mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 03:02:36 +01:00
4cefe8e200
An indirect call site needs to be probed for its potential call targets. With CSSPGO a direct call also needs a probe so that a calling context can be represented by a stack of callsite probes. Unlike pseudo probes for basic blocks that are in form of standalone intrinsic call instructions, pseudo probes for callsites have to be attached to the call instruction, thus a separate instruction would not work. One possible way of attaching a probe to a call instruction is to use a special metadata that carries information about the probe. The special metadata will have to make its way through the optimization pipeline down to object emission. This requires additional efforts to maintain the metadata in various places. Given that the `!dbg` metadata is a first-class metadata and has all essential support in place , leveraging the `!dbg` metadata as a channel to encode pseudo probe information is probably the easiest solution. With the requirement of not inflating `!dbg` metadata that is allocated for almost every instruction, we found that the 32-bit DWARF discriminator field which mainly serves AutoFDO can be reused for pseudo probes. DWARF discriminators distinguish identical source locations between instructions and with pseudo probes such support is not required. In this change we are using the discriminator field to encode the ID and type of a callsite probe and the encoded value will be unpacked and consumed right before object emission. When a callsite is inlined, the callsite discriminator field will go with the inlined instructions. The `!dbg` metadata of an inlined instruction is in form of a scope stack. The top of the stack is the instruction's original `!dbg` metadata and the bottom of the stack is for the original callsite of the top-level inliner. Except for the top of the stack, all other elements of the stack actually refer to the nested inlined callsites whose discriminator field (which actually represents a calliste probe) can be used together to represent the inline context of an inlined PseudoProbeInst or CallInst. To avoid collision with the baseline AutoFDO in various places that handles dwarf discriminators where a check against the `-pseudo-probe-for-profiling` switch is not available, a special encoding scheme is used to tell apart a pseudo probe discriminator from a regular discriminator. For the regular discriminator, if all lowest 3 bits are non-zero, it means the discriminator is basically empty and all higher 29 bits can be reversed for pseudo probe use. Callsite pseudo probes are inserted in `SampleProfileProbePass` and a target-independent MIR pass `PseudoProbeInserter` is added to unpack the probe ID/type from `!dbg`. Note that with this work the switch -debug-info-for-profiling will not work with -pseudo-probe-for-profiling anymore. They cannot be used at the same time. Reviewed By: wmi Differential Revision: https://reviews.llvm.org/D91756
