Shader Class Reference

#include <shader.hh>

Inheritance diagram for Shader:

Public Types
enum	hsail_mode_e { SIMT, VECTOR_SCALAR }
typedef ShaderParams	Params
Public Types inherited from ClockedObject
typedef ClockedObjectParams	Params
	Parameters of ClockedObject. More...
Public Types inherited from SimObject
typedef SimObjectParams	Params

Public Member Functions
GPUDispatcher &	dispatcher ()
void	sampleLoad (const Tick accessTime)
void	sampleStore (const Tick accessTime)
void	sampleInstRoundTrip (std::vector< Tick > roundTripTime)
void	sampleLineRoundTrip (const std::map< Addr, std::vector< Tick >> &roundTripTime)
const ApertureRegister &	gpuVmApe () const
const ApertureRegister &	ldsApe () const
const ApertureRegister &	scratchApe () const
bool	isGpuVmApe (Addr addr) const
bool	isLdsApe (Addr addr) const
bool	isScratchApe (Addr addr) const
Addr	getScratchBase ()
Addr	getHiddenPrivateBase ()
void	initShHiddenPrivateBase (Addr queueBase, uint32_t offset)
void	regStats ()
	Callback to set stat parameters. More...
	Shader (const Params *p)
	~Shader ()
virtual void	init ()
	init() is called after all C++ SimObjects have been created and all ports are connected. More...
void	execScheduledAdds ()
void	ScheduleAdd (int *val, Tick when, int x)
bool	processTimingPacket (PacketPtr pkt)
void	AccessMem (uint64_t address, void *ptr, uint32_t size, int cu_id, MemCmd cmd, bool suppress_func_errors)
void	ReadMem (uint64_t address, void *ptr, uint32_t sz, int cu_id)
void	ReadMem (uint64_t address, void *ptr, uint32_t sz, int cu_id, bool suppress_func_errors)
void	WriteMem (uint64_t address, void *ptr, uint32_t sz, int cu_id)
void	WriteMem (uint64_t address, void *ptr, uint32_t sz, int cu_id, bool suppress_func_errors)
void	doFunctionalAccess (const RequestPtr &req, MemCmd cmd, void *data, bool suppress_func_errors, int cu_id)
void	registerCU (int cu_id, ComputeUnit *compute_unit)
void	prepareInvalidate (HSAQueueEntry *task)
void	prepareFlush (GPUDynInstPtr gpuDynInst)
	dispatcher/shader arranges flush requests to the CUs More...
bool	dispatchWorkgroups (HSAQueueEntry *task)
Addr	mmap (int length)
void	functionalTLBAccess (PacketPtr pkt, int cu_id, BaseTLB::Mode mode)
void	updateContext (int cid)
void	notifyCuSleep ()
Public Member Functions inherited from ClockedObject
	ClockedObject (const ClockedObjectParams *p)
const Params *	params () const
void	serialize (CheckpointOut &cp) const override
	Serialize an object. More...
void	unserialize (CheckpointIn &cp) override
	Unserialize an object. More...
Public Member Functions inherited from SimObject
const Params *	params () const
	SimObject (const Params *_params)
virtual	~SimObject ()
virtual const std::string	name () const
virtual void	loadState (CheckpointIn &cp)
	loadState() is called on each SimObject when restoring from a checkpoint. More...
virtual void	initState ()
	initState() is called on each SimObject when not restoring from a checkpoint. More...
virtual void	regProbePoints ()
	Register probe points for this object. More...
virtual void	regProbeListeners ()
	Register probe listeners for this object. More...
ProbeManager *	getProbeManager ()
	Get the probe manager for this object. More...
virtual Port &	getPort (const std::string &if_name, PortID idx=InvalidPortID)
	Get a port with a given name and index. More...
virtual void	startup ()
	startup() is the final initialization call before simulation. More...
DrainState	drain () override
	Provide a default implementation of the drain interface for objects that don't need draining. More...
virtual void	memWriteback ()
	Write back dirty buffers to memory using functional writes. More...
virtual void	memInvalidate ()
	Invalidate the contents of memory buffers. More...
void	serialize (CheckpointOut &cp) const override
	Serialize an object. More...
void	unserialize (CheckpointIn &cp) override
	Unserialize an object. More...
Public Member Functions inherited from EventManager
EventQueue *	eventQueue () const
void	schedule (Event &event, Tick when)
void	deschedule (Event &event)
void	reschedule (Event &event, Tick when, bool always=false)
void	schedule (Event *event, Tick when)
void	deschedule (Event *event)
void	reschedule (Event *event, Tick when, bool always=false)
void	wakeupEventQueue (Tick when=(Tick) -1)
	This function is not needed by the usual gem5 event loop but may be necessary in derived EventQueues which host gem5 on other schedulers. More...
void	setCurTick (Tick newVal)
	EventManager (EventManager &em)
	Event manger manages events in the event queue. More...
	EventManager (EventManager *em)
	EventManager (EventQueue *eq)
Public Member Functions inherited from Serializable
	Serializable ()
virtual	~Serializable ()
void	serializeSection (CheckpointOut &cp, const char *name) const
	Serialize an object into a new section. More...
void	serializeSection (CheckpointOut &cp, const std::string &name) const
void	unserializeSection (CheckpointIn &cp, const char *name)
	Unserialize an a child object. More...
void	unserializeSection (CheckpointIn &cp, const std::string &name)
Public Member Functions inherited from Drainable
DrainState	drainState () const
	Return the current drain state of an object. More...
virtual void	notifyFork ()
	Notify a child process of a fork. More...
Public Member Functions inherited from Stats::Group
	Group (Group *parent, const char *name=nullptr)
	Construct a new statistics group. More...
virtual	~Group ()
virtual void	resetStats ()
	Callback to reset stats. More...
virtual void	preDumpStats ()
	Callback before stats are dumped. More...
void	addStat (Stats::Info *info)
	Register a stat with this group. More...
const std::map< std::string, Group * > &	getStatGroups () const
	Get all child groups associated with this object. More...
const std::vector< Info * > &	getStats () const
	Get all stats associated with this object. More...
void	addStatGroup (const char *name, Group *block)
	Add a stat block as a child of this block. More...
const Info *	resolveStat (std::string name) const
	Resolve a stat by its name within this group. More...
	Group ()=delete
	Group (const Group &)=delete
Group &	operator= (const Group &)=delete
Public Member Functions inherited from Clocked
void	updateClockPeriod ()
	Update the tick to the current tick. More...
Tick	clockEdge (Cycles cycles=Cycles(0)) const
	Determine the tick when a cycle begins, by default the current one, but the argument also enables the caller to determine a future cycle. More...
Cycles	curCycle () const
	Determine the current cycle, corresponding to a tick aligned to a clock edge. More...
Tick	nextCycle () const
	Based on the clock of the object, determine the start tick of the first cycle that is at least one cycle in the future. More...
uint64_t	frequency () const
Tick	clockPeriod () const
double	voltage () const
Cycles	ticksToCycles (Tick t) const
Tick	cyclesToTicks (Cycles c) const

