CandidateHeuristics contains state and implementations to facilitate making per instruction scheduling decisions; it contains methods used in tryCandidate to decide which instruction to schedule next. More...

#include "Target/AMDGPU/AMDGPUCoExecSchedStrategy.h"

Public Member Functions
	CandidateHeuristics ()=default
void	initialize (ScheduleDAGMI DAG, const TargetSchedModel SchedModel, const TargetRegisterInfo *TRI)
void	updateForScheduling (SUnit *SU)
	Update the state to reflect that `SU` is going to be scheduled.
HardwareUnitInfo *	getHWUIFromFlavor (AMDGPU::InstructionFlavor Flavor)
	Given a `Flavor` , find the corresponding HardwareUnit.
void	sortHWUIResources ()
	Sort the HardwarUnitInfo vector.
bool	tryCriticalResource (GenericSchedulerBase::SchedCandidate &TryCand, GenericSchedulerBase::SchedCandidate &Cand, SchedBoundary *Zone) const
	Check for critical resource consumption.
bool	tryCriticalResourceDependency (GenericSchedulerBase::SchedCandidate &TryCand, GenericSchedulerBase::SchedCandidate &Cand, SchedBoundary *Zone) const
	Check for dependencies of instructions that use prioritized HardwareUnits.
void	dumpRegionSummary ()

Protected Member Functions
void	collectHWUIPressure ()
	Walk over the region and collect total usage per HardwareUnit.
unsigned	getHWUICyclesForInst (SUnit *SU)
	Compute the blocking cycles for the appropriate HardwareUnit given an `SU`.

Protected Attributes
ScheduleDAGMI *	DAG
const SIInstrInfo *	SII
const SIRegisterInfo *	SRI
const TargetSchedModel *	SchedModel
SmallVector< HardwareUnitInfo, 8 >	HWUInfo

Detailed Description

CandidateHeuristics contains state and implementations to facilitate making per instruction scheduling decisions; it contains methods used in tryCandidate to decide which instruction to schedule next.

Definition at line 199 of file AMDGPUCoExecSchedStrategy.h.

Constructor & Destructor Documentation

◆ CandidateHeuristics()

llvm::CandidateHeuristics::CandidateHeuristics ( )

default

References DAG, SchedModel, and TRI.

Member Function Documentation

◆ collectHWUIPressure()

void CandidateHeuristics::collectHWUIPressure ( )

protected

Walk over the region and collect total usage per HardwareUnit.

Definition at line 263 of file AMDGPUCoExecSchedStrategy.cpp.

References llvm::AMDGPU::classifyFlavor(), DAG, dumpRegionSummary(), getHWUICyclesForInst(), HWUInfo, LLVM_DEBUG, SchedModel, and SII.

Referenced by initialize().

◆ dumpRegionSummary()

void CandidateHeuristics::dumpRegionSummary ( )

Definition at line 278 of file AMDGPUCoExecSchedStrategy.cpp.

References DAG, llvm::dbgs(), llvm::AMDGPU::getFlavorName(), llvm::MachineBasicBlock::getNumber(), and HWUInfo.

Referenced by collectHWUIPressure().

◆ getHWUICyclesForInst()

unsigned CandidateHeuristics::getHWUICyclesForInst ( SUnit * SU )

protected

Compute the blocking cycles for the appropriate HardwareUnit given an SU.

Definition at line 215 of file AMDGPUCoExecSchedStrategy.cpp.

References assert(), DAG, llvm::SUnit::getInstr(), MI, SchedModel, and SII.

Referenced by collectHWUIPressure(), and updateForScheduling().

◆ getHWUIFromFlavor()

HardwareUnitInfo * CandidateHeuristics::getHWUIFromFlavor ( AMDGPU::InstructionFlavor Flavor )

Given a Flavor , find the corresponding HardwareUnit.

Returns: the mapped HardwareUnit.

Definition at line 206 of file AMDGPUCoExecSchedStrategy.cpp.

References HWUInfo.

Referenced by updateForScheduling().

◆ initialize()

void CandidateHeuristics::initialize	(	ScheduleDAGMI *	DAG,
		const TargetSchedModel *	SchedModel,
		const TargetRegisterInfo *	TRI )

Definition at line 238 of file AMDGPUCoExecSchedStrategy.cpp.

References assert(), collectHWUIPressure(), DAG, llvm::AMDGPU::DefaultBufferSizes::DS, llvm::AMDGPU::DS, HWUInfo, I, llvm::AMDGPU::MultiCycleVALU, llvm::AMDGPU::NUM_FLAVORS, SchedModel, SII, SRI, llvm::AMDGPU::TRANS, TRI, and llvm::AMDGPU::WMMA.

◆ sortHWUIResources()

void CandidateHeuristics::sortHWUIResources ( )

Sort the HardwarUnitInfo vector.

After sorting, the HWUI that are highest priority are first. Priority is determined by maximizing coexecution and keeping the critical HardwareUnit busy.

Definition at line 295 of file AMDGPUCoExecSchedStrategy.cpp.

References A(), B(), HWUInfo, and llvm::sort().

◆ tryCriticalResource()

bool CandidateHeuristics::tryCriticalResource	(	GenericSchedulerBase::SchedCandidate &	TryCand,
		GenericSchedulerBase::SchedCandidate &	Cand,
		SchedBoundary *	Zone ) const

Check for critical resource consumption.

Prefer the candidate that uses the most prioritized HardwareUnit. If both candidates use the same HarwareUnit, prefer the candidate with higher priority on that HardwareUnit.

Definition at line 403 of file AMDGPUCoExecSchedStrategy.cpp.

References llvm::HardwareUnitInfo::contains(), llvm::AMDGPU::DS, llvm::HardwareUnitInfo::getHigherPriority(), llvm::HardwareUnitInfo::getType(), HWUInfo, I, llvm::GenericSchedulerBase::SchedCandidate::Reason, llvm::GenericSchedulerBase::RegCritical, llvm::GenericSchedulerBase::SchedCandidate::SU, and tryCriticalResourceDependency().

◆ tryCriticalResourceDependency()

bool CandidateHeuristics::tryCriticalResourceDependency	(	GenericSchedulerBase::SchedCandidate &	TryCand,
		GenericSchedulerBase::SchedCandidate &	Cand,
		SchedBoundary *	Zone ) const

Check for dependencies of instructions that use prioritized HardwareUnits.

Prefer the candidate that is a dependency of an instruction that uses the most prioritized HardwareUnit. If both candidates enable the same HardwareUnit, prefer the candidate that enables the higher priority instruction on that HardwareUnit.

Definition at line 316 of file AMDGPUCoExecSchedStrategy.cpp.

References llvm::AMDGPU::classifyFlavor(), DAG, llvm::AMDGPU::DS, llvm::Enabled, llvm::SUnit::getHeight(), llvm::SUnit::getInstr(), llvm::HardwareUnitInfo::getNextTargetSU(), llvm::HardwareUnitInfo::getType(), HWUInfo, I, llvm::GenericSchedulerBase::SchedCandidate::Reason, llvm::GenericSchedulerBase::RegCritical, SII, llvm::GenericSchedulerBase::SchedCandidate::SU, and llvm::AMDGPU::WMMA.