   /// vectorization and interleaving should be avoided up front.
-  Optional<VectorizationFactor> plan(bool OptForSize, unsigned UserVF);
+  Optional<VectorizationFactor> plan(unsigned UserVF);
 
   /// Use the VPlan-native path to plan how to best vectorize, return the best
   /// VF and its cost.
-  VectorizationFactor planInVPlanNativePath(bool OptForSize, unsigned UserVF);
+  VectorizationFactor planInVPlanNativePath(unsigned UserVF);
 
   /// Finalize the best decision and dispose of all other VPlans.
   void setBestPlan(unsigned VF, unsigned UF);
 
   /// Generate the IR code for the body of the vectorized loop according to the
   /// best selected VPlan.
   void executePlan(InnerLoopVectorizer &LB, DominatorTree *DT);
 

lib/Transforms/Vectorize/LoopVectorize.cpp

void InnerLoopVectorizer::addMetadata(ArrayRef<Value *> To,
   for (Value *V : To) {
     if (Instruction *I = dyn_cast<Instruction>(V))
       addMetadata(I, From);
   }
 }
 
 namespace llvm {
 
+// Loop vectorization cost-model hints how the scalar epilogue loop should be
+// lowered.
+enum ScalarEpilogueLowering {
+  CM_ScalarEpilogueAllowed,
+  CM_ScalarEpilogueNotAllowedOptSize,
+  CM_ScalarEpilogueNotAllowedLowTripLoop
+};
+
 /// LoopVectorizationCostModel - estimates the expected speedups due to
 /// vectorization.
 /// In many cases vectorization is not profitable. This can happen because of
 /// a number of reasons. In this class we mainly attempt to predict the
 /// expected speedup/slowdowns due to the supported instruction set. We use the
 /// TargetTransformInfo to query the different backends for the cost of
 /// different operations.
 class LoopVectorizationCostModel {
 public:
-  LoopVectorizationCostModel(Loop *L, PredicatedScalarEvolution &PSE,
+  LoopVectorizationCostModel(ScalarEpilogueLowering SEL, Loop *L,
+                             PredicatedScalarEvolution &PSE,
                              LoopInfo *LI, LoopVectorizationLegality *Legal,
                              const TargetTransformInfo &TTI,
                              const TargetLibraryInfo *TLI, DemandedBits *DB,
                              AssumptionCache *AC,
                              OptimizationRemarkEmitter *ORE, const Function *F,
                              const LoopVectorizeHints *Hints,
                              InterleavedAccessInfo &IAI)
-      : TheLoop(L), PSE(PSE), LI(LI), Legal(Legal), TTI(TTI), TLI(TLI), DB(DB),
-    AC(AC), ORE(ORE), TheFunction(F), Hints(Hints), InterleaveInfo(IAI) {}
+      : ScalarEpilogueStatus(SEL), TheLoop(L), PSE(PSE),
+    LI(LI), Legal(Legal), TTI(TTI), TLI(TLI), DB(DB), AC(AC), ORE(ORE),
+    TheFunction(F), Hints(Hints), InterleaveInfo(IAI) {}
 
   /// \return An upper bound for the vectorization factor, or None if
   /// vectorization and interleaving should be avoided up front.
-  Optional<unsigned> computeMaxVF(bool OptForSize);
+  Optional<unsigned> computeMaxVF();
 
   /// \return The most profitable vectorization factor and the cost of that VF.
   /// This method checks every power of two up to MaxVF. If UserVF is not ZERO
   /// then this vectorization factor will be selected if vectorization is
   /// possible.
   VectorizationFactor selectVectorizationFactor(unsigned MaxVF);
 
   /// Setup cost-based decisions for user vectorization factor.
   void selectUserVectorizationFactor(unsigned UserVF) {
     collectUniformsAndScalars(UserVF);
     collectInstsToScalarize(UserVF);
   }
 
