void computeProcResourceMasks(const MCSchedModel &SM,
SmallVectorImpl<uint64_t> &Masks) {
unsigned ProcResourceID = 0;
// Create a unique bitmask for every processor resource unit.
// Skip resource at index 0, since it always references 'InvalidUnit'.
Masks.resize(SM.getNumProcResourceKinds());
for (unsigned I = 1, E = SM.getNumProcResourceKinds(); I < E; ++I) {
const MCProcResourceDesc &Desc = *SM.getProcResource(I);
if (Desc.SubUnitsIdxBegin)
continue;
Masks[I] = 1ULL << ProcResourceID;
ProcResourceID++;
}
// Create a unique bitmask for every processor resource group.
for (unsigned I = 1, E = SM.getNumProcResourceKinds(); I < E; ++I) {
const MCProcResourceDesc &Desc = *SM.getProcResource(I);
if (!Desc.SubUnitsIdxBegin)
continue;
Masks[I] = 1ULL << ProcResourceID;
for (unsigned U = 0; U < Desc.NumUnits; ++U) {
uint64_t OtherMask = Masks[Desc.SubUnitsIdxBegin[U]];
Masks[I] |= OtherMask;
}
ProcResourceID++;
}
}
void RegisterFile::initialize(const MCSchedModel &SM, unsigned NumRegs) {
// Create a default register file that "sees" all the machine registers
// declared by the target. The number of physical registers in the default
// register file is set equal to `NumRegs`. A value of zero for `NumRegs`
// means: this register file has an unbounded number of physical registers.
addRegisterFile({} /* all registers */, NumRegs);
if (!SM.hasExtraProcessorInfo())
return;
// For each user defined register file, allocate a RegisterMappingTracker
// object. The size of every register file, as well as the mapping between
// register files and register classes is specified via tablegen.
const MCExtraProcessorInfo &Info = SM.getExtraProcessorInfo();
for (unsigned I = 0, E = Info.NumRegisterFiles; I < E; ++I) {
const MCRegisterFileDesc &RF = Info.RegisterFiles[I];
// Skip invalid register files with zero physical registers.
unsigned Length = RF.NumRegisterCostEntries;
if (!RF.NumPhysRegs)
continue;
// The cost of a register definition is equivalent to the number of
// physical registers that are allocated at register renaming stage.
const MCRegisterCostEntry *FirstElt =
&Info.RegisterCostTable[RF.RegisterCostEntryIdx];
addRegisterFile(ArrayRef<MCRegisterCostEntry>(FirstElt, Length),
RF.NumPhysRegs);
}
}
/// \brief Gets latency information for \p Inst, based on \p DC information.
/// \return The maximum expected latency over all the definitions or -1
/// if no information is available.
static int getLatency(LLVMDisasmContext *DC, const MCInst &Inst) {
// Try to compute scheduling information.
const MCSubtargetInfo *STI = DC->getSubtargetInfo();
const MCSchedModel SCModel = STI->getSchedModel();
const int NoInformationAvailable = -1;
// Check if we have a scheduling model for instructions.
if (!SCModel.hasInstrSchedModel())
// Try to fall back to the itinerary model if the scheduling model doesn't
// have a scheduling table. Note the default does not have a table.
return getItineraryLatency(DC, Inst);
// Get the scheduling class of the requested instruction.
const MCInstrDesc& Desc = DC->getInstrInfo()->get(Inst.getOpcode());
unsigned SCClass = Desc.getSchedClass();
const MCSchedClassDesc *SCDesc = SCModel.getSchedClassDesc(SCClass);
// Resolving the variant SchedClass requires an MI to pass to
// SubTargetInfo::resolveSchedClass.
if (!SCDesc || !SCDesc->isValid() || SCDesc->isVariant())
return NoInformationAvailable;
// Compute output latency.
int Latency = 0;
for (unsigned DefIdx = 0, DefEnd = SCDesc->NumWriteLatencyEntries;
DefIdx != DefEnd; ++DefIdx) {
// Lookup the definition's write latency in SubtargetInfo.
const MCWriteLatencyEntry *WLEntry = STI->getWriteLatencyEntry(SCDesc,
DefIdx);
Latency = std::max(Latency, WLEntry->Cycles);
}
return Latency;
}
RetireControlUnit::RetireControlUnit(const MCSchedModel &SM)
: NextAvailableSlotIdx(0), CurrentInstructionSlotIdx(0),
AvailableSlots(SM.MicroOpBufferSize), MaxRetirePerCycle(0) {
// Check if the scheduling model provides extra information about the machine
// processor. If so, then use that information to set the reorder buffer size
// and the maximum number of instructions retired per cycle.
if (SM.hasExtraProcessorInfo()) {
const MCExtraProcessorInfo &EPI = SM.getExtraProcessorInfo();
if (EPI.ReorderBufferSize)
AvailableSlots = EPI.ReorderBufferSize;
MaxRetirePerCycle = EPI.MaxRetirePerCycle;
}
assert(AvailableSlots && "Invalid reorder buffer size!");
Queue.resize(AvailableSlots);
}