[LoopVectorize] Use predicated version of getSmallConstantMaxTripCount (#109928)

There are a number of places where we call getSmallConstantMaxTripCount
without passing a vector of predicates:

getSmallBestKnownTC
isIndvarOverflowCheckKnownFalse
computeMaxVF
isMoreProfitable

I've changed all of these to now pass in a predicate vector so that
we get the benefit of making better vectorisation choices when we
know the max trip count for loops that require SCEV predicate checks.

I've tried to add tests that cover all the cases affected by these
changes.

Author: david-arm

llvm/include/llvm/Analysis/ScalarEvolution.h

@@ -2376,6 +2376,10 @@ class PredicatedScalarEvolution {
   /// Get the (predicated) symbolic max backedge count for the analyzed loop.
   const SCEV *getSymbolicMaxBackedgeTakenCount();
 
+  /// Returns the upper bound of the loop trip count as a normal unsigned
+  /// value, or 0 if the trip count is unknown.
+  unsigned getSmallConstantMaxTripCount();
+
   /// Adds a new predicate.
   void addPredicate(const SCEVPredicate &Pred);
 
@@ -2447,6 +2451,9 @@ class PredicatedScalarEvolution {
 
   /// The symbolic backedge taken count.
   const SCEV *SymbolicMaxBackedgeCount = nullptr;
+
+  /// The constant max trip count for the loop.
+  std::optional<unsigned> SmallConstantMaxTripCount;
 };
 
 template <> struct DenseMapInfo<ScalarEvolution::FoldID> {

llvm/lib/Analysis/ScalarEvolution.cpp

@@ -15050,6 +15050,16 @@ const SCEV *PredicatedScalarEvolution::getSymbolicMaxBackedgeTakenCount() {
   return SymbolicMaxBackedgeCount;
 }
 
+unsigned PredicatedScalarEvolution::getSmallConstantMaxTripCount() {
+  if (!SmallConstantMaxTripCount) {
+    SmallVector<const SCEVPredicate *, 4> Preds;
+    SmallConstantMaxTripCount = SE.getSmallConstantMaxTripCount(&L, &Preds);
+    for (const auto *P : Preds)
+      addPredicate(*P);
+  }
+  return *SmallConstantMaxTripCount;
+}
+
 void PredicatedScalarEvolution::addPredicate(const SCEVPredicate &Pred) {
   if (Preds->implies(&Pred))
     return;

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -411,10 +411,10 @@ static bool hasIrregularType(Type *Ty, const DataLayout &DL) {
 ///   3) Returns upper bound estimate if known, and if \p CanUseConstantMax.
 ///   4) Returns std::nullopt if all of the above failed.
 static std::optional<unsigned>
-getSmallBestKnownTC(ScalarEvolution &SE, Loop *L,
+getSmallBestKnownTC(PredicatedScalarEvolution &PSE, Loop *L,
                     bool CanUseConstantMax = true) {
   // Check if exact trip count is known.
-  if (unsigned ExpectedTC = SE.getSmallConstantTripCount(L))
+  if (unsigned ExpectedTC = PSE.getSE()->getSmallConstantTripCount(L))
     return ExpectedTC;
 
   // Check if there is an expected trip count available from profile data.
@@ -426,7 +426,7 @@ getSmallBestKnownTC(ScalarEvolution &SE, Loop *L,
     return std::nullopt;
 
   // Check if upper bound estimate is known.
-  if (unsigned ExpectedTC = SE.getSmallConstantMaxTripCount(L))
+  if (unsigned ExpectedTC = PSE.getSmallConstantMaxTripCount())
     return ExpectedTC;
 
   return std::nullopt;
@@ -1789,12 +1789,15 @@ class GeneratedRTChecks {
 
   Loop *OuterLoop = nullptr;
 
