[llvm] 96f37ae - [NFC] Use initial-stack-allocations for more data structures (#110544)
via llvm-commits
llvm-commits at lists.llvm.org
Mon Sep 30 15:15:21 PDT 2024
Author: Jeremy Morse
Date: 2024-09-30T23:15:18+01:00
New Revision: 96f37ae45310885e09195be09d9c05e1c1dff86b
URL: https://github.com/llvm/llvm-project/commit/96f37ae45310885e09195be09d9c05e1c1dff86b
DIFF: https://github.com/llvm/llvm-project/commit/96f37ae45310885e09195be09d9c05e1c1dff86b.diff
LOG: [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.
Added:
Modified:
llvm/include/llvm/IR/Instructions.h
llvm/include/llvm/IR/Operator.h
llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp
llvm/lib/CodeGen/LiveDebugValues/InstrRefBasedImpl.h
llvm/lib/CodeGen/ScheduleDAGInstrs.cpp
llvm/lib/CodeGen/SelectionDAG/ScheduleDAGRRList.cpp
llvm/lib/IR/Instructions.cpp
llvm/lib/IR/Operator.cpp
llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
llvm/lib/Transforms/AggressiveInstCombine/AggressiveInstCombine.cpp
llvm/lib/Transforms/IPO/AttributorAttributes.cpp
llvm/lib/Transforms/Scalar/ConstraintElimination.cpp
llvm/lib/Transforms/Scalar/GVN.cpp
llvm/lib/Transforms/Scalar/JumpTableToSwitch.cpp
llvm/lib/Transforms/Utils/Local.cpp
llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
Removed:
################################################################################
diff --git a/llvm/include/llvm/IR/Instructions.h b/llvm/include/llvm/IR/Instructions.h
index 75a059760f48fa..695a7a6aa9f254 100644
--- a/llvm/include/llvm/IR/Instructions.h
+++ b/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) {
diff --git a/llvm/include/llvm/IR/Operator.h b/llvm/include/llvm/IR/Operator.h
index 88b9bfc0be4b15..0e9f6ed35dcb4e 100644
--- a/llvm/include/llvm/IR/Operator.h
+++ b/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;
};
diff --git a/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp b/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp
index 6f211abb299e7a..aa44d62da47be9 100644
--- a/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp
+++ b/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);
diff --git a/llvm/lib/CodeGen/LiveDebugValues/InstrRefBasedImpl.h b/llvm/lib/CodeGen/LiveDebugValues/InstrRefBasedImpl.h
index f157ffc6bcc2d7..68db65ace9a427 100644
--- a/llvm/lib/CodeGen/LiveDebugValues/InstrRefBasedImpl.h
+++ b/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>;
diff --git a/llvm/lib/CodeGen/ScheduleDAGInstrs.cpp b/llvm/lib/CodeGen/ScheduleDAGInstrs.cpp
index 68dece6cf73e91..a0632eb17e65e6 100644
--- a/llvm/lib/CodeGen/ScheduleDAGInstrs.cpp
+++ b/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;
}
diff --git a/llvm/lib/CodeGen/SelectionDAG/ScheduleDAGRRList.cpp b/llvm/lib/CodeGen/SelectionDAG/ScheduleDAGRRList.cpp
index e4ee3fd99f16e3..9e5867c70d7b6d 100644
--- a/llvm/lib/CodeGen/SelectionDAG/ScheduleDAGRRList.cpp
+++ b/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,
diff --git a/llvm/lib/IR/Instructions.cpp b/llvm/lib/IR/Instructions.cpp
index e95b98a6404432..009e0c03957c97 100644
--- a/llvm/lib/IR/Instructions.cpp
+++ b/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,
diff --git a/llvm/lib/IR/Operator.cpp b/llvm/lib/IR/Operator.cpp
index 6c9862556f5504..f93ff8f6fc8a25 100644
--- a/llvm/lib/IR/Operator.cpp
+++ b/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.");
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp b/llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
index 7bd618b2d9660c..24bfbff41ec5c0 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
+++ b/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))
diff --git a/llvm/lib/Transforms/AggressiveInstCombine/AggressiveInstCombine.cpp b/llvm/lib/Transforms/AggressiveInstCombine/AggressiveInstCombine.cpp
index 01642b0677aba3..9943c3cbb9fc7d 100644
--- a/llvm/lib/Transforms/AggressiveInstCombine/AggressiveInstCombine.cpp
+++ b/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;
diff --git a/llvm/lib/Transforms/IPO/AttributorAttributes.cpp b/llvm/lib/Transforms/IPO/AttributorAttributes.cpp
index 416dd09ca874bf..238bdf9c344b08 100644
--- a/llvm/lib/Transforms/IPO/AttributorAttributes.cpp
+++ b/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() &&
diff --git a/llvm/lib/Transforms/Scalar/ConstraintElimination.cpp b/llvm/lib/Transforms/Scalar/ConstraintElimination.cpp
index 7e2721d0c5a5e6..7c06e0c757e1cc 100644
--- a/llvm/lib/Transforms/Scalar/ConstraintElimination.cpp
+++ b/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);
diff --git a/llvm/lib/Transforms/Scalar/GVN.cpp b/llvm/lib/Transforms/Scalar/GVN.cpp
index db39d8621d0771..2ba600497e00d3 100644
--- a/llvm/lib/Transforms/Scalar/GVN.cpp
+++ b/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
diff --git a/llvm/lib/Transforms/Scalar/JumpTableToSwitch.cpp b/llvm/lib/Transforms/Scalar/JumpTableToSwitch.cpp
index 2a4f68e1252523..7f99cd2060a9d8 100644
--- a/llvm/lib/Transforms/Scalar/JumpTableToSwitch.cpp
+++ b/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;
diff --git a/llvm/lib/Transforms/Utils/Local.cpp b/llvm/lib/Transforms/Utils/Local.cpp
index 7659fc69196151..cfe40f91f9a5df 100644
--- a/llvm/lib/Transforms/Utils/Local.cpp
+++ b/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;
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 034765bee40e7b..f5ef50934f59fd 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/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)
diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index 6b8ec55b30426c..68bf5c52814f56 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/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;
More information about the llvm-commits
mailing list