   /// \return The size (in bits) of the smallest and widest types in the code
   /// that needs to be vectorized. We ignore values that remain scalar such as
   /// 64 bit loop indices.
   std::pair<unsigned, unsigned> getSmallestAndWidestTypes();
 
   /// \return The desired interleave count.
   /// If interleave count has been specified by metadata it will be returned.
   /// Otherwise, the interleave count is computed and returned. VF and LoopCost
   /// are the selected vectorization factor and the cost of the selected VF.
-  unsigned selectInterleaveCount(bool OptForSize, unsigned VF,
-                                 unsigned LoopCost);
+  unsigned selectInterleaveCount(unsigned VF, unsigned LoopCost);
 
   /// Memory access instruction may be vectorized in more than one way.
   /// Form of instruction after vectorization depends on cost.
   /// This function takes cost-based decisions for Load/Store instructions
   /// and collects them in a map. This decisions map is used for building
   /// the lists of loop-uniform and loop-scalar instructions.
   /// The calculated cost is saved with widening decision in order to
   /// avoid redundant calculations.
public:
   getInterleavedAccessGroup(Instruction *Instr) {
     return InterleaveInfo.getInterleaveGroup(Instr);
   }
 
   /// Returns true if an interleaved group requires a scalar iteration
   /// to handle accesses with gaps, and there is nothing preventing us from
   /// creating a scalar epilogue.
   bool requiresScalarEpilogue() const {
-    return IsScalarEpilogueAllowed && InterleaveInfo.requiresScalarEpilogue();
+    return isScalarEpilogueAllowed() && InterleaveInfo.requiresScalarEpilogue();
   }
 
-  /// Returns true if a scalar epilogue is not allowed due to optsize.
-  bool isScalarEpilogueAllowed() const { return IsScalarEpilogueAllowed; }
+  /// Returns true if a scalar epilogue is not allowed due to optsize or a
+  /// loop hint annotation.
+  bool isScalarEpilogueAllowed() const {
+    return ScalarEpilogueStatus == CM_ScalarEpilogueAllowed;
+  }
 
   /// Returns true if all loop blocks should be masked to fold tail loop.
   bool foldTailByMasking() const { return FoldTailByMasking; }
 
   bool blockNeedsPredication(BasicBlock *BB) {
     return foldTailByMasking() || Legal->blockNeedsPredication(BB);
   }
 
public:
   /// i.e. either vector version isn't available, or is too expensive.
   unsigned getVectorCallCost(CallInst *CI, unsigned VF, bool &NeedToScalarize);
 
 private:
   unsigned NumPredStores = 0;
 
   /// \return An upper bound for the vectorization factor, larger than zero.
   /// One is returned if vectorization should best be avoided due to cost.
-  unsigned computeFeasibleMaxVF(bool OptForSize, unsigned ConstTripCount);
+  unsigned computeFeasibleMaxVF(unsigned ConstTripCount);
 
   /// The vectorization cost is a combination of the cost itself and a boolean
   /// indicating whether any of the contributing operations will actually
   /// operate on
   /// vector values after type legalization in the backend. If this latter value
   /// is
   /// false, then all operations will be scalarized (i.e. no vectorization has
   /// actually taken place).
private:
   /// pairs.
   using ScalarCostsTy = DenseMap<Instruction *, unsigned>;
 
   /// A set containing all BasicBlocks that are known to present after
   /// vectorization as a predicated block.
   SmallPtrSet<BasicBlock *, 4> PredicatedBBsAfterVectorization;
 
   /// Records whether it is allowed to have the original scalar loop execute at
-  /// least once. This may be needed as a fallback loop in case runtime 
+  /// least once. This may be needed as a fallback loop in case runtime
   /// aliasing/dependence checks fail, or to handle the tail/remainder
   /// iterations when the trip count is unknown or doesn't divide by the VF,
   /// or as a peel-loop to handle gaps in interleave-groups.
   /// Under optsize and when the trip count is very small we don't allow any
   /// iterations to execute in the scalar loop.
-  bool IsScalarEpilogueAllowed = true;
+  ScalarEpilogueLowering ScalarEpilogueStatus = CM_ScalarEpilogueAllowed;
 
