[NFC] Use initial-stack-allocations for more data structures (#110544)

This replaces some of the most frequent offenders of using a DenseMap that
cause a malloc, where the typical element-count is small enough to fit in
an initial stack allocation.

Most of these are fairly obvious, one to highlight is the collectOffset
method of GEP instructions: if there's a GEP, of course it's going to have
at least one offset, but every time we've called collectOffset we end up
calling malloc as well for the DenseMap in the MapVector.

Author: jmorse

llvm/include/llvm/IR/Instructions.h

@@ -1117,7 +1117,7 @@ class GetElementPtrInst : public Instruction {
   /// the base GEP pointer.
   bool accumulateConstantOffset(const DataLayout &DL, APInt &Offset) const;
   bool collectOffset(const DataLayout &DL, unsigned BitWidth,
-                     MapVector<Value *, APInt> &VariableOffsets,
+                     SmallMapVector<Value *, APInt, 4> &VariableOffsets,
                      APInt &ConstantOffset) const;
   // Methods for support type inquiry through isa, cast, and dyn_cast:
   static bool classof(const Instruction *I) {

llvm/include/llvm/IR/Operator.h

@@ -528,7 +528,7 @@ class GEPOperator
   /// Collect the offset of this GEP as a map of Values to their associated
   /// APInt multipliers, as well as a total Constant Offset.
   bool collectOffset(const DataLayout &DL, unsigned BitWidth,
-                     MapVector<Value *, APInt> &VariableOffsets,
+                     SmallMapVector<Value *, APInt, 4> &VariableOffsets,
                      APInt &ConstantOffset) const;
 };
 

llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp

@@ -2831,7 +2831,8 @@ static void emitRangeList(
 
   // Gather all the ranges that apply to the same section so they can share
   // a base address entry.
-  MapVector<const MCSection *, std::vector<decltype(&*R.begin())>> SectionRanges;
+  SmallMapVector<const MCSection *, std::vector<decltype(&*R.begin())>, 16>
+      SectionRanges;
 
   for (const auto &Range : R)
     SectionRanges[&Range.Begin->getSection()].push_back(&Range);

llvm/lib/CodeGen/LiveDebugValues/InstrRefBasedImpl.h

@@ -1046,7 +1046,7 @@ class VLocTracker {
   /// transfer function for this block, as part of the dataflow analysis. The
   /// movement of values between locations inside of a block is handled at a
   /// much later stage, in the TransferTracker class.
-  MapVector<DebugVariableID, DbgValue> Vars;
+  SmallMapVector<DebugVariableID, DbgValue, 8> Vars;
   SmallDenseMap<DebugVariableID, const DILocation *, 8> Scopes;
   MachineBasicBlock *MBB = nullptr;
   const OverlapMap &OverlappingFragments;
@@ -1128,7 +1128,7 @@ class InstrRefBasedLDV : public LDVImpl {
 
   /// Live in/out structure for the variable values: a per-block map of
   /// variables to their values.
-  using LiveIdxT = DenseMap<const MachineBasicBlock *, DbgValue *>;
+  using LiveIdxT = SmallDenseMap<const MachineBasicBlock *, DbgValue *, 16>;
 
   using VarAndLoc = std::pair<DebugVariableID, DbgValue>;
 

llvm/lib/CodeGen/ScheduleDAGInstrs.cpp

@@ -621,7 +621,8 @@ void ScheduleDAGInstrs::initSUnits() {
   }
 }
 
-class ScheduleDAGInstrs::Value2SUsMap : public MapVector<ValueType, SUList> {
+class ScheduleDAGInstrs::Value2SUsMap
+    : public SmallMapVector<ValueType, SUList, 4> {
   /// Current total number of SUs in map.
   unsigned NumNodes = 0;
 
@@ -656,7 +657,7 @@ class ScheduleDAGInstrs::Value2SUsMap : public MapVector<ValueType, SUList> {
 
   /// Clears map from all contents.
   void clear() {
-    MapVector<ValueType, SUList>::clear();
+    SmallMapVector<ValueType, SUList, 4>::clear();
     NumNodes = 0;
   }
 

llvm/lib/CodeGen/SelectionDAG/ScheduleDAGRRList.cpp

@@ -183,7 +183,7 @@ class ScheduleDAGRRList : public ScheduleDAGSDNodes {
 
   // Hack to keep track of the inverse of FindCallSeqStart without more crazy
   // DAG crawling.
-  DenseMap<SUnit*, SUnit*> CallSeqEndForStart;
+  SmallDenseMap<SUnit *, SUnit *, 16> CallSeqEndForStart;
 
 public:
   ScheduleDAGRRList(MachineFunction &mf, bool needlatency,

llvm/lib/IR/Instructions.cpp

@@ -1584,7 +1584,7 @@ bool GetElementPtrInst::accumulateConstantOffset(const DataLayout &DL,
 
