//===----------------------------------------------------------------------===//
#include "llvm/Transforms/Scalar.h"
-#include "llvm/Transforms/Utils/UnifyFunctionExitNodes.h"
-#include "llvm/Constants.h"
-#include "llvm/Function.h"
-#include "llvm/Instructions.h"
-#include "llvm/LLVMContext.h"
-#include "llvm/Pass.h"
+#include "llvm/Transforms/Utils/BasicBlockUtils.h"
#include "llvm/ADT/STLExtras.h"
+#include "llvm/IR/Constants.h"
+#include "llvm/IR/Function.h"
+#include "llvm/IR/Instructions.h"
+#include "llvm/IR/LLVMContext.h"
+#include "llvm/IR/CFG.h"
+#include "llvm/Pass.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"
+#include "llvm/Transforms/Utils/UnifyFunctionExitNodes.h"
#include <algorithm>
using namespace llvm;
+#define DEBUG_TYPE "lower-switch"
+
namespace {
+ struct IntRange {
+ int64_t Low, High;
+ };
+ // Return true iff R is covered by Ranges.
+ static bool IsInRanges(const IntRange &R,
+ const std::vector<IntRange> &Ranges) {
+ // Note: Ranges must be sorted, non-overlapping and non-adjacent.
+
+ // Find the first range whose High field is >= R.High,
+ // then check if the Low field is <= R.Low. If so, we
+ // have a Range that covers R.
+ auto I = std::lower_bound(
+ Ranges.begin(), Ranges.end(), R,
+ [](const IntRange &A, const IntRange &B) { return A.High < B.High; });
+ return I != Ranges.end() && I->Low <= R.Low;
+ }
+
/// LowerSwitch Pass - Replace all SwitchInst instructions with chained branch
/// instructions.
class LowerSwitch : public FunctionPass {
initializeLowerSwitchPass(*PassRegistry::getPassRegistry());
}
- virtual bool runOnFunction(Function &F);
-
- virtual void getAnalysisUsage(AnalysisUsage &AU) const {
+ bool runOnFunction(Function &F) override;
+
+ void getAnalysisUsage(AnalysisUsage &AU) const override {
// This is a cluster of orthogonal Transforms
AU.addPreserved<UnifyFunctionExitNodes>();
- AU.addPreserved("mem2reg");
AU.addPreservedID(LowerInvokePassID);
}
struct CaseRange {
- Constant* Low;
- Constant* High;
+ ConstantInt* Low;
+ ConstantInt* High;
BasicBlock* BB;
- CaseRange(Constant *low = 0, Constant *high = 0, BasicBlock *bb = 0) :
- Low(low), High(high), BB(bb) { }
+ CaseRange(ConstantInt *low, ConstantInt *high, BasicBlock *bb)
+ : Low(low), High(high), BB(bb) {}
};
- typedef std::vector<CaseRange> CaseVector;
+ typedef std::vector<CaseRange> CaseVector;
typedef std::vector<CaseRange>::iterator CaseItr;
private:
void processSwitchInst(SwitchInst *SI);
- BasicBlock* switchConvert(CaseItr Begin, CaseItr End, Value* Val,
- BasicBlock* OrigBlock, BasicBlock* Default);
- BasicBlock* newLeafBlock(CaseRange& Leaf, Value* Val,
- BasicBlock* OrigBlock, BasicBlock* Default);
- unsigned Clusterify(CaseVector& Cases, SwitchInst *SI);
+ BasicBlock *switchConvert(CaseItr Begin, CaseItr End,
+ ConstantInt *LowerBound, ConstantInt *UpperBound,
+ Value *Val, BasicBlock *Predecessor,
+ BasicBlock *OrigBlock, BasicBlock *Default,
+ const std::vector<IntRange> &UnreachableRanges);
+ BasicBlock *newLeafBlock(CaseRange &Leaf, Value *Val, BasicBlock *OrigBlock,
+ BasicBlock *Default);
+ unsigned Clusterify(CaseVector &Cases, SwitchInst *SI);
+ };
+
+ /// The comparison function for sorting the switch case values in the vector.
+ /// WARNING: Case ranges should be disjoint!
