Optional<Value *> LoopPredication::widenICmpRangeCheckDecrementingLoop(
LoopPredication::LoopICmp LatchCheck, LoopPredication::LoopICmp RangeCheck,
SCEVExpander &Expander, IRBuilder<> &Builder) {
auto *Ty = RangeCheck.IV->getType();
const SCEV *GuardStart = RangeCheck.IV->getStart();
const SCEV *GuardLimit = RangeCheck.Limit;
const SCEV *LatchLimit = LatchCheck.Limit;
if (!CanExpand(GuardStart) || !CanExpand(GuardLimit) ||
!CanExpand(LatchLimit)) {
LLVM_DEBUG(dbgs() << "Can't expand limit check!\n");
return None;
}
// The decrement of the latch check IV should be the same as the
// rangeCheckIV.
auto *PostDecLatchCheckIV = LatchCheck.IV->getPostIncExpr(*SE);
if (RangeCheck.IV != PostDecLatchCheckIV) {
LLVM_DEBUG(dbgs() << "Not the same. PostDecLatchCheckIV: "
<< *PostDecLatchCheckIV
<< " and RangeCheckIV: " << *RangeCheck.IV << "\n");
return None;
}
// Generate the widened condition for CountDownLoop:
// guardStart u< guardLimit &&
// latchLimit <pred> 1.
// See the header comment for reasoning of the checks.
Instruction *InsertAt = Preheader->getTerminator();
auto LimitCheckPred =
ICmpInst::getFlippedStrictnessPredicate(LatchCheck.Pred);
auto *FirstIterationCheck = expandCheck(Expander, Builder, ICmpInst::ICMP_ULT,
GuardStart, GuardLimit, InsertAt);
auto *LimitCheck = expandCheck(Expander, Builder, LimitCheckPred, LatchLimit,
SE->getOne(Ty), InsertAt);
return Builder.CreateAnd(FirstIterationCheck, LimitCheck);
}
Value* AndExpression::getValue() {
assert(leftExpression != NULL);
assert(rightExpression != NULL);
IRBuilder<>* builder = codegen::getBuilder();
return builder->CreateAnd(leftExpression->getValue(), rightExpression->getValue());
}
Optional<Value *> LoopPredication::widenICmpRangeCheckIncrementingLoop(
LoopPredication::LoopICmp LatchCheck, LoopPredication::LoopICmp RangeCheck,
SCEVExpander &Expander, IRBuilder<> &Builder) {
auto *Ty = RangeCheck.IV->getType();
// Generate the widened condition for the forward loop:
// guardStart u< guardLimit &&
// latchLimit <pred> guardLimit - 1 - guardStart + latchStart
// where <pred> depends on the latch condition predicate. See the file
// header comment for the reasoning.
// guardLimit - guardStart + latchStart - 1
const SCEV *GuardStart = RangeCheck.IV->getStart();
const SCEV *GuardLimit = RangeCheck.Limit;
const SCEV *LatchStart = LatchCheck.IV->getStart();
const SCEV *LatchLimit = LatchCheck.Limit;
// guardLimit - guardStart + latchStart - 1
const SCEV *RHS =
SE->getAddExpr(SE->getMinusSCEV(GuardLimit, GuardStart),
SE->getMinusSCEV(LatchStart, SE->getOne(Ty)));
if (!CanExpand(GuardStart) || !CanExpand(GuardLimit) ||
!CanExpand(LatchLimit) || !CanExpand(RHS)) {
LLVM_DEBUG(dbgs() << "Can't expand limit check!\n");
return None;
}
auto LimitCheckPred =
ICmpInst::getFlippedStrictnessPredicate(LatchCheck.Pred);
LLVM_DEBUG(dbgs() << "LHS: " << *LatchLimit << "\n");
LLVM_DEBUG(dbgs() << "RHS: " << *RHS << "\n");
LLVM_DEBUG(dbgs() << "Pred: " << LimitCheckPred << "\n");
Instruction *InsertAt = Preheader->getTerminator();
auto *LimitCheck =
expandCheck(Expander, Builder, LimitCheckPred, LatchLimit, RHS, InsertAt);
auto *FirstIterationCheck = expandCheck(Expander, Builder, RangeCheck.Pred,
GuardStart, GuardLimit, InsertAt);
return Builder.CreateAnd(FirstIterationCheck, LimitCheck);
}
void MmixLlvm::Private::emitAndnl(VerticeContext& vctx, IRBuilder<>& builder, MXByte xarg, MXWyde yzarg)
{
Value* result = builder.CreateAnd(vctx.getRegister( xarg), builder.getInt64((MXOcta) yzarg));
assignRegister(vctx, builder, xarg, result);
builder.CreateBr(vctx.getOCExit());
}
/// If \param [in] BB has more than one predecessor that is a conditional
/// branch, attempt to use parallel and/or for the branch condition. \returns
/// true on success.