 bool GetElementPtrInst::collectOffset(
     const DataLayout &DL, unsigned BitWidth,
-    MapVector<Value *, APInt> &VariableOffsets,
+    SmallMapVector<Value *, APInt, 4> &VariableOffsets,
     APInt &ConstantOffset) const {
   // Delegate to the generic GEPOperator implementation.
   return cast<GEPOperator>(this)->collectOffset(DL, BitWidth, VariableOffsets,

llvm/lib/IR/Operator.cpp

@@ -201,7 +201,7 @@ bool GEPOperator::accumulateConstantOffset(
 
 bool GEPOperator::collectOffset(
     const DataLayout &DL, unsigned BitWidth,
-    MapVector<Value *, APInt> &VariableOffsets,
+    SmallMapVector<Value *, APInt, 4> &VariableOffsets,
     APInt &ConstantOffset) const {
   assert(BitWidth == DL.getIndexSizeInBits(getPointerAddressSpace()) &&
          "The offset bit width does not match DL specification.");

llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp

@@ -402,7 +402,7 @@ static Value *GEPToVectorIndex(GetElementPtrInst *GEP, AllocaInst *Alloca,
   // TODO: Extracting a "multiple of X" from a GEP might be a useful generic
   // helper.
   unsigned BW = DL.getIndexTypeSizeInBits(GEP->getType());
-  MapVector<Value *, APInt> VarOffsets;
+  SmallMapVector<Value *, APInt, 4> VarOffsets;
   APInt ConstOffset(BW, 0);
   if (GEP->getPointerOperand()->stripPointerCasts() != Alloca ||
       !GEP->collectOffset(DL, BW, VarOffsets, ConstOffset))

llvm/lib/Transforms/AggressiveInstCombine/AggressiveInstCombine.cpp

@@ -843,7 +843,7 @@ getStrideAndModOffsetOfGEP(Value *PtrOp, const DataLayout &DL) {
   // Return a minimum gep stride, greatest common divisor of consective gep
   // index scales(c.f. Bézout's identity).
   while (auto *GEP = dyn_cast<GEPOperator>(PtrOp)) {
-    MapVector<Value *, APInt> VarOffsets;
+    SmallMapVector<Value *, APInt, 4> VarOffsets;
     if (!GEP->collectOffset(DL, BW, VarOffsets, ModOffset))
       break;
 

llvm/lib/Transforms/IPO/AttributorAttributes.cpp

@@ -1557,7 +1557,7 @@ bool AAPointerInfoFloating::collectConstantsForGEP(Attributor &A,
                                                    const OffsetInfo &PtrOI,
                                                    const GEPOperator *GEP) {
   unsigned BitWidth = DL.getIndexTypeSizeInBits(GEP->getType());
-  MapVector<Value *, APInt> VariableOffsets;
+  SmallMapVector<Value *, APInt, 4> VariableOffsets;
   APInt ConstantOffset(BitWidth, 0);
 
   assert(!UsrOI.isUnknown() && !PtrOI.isUnknown() &&

llvm/lib/Transforms/Scalar/ConstraintElimination.cpp

@@ -385,7 +385,7 @@ struct Decomposition {
 struct OffsetResult {
   Value *BasePtr;
   APInt ConstantOffset;
-  MapVector<Value *, APInt> VariableOffsets;
+  SmallMapVector<Value *, APInt, 4> VariableOffsets;
   bool AllInbounds;
 
   OffsetResult() : BasePtr(nullptr), ConstantOffset(0, uint64_t(0)) {}
@@ -410,7 +410,7 @@ static OffsetResult collectOffsets(GEPOperator &GEP, const DataLayout &DL) {
   // If we have a nested GEP, check if we can combine the constant offset of the
   // inner GEP with the outer GEP.
   if (auto *InnerGEP = dyn_cast<GetElementPtrInst>(Result.BasePtr)) {
-    MapVector<Value *, APInt> VariableOffsets2;
+    SmallMapVector<Value *, APInt, 4> VariableOffsets2;
     APInt ConstantOffset2(BitWidth, 0);
     bool CanCollectInner = InnerGEP->collectOffset(
         DL, BitWidth, VariableOffsets2, ConstantOffset2);

llvm/lib/Transforms/Scalar/GVN.cpp

@@ -422,7 +422,7 @@ GVNPass::Expression GVNPass::ValueTable::createGEPExpr(GetElementPtrInst *GEP) {
   Type *PtrTy = GEP->getType()->getScalarType();
   const DataLayout &DL = GEP->getDataLayout();
   unsigned BitWidth = DL.getIndexTypeSizeInBits(PtrTy);
-  MapVector<Value *, APInt> VariableOffsets;
+  SmallMapVector<Value *, APInt, 4> VariableOffsets;
   APInt ConstantOffset(BitWidth, 0);
   if (GEP->collectOffset(DL, BitWidth, VariableOffsets, ConstantOffset)) {
     // Convert into offset representation, to recognize equivalent address