   /// All blocks of loop are to be masked to fold tail of scalar iterations.
   bool FoldTailByMasking = false;
 
   /// A map holding scalar costs for different vectorization factors. The
   /// presence of a cost for an instruction in the mapping indicates that the
   /// instruction will be scalarized when vectorizing with the associated
   /// vectorization factor. The entries are VF-ScalarCostTy pairs.
bool LoopVectorizationCostModel::interleavedAccessCanBeWidened(Instruction *I,
   auto &DL = I->getModule()->getDataLayout();
   auto *ScalarTy = getMemInstValueType(I);
   if (hasIrregularType(ScalarTy, DL, VF))
     return false;
 
   // Check if masking is required.
   // A Group may need masking for one of two reasons: it resides in a block that
   // needs predication, or it was decided to use masking to deal with gaps.
-  bool PredicatedAccessRequiresMasking = 
+  bool PredicatedAccessRequiresMasking =
       Legal->blockNeedsPredication(I->getParent()) && Legal->isMaskRequired(I);
-  bool AccessWithGapsRequiresMasking = 
-      Group->requiresScalarEpilogue() && !IsScalarEpilogueAllowed;
+  bool AccessWithGapsRequiresMasking =
+      Group->requiresScalarEpilogue() && !isScalarEpilogueAllowed();
   if (!PredicatedAccessRequiresMasking && !AccessWithGapsRequiresMasking)
     return true;
 
   // If masked interleaving is required, we expect that the user/target had
   // enabled it, because otherwise it either wouldn't have been created or
   // it should have been invalidated by the CostModel.
   assert(useMaskedInterleavedAccesses(TTI) &&
          "Masked interleave-groups for predicated accesses are not enabled.");
for (auto &Induction : *Legal->getInductionVars()) {
     LLVM_DEBUG(dbgs() << "LV: Found uniform instruction: " << *Ind << "\n");
     LLVM_DEBUG(dbgs() << "LV: Found uniform instruction: " << *IndUpdate
                       << "\n");
   }
 
   Uniforms[VF].insert(Worklist.begin(), Worklist.end());
 }
 
-Optional<unsigned> LoopVectorizationCostModel::computeMaxVF(bool OptForSize) {
+Optional<unsigned> LoopVectorizationCostModel::computeMaxVF() {
   if (Legal->getRuntimePointerChecking()->Need && TTI.hasBranchDivergence()) {
     // TODO: It may by useful to do since it's still likely to be dynamically
     // uniform if the target can skip.
     LLVM_DEBUG(
         dbgs() << "LV: Not inserting runtime ptr check for divergent target");
 
     ORE->emit(
       createMissedAnalysis("CantVersionLoopWithDivergentTarget")
       << "runtime pointer checks needed. Not enabled for divergent target");
 
     return None;
   }
 
   unsigned TC = PSE.getSE()->getSmallConstantTripCount(TheLoop);
-  if (!OptForSize) // Remaining checks deal with scalar loop when OptForSize.
-    return computeFeasibleMaxVF(OptForSize, TC);
+  if (isScalarEpilogueAllowed())
+    return computeFeasibleMaxVF(TC);
+
+  LLVM_DEBUG(dbgs() << "LV: Not allowing scalar epilogue.\n" <<
+                       "LV: Performing code size checks.\n");
 
   if (Legal->getRuntimePointerChecking()->Need) {
     ORE->emit(createMissedAnalysis("CantVersionLoopWithOptForSize")
               << "runtime pointer checks needed. Enable vectorization of this "
                  "loop with '#pragma clang loop vectorize(enable)' when "
                  "compiling with -Os/-Oz");
     LLVM_DEBUG(
         dbgs()
ORE->emit(createMissedAnalysis("SingleIterationLoop")
               << "loop trip count is one, irrelevant for vectorization");
     LLVM_DEBUG(dbgs() << "LV: Aborting, single iteration (non) loop.\n");
     return None;
   }
 