+  PredicatedScalarEvolution &PSE;
+
 public:
-  GeneratedRTChecks(ScalarEvolution &SE, DominatorTree *DT, LoopInfo *LI,
-                    TargetTransformInfo *TTI, const DataLayout &DL,
-                    bool AddBranchWeights)
-      : DT(DT), LI(LI), TTI(TTI), SCEVExp(SE, DL, "scev.check"),
-        MemCheckExp(SE, DL, "scev.check"), AddBranchWeights(AddBranchWeights) {}
+  GeneratedRTChecks(PredicatedScalarEvolution &PSE, DominatorTree *DT,
+                    LoopInfo *LI, TargetTransformInfo *TTI,
+                    const DataLayout &DL, bool AddBranchWeights)
+      : DT(DT), LI(LI), TTI(TTI), SCEVExp(*PSE.getSE(), DL, "scev.check"),
+        MemCheckExp(*PSE.getSE(), DL, "scev.check"),
+        AddBranchWeights(AddBranchWeights), PSE(PSE) {}
 
   /// Generate runtime checks in SCEVCheckBlock and MemCheckBlock, so we can
   /// accurately estimate the cost of the runtime checks. The blocks are
@@ -1941,7 +1944,7 @@ class GeneratedRTChecks {
 
           // Get the best known TC estimate.
           if (auto EstimatedTC = getSmallBestKnownTC(
-                  *SE, OuterLoop, /* CanUseConstantMax = */ false))
+                  PSE, OuterLoop, /* CanUseConstantMax = */ false))
             BestTripCount = *EstimatedTC;
 
           BestTripCount = std::max(BestTripCount, 1U);
@@ -2272,8 +2275,7 @@ static bool isIndvarOverflowCheckKnownFalse(
   // We know the runtime overflow check is known false iff the (max) trip-count
   // is known and (max) trip-count + (VF * UF) does not overflow in the type of
   // the vector loop induction variable.
-  if (unsigned TC =
-          Cost->PSE.getSE()->getSmallConstantMaxTripCount(Cost->TheLoop)) {
+  if (unsigned TC = Cost->PSE.getSmallConstantMaxTripCount()) {
     uint64_t MaxVF = VF.getKnownMinValue();
     if (VF.isScalable()) {
       std::optional<unsigned> MaxVScale =
@@ -3962,8 +3964,10 @@ LoopVectorizationCostModel::computeMaxVF(ElementCount UserVF, unsigned UserIC) {
   }
 
   unsigned TC = PSE.getSE()->getSmallConstantTripCount(TheLoop);
-  unsigned MaxTC = PSE.getSE()->getSmallConstantMaxTripCount(TheLoop);
+  unsigned MaxTC = PSE.getSmallConstantMaxTripCount();
   LLVM_DEBUG(dbgs() << "LV: Found trip count: " << TC << '\n');
+  if (TC != MaxTC)
+    LLVM_DEBUG(dbgs() << "LV: Found maximum trip count: " << MaxTC << '\n');
   if (TC == 1) {
     reportVectorizationFailure("Single iteration (non) loop",
         "loop trip count is one, irrelevant for vectorization",
@@ -4257,7 +4261,7 @@ bool LoopVectorizationPlanner::isMoreProfitable(
   InstructionCost CostA = A.Cost;
   InstructionCost CostB = B.Cost;
 
-  unsigned MaxTripCount = PSE.getSE()->getSmallConstantMaxTripCount(OrigLoop);
+  unsigned MaxTripCount = PSE.getSmallConstantMaxTripCount();
 
   // Improve estimate for the vector width if it is scalable.
   unsigned EstimatedWidthA = A.Width.getKnownMinValue();
@@ -4852,7 +4856,7 @@ LoopVectorizationCostModel::selectInterleaveCount(ElementCount VF,
   if (!Legal->isSafeForAnyVectorWidth())
     return 1;
 
-  auto BestKnownTC = getSmallBestKnownTC(*PSE.getSE(), TheLoop);
+  auto BestKnownTC = getSmallBestKnownTC(PSE, TheLoop);
   const bool HasReductions = !Legal->getReductionVars().empty();
 