Public Attributes
SimpleThread *	cpuThread
ThreadContext *	gpuTc
BaseCPU *	cpuPointer
EventFunctionWrapper	tickEvent
bool	timingSim
hsail_mode_e	hsail_mode
int	impl_kern_launch_acq
int	impl_kern_end_rel
int	coissue_return
int	trace_vgpr_all
int	n_cu
int	n_wf
int	globalMemSize
int	nextSchedCu
uint32_t	sa_n
std::vector< int * >	sa_val
std::vector< uint64_t >	sa_when
std::vector< int32_t >	sa_x
std::vector< ComputeUnit * >	cuList
GPUCommandProcessor &	gpuCmdProc
GPUDispatcher &	_dispatcher
Stats::Scalar	shaderActiveTicks
	Statistics. More...
Stats::Vector	vectorInstSrcOperand
Stats::Vector	vectorInstDstOperand
int64_t	max_valu_insts
int64_t	total_valu_insts
Public Attributes inherited from ClockedObject
PowerState *	powerState

Private Attributes
ApertureRegister	_gpuVmApe
ApertureRegister	_ldsApe
ApertureRegister	_scratchApe
Addr	shHiddenPrivateBaseVmid
int	_activeCus
Tick	_lastInactiveTick
Stats::Distribution	allLatencyDist
Stats::Distribution	loadLatencyDist
Stats::Distribution	storeLatencyDist
Stats::Distribution	initToCoalesceLatency
Stats::Distribution	rubyNetworkLatency
Stats::Distribution	gmEnqueueLatency
Stats::Distribution	gmToCompleteLatency
Stats::Distribution	coalsrLineAddresses
Stats::Distribution *	cacheBlockRoundTrip

Additional Inherited Members
Static Public Member Functions inherited from SimObject
static void	serializeAll (CheckpointOut &cp)
	Serialize all SimObjects in the system. More...
static SimObject *	find (const char *name)
	Find the SimObject with the given name and return a pointer to it. More...
Static Public Member Functions inherited from Serializable
static const std::string &	currentSection ()
	Gets the fully-qualified name of the active section. More...
static void	serializeAll (const std::string &cpt_dir)
	Serializes all the SimObjects. More...
static void	unserializeGlobals (CheckpointIn &cp)
Protected Member Functions inherited from Drainable
	Drainable ()
virtual	~Drainable ()
virtual void	drainResume ()
	Resume execution after a successful drain. More...
void	signalDrainDone () const
	Signal that an object is drained. More...
Protected Member Functions inherited from Clocked
	Clocked (ClockDomain &clk_domain)
	Create a clocked object and set the clock domain based on the parameters. More...
	Clocked (Clocked &)=delete
Clocked &	operator= (Clocked &)=delete
virtual	~Clocked ()
	Virtual destructor due to inheritance. More...
void	resetClock () const
	Reset the object's clock using the current global tick value. More...
virtual void	clockPeriodUpdated ()
	A hook subclasses can implement so they can do any extra work that's needed when the clock rate is changed. More...
Protected Attributes inherited from SimObject
const SimObjectParams *	_params
	Cached copy of the object parameters. More...
Protected Attributes inherited from EventManager
EventQueue *	eventq
	A pointer to this object's event queue. More...