   // Record that scalar epilogue is not allowed.
   LLVM_DEBUG(dbgs() << "LV: Not allowing scalar epilogue due to -Os/-Oz.\n");
 
-  IsScalarEpilogueAllowed = !OptForSize;
-
   // We don't create an epilogue when optimizing for size.
   // Invalidate interleave groups that require an epilogue if we can't mask
   // the interleave-group.
-  if (!useMaskedInterleavedAccesses(TTI)) 
+  if (!useMaskedInterleavedAccesses(TTI))
     InterleaveInfo.invalidateGroupsRequiringScalarEpilogue();
 
-  unsigned MaxVF = computeFeasibleMaxVF(OptForSize, TC);
+  unsigned MaxVF = computeFeasibleMaxVF(TC);
 
   if (TC > 0 && TC % MaxVF == 0) {
     LLVM_DEBUG(dbgs() << "LV: No tail will remain for any chosen VF.\n");
     return MaxVF;
   }
 
   // If we don't know the precise trip count, or if the trip count that we
   // found modulo the vectorization factor is not zero, try to fold the tail
Optional<unsigned> LoopVectorizationCostModel::computeMaxVF() {
   ORE->emit(createMissedAnalysis("NoTailLoopWithOptForSize")
             << "cannot optimize for size and vectorize at the same time. "
                "Enable vectorization of this loop with '#pragma clang loop "
                "vectorize(enable)' when compiling with -Os/-Oz");
   return None;
 }
 
 unsigned
-LoopVectorizationCostModel::computeFeasibleMaxVF(bool OptForSize,
-                                                 unsigned ConstTripCount) {
+LoopVectorizationCostModel::computeFeasibleMaxVF(unsigned ConstTripCount) {
   MinBWs = computeMinimumValueSizes(TheLoop->getBlocks(), *DB, &TTI);
   unsigned SmallestType, WidestType;
   std::tie(SmallestType, WidestType) = getSmallestAndWidestTypes();
   unsigned WidestRegister = TTI.getRegisterBitWidth(true);
 
   // Get the maximum safe dependence distance in bits computed by LAA.
   // It is computed by MaxVF * sizeOf(type) * 8, where type is taken from
   // the memory accesses that is most restrictive (involved in the smallest
if (MaxVectorSize == 0) {
     // choosing a higher viable VF as done in the loop below.
     LLVM_DEBUG(dbgs() << "LV: Clamping the MaxVF to the constant trip count: "
                       << ConstTripCount << "\n");
     MaxVectorSize = ConstTripCount;
     return MaxVectorSize;
   }
 
   unsigned MaxVF = MaxVectorSize;
-  if (TTI.shouldMaximizeVectorBandwidth(OptForSize) ||
-      (MaximizeBandwidth && !OptForSize)) {
+  if (TTI.shouldMaximizeVectorBandwidth(!isScalarEpilogueAllowed()) ||
+      (MaximizeBandwidth && isScalarEpilogueAllowed())) {
     // Collect all viable vectorization factors larger than the default MaxVF
     // (i.e. MaxVectorSize).
     SmallVector<unsigned, 8> VFs;
     unsigned NewMaxVectorSize = WidestRegister / SmallestType;
     for (unsigned VS = MaxVectorSize * 2; VS <= NewMaxVectorSize; VS *= 2)
       VFs.push_back(VS);
 