///
/// Before:
/// ......
/// %cmp10 = fcmp une float %tmp1, %tmp2
/// br i1 %cmp1, label %if.then, label %lor.rhs
///
/// lor.rhs:
/// ......
/// %cmp11 = fcmp une float %tmp3, %tmp4
/// br i1 %cmp11, label %if.then, label %ifend
///
/// if.end: // the merge block
/// ......
///
/// if.then: // has two predecessors, both of them contains conditional branch.
/// ......
/// br label %if.end;
///
/// After:
/// ......
/// %cmp10 = fcmp une float %tmp1, %tmp2
/// ......
/// %cmp11 = fcmp une float %tmp3, %tmp4
/// %cmp12 = or i1 %cmp10, %cmp11 // parallel-or mode.
/// br i1 %cmp12, label %if.then, label %ifend
///
/// if.end:
/// ......
///
/// if.then:
/// ......
/// br label %if.end;
///
/// Current implementation handles two cases.
/// Case 1: \param BB is on the else-path.
///
/// BB1
/// / |
/// BB2 |
/// / \ |
/// BB3 \ | where, BB1, BB2 contain conditional branches.
/// \ | / BB3 contains unconditional branch.
/// \ | / BB4 corresponds to \param BB which is also the merge.
/// BB => BB4
///
///
/// Corresponding source code:
///
/// if (a == b && c == d)
/// statement; // BB3
///
/// Case 2: \param BB BB is on the then-path.
///
/// BB1
/// / |
/// | BB2
/// \ / | where BB1, BB2 contain conditional branches.
/// BB => BB3 | BB3 contains unconditiona branch and corresponds
/// \ / to \param BB. BB4 is the merge.
/// BB4
///
/// Corresponding source code:
///
/// if (a == b || c == d)
/// statement; // BB3
///
/// In both cases, \param BB is the common successor of conditional branches.
/// In Case 1, \param BB (BB4) has an unconditional branch (BB3) as
/// its predecessor. In Case 2, \param BB (BB3) only has conditional branches
/// as its predecessors.
///
bool FlattenCFGOpt::FlattenParallelAndOr(BasicBlock *BB, IRBuilder<> &Builder,
Pass *P) {
PHINode *PHI = dyn_cast<PHINode>(BB->begin());
if (PHI)
return false; // For simplicity, avoid cases containing PHI nodes.
BasicBlock *LastCondBlock = NULL;
BasicBlock *FirstCondBlock = NULL;
BasicBlock *UnCondBlock = NULL;
int Idx = -1;
// Check predecessors of \param BB.
SmallPtrSet<BasicBlock *, 16> Preds(pred_begin(BB), pred_end(BB));
for (SmallPtrSetIterator<BasicBlock *> PI = Preds.begin(), PE = Preds.end();
PI != PE; ++PI) {
BasicBlock *Pred = *PI;
BranchInst *PBI = dyn_cast<BranchInst>(Pred->getTerminator());
// All predecessors should terminate with a branch.
if (!PBI)
return false;
BasicBlock *PP = Pred->getSinglePredecessor();
if (PBI->isUnconditional()) {
// Case 1: Pred (BB3) is an unconditional block, it should
// have a single predecessor (BB2) that is also a predecessor
// of \param BB (BB4) and should not have address-taken.
// There should exist only one such unconditional
// branch among the predecessors.
if (UnCondBlock || !PP || (Preds.count(PP) == 0) ||
Pred->hasAddressTaken())
return false;
UnCondBlock = Pred;
continue;
}
// Only conditional branches are allowed beyond this point.
assert(PBI->isConditional());
// Condition's unique use should be the branch instruction.
Value *PC = PBI->getCondition();
if (!PC || !PC->hasOneUse())
return false;
if (PP && Preds.count(PP)) {
// These are internal condition blocks to be merged from, e.g.,
// BB2 in both cases.
// Should not be address-taken.
if (Pred->hasAddressTaken())
return false;
// Instructions in the internal condition blocks should be safe
// to hoist up.
for (BasicBlock::iterator BI = Pred->begin(), BE = PBI; BI != BE;) {
Instruction *CI = BI++;
if (isa<PHINode>(CI) || !isSafeToSpeculativelyExecute(CI))
return false;
}
} else {
// This is the condition block to be merged into, e.g. BB1 in
// both cases.
if (FirstCondBlock)
return false;
FirstCondBlock = Pred;
}
// Find whether BB is uniformly on the true (or false) path
// for all of its predecessors.