219 lines
4.8 KiB
CMake
219 lines
4.8 KiB
CMake
add_llvm_component_library(LLVMCodeGen
|
|
AggressiveAntiDepBreaker.cpp
|
|
AllocationOrder.cpp
|
|
Analysis.cpp
|
|
AtomicExpandPass.cpp
|
|
BasicTargetTransformInfo.cpp
|
|
BranchFolding.cpp
|
|
BranchRelaxation.cpp
|
|
BreakFalseDeps.cpp
|
|
BuiltinGCs.cpp
|
|
BasicBlockSections.cpp
|
|
CalcSpillWeights.cpp
|
|
CallingConvLower.cpp
|
|
CFGuardLongjmp.cpp
|
|
CFIInstrInserter.cpp
|
|
CodeGen.cpp
|
|
CodeGenPrepare.cpp
|
|
CommandFlags.cpp
|
|
CriticalAntiDepBreaker.cpp
|
|
DeadMachineInstructionElim.cpp
|
|
DetectDeadLanes.cpp
|
|
DFAPacketizer.cpp
|
|
DwarfEHPrepare.cpp
|
|
EarlyIfConversion.cpp
|
|
EdgeBundles.cpp
|
|
ExecutionDomainFix.cpp
|
|
ExpandMemCmp.cpp
|
|
ExpandPostRAPseudos.cpp
|
|
ExpandReductions.cpp
|
|
FaultMaps.cpp
|
|
FEntryInserter.cpp
|
|
FinalizeISel.cpp
|
|
FixupStatepointCallerSaved.cpp
|
|
FuncletLayout.cpp
|
|
GCMetadata.cpp
|
|
GCMetadataPrinter.cpp
|
|
GCRootLowering.cpp
|
|
GCStrategy.cpp
|
|
GlobalMerge.cpp
|
|
HardwareLoops.cpp
|
|
IfConversion.cpp
|
|
ImplicitNullChecks.cpp
|
|
IndirectBrExpandPass.cpp
|
|
InlineSpiller.cpp
|
|
InterferenceCache.cpp
|
|
InterleavedAccessPass.cpp
|
|
InterleavedLoadCombinePass.cpp
|
|
IntrinsicLowering.cpp
|
|
LatencyPriorityQueue.cpp
|
|
LazyMachineBlockFrequencyInfo.cpp
|
|
LexicalScopes.cpp
|
|
LiveDebugVariables.cpp
|
|
LiveIntervals.cpp
|
|
LiveInterval.cpp
|
|
LiveIntervalUnion.cpp
|
|
LivePhysRegs.cpp
|
|
LiveRangeCalc.cpp
|
|
LiveIntervalCalc.cpp
|
|
LiveRangeEdit.cpp
|
|
LiveRangeShrink.cpp
|
|
LiveRegMatrix.cpp
|
|
LiveRegUnits.cpp
|
|
LiveStacks.cpp
|
|
LiveVariables.cpp
|
|
LLVMTargetMachine.cpp
|
|
LocalStackSlotAllocation.cpp
|
|
LoopTraversal.cpp
|
|
LowLevelType.cpp
|
|
LowerEmuTLS.cpp
|
|
MachineBasicBlock.cpp
|
|
MachineBlockFrequencyInfo.cpp
|
|
MachineBlockPlacement.cpp
|
|
MachineBranchProbabilityInfo.cpp
|
|
MachineCombiner.cpp
|
|
MachineCopyPropagation.cpp
|
|
MachineCSE.cpp
|
|
MachineDebugify.cpp
|
|
MachineDominanceFrontier.cpp
|
|
MachineDominators.cpp
|
|
MachineFrameInfo.cpp
|
|
MachineFunction.cpp
|
|
MachineFunctionPass.cpp
|
|
MachineFunctionPrinterPass.cpp
|
|
MachineFunctionSplitter.cpp
|
|
MachineInstrBundle.cpp
|
|
MachineInstr.cpp
|
|
MachineLICM.cpp
|
|
MachineLoopInfo.cpp
|
|
MachineLoopUtils.cpp
|
|
MachineModuleInfo.cpp
|
|
MachineModuleInfoImpls.cpp
|
|
MachineOperand.cpp
|
|
MachineOptimizationRemarkEmitter.cpp
|
|
MachineOutliner.cpp
|
|
MachinePassManager.cpp
|
|
MachinePipeliner.cpp
|
|
MachinePostDominators.cpp
|
|
MachineRegionInfo.cpp
|
|
MachineRegisterInfo.cpp
|
|
MachineScheduler.cpp
|
|