     // For each VF calculate its register usage.
for (Instruction &I : BB->instructionsWithoutDebug()) {
       MaxWidth = std::max(MaxWidth,
                           (unsigned)DL.getTypeSizeInBits(T->getScalarType()));
     }
   }
 
   return {MinWidth, MaxWidth};
 }
 
-unsigned LoopVectorizationCostModel::selectInterleaveCount(bool OptForSize,
-                                                           unsigned VF,
+unsigned LoopVectorizationCostModel::selectInterleaveCount(unsigned VF,
                                                            unsigned LoopCost) {
   // -- The interleave heuristics --
   // We interleave the loop in order to expose ILP and reduce the loop overhead.
   // There are many micro-architectural considerations that we can't predict
   // at this level. For example, frontend pressure (on decode or fetch) due to
   // code size, or the number and capabilities of the execution ports.
   //
   // We use the following heuristics to select the interleave count:
   // 1. If the code has reductions, then we interleave to break the cross
   // iteration dependency.
   // 2. If the loop is really small, then we interleave to reduce the loop
   // overhead.
   // 3. We don't interleave if we think that we will spill registers to memory
   // due to the increased register pressure.
 
-  // When we optimize for size, we don't interleave.
-  if (OptForSize)
+  if (!isScalarEpilogueAllowed())
     return 1;
 
   // We used the distance for the interleave count.
   if (Legal->getMaxSafeDepDistBytes() != -1U)
     return 1;
 
   // Do not interleave loops with a relatively small trip count.
   unsigned TC = PSE.getSE()->getSmallConstantTripCount(TheLoop);
unsigned LoopVectorizationCostModel::getInterleaveGroupCost(Instruction *I,
   SmallVector<unsigned, 4> Indices;
   if (isa<LoadInst>(I)) {
     for (unsigned i = 0; i < InterleaveFactor; i++)
       if (Group->getMember(i))
         Indices.push_back(i);
   }
 
   // Calculate the cost of the whole interleaved group.
-  bool UseMaskForGaps = 
-      Group->requiresScalarEpilogue() && !IsScalarEpilogueAllowed;
+  bool UseMaskForGaps =
+      Group->requiresScalarEpilogue() && !isScalarEpilogueAllowed();
   unsigned Cost = TTI.getInterleavedMemoryOpCost(
       I->getOpcode(), WideVecTy, Group->getFactor(), Indices,
       Group->getAlignment(), AS, Legal->isMaskRequired(I), UseMaskForGaps);
 
   if (Group->isReverse()) {
     // TODO: Add support for reversed masked interleaved access.
     assert(!Legal->isMaskRequired(I) &&
            "Reverse masked interleaved access not supported.");

 static unsigned determineVPlanVF(const unsigned WidestVectorRegBits,
                                  LoopVectorizationCostModel &CM) {
   unsigned WidestType;
   std::tie(std::ignore, WidestType) = CM.getSmallestAndWidestTypes();
   return WidestVectorRegBits / WidestType;
 }
 
 VectorizationFactor
-LoopVectorizationPlanner::planInVPlanNativePath(bool OptForSize,
-                                                unsigned UserVF) {
+LoopVectorizationPlanner::planInVPlanNativePath(unsigned UserVF) {
   unsigned VF = UserVF;
   // Outer loop handling: They may require CFG and instruction level
   // transformations before even evaluating whether vectorization is profitable.
   // Since we cannot modify the incoming IR, we need to build VPlan upfront in
   // the vectorization pipeline.
   if (!OrigLoop->empty()) {
     // If the user doesn't provide a vectorization factor, determine a
     // reasonable one.
LoopVectorizationPlanner::planInVPlanNativePath(unsigned UserVF) {
   }
 
   LLVM_DEBUG(
       dbgs() << "LV: Not vectorizing. Inner loops aren't supported in the "
                 "VPlan-native path.\n");
   return VectorizationFactor::Disabled();
 }
 