+ struct CaseCmp {
+ bool operator () (const LowerSwitch::CaseRange& C1,
+ const LowerSwitch::CaseRange& C2) {
+
+ const ConstantInt* CI1 = cast<const ConstantInt>(C1.Low);
+ const ConstantInt* CI2 = cast<const ConstantInt>(C2.High);
+ return CI1->getValue().slt(CI2->getValue());
+ }
};
}
return O << "]";
}
+// \brief Update the first occurrence of the "switch statement" BB in the PHI
+// node with the "new" BB. The other occurrences will:
+//
+// 1) Be updated by subsequent calls to this function. Switch statements may
+// have more than one outcoming edge into the same BB if they all have the same
+// value. When the switch statement is converted these incoming edges are now
+// coming from multiple BBs.
+// 2) Removed if subsequent incoming values now share the same case, i.e.,
+// multiple outcome edges are condensed into one. This is necessary to keep the
+// number of phi values equal to the number of branches to SuccBB.
+static void fixPhis(BasicBlock *SuccBB, BasicBlock *OrigBB, BasicBlock *NewBB,
+ unsigned NumMergedCases) {
+ for (BasicBlock::iterator I = SuccBB->begin(), IE = SuccBB->getFirstNonPHI();
+ I != IE; ++I) {
+ PHINode *PN = cast<PHINode>(I);
+
+ // Only update the first occurence.
+ unsigned Idx = 0, E = PN->getNumIncomingValues();
+ unsigned LocalNumMergedCases = NumMergedCases;
+ for (; Idx != E; ++Idx) {
+ if (PN->getIncomingBlock(Idx) == OrigBB) {
+ PN->setIncomingBlock(Idx, NewBB);
+ break;
+ }
+ }
+
+ // Remove additional occurences coming from condensed cases and keep the
+ // number of incoming values equal to the number of branches to SuccBB.
+ SmallVector<unsigned, 8> Indices;
+ for (++Idx; LocalNumMergedCases > 0 && Idx < E; ++Idx)
+ if (PN->getIncomingBlock(Idx) == OrigBB) {
+ Indices.push_back(Idx);
+ LocalNumMergedCases--;
+ }
+ // Remove incoming values in the reverse order to prevent invalidating
+ // *successive* index.
+ for (auto III = Indices.rbegin(), IIE = Indices.rend(); III != IIE; ++III)
+ PN->removeIncomingValue(*III);
+ }
+}
+
// switchConvert - Convert the switch statement into a binary lookup of
// the case values. The function recursively builds this tree.
-//
-BasicBlock* LowerSwitch::switchConvert(CaseItr Begin, CaseItr End,
- Value* Val, BasicBlock* OrigBlock,
- BasicBlock* Default)
-{
+// LowerBound and UpperBound are used to keep track of the bounds for Val
+// that have already been checked by a block emitted by one of the previous
+// calls to switchConvert in the call stack.
+BasicBlock *
+LowerSwitch::switchConvert(CaseItr Begin, CaseItr End, ConstantInt *LowerBound,
+ ConstantInt *UpperBound, Value *Val,
+ BasicBlock *Predecessor, BasicBlock *OrigBlock,
+ BasicBlock *Default,
+ const std::vector<IntRange> &UnreachableRanges) {
unsigned Size = End - Begin;
- if (Size == 1)
+ if (Size == 1) {
+ // Check if the Case Range is perfectly squeezed in between
+ // already checked Upper and Lower bounds. If it is then we can avoid
+ // emitting the code that checks if the value actually falls in the range
+ // because the bounds already tell us so.
+ if (Begin->Low == LowerBound && Begin->High == UpperBound) {
+ unsigned NumMergedCases = 0;
+ if (LowerBound && UpperBound)
+ NumMergedCases =
+ UpperBound->getSExtValue() - LowerBound->getSExtValue();
+ fixPhis(Begin->BB, OrigBlock, Predecessor, NumMergedCases);
+ return Begin->BB;
+ }
return newLeafBlock(*Begin, Val, OrigBlock, Default);
+ }
unsigned Mid = Size / 2;
std::vector<CaseRange> LHS(Begin, Begin + Mid);
std::vector<CaseRange> RHS(Begin + Mid, End);
DEBUG(dbgs() << "RHS: " << RHS << "\n");
- CaseRange& Pivot = *(Begin + Mid);
- DEBUG(dbgs() << "Pivot ==> "
- << cast<ConstantInt>(Pivot.Low)->getValue() << " -"
- << cast<ConstantInt>(Pivot.High)->getValue() << "\n");
+ CaseRange &Pivot = *(Begin + Mid);
+ DEBUG(dbgs() << "Pivot ==> "
+ << Pivot.Low->getValue()
+ << " -" << Pivot.High->getValue() << "\n");
+
+ // NewLowerBound here should never be the integer minimal value.