BasicBlock *PS1 = PBI->getSuccessor(0);
BasicBlock *PS2 = PBI->getSuccessor(1);
BasicBlock *PS = (PS1 == BB) ? PS2 : PS1;
int CIdx = (PS1 == BB) ? 0 : 1;
if (Idx == -1)
Idx = CIdx;
else if (CIdx != Idx)
return false;
// PS is the successor which is not BB. Check successors to identify
// the last conditional branch.
if (Preds.count(PS) == 0) {
// Case 2.
LastCondBlock = Pred;
} else {
// Case 1
BranchInst *BPS = dyn_cast<BranchInst>(PS->getTerminator());
if (BPS && BPS->isUnconditional()) {
// Case 1: PS(BB3) should be an unconditional branch.
LastCondBlock = Pred;
}
}
}
if (!FirstCondBlock || !LastCondBlock || (FirstCondBlock == LastCondBlock))
return false;
TerminatorInst *TBB = LastCondBlock->getTerminator();
BasicBlock *PS1 = TBB->getSuccessor(0);
BasicBlock *PS2 = TBB->getSuccessor(1);
BranchInst *PBI1 = dyn_cast<BranchInst>(PS1->getTerminator());
BranchInst *PBI2 = dyn_cast<BranchInst>(PS2->getTerminator());
// If PS1 does not jump into PS2, but PS2 jumps into PS1,
// attempt branch inversion.
if (!PBI1 || !PBI1->isUnconditional() ||
(PS1->getTerminator()->getSuccessor(0) != PS2)) {
// Check whether PS2 jumps into PS1.
if (!PBI2 || !PBI2->isUnconditional() ||
(PS2->getTerminator()->getSuccessor(0) != PS1))
return false;
// Do branch inversion.
BasicBlock *CurrBlock = LastCondBlock;
bool EverChanged = false;
while (1) {
BranchInst *BI = dyn_cast<BranchInst>(CurrBlock->getTerminator());
CmpInst *CI = dyn_cast<CmpInst>(BI->getCondition());
CmpInst::Predicate Predicate = CI->getPredicate();
// Cannonicalize icmp_ne -> icmp_eq, fcmp_one -> fcmp_oeq
if ((Predicate == CmpInst::ICMP_NE) || (Predicate == CmpInst::FCMP_ONE)) {
CI->setPredicate(ICmpInst::getInversePredicate(Predicate));
BI->swapSuccessors();
EverChanged = true;
}
if (CurrBlock == FirstCondBlock)
break;
CurrBlock = CurrBlock->getSinglePredecessor();
}
return EverChanged;
}
// PS1 must have a conditional branch.
if (!PBI1 || !PBI1->isUnconditional())
return false;
// PS2 should not contain PHI node.
PHI = dyn_cast<PHINode>(PS2->begin());
if (PHI)
return false;
// Do the transformation.
BasicBlock *CB;
BranchInst *PBI = dyn_cast<BranchInst>(FirstCondBlock->getTerminator());
bool Iteration = true;
BasicBlock *SaveInsertBB = Builder.GetInsertBlock();
BasicBlock::iterator SaveInsertPt = Builder.GetInsertPoint();
Value *PC = PBI->getCondition();
do {
CB = PBI->getSuccessor(1 - Idx);
// Delete the conditional branch.
FirstCondBlock->getInstList().pop_back();
FirstCondBlock->getInstList()
.splice(FirstCondBlock->end(), CB->getInstList());
PBI = cast<BranchInst>(FirstCondBlock->getTerminator());
Value *CC = PBI->getCondition();
// Merge conditions.
Builder.SetInsertPoint(PBI);
Value *NC;
if (Idx == 0)
// Case 2, use parallel or.
NC = Builder.CreateOr(PC, CC);
else
// Case 1, use parallel and.
NC = Builder.CreateAnd(PC, CC);
PBI->replaceUsesOfWith(CC, NC);
PC = NC;
if (CB == LastCondBlock)
Iteration = false;
// Remove internal conditional branches.
CB->dropAllReferences();
// make CB unreachable and let downstream to delete the block.
new UnreachableInst(CB->getContext(), CB);
} while (Iteration);
Builder.SetInsertPoint(SaveInsertBB, SaveInsertPt);
DEBUG(dbgs() << "Use parallel and/or in:\n" << *FirstCondBlock);
return true;
}
static Value* emitCond(IRBuilder<>& builder, Value* arg) {
return builder.CreateICmpNE(builder.CreateAnd(arg, builder.getInt64(1)), builder.getInt64(0));
}