-Optional<VectorizationFactor> LoopVectorizationPlanner::plan(bool OptForSize,
-                                                             unsigned UserVF) {
+Optional<VectorizationFactor> LoopVectorizationPlanner::plan(unsigned UserVF) {
   assert(OrigLoop->empty() && "Inner loop expected.");
-  Optional<unsigned> MaybeMaxVF = CM.computeMaxVF(OptForSize);
+  Optional<unsigned> MaybeMaxVF = CM.computeMaxVF();
   if (!MaybeMaxVF) // Cases that should not to be vectorized nor interleaved.
     return None;
 
   // Invalidate interleave groups if all blocks of loop will be predicated.
   if (CM.blockNeedsPredication(OrigLoop->getHeader()) &&
       !useMaskedInterleavedAccesses(*TTI)) {
     LLVM_DEBUG(
         dbgs()
static bool processLoopInVPlanNativePath(
     LoopVectorizationLegality *LVL, TargetTransformInfo *TTI,
     TargetLibraryInfo *TLI, DemandedBits *DB, AssumptionCache *AC,
     OptimizationRemarkEmitter *ORE, BlockFrequencyInfo *BFI,
     ProfileSummaryInfo *PSI, LoopVectorizeHints &Hints) {
 
   assert(EnableVPlanNativePath && "VPlan-native path is disabled.");
   Function *F = L->getHeader()->getParent();
   InterleavedAccessInfo IAI(PSE, L, DT, LI, LVL->getLAI());
-  LoopVectorizationCostModel CM(L, PSE, LI, LVL, *TTI, TLI, DB, AC, ORE, F,
-                                &Hints, IAI);
+
+  ScalarEpilogueLowering SEL = CM_ScalarEpilogueAllowed;
+  if (Hints.getForce() != LoopVectorizeHints::FK_Enabled &&
+      (F->hasOptSize() ||
+       llvm::shouldOptimizeForSize(L->getHeader(), PSI, BFI)))
+    SEL = CM_ScalarEpilogueNotAllowedOptSize;
+
+  LoopVectorizationCostModel CM(SEL, L, PSE, LI, LVL, *TTI, TLI,
+                                DB, AC, ORE, F, &Hints, IAI);
   // Use the planner for outer loop vectorization.
   // TODO: CM is not used at this point inside the planner. Turn CM into an
   // optional argument if we don't need it in the future.
   LoopVectorizationPlanner LVP(L, LI, TLI, TTI, LVL, CM);
 
   // Get user vectorization factor.
   const unsigned UserVF = Hints.getWidth();
 
-  // Check the function attributes and profiles to find out if this function
-  // should be optimized for size.
-  bool OptForSize =
-      Hints.getForce() != LoopVectorizeHints::FK_Enabled &&
-      (F->hasOptSize() ||
-       llvm::shouldOptimizeForSize(L->getHeader(), PSI, BFI));
-
   // Plan how to best vectorize, return the best VF and its cost.
-  const VectorizationFactor VF = LVP.planInVPlanNativePath(OptForSize, UserVF);
+  const VectorizationFactor VF = LVP.planInVPlanNativePath(UserVF);
 
   // If we are stress testing VPlan builds, do not attempt to generate vector
   // code. Masked vector code generation support will follow soon.
   // Also, do not attempt to vectorize if no vector code will be produced.
   if (VPlanBuildStressTest || EnableVPlanPredication ||
       VectorizationFactor::Disabled() == VF)
     return false;
 
#endif /* NDEBUG */
   if (!LVL.canVectorize(EnableVPlanNativePath)) {
     LLVM_DEBUG(dbgs() << "LV: Not vectorizing: Cannot prove legality.\n");
     Hints.emitRemarkWithHints();
     return false;
   }
 
