bool VectorBlockGenerator::extractScalarValues(const Instruction *Inst,
ValueMapT &VectorMap,
VectorValueMapT &ScalarMaps) {
bool HasVectorOperand = false;
int VectorWidth = getVectorWidth();
for (Value *Operand : Inst->operands()) {
ValueMapT::iterator VecOp = VectorMap.find(Operand);
if (VecOp == VectorMap.end())
continue;
HasVectorOperand = true;
Value *NewVector = VecOp->second;
for (int i = 0; i < VectorWidth; ++i) {
ValueMapT &SM = ScalarMaps[i];
// If there is one scalar extracted, all scalar elements should have
// already been extracted by the code here. So no need to check for the
// existance of all of them.
if (SM.count(Operand))
break;
SM[Operand] =
Builder.CreateExtractElement(NewVector, Builder.getInt32(i));
}
}
return HasVectorOperand;
}
bool VectorBlockGenerator::hasVectorOperands(const Instruction *Inst,
ValueMapT &VectorMap) {
for (Value *Operand : Inst->operands())
if (VectorMap.count(Operand))
return true;
return false;
}
bool VectorBlockGenerator::hasVectorOperands(const Instruction *Inst,
ValueMapT &VectorMap) {
for (Instruction::const_op_iterator OI = Inst->op_begin(),
OE = Inst->op_end();
OI != OE; ++OI)
if (VectorMap.count(*OI))
return true;
return false;
}
const SCEV *visitUnknown(const SCEVUnknown *E) {
// If a value mapping was given try if the underlying value is remapped.
Value *NewVal = VMap ? VMap->lookup(E->getValue()) : nullptr;
if (NewVal) {
auto *NewE = SE.getSCEV(NewVal);
// While the mapped value might be different the SCEV representation might
// not be. To this end we will check before we go into recursion here.
if (E != NewE)
return visit(NewE);
}
Instruction *Inst = dyn_cast<Instruction>(E->getValue());
Instruction *IP;
if (Inst && !R.contains(Inst))
IP = Inst;
else if (Inst && RTCBB->getParent() == Inst->getFunction())
IP = RTCBB->getTerminator();
else
IP = RTCBB->getParent()->getEntryBlock().getTerminator();
if (!Inst || (Inst->getOpcode() != Instruction::SRem &&
Inst->getOpcode() != Instruction::SDiv))
return visitGenericInst(E, Inst, IP);
const SCEV *LHSScev = SE.getSCEV(Inst->getOperand(0));
const SCEV *RHSScev = SE.getSCEV(Inst->getOperand(1));
if (!SE.isKnownNonZero(RHSScev))
RHSScev = SE.getUMaxExpr(RHSScev, SE.getConstant(E->getType(), 1));
Value *LHS = expandCodeFor(LHSScev, E->getType(), IP);
Value *RHS = expandCodeFor(RHSScev, E->getType(), IP);
Inst = BinaryOperator::Create((Instruction::BinaryOps)Inst->getOpcode(),
LHS, RHS, Inst->getName() + Name, IP);
return SE.getSCEV(Inst);
}
void RegionGenerator::copyStmt(ScopStmt &Stmt, ValueMapT &GlobalMap,
LoopToScevMapT <S) {
assert(Stmt.isRegionStmt() &&
"Only region statements can be copied by the block generator");
// Forget all old mappings.
BlockMap.clear();
RegionMaps.clear();
IncompletePHINodeMap.clear();
// The region represented by the statement.
Region *R = Stmt.getRegion();
// Create a dedicated entry for the region where we can reload all demoted
// inputs.
BasicBlock *EntryBB = R->getEntry();
BasicBlock *EntryBBCopy =
SplitBlock(Builder.GetInsertBlock(), Builder.GetInsertPoint(), &DT, &LI);
EntryBBCopy->setName("polly.stmt." + EntryBB->getName() + ".entry");
Builder.SetInsertPoint(EntryBBCopy->begin());
for (auto PI = pred_begin(EntryBB), PE = pred_end(EntryBB); PI != PE; ++PI)
if (!R->contains(*PI))
BlockMap[*PI] = EntryBBCopy;
// Iterate over all blocks in the region in a breadth-first search.
std::deque<BasicBlock *> Blocks;
SmallPtrSet<BasicBlock *, 8> SeenBlocks;
Blocks.push_back(EntryBB);
SeenBlocks.insert(EntryBB);
while (!Blocks.empty()) {
BasicBlock *BB = Blocks.front();
Blocks.pop_front();
// First split the block and update dominance information.