   // If we did not calculate the cost for VF (because the user selected the VF)
@@ -9618,8 +9622,8 @@ static bool processLoopInVPlanNativePath(
   {
     bool AddBranchWeights =
         hasBranchWeightMD(*L->getLoopLatch()->getTerminator());
-    GeneratedRTChecks Checks(*PSE.getSE(), DT, LI, TTI,
-                             F->getDataLayout(), AddBranchWeights);
+    GeneratedRTChecks Checks(PSE, DT, LI, TTI, F->getDataLayout(),
+                             AddBranchWeights);
     InnerLoopVectorizer LB(L, PSE, LI, DT, TLI, TTI, AC, ORE, VF.Width,
                            VF.Width, 1, LVL, &CM, BFI, PSI, Checks);
     LLVM_DEBUG(dbgs() << "Vectorizing outer loop in \""
@@ -9683,7 +9687,7 @@ static void checkMixedPrecision(Loop *L, OptimizationRemarkEmitter *ORE) {
 static bool areRuntimeChecksProfitable(GeneratedRTChecks &Checks,
                                        VectorizationFactor &VF,
                                        std::optional<unsigned> VScale, Loop *L,
-                                       ScalarEvolution &SE,
+                                       PredicatedScalarEvolution &PSE,
                                        ScalarEpilogueLowering SEL) {
   InstructionCost CheckCost = Checks.getCost();
   if (!CheckCost.isValid())
@@ -9768,7 +9772,7 @@ static bool areRuntimeChecksProfitable(GeneratedRTChecks &Checks,
 
   // Skip vectorization if the expected trip count is less than the minimum
   // required trip count.
-  if (auto ExpectedTC = getSmallBestKnownTC(SE, L)) {
+  if (auto ExpectedTC = getSmallBestKnownTC(PSE, L)) {
     if (ElementCount::isKnownLT(ElementCount::getFixed(*ExpectedTC),
                                 VF.MinProfitableTripCount)) {
       LLVM_DEBUG(dbgs() << "LV: Vectorization is not beneficial: expected "
@@ -9875,7 +9879,7 @@ bool LoopVectorizePass::processLoop(Loop *L) {
 
   // Check the loop for a trip count threshold: vectorize loops with a tiny trip
   // count by optimizing for size, to minimize overheads.
-  auto ExpectedTC = getSmallBestKnownTC(*SE, L);
+  auto ExpectedTC = getSmallBestKnownTC(PSE, L);
   if (ExpectedTC && *ExpectedTC < TinyTripCountVectorThreshold) {
     LLVM_DEBUG(dbgs() << "LV: Found a loop with a very small trip count. "
                       << "This loop is worth vectorizing only if no scalar "
@@ -9973,8 +9977,8 @@ bool LoopVectorizePass::processLoop(Loop *L) {
 
   bool AddBranchWeights =
       hasBranchWeightMD(*L->getLoopLatch()->getTerminator());
-  GeneratedRTChecks Checks(*PSE.getSE(), DT, LI, TTI,
-                           F->getDataLayout(), AddBranchWeights);
+  GeneratedRTChecks Checks(PSE, DT, LI, TTI, F->getDataLayout(),
+                           AddBranchWeights);
   if (LVP.hasPlanWithVF(VF.Width)) {
     // Select the interleave count.
     IC = CM.selectInterleaveCount(VF.Width, VF.Cost);
@@ -9990,7 +9994,7 @@ bool LoopVectorizePass::processLoop(Loop *L) {
         Hints.getForce() == LoopVectorizeHints::FK_Enabled;
     if (!ForceVectorization &&
         !areRuntimeChecksProfitable(Checks, VF, getVScaleForTuning(L, *TTI), L,
-                                    *PSE.getSE(), SEL)) {
+                                    PSE, SEL)) {
       ORE->emit([&]() {
         return OptimizationRemarkAnalysisAliasing(
                    DEBUG_TYPE, "CantReorderMemOps", L->getStartLoc(),