+ // This is because it is computed from a case range that is never
+ // the smallest, so there is always a case range that has at least
+ // a smaller value.
+ ConstantInt *NewLowerBound = Pivot.Low;
+
+ // Because NewLowerBound is never the smallest representable integer
+ // it is safe here to subtract one.
+ ConstantInt *NewUpperBound = ConstantInt::get(NewLowerBound->getContext(),
+ NewLowerBound->getValue() - 1);
+
+ if (!UnreachableRanges.empty()) {
+ // Check if the gap between LHS's highest and NewLowerBound is unreachable.
+ int64_t GapLow = LHS.back().High->getSExtValue() + 1;
+ int64_t GapHigh = NewLowerBound->getSExtValue() - 1;
+ IntRange Gap = { GapLow, GapHigh };
+ if (GapHigh >= GapLow && IsInRanges(Gap, UnreachableRanges))
+ NewUpperBound = LHS.back().High;
+ }
- BasicBlock* LBranch = switchConvert(LHS.begin(), LHS.end(), Val,
- OrigBlock, Default);
- BasicBlock* RBranch = switchConvert(RHS.begin(), RHS.end(), Val,
- OrigBlock, Default);
+ DEBUG(dbgs() << "LHS Bounds ==> ";
+ if (LowerBound) {
+ dbgs() << LowerBound->getSExtValue();
+ } else {
+ dbgs() << "NONE";
+ }
+ dbgs() << " - " << NewUpperBound->getSExtValue() << "\n";
+ dbgs() << "RHS Bounds ==> ";
+ dbgs() << NewLowerBound->getSExtValue() << " - ";
+ if (UpperBound) {
+ dbgs() << UpperBound->getSExtValue() << "\n";
+ } else {
+ dbgs() << "NONE\n";
+ });
// Create a new node that checks if the value is < pivot. Go to the
// left branch if it is and right branch if not.
Function* F = OrigBlock->getParent();
BasicBlock* NewNode = BasicBlock::Create(Val->getContext(), "NodeBlock");
- Function::iterator FI = OrigBlock;
- F->getBasicBlockList().insert(++FI, NewNode);
- ICmpInst* Comp = new ICmpInst(ICmpInst::ICMP_ULT,
+ ICmpInst* Comp = new ICmpInst(ICmpInst::ICMP_SLT,
Val, Pivot.Low, "Pivot");
+
+ BasicBlock *LBranch = switchConvert(LHS.begin(), LHS.end(), LowerBound,
+ NewUpperBound, Val, NewNode, OrigBlock,
+ Default, UnreachableRanges);
+ BasicBlock *RBranch = switchConvert(RHS.begin(), RHS.end(), NewLowerBound,
+ UpperBound, Val, NewNode, OrigBlock,
+ Default, UnreachableRanges);
+
+ Function::iterator FI = OrigBlock;
+ F->getBasicBlockList().insert(++FI, NewNode);
NewNode->getInstList().push_back(Comp);
+
BranchInst::Create(LBranch, RBranch, Comp, NewNode);
return NewNode;
}
F->getBasicBlockList().insert(++FI, NewLeaf);
// Emit comparison
- ICmpInst* Comp = NULL;
+ ICmpInst* Comp = nullptr;
if (Leaf.Low == Leaf.High) {
// Make the seteq instruction...