MachineSink.cpp
|
|
MachineSizeOpts.cpp
|
|
MachineSSAUpdater.cpp
|
|
MachineStripDebug.cpp
|
|
MachineTraceMetrics.cpp
|
|
MachineVerifier.cpp
|
|
ModuloSchedule.cpp
|
|
MultiHazardRecognizer.cpp
|
|
PatchableFunction.cpp
|
|
MBFIWrapper.cpp
|
|
MIRPrinter.cpp
|
|
MIRPrintingPass.cpp
|
|
MacroFusion.cpp
|
|
NonRelocatableStringpool.cpp
|
|
OptimizePHIs.cpp
|
|
ParallelCG.cpp
|
|
PeepholeOptimizer.cpp
|
|
PHIElimination.cpp
|
|
PHIEliminationUtils.cpp
|
|
PostRAHazardRecognizer.cpp
|
|
PostRASchedulerList.cpp
|
|
PreISelIntrinsicLowering.cpp
|
|
ProcessImplicitDefs.cpp
|
|
PrologEpilogInserter.cpp
|
|
PseudoProbeInserter.cpp
|
|
PseudoSourceValue.cpp
|
|
RDFGraph.cpp
|
|
RDFLiveness.cpp
|
|
RDFRegisters.cpp
|
|
ReachingDefAnalysis.cpp
|
|
RegAllocBase.cpp
|
|
RegAllocBasic.cpp
|
|
RegAllocFast.cpp
|
|
RegAllocGreedy.cpp
|
|
RegAllocPBQP.cpp
|
|
RegisterClassInfo.cpp
|
|
RegisterCoalescer.cpp
|
|
RegisterPressure.cpp
|
|
RegisterScavenging.cpp
|
|
RenameIndependentSubregs.cpp
|
|
MachineStableHash.cpp
|
|
MIRVRegNamerUtils.cpp
|
|
MIRNamerPass.cpp
|
|
MIRCanonicalizerPass.cpp
|
|
RegisterUsageInfo.cpp
|
|
RegUsageInfoCollector.cpp
|
|
RegUsageInfoPropagate.cpp
|
|
ResetMachineFunctionPass.cpp
|
|
SafeStack.cpp
|
|
SafeStackLayout.cpp
|
|
ScalarizeMaskedMemIntrin.cpp
|
|
ScheduleDAG.cpp
|
|
ScheduleDAGInstrs.cpp
|
|
ScheduleDAGPrinter.cpp
|
|
ScoreboardHazardRecognizer.cpp
|
|
ShadowStackGCLowering.cpp
|
|
ShrinkWrap.cpp
|
|
SjLjEHPrepare.cpp
|
|
SlotIndexes.cpp
|
|
SpillPlacement.cpp
|
|
SplitKit.cpp
|
|
StackColoring.cpp
|
|
StackMapLivenessAnalysis.cpp
|
|
StackMaps.cpp
|
|
StackProtector.cpp
|
|
StackSlotColoring.cpp
|
|
SwiftErrorValueTracking.cpp
|
|
SwitchLoweringUtils.cpp
|
|
TailDuplication.cpp
|
|
TailDuplicator.cpp
|
|
TargetFrameLoweringImpl.cpp
|
|
TargetInstrInfo.cpp
|
|
TargetLoweringBase.cpp
|
|
TargetLoweringObjectFileImpl.cpp
|
|
TargetOptionsImpl.cpp
|
|
TargetPassConfig.cpp
|
|
TargetRegisterInfo.cpp
|
|
TargetSchedule.cpp
|
|
TargetSubtargetInfo.cpp
|
|
TypePromotion.cpp
|
|
TwoAddressInstructionPass.cpp
|
|
UnreachableBlockElim.cpp
|
|
ValueTypes.cpp
|
|
VirtRegMap.cpp
|
|
WasmEHPrepare.cpp
|
|
WinEHPrepare.cpp
|
|
XRayInstrumentation.cpp
|
|
|
|
LiveDebugValues/LiveDebugValues.cpp
|
|
LiveDebugValues/VarLocBasedImpl.cpp
|
|
LiveDebugValues/InstrRefBasedImpl.cpp
|
|
|
|
ADDITIONAL_HEADER_DIRS
|
|
${LLVM_MAIN_INCLUDE_DIR}/llvm/CodeGen
|
|
${LLVM_MAIN_INCLUDE_DIR}/llvm/CodeGen/PBQP
|
|
|
|
LINK_LIBS ${LLVM_PTHREAD_LIB}
|
|
|
|
DEPENDS
|
|
intrinsics_gen
|
|
|
|
LINK_COMPONENTS
|
|
Analysis
|
|
BitReader
|
|
BitWriter
|
|
Core
|
|
MC
|
|
ProfileData
|
|
Scalar
|
|
Support
|
|
Target
|
|
TransformUtils
|
|
)
|
|
|
|
add_subdirectory(SelectionDAG)
|
|
add_subdirectory(AsmPrinter)
|
|
add_subdirectory(MIRParser)
|
|
add_subdirectory(GlobalISel)
|