namespace {
class AtomicExpand: public FunctionPass {
const TargetMachine *TM;
+ const TargetLowering *TLI;
public:
static char ID; // Pass identification, replacement for typeid
explicit AtomicExpand(const TargetMachine *TM = nullptr)
- : FunctionPass(ID), TM(TM) {
+ : FunctionPass(ID), TM(TM), TLI(nullptr) {
initializeAtomicExpandPass(*PassRegistry::getPassRegistry());
}
bool expandAtomicRMWToLLSC(AtomicRMWInst *AI);
bool expandAtomicRMWToCmpXchg(AtomicRMWInst *AI);
bool expandAtomicCmpXchg(AtomicCmpXchgInst *CI);
+ bool isIdempotentRMW(AtomicRMWInst *AI);
+ bool simplifyIdempotentRMW(AtomicRMWInst *AI);
};
}
}
bool AtomicExpand::runOnFunction(Function &F) {
- if (!TM || !TM->getSubtargetImpl()->enableAtomicExpand())
+ if (!TM || !TM->getSubtargetImpl(F)->enableAtomicExpand())
return false;
- auto TargetLowering = TM->getSubtargetImpl()->getTargetLowering();
+ TLI = TM->getSubtargetImpl(F)->getTargetLowering();
SmallVector<Instruction *, 1> AtomicInsts;
auto FenceOrdering = Monotonic;
bool IsStore, IsLoad;
- if (TargetLowering->getInsertFencesForAtomic()) {
+ if (TLI->getInsertFencesForAtomic()) {
if (LI && isAtLeastAcquire(LI->getOrdering())) {
FenceOrdering = LI->getOrdering();
LI->setOrdering(Monotonic);
FenceOrdering = RMWI->getOrdering();
RMWI->setOrdering(Monotonic);
IsStore = IsLoad = true;
- } else if (CASI && !TargetLowering->hasLoadLinkedStoreConditional() &&
- (isAtLeastRelease(CASI->getSuccessOrdering()) ||
- isAtLeastAcquire(CASI->getSuccessOrdering()))) {
+ } else if (CASI && !TLI->hasLoadLinkedStoreConditional() &&
+ (isAtLeastRelease(CASI->getSuccessOrdering()) ||
+ isAtLeastAcquire(CASI->getSuccessOrdering()))) {
// If a compare and swap is lowered to LL/SC, we can do smarter fence
// insertion, with a stronger one on the success path than on the
// failure path. As a result, fence insertion is directly done by
}
}
- if (LI && TargetLowering->shouldExpandAtomicLoadInIR(LI)) {
+ if (LI && TLI->shouldExpandAtomicLoadInIR(LI)) {
MadeChange |= expandAtomicLoad(LI);
- } else if (SI && TargetLowering->shouldExpandAtomicStoreInIR(SI)) {
+ } else if (SI && TLI->shouldExpandAtomicStoreInIR(SI)) {
MadeChange |= expandAtomicStore(SI);
- } else if (RMWI && TargetLowering->shouldExpandAtomicRMWInIR(RMWI)) {
- MadeChange |= expandAtomicRMW(RMWI);
- } else if (CASI && TargetLowering->hasLoadLinkedStoreConditional()) {
+ } else if (RMWI) {
+ // There are two different ways of expanding RMW instructions:
+ // - into a load if it is idempotent
+ // - into a Cmpxchg/LL-SC loop otherwise
+ // we try them in that order.
+ MadeChange |=
+ (isIdempotentRMW(RMWI) && simplifyIdempotentRMW(RMWI)) ||
+ (TLI->shouldExpandAtomicRMWInIR(RMWI) && expandAtomicRMW(RMWI));
+ } else if (CASI && TLI->hasLoadLinkedStoreConditional()) {
MadeChange |= expandAtomicCmpXchg(CASI);
}
}
bool IsStore, bool IsLoad) {
IRBuilder<> Builder(I);
- auto LeadingFence =
- TM->getSubtargetImpl()->getTargetLowering()->emitLeadingFence(
- Builder, Order, IsStore, IsLoad);
+ auto LeadingFence = TLI->emitLeadingFence(Builder, Order, IsStore, IsLoad);
- auto TrailingFence =
- TM->getSubtargetImpl()->getTargetLowering()->emitTrailingFence(
- Builder, Order, IsStore, IsLoad);
+ auto TrailingFence = TLI->emitTrailingFence(Builder, Order, IsStore, IsLoad);
// The trailing fence is emitted before the instruction instead of after
// because there is no easy way of setting Builder insertion point after
// an instruction. So we must erase it from the BB, and insert it back
}
bool AtomicExpand::expandAtomicLoad(LoadInst *LI) {
- if (TM->getSubtargetImpl()
- ->getTargetLowering()
- ->hasLoadLinkedStoreConditional())
+ if (TLI->hasLoadLinkedStoreConditional())
return expandAtomicLoadToLL(LI);
else
return expandAtomicLoadToCmpXchg(LI);
}
bool AtomicExpand::expandAtomicLoadToLL(LoadInst *LI) {
- auto TLI = TM->getSubtargetImpl()->getTargetLowering();
IRBuilder<> Builder(LI);
// On some architectures, load-linked instructions are atomic for larger
}
bool AtomicExpand::expandAtomicRMW(AtomicRMWInst *AI) {
- if (TM->getSubtargetImpl()
- ->getTargetLowering()
- ->hasLoadLinkedStoreConditional())
+ if (TLI->hasLoadLinkedStoreConditional())
return expandAtomicRMWToLLSC(AI);
else
return expandAtomicRMWToCmpXchg(AI);
}
bool AtomicExpand::expandAtomicRMWToLLSC(AtomicRMWInst *AI) {
- auto TLI = TM->getSubtargetImpl()->getTargetLowering();
AtomicOrdering MemOpOrder = AI->getOrdering();
Value *Addr = AI->getPointerOperand();
BasicBlock *BB = AI->getParent();
}
bool AtomicExpand::expandAtomicCmpXchg(AtomicCmpXchgInst *CI) {
- auto TLI = TM->getSubtargetImpl()->getTargetLowering();
AtomicOrdering SuccessOrder = CI->getSuccessOrdering();
AtomicOrdering FailureOrder = CI->getFailureOrdering();
Value *Addr = CI->getPointerOperand();
CI->eraseFromParent();
return true;
}
+
+bool AtomicExpand::isIdempotentRMW(AtomicRMWInst* RMWI) {
+ auto C = dyn_cast<ConstantInt>(RMWI->getValOperand());
+ if(!C)
+ return false;
+
+ AtomicRMWInst::BinOp Op = RMWI->getOperation();
+ switch(Op) {
+ case AtomicRMWInst::Add:
+ case AtomicRMWInst::Sub:
+ case AtomicRMWInst::Or:
+ case AtomicRMWInst::Xor:
+ return C->isZero();
+ case AtomicRMWInst::And:
+ return C->isMinusOne();
+ // FIXME: we could also treat Min/Max/UMin/UMax by the INT_MIN/INT_MAX/...
+ default:
+ return false;
+ }
+}
+
+bool AtomicExpand::simplifyIdempotentRMW(AtomicRMWInst* RMWI) {
+ if (auto ResultingLoad = TLI->lowerIdempotentRMWIntoFencedLoad(RMWI)) {
+ if (TLI->shouldExpandAtomicLoadInIR(ResultingLoad))
+ expandAtomicLoad(ResultingLoad);
+ return true;
+ }
+ return false;
+}