BasicBlock *BBCopy = splitBB(BB);
BasicBlock *BBCopyIDom = repairDominance(BB, BBCopy);
// In order to remap PHI nodes we store also basic block mappings.
BlockMap[BB] = BBCopy;
// Get the mapping for this block and initialize it with the mapping
// available at its immediate dominator (in the new region).
ValueMapT &RegionMap = RegionMaps[BBCopy];
RegionMap = RegionMaps[BBCopyIDom];
// Copy the block with the BlockGenerator.
copyBB(Stmt, BB, BBCopy, RegionMap, GlobalMap, LTS);
// In order to remap PHI nodes we store also basic block mappings.
BlockMap[BB] = BBCopy;
// Add values to incomplete PHI nodes waiting for this block to be copied.
for (const PHINodePairTy &PHINodePair : IncompletePHINodeMap[BB])
addOperandToPHI(Stmt, PHINodePair.first, PHINodePair.second, BB,
GlobalMap, LTS);
IncompletePHINodeMap[BB].clear();
// And continue with new successors inside the region.
for (auto SI = succ_begin(BB), SE = succ_end(BB); SI != SE; SI++)
if (R->contains(*SI) && SeenBlocks.insert(*SI).second)
Blocks.push_back(*SI);
}
// Now create a new dedicated region exit block and add it to the region map.
BasicBlock *ExitBBCopy =
SplitBlock(Builder.GetInsertBlock(), Builder.GetInsertPoint(), &DT, &LI);
ExitBBCopy->setName("polly.stmt." + R->getExit()->getName() + ".exit");
BlockMap[R->getExit()] = ExitBBCopy;
repairDominance(R->getExit(), ExitBBCopy);
// As the block generator doesn't handle control flow we need to add the
// region control flow by hand after all blocks have been copied.
for (BasicBlock *BB : SeenBlocks) {
BranchInst *BI = cast<BranchInst>(BB->getTerminator());
BasicBlock *BBCopy = BlockMap[BB];
Instruction *BICopy = BBCopy->getTerminator();
ValueMapT &RegionMap = RegionMaps[BBCopy];
RegionMap.insert(BlockMap.begin(), BlockMap.end());
Builder.SetInsertPoint(BBCopy);
copyInstScalar(Stmt, BI, RegionMap, GlobalMap, LTS);
BICopy->eraseFromParent();
}
// Add counting PHI nodes to all loops in the region that can be used as
// replacement for SCEVs refering to the old loop.
for (BasicBlock *BB : SeenBlocks) {
Loop *L = LI.getLoopFor(BB);
if (L == nullptr || L->getHeader() != BB)
continue;
BasicBlock *BBCopy = BlockMap[BB];
Value *NullVal = Builder.getInt32(0);
PHINode *LoopPHI =
PHINode::Create(Builder.getInt32Ty(), 2, "polly.subregion.iv");
Instruction *LoopPHIInc = BinaryOperator::CreateAdd(
LoopPHI, Builder.getInt32(1), "polly.subregion.iv.inc");
LoopPHI->insertBefore(BBCopy->begin());
LoopPHIInc->insertBefore(BBCopy->getTerminator());
for (auto *PredBB : make_range(pred_begin(BB), pred_end(BB))) {
if (!R->contains(PredBB))
continue;
if (L->contains(PredBB))
LoopPHI->addIncoming(LoopPHIInc, BlockMap[PredBB]);
else
LoopPHI->addIncoming(NullVal, BlockMap[PredBB]);
}
for (auto *PredBBCopy : make_range(pred_begin(BBCopy), pred_end(BBCopy)))
if (LoopPHI->getBasicBlockIndex(PredBBCopy) < 0)
LoopPHI->addIncoming(NullVal, PredBBCopy);
LTS[L] = SE.getUnknown(LoopPHI);
}
// Add all mappings from the region to the global map so outside uses will use
// the copied instructions.
for (auto &BBMap : RegionMaps)
GlobalMap.insert(BBMap.second.begin(), BBMap.second.end());
// Reset the old insert point for the build.
Builder.SetInsertPoint(ExitBBCopy->begin());
}