   // Check the function attributes and profiles to find out if this function
   // should be optimized for size.
-  bool OptForSize =
-      Hints.getForce() != LoopVectorizeHints::FK_Enabled &&
+  ScalarEpilogueLowering SEL = CM_ScalarEpilogueAllowed;
+  if (Hints.getForce() != LoopVectorizeHints::FK_Enabled &&
       (F->hasOptSize() ||
-       llvm::shouldOptimizeForSize(L->getHeader(), PSI, BFI));
+       llvm::shouldOptimizeForSize(L->getHeader(), PSI, BFI)))
+    SEL = CM_ScalarEpilogueNotAllowedOptSize;
 
   // Entrance to the VPlan-native vectorization path. Outer loops are processed
   // here. They may require CFG and instruction level transformations before
   // even evaluating whether vectorization is profitable. Since we cannot modify
   // the incoming IR, we need to build VPlan upfront in the vectorization
   // pipeline.
   if (!L->empty())
     return processLoopInVPlanNativePath(L, PSE, LI, DT, &LVL, TTI, TLI, DB, AC,
LLVM_DEBUG(dbgs() << "LV: Found a loop with a very small trip count. "
                       << "iteration overheads are incurred.");
     if (Hints.getForce() == LoopVectorizeHints::FK_Enabled)
       LLVM_DEBUG(dbgs() << " But vectorizing was explicitly forced.\n");
     else {
       LLVM_DEBUG(dbgs() << "\n");
       // Loops with a very small trip count are considered for vectorization
       // under OptForSize, thereby making sure the cost of their loop body is
       // dominant, free of runtime guards and scalar iteration overheads.
-      OptForSize = true;
+      SEL = CM_ScalarEpilogueNotAllowedLowTripLoop;
     }
   }
 
   // Check the function attributes to see if implicit floats are allowed.
   // FIXME: This check doesn't seem possibly correct -- what if the loop is
   // an integer loop and the vector instructions selected are purely integer
   // vector instructions?
   if (F->hasFnAttribute(Attribute::NoImplicitFloat)) {
if (EnableInterleavedMemAccesses.getNumOccurrences() > 0)
     UseInterleaved = EnableInterleavedMemAccesses;
 
   // Analyze interleaved memory accesses.
   if (UseInterleaved) {
     IAI.analyzeInterleaving(useMaskedInterleavedAccesses(*TTI));
   }
 
   // Use the cost model.
-  LoopVectorizationCostModel CM(L, PSE, LI, &LVL, *TTI, TLI, DB, AC, ORE, F,
-                                &Hints, IAI);
+  LoopVectorizationCostModel CM(SEL, L, PSE, LI, &LVL, *TTI, TLI,
+                                DB, AC, ORE, F, &Hints, IAI);
   CM.collectValuesToIgnore();
 
   // Use the planner for vectorization.
   LoopVectorizationPlanner LVP(L, LI, TLI, TTI, &LVL, CM);
 
   // Get user vectorization factor.
   unsigned UserVF = Hints.getWidth();
 
   // Plan how to best vectorize, return the best VF and its cost.
-  Optional<VectorizationFactor> MaybeVF = LVP.plan(OptForSize, UserVF);
+  Optional<VectorizationFactor> MaybeVF = LVP.plan(UserVF);
 
   VectorizationFactor VF = VectorizationFactor::Disabled();
   unsigned IC = 1;
   unsigned UserIC = Hints.getInterleave();
 
   if (MaybeVF) {
     VF = *MaybeVF;
     // Select the interleave count.
-    IC = CM.selectInterleaveCount(OptForSize, VF.Width, VF.Cost);
+    IC = CM.selectInterleaveCount(VF.Width, VF.Cost);
   }
 
   // Identify the diagnostic messages that should be produced.
   std::pair<StringRef, std::string> VecDiagMsg, IntDiagMsg;
   bool VectorizeLoop = true, InterleaveLoop = true;
   if (Requirements.doesNotMeet(F, L, Hints)) {
     LLVM_DEBUG(dbgs() << "LV: Not vectorizing: loop did not meet vectorization "
                          "requirements.\n");