llvm/lib/Transforms/Scalar/JumpTableToSwitch.cpp

@@ -56,7 +56,7 @@ static std::optional<JumpTableTy> parseJumpTable(GetElementPtrInst *GEP,
   const DataLayout &DL = F.getDataLayout();
   const unsigned BitWidth =
       DL.getIndexSizeInBits(GEP->getPointerAddressSpace());
-  MapVector<Value *, APInt> VariableOffsets;
+  SmallMapVector<Value *, APInt, 4> VariableOffsets;
   APInt ConstantOffset(BitWidth, 0);
   if (!GEP->collectOffset(DL, BitWidth, VariableOffsets, ConstantOffset))
     return std::nullopt;

llvm/lib/Transforms/Utils/Local.cpp

@@ -925,7 +925,7 @@ CanPropagatePredecessorsForPHIs(BasicBlock *BB, BasicBlock *Succ,
 }
 
 using PredBlockVector = SmallVector<BasicBlock *, 16>;
-using IncomingValueMap = DenseMap<BasicBlock *, Value *>;
+using IncomingValueMap = SmallDenseMap<BasicBlock *, Value *, 16>;
 
 /// Determines the value to use as the phi node input for a block.
 ///
@@ -2467,7 +2467,7 @@ Value *getSalvageOpsForGEP(GetElementPtrInst *GEP, const DataLayout &DL,
                            SmallVectorImpl<Value *> &AdditionalValues) {
   unsigned BitWidth = DL.getIndexSizeInBits(GEP->getPointerAddressSpace());
   // Rewrite a GEP into a DIExpression.
-  MapVector<Value *, APInt> VariableOffsets;
+  SmallMapVector<Value *, APInt, 4> VariableOffsets;
   APInt ConstantOffset(BitWidth, 0);
   if (!GEP->collectOffset(DL, BitWidth, VariableOffsets, ConstantOffset))
     return nullptr;

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -5122,7 +5122,7 @@ LoopVectorizationCostModel::calculateRegisterUsage(ArrayRef<ElementCount> VFs) {
   // Each 'key' in the map opens a new interval. The values
   // of the map are the index of the 'last seen' usage of the
   // instruction that is the key.
-  using IntervalMap = DenseMap<Instruction *, unsigned>;
+  using IntervalMap = SmallDenseMap<Instruction *, unsigned, 16>;
 
   // Maps instruction to its index.
   SmallVector<Instruction *, 64> IdxToInstr;
@@ -5165,7 +5165,7 @@ LoopVectorizationCostModel::calculateRegisterUsage(ArrayRef<ElementCount> VFs) {
 
   // Saves the list of intervals that end with the index in 'key'.
   using InstrList = SmallVector<Instruction *, 2>;
-  DenseMap<unsigned, InstrList> TransposeEnds;
+  SmallDenseMap<unsigned, InstrList, 16> TransposeEnds;
 
   // Transpose the EndPoints to a list of values that end at each index.
   for (auto &Interval : EndPoint)

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

@@ -5470,7 +5470,7 @@ BoUpSLP::getReorderingData(const TreeEntry &TE, bool TopToBottom) {
         }
       return I1 < I2;
     };
-    DenseMap<unsigned, unsigned> PhiToId;
+    SmallDenseMap<unsigned, unsigned, 16> PhiToId;
     SmallVector<unsigned> Phis(TE.Scalars.size());
     std::iota(Phis.begin(), Phis.end(), 0);
     OrdersType ResOrder(TE.Scalars.size());
@@ -10319,7 +10319,7 @@ BoUpSLP::getEntryCost(const TreeEntry *E, ArrayRef<Value *> VectorizedVals,
       E->isAltShuffle() ? (unsigned)Instruction::ShuffleVector : E->getOpcode();
   if (E->CombinedOp != TreeEntry::NotCombinedOp)
     ShuffleOrOp = E->CombinedOp;
-  SetVector<Value *> UniqueValues(VL.begin(), VL.end());
+  SmallSetVector<Value *, 16> UniqueValues(VL.begin(), VL.end());
   const unsigned Sz = UniqueValues.size();
   SmallBitVector UsedScalars(Sz, false);
   for (unsigned I = 0; I < Sz; ++I) {
@@ -18013,7 +18013,7 @@ class HorizontalReduction {
   /// List of possibly reduced values.
   SmallVector<SmallVector<Value *>> ReducedVals;
   /// Maps reduced value to the corresponding reduction operation.
-  DenseMap<Value *, SmallVector<Instruction *>> ReducedValsToOps;
+  SmallDenseMap<Value *, SmallVector<Instruction *>, 16> ReducedValsToOps;
   WeakTrackingVH ReductionRoot;
   /// The type of reduction operation.
   RecurKind RdxKind;
@@ -18382,7 +18382,9 @@ class HorizontalReduction {
     // instruction op id and/or alternate op id, plus do extra analysis for
     // loads (grouping them by the distabce between pointers) and cmp
     // instructions (grouping them by the predicate).
-    MapVector<size_t, MapVector<size_t, MapVector<Value *, unsigned>>>
+    SmallMapVector<
+        size_t, SmallMapVector<size_t, SmallMapVector<Value *, unsigned, 2>, 2>,
+        8>
         PossibleReducedVals;
     initReductionOps(Root);
     DenseMap<Value *, SmallVector<LoadInst *>> LoadsMap;