Comp = new ICmpInst(*NewLeaf, ICmpInst::ICMP_EQ, Val,
Leaf.Low, "SwitchLeaf");
} else {
// Make range comparison
- if (cast<ConstantInt>(Leaf.Low)->isMinValue(true /*isSigned*/)) {
+ if (Leaf.Low->isMinValue(true /*isSigned*/)) {
// Val >= Min && Val <= Hi --> Val <= Hi
Comp = new ICmpInst(*NewLeaf, ICmpInst::ICMP_SLE, Val, Leaf.High,
"SwitchLeaf");
- } else if (cast<ConstantInt>(Leaf.Low)->isZero()) {
+ } else if (Leaf.Low->isZero()) {
// Val >= 0 && Val <= Hi --> Val <=u Hi
Comp = new ICmpInst(*NewLeaf, ICmpInst::ICMP_ULE, Val, Leaf.High,
"SwitchLeaf");
for (BasicBlock::iterator I = Succ->begin(); isa<PHINode>(I); ++I) {
PHINode* PN = cast<PHINode>(I);
// Remove all but one incoming entries from the cluster
- uint64_t Range = cast<ConstantInt>(Leaf.High)->getSExtValue() -
- cast<ConstantInt>(Leaf.Low)->getSExtValue();
+ uint64_t Range = Leaf.High->getSExtValue() -
+ Leaf.Low->getSExtValue();
for (uint64_t j = 0; j < Range; ++j) {
PN->removeIncomingValue(OrigBlock);
}
// Clusterify - Transform simple list of Cases into list of CaseRange's
unsigned LowerSwitch::Clusterify(CaseVector& Cases, SwitchInst *SI) {
-
- IntegersSubsetToBB TheClusterifier;
+ unsigned numCmps = 0;
// Start with "simple" cases
- for (SwitchInst::CaseIt i = SI->case_begin(), e = SI->case_end();
- i != e; ++i) {
- BasicBlock *SuccBB = i.getCaseSuccessor();
- IntegersSubset CaseRanges = i.getCaseValueEx();
- TheClusterifier.add(CaseRanges, SuccBB);
- }
+ for (SwitchInst::CaseIt i = SI->case_begin(), e = SI->case_end(); i != e; ++i)
+ Cases.push_back(CaseRange(i.getCaseValue(), i.getCaseValue(),
+ i.getCaseSuccessor()));
- TheClusterifier.optimize();
-
- size_t numCmps = 0;
- for (IntegersSubsetToBB::RangeIterator i = TheClusterifier.begin(),
- e = TheClusterifier.end(); i != e; ++i, ++numCmps) {
- const IntegersSubsetToBB::RangeTy &R = i->first;
- BasicBlock *S = i->second;
-
- // FIXME: Currently work with ConstantInt based numbers.
- // Changing it to APInt based is a pretty heavy for this commit.
- Cases.push_back(CaseRange(R.getLow().toConstantInt(),
- R.getHigh().toConstantInt(), S));
- if (R.isSingleNumber())
+ std::sort(Cases.begin(), Cases.end(), CaseCmp());
+
+ // Merge case into clusters
+ if (Cases.size()>=2)
+ for (CaseItr I = Cases.begin(), J = std::next(Cases.begin());
+ J != Cases.end();) {
+ int64_t nextValue = J->Low->getSExtValue();
+ int64_t currentValue = I->High->getSExtValue();
+ BasicBlock* nextBB = J->BB;
+ BasicBlock* currentBB = I->BB;
+
+ // If the two neighboring cases go to the same destination, merge them
+ // into a single case.
+ if ((nextValue-currentValue==1) && (currentBB == nextBB)) {
+ I->High = J->High;
+ J = Cases.erase(J);
+ } else {
+ I = J++;
+ }
+ }
+
+ for (CaseItr I=Cases.begin(), E=Cases.end(); I!=E; ++I, ++numCmps) {
+ if (I->Low != I->High)
// A range counts double, since it requires two compares.
++numCmps;
}
- return numCmps;
+ return numCmps;
}
// processSwitchInst - Replace the specified switch instruction with a sequence
Value *Val = SI->getCondition(); // The value we are switching on...
BasicBlock* Default = SI->getDefaultDest();
- // If there is only the default destination, don't bother with the code below.
+ // If there is only the default destination, just branch.
if (!SI->getNumCases()) {
- BranchInst::Create(SI->getDefaultDest(), CurBlock);
- CurBlock->getInstList().erase(SI);
+ BranchInst::Create(Default, CurBlock);
+ SI->eraseFromParent();
return;
}
+ // Prepare cases vector.
+ CaseVector Cases;
+ unsigned numCmps = Clusterify(Cases, SI);
+ DEBUG(dbgs() << "Clusterify finished. Total clusters: " << Cases.size()
+ << ". Total compares: " << numCmps << "\n");
+ DEBUG(dbgs() << "Cases: " << Cases << "\n");
+ (void)numCmps;
+
+ ConstantInt *LowerBound = nullptr;
+ ConstantInt *UpperBound = nullptr;
+ std::vector<IntRange> UnreachableRanges;
+
+ if (isa<UnreachableInst>(Default->getFirstNonPHIOrDbg())) {
+ // Make the bounds tightly fitted around the case value range, becase we
+ // know that the value passed to the switch must be exactly one of the case
+ // values.
