GCNSchedStrategy.cpp File Reference

This contains a MachineSchedStrategy implementation for maximizing wave occupancy on GCN hardware. More...

#include "GCNSchedStrategy.h"
#include "AMDGPUIGroupLP.h"
#include "SIMachineFunctionInfo.h"
#include "llvm/CodeGen/RegisterClassInfo.h"

Go to the source code of this file.

Classes
struct	EarlierIssuingCycle

Macros
#define	DEBUG_TYPE   "machine-scheduler"
	Generally, the reason for having multiple scheduling stages is to account for the kernel-wide effect of register usage on occupancy.

Functions
static void	printScheduleModel (std::set< std::pair< MachineInstr *, unsigned >, EarlierIssuingCycle > &ReadyCycles)
static bool	hasIGLPInstrs (ScheduleDAGInstrs *DAG)

Variables
static cl::opt< bool >	DisableUnclusterHighRP ("amdgpu-disable-unclustered-high-rp-reschedule", cl::Hidden, cl::desc("Disable unclustered high register pressure " "reduction scheduling stage."), cl::init(false))
static cl::opt< bool >	DisableClusteredLowOccupancy ("amdgpu-disable-clustered-low-occupancy-reschedule", cl::Hidden, cl::desc("Disable clustered low occupancy " "rescheduling for ILP scheduling stage."), cl::init(false))
static cl::opt< unsigned >	ScheduleMetricBias ("amdgpu-schedule-metric-bias", cl::Hidden, cl::desc("Sets the bias which adds weight to occupancy vs latency. Set it to " "100 to chase the occupancy only."), cl::init(10))
static cl::opt< bool >	RelaxedOcc ("amdgpu-schedule-relaxed-occupancy", cl::Hidden, cl::desc("Relax occupancy targets for kernels which are memory " "bound (amdgpu-membound-threshold), or " "Wave Limited (amdgpu-limit-wave-threshold)."), cl::init(false))

Detailed Description

This contains a MachineSchedStrategy implementation for maximizing wave occupancy on GCN hardware.

This pass will apply multiple scheduling stages to the same function. Regions are first recorded in GCNScheduleDAGMILive::schedule. The actual entry point for the scheduling of those regions is GCNScheduleDAGMILive::runSchedStages.

Definition in file GCNSchedStrategy.cpp.

Macro Definition Documentation

DEBUG_TYPE

#define DEBUG_TYPE   "machine-scheduler"

Generally, the reason for having multiple scheduling stages is to account for the kernel-wide effect of register usage on occupancy.

Usually, only a few scheduling regions will have register pressure high enough to limit occupancy for the kernel, so constraints can be relaxed to improve ILP in other regions.

Definition at line 31 of file GCNSchedStrategy.cpp.

Function Documentation

hasIGLPInstrs()

static bool hasIGLPInstrs ( ScheduleDAGInstrs *  DAG )

static

Definition at line 1552 of file GCNSchedStrategy.cpp.

References llvm::ScheduleDAGInstrs::begin(), llvm::ScheduleDAGInstrs::end(), and MI.

Referenced by llvm::GCNPostScheduleDAGMILive::schedule().

printScheduleModel()

static void printScheduleModel ( std::set< std::pair< MachineInstr *, unsigned >, EarlierIssuingCycle > &  ReadyCycles )

static

Definition at line 1018 of file GCNSchedStrategy.cpp.

References llvm::dbgs(), and I.

Referenced by llvm::GCNSchedStage::getScheduleMetrics().

Variable Documentation

DisableClusteredLowOccupancy

cl::opt< bool > DisableClusteredLowOccupancy("amdgpu-disable-clustered-low-occupancy-reschedule", cl::Hidden, cl::desc("Disable clustered low occupancy " "rescheduling for ILP scheduling stage."), cl::init(false)) ( "amdgpu-disable-clustered-low-occupancy-reschedule"  , cl::Hidden  , cl::desc("Disable clustered low occupancy " "rescheduling for ILP scheduling stage.")  , cl::init(false)    )

static

Referenced by llvm::ClusteredLowOccStage::initGCNSchedStage().

DisableUnclusterHighRP

cl::opt< bool > DisableUnclusterHighRP("amdgpu-disable-unclustered-high-rp-reschedule", cl::Hidden, cl::desc("Disable unclustered high register pressure " "reduction scheduling stage."), cl::init(false)) ( "amdgpu-disable-unclustered-high-rp-reschedule"  , cl::Hidden  , cl::desc("Disable unclustered high register pressure " "reduction scheduling stage.")  , cl::init(false)    )

static

Referenced by llvm::UnclusteredHighRPStage::initGCNSchedStage().

RelaxedOcc

cl::opt< bool > RelaxedOcc("amdgpu-schedule-relaxed-occupancy", cl::Hidden, cl::desc("Relax occupancy targets for kernels which are memory " "bound (amdgpu-membound-threshold), or " "Wave Limited (amdgpu-limit-wave-threshold)."), cl::init(false)) ( "amdgpu-schedule-relaxed-occupancy"  , cl::Hidden  , cl::desc("Relax occupancy targets for kernels which are memory " "bound (amdgpu-membound-threshold), or " "Wave Limited (amdgpu-limit-wave-threshold).")  , cl::init(false)    )

static

Referenced by llvm::GCNScheduleDAGMILive::GCNScheduleDAGMILive(), and llvm::GCNSchedStrategy::initialize().

ScheduleMetricBias

cl::opt< unsigned > ScheduleMetricBias("amdgpu-schedule-metric-bias", cl::Hidden, cl::desc( "Sets the bias which adds weight to occupancy vs latency. Set it to " "100 to chase the occupancy only."), cl::init(10)) ( "amdgpu-schedule-metric-bias"  , cl::Hidden  , cl::desc( "Sets the bias which adds weight to occupancy vs latency. Set it to " "100 to chase the occupancy only.")  , cl::init(10)    )

static

Referenced by llvm::UnclusteredHighRPStage::shouldRevertScheduling().