void RegionGenerator::addOperandToPHI(ScopStmt &Stmt, const PHINode *PHI,
PHINode *PHICopy, BasicBlock *IncomingBB,
ValueMapT &GlobalMap,
LoopToScevMapT <S) {
Region *StmtR = Stmt.getRegion();
// If the incoming block was not yet copied mark this PHI as incomplete.
// Once the block will be copied the incoming value will be added.
BasicBlock *BBCopy = BlockMap[IncomingBB];
if (!BBCopy) {
assert(StmtR->contains(IncomingBB) &&
"Bad incoming block for PHI in non-affine region");
IncompletePHINodeMap[IncomingBB].push_back(std::make_pair(PHI, PHICopy));
return;
}
Value *OpCopy = nullptr;
if (StmtR->contains(IncomingBB)) {
assert(RegionMaps.count(BBCopy) &&
"Incoming PHI block did not have a BBMap");
ValueMapT &BBCopyMap = RegionMaps[BBCopy];
Value *Op = PHI->getIncomingValueForBlock(IncomingBB);
OpCopy =
getNewValue(Stmt, Op, BBCopyMap, GlobalMap, LTS, getLoopForInst(PHI));
} else {
if (PHICopy->getBasicBlockIndex(BBCopy) >= 0)
return;
AllocaInst *PHIOpAddr =
getOrCreateAlloca(const_cast<PHINode *>(PHI), PHIOpMap, ".phiops");
OpCopy = new LoadInst(PHIOpAddr, PHIOpAddr->getName() + ".reload",
BlockMap[IncomingBB]->getTerminator());
}
assert(OpCopy && "Incoming PHI value was not copied properly");
assert(BBCopy && "Incoming PHI block was not copied properly");
PHICopy->addIncoming(OpCopy, BBCopy);
}
void BlockGenerator::copyInstruction(ScopStmt &Stmt, const Instruction *Inst,
ValueMapT &BBMap, ValueMapT &GlobalMap,
LoopToScevMapT <S) {
// First check for possible scalar dependences for this instruction.
generateScalarLoads(Stmt, Inst, BBMap);
// Terminator instructions control the control flow. They are explicitly
// expressed in the clast and do not need to be copied.
if (Inst->isTerminator())
return;
Loop *L = getLoopForInst(Inst);
if ((Stmt.isBlockStmt() || !Stmt.getRegion()->contains(L)) &&
canSynthesize(Inst, &LI, &SE, &Stmt.getParent()->getRegion())) {
Value *NewValue = getNewValue(Stmt, Inst, BBMap, GlobalMap, LTS, L);
BBMap[Inst] = NewValue;
return;
}
if (const LoadInst *Load = dyn_cast<LoadInst>(Inst)) {
Value *NewLoad = generateScalarLoad(Stmt, Load, BBMap, GlobalMap, LTS);
// Compute NewLoad before its insertion in BBMap to make the insertion
// deterministic.
BBMap[Load] = NewLoad;
return;
}
if (const StoreInst *Store = dyn_cast<StoreInst>(Inst)) {
Value *NewStore = generateScalarStore(Stmt, Store, BBMap, GlobalMap, LTS);
// Compute NewStore before its insertion in BBMap to make the insertion
// deterministic.
BBMap[Store] = NewStore;
return;
}
if (const PHINode *PHI = dyn_cast<PHINode>(Inst)) {
copyPHIInstruction(Stmt, PHI, BBMap, GlobalMap, LTS);
return;
}
// Skip some special intrinsics for which we do not adjust the semantics to
// the new schedule. All others are handled like every other instruction.
if (auto *IT = dyn_cast<IntrinsicInst>(Inst)) {
switch (IT->getIntrinsicID()) {
// Lifetime markers are ignored.
case llvm::Intrinsic::lifetime_start:
case llvm::Intrinsic::lifetime_end:
// Invariant markers are ignored.
case llvm::Intrinsic::invariant_start:
case llvm::Intrinsic::invariant_end:
// Some misc annotations are ignored.
case llvm::Intrinsic::var_annotation:
case llvm::Intrinsic::ptr_annotation:
case llvm::Intrinsic::annotation:
case llvm::Intrinsic::donothing:
case llvm::Intrinsic::assume:
case llvm::Intrinsic::expect:
return;
default:
// Other intrinsics are copied.
break;
}
}
copyInstScalar(Stmt, Inst, BBMap, GlobalMap, LTS);
}
void RegionGenerator::generateScalarStores(ScopStmt &Stmt, BasicBlock *BB,
ValueMapT &BBMap,
ValueMapT &GlobalMap) {
const Region &R = Stmt.getParent()->getRegion();
Region *StmtR = Stmt.getRegion();
assert(StmtR && "Block statements need to use the generateScalarStores() "
"function in the BlockGenerator");
BasicBlock *ExitBB = StmtR->getExit();
// For region statements three kinds of scalar stores exists:
// (1) A definition used by a non-phi instruction outside the region.
// (2) A phi-instruction in the region entry.
// (3) A write to a phi instruction in the region exit.
// The last case is the tricky one since we do not know anymore which
// predecessor of the exit needs to store the operand value that doesn't
// have a definition in the region. Therefore, we have to check in each
// block in the region if we should store the value or not.
// Iterate over all accesses in the given statement.
for (MemoryAccess *MA : Stmt) {
// Skip non-scalar and read accesses.
if (!MA->isScalar() || MA->isRead())
continue;
Instruction *ScalarBase = cast<Instruction>(MA->getBaseAddr());
Instruction *ScalarInst = MA->getAccessInstruction();
PHINode *ScalarBasePHI = dyn_cast<PHINode>(ScalarBase);
Value *ScalarValue = nullptr;
AllocaInst *ScalarAddr = nullptr;
if (!ScalarBasePHI) {
// Case (1)
ScalarAddr = getOrCreateAlloca(ScalarBase, ScalarMap, ".s2a");
ScalarValue = ScalarInst;
} else if (ScalarBasePHI->getParent() != ExitBB) {
// Case (2)
assert(ScalarBasePHI->getParent() == StmtR->getEntry() &&
"Bad PHI self write in non-affine region");
assert(ScalarBase == ScalarInst &&
"Bad PHI self write in non-affine region");
ScalarAddr = getOrCreateAlloca(ScalarBase, ScalarMap, ".s2a");
ScalarValue = ScalarInst;
} else {
int PHIIdx = ScalarBasePHI->getBasicBlockIndex(BB);
// Skip accesses we will not handle in this basic block but in another one
// in the statement region.
if (PHIIdx < 0)
continue;
// Case (3)
ScalarAddr = getOrCreateAlloca(ScalarBase, PHIOpMap, ".phiops");
ScalarValue = ScalarBasePHI->getIncomingValue(PHIIdx);
}
ScalarValue =
getNewScalarValue(ScalarValue, R, ScalarMap, BBMap, GlobalMap);
Builder.CreateStore(ScalarValue, ScalarAddr);
}
}
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());
}