+ assert(!Cases.empty());
+ LowerBound = Cases.front().Low;
+ UpperBound = Cases.back().High;
+
+ DenseMap<BasicBlock *, unsigned> Popularity;
+ unsigned MaxPop = 0;
+ BasicBlock *PopSucc = nullptr;
+
+ IntRange R = { INT64_MIN, INT64_MAX };
+ UnreachableRanges.push_back(R);
+ for (const auto &I : Cases) {
+ int64_t Low = I.Low->getSExtValue();
+ int64_t High = I.High->getSExtValue();
+
+ IntRange &LastRange = UnreachableRanges.back();
+ if (LastRange.Low == Low) {
+ // There is nothing left of the previous range.
+ UnreachableRanges.pop_back();
+ } else {
+ // Terminate the previous range.
+ assert(Low > LastRange.Low);
+ LastRange.High = Low - 1;
+ }
+ if (High != INT64_MAX) {
+ IntRange R = { High + 1, INT64_MAX };
+ UnreachableRanges.push_back(R);
+ }
+
+ // Count popularity.
+ int64_t N = High - Low + 1;
+ unsigned &Pop = Popularity[I.BB];
+ if ((Pop += N) > MaxPop) {
+ MaxPop = Pop;
+ PopSucc = I.BB;
+ }
+ }
+#ifndef NDEBUG
+ /* UnreachableRanges should be sorted and the ranges non-adjacent. */
+ for (auto I = UnreachableRanges.begin(), E = UnreachableRanges.end();
+ I != E; ++I) {
+ assert(I->Low <= I->High);
+ auto Next = I + 1;
+ if (Next != E) {
+ assert(Next->Low > I->High);
+ }
+ }
+#endif
+
+ // Use the most popular block as the new default, reducing the number of
+ // cases.
+ assert(MaxPop > 0 && PopSucc);
+ Default = PopSucc;
+ for (CaseItr I = Cases.begin(); I != Cases.end();) {
+ if (I->BB == PopSucc)
+ I = Cases.erase(I);
+ else
+ ++I;
+ }
+
+ // If there are no cases left, just branch.
+ if (Cases.empty()) {
+ BranchInst::Create(Default, CurBlock);
+ SI->eraseFromParent();
+ return;
+ }
+ }
+
// Create a new, empty default block so that the new hierarchy of
// if-then statements go to this and the PHI nodes are happy.
- BasicBlock* NewDefault = BasicBlock::Create(SI->getContext(), "NewDefault");
+ BasicBlock *NewDefault = BasicBlock::Create(SI->getContext(), "NewDefault");
F->getBasicBlockList().insert(Default, NewDefault);
-
BranchInst::Create(Default, NewDefault);
// If there is an entry in any PHI nodes for the default edge, make sure
PN->setIncomingBlock((unsigned)BlockIdx, NewDefault);
}
- // Prepare cases vector.
- CaseVector Cases;
- unsigned numCmps = Clusterify(Cases, SI);
-
- DEBUG(dbgs() << "Clusterify finished. Total clusters: " << Cases.size()
- << ". Total compares: " << numCmps << "\n");
- DEBUG(dbgs() << "Cases: " << Cases << "\n");
- (void)numCmps;
-
- BasicBlock* SwitchBlock = switchConvert(Cases.begin(), Cases.end(), Val,
- OrigBlock, NewDefault);
+ BasicBlock *SwitchBlock =
+ switchConvert(Cases.begin(), Cases.end(), LowerBound, UpperBound, Val,
+ OrigBlock, OrigBlock, NewDefault, UnreachableRanges);
// Branch to our shiny new if-then stuff...
BranchInst::Create(SwitchBlock, OrigBlock);
// We are now done with the switch instruction, delete it.
+ BasicBlock *OldDefault = SI->getDefaultDest();
CurBlock->getInstList().erase(SI);
+
+ // If the Default block has no more predecessors just remove it.
+ if (pred_begin(OldDefault) == pred_end(OldDefault))
+ DeleteDeadBlock(OldDefault);
}