Detailed Description

Definition at line 87 of file shader.hh.

Member Typedef Documentation

Params

typedef ShaderParams Shader::Params

Definition at line 122 of file shader.hh.

Member Enumeration Documentation

hsail_mode_e

enum Shader::hsail_mode_e

Enumerator
SIMT
VECTOR_SCALAR

Definition at line 123 of file shader.hh.

Constructor & Destructor Documentation

Shader()

Shader::Shader

(

const Params *

p

)

Definition at line 54 of file shader.cc.

References execScheduledAdds().

~Shader()

Shader::~Shader

(

)

Definition at line 143 of file shader.cc.

References cuList, ArmISA::j, and n_cu.

Member Function Documentation

AccessMem()

void Shader::AccessMem	(	uint64_t	address,
		void *	ptr,
		uint32_t	size,
		int	cu_id,
		MemCmd	cmd,
		bool	suppress_func_errors
	)

Definition at line 450 of file shader.cc.

References cuList, doFunctionalAccess(), and ChunkGenerator::done().

Referenced by ReadMem(), and WriteMem().

dispatcher()

GPUDispatcher & Shader::dispatcher

(

)

Definition at line 96 of file shader.cc.

References _dispatcher.

Referenced by Gcn3ISA::Inst_SOPP__S_ENDPGM::execute(), and ComputeUnit::DataPort::recvTimingResp().

dispatchWorkgroups()

bool Shader::dispatchWorkgroups

(

HSAQueueEntry *

task

)

Definition at line 235 of file shader.cc.

References _activeCus, _lastInactiveTick, cuList, curTick(), HSAQueueEntry::dispComplete(), DPRINTF, HSAQueueEntry::globalWgId(), HSAQueueEntry::markWgDispatch(), n_cu, nextSchedCu, panic_if, Event::scheduled(), and tickEvent.

Referenced by GPUDispatcher::exec().

doFunctionalAccess()

void Shader::doFunctionalAccess	(	const RequestPtr &	req,
		MemCmd	cmd,
		void *	data,
		bool	suppress_func_errors,
		int	cu_id
	)

Definition at line 358 of file shader.cc.

References cuList, data, Packet::dataStatic(), fatal, functionalTLBAccess(), BaseTLB::Read, MemCmd::ReadReq, Packet::req, roundDown(), Packet::setSuppressFuncError(), BaseTLB::Write, and MemCmd::WriteReq.

Referenced by AccessMem().

execScheduledAdds()

void Shader::execScheduledAdds

(

)

Definition at line 164 of file shader.cc.

References curTick(), DPRINTF, ArmISA::i, panic_if, sa_n, sa_val, sa_when, sa_x, EventManager::schedule(), and tickEvent.

Referenced by Shader().

functionalTLBAccess()

void Shader::functionalTLBAccess	(	PacketPtr	pkt,
		int	cu_id,
		BaseTLB::Mode	mode
	)

Definition at line 501 of file shader.cc.

References cuList, gpuTc, ArmISA::mode, and Packet::senderState.

Referenced by doFunctionalAccess().

getHiddenPrivateBase()

Addr Shader::getHiddenPrivateBase ( )

inline

Definition at line 186 of file shader.hh.

References shHiddenPrivateBaseVmid.

Referenced by GPUDynInst::resolveFlatSegment().

getScratchBase()

Addr Shader::getScratchBase ( )

inline

Definition at line 180 of file shader.hh.

References _scratchApe, and ApertureRegister::base.

Referenced by GPUDynInst::resolveFlatSegment().

gpuVmApe()

const ApertureRegister& Shader::gpuVmApe ( ) const

inline

Definition at line 137 of file shader.hh.

References _gpuVmApe.

init()

void Shader::init ( )

virtual

init() is called after all C++ SimObjects have been created and all ports are connected.

Initializations that are independent of unserialization but rely on a fully instantiated and connected SimObject graph should be done here.

Reimplemented from SimObject.

Definition at line 135 of file shader.cc.

References cpuPointer, BaseCPU::getContext(), and gpuTc.

initShHiddenPrivateBase()

void Shader::initShHiddenPrivateBase ( Addr  queueBase, uint32_t  offset  )

inline

Definition at line 192 of file shader.hh.

References ArmISA::offset, panic_if, and shHiddenPrivateBaseVmid.

Referenced by Wavefront::initRegState().

isGpuVmApe()

bool Shader::isGpuVmApe ( Addr  addr ) const

inline

Definition at line 155 of file shader.hh.

References _gpuVmApe, addr, ApertureRegister::base, and ApertureRegister::limit.

isLdsApe()

bool Shader::isLdsApe ( Addr  addr ) const

inline

Definition at line 163 of file shader.hh.

References _ldsApe, addr, ApertureRegister::base, and ApertureRegister::limit.

Referenced by GPUDynInst::doApertureCheck().

isScratchApe()

bool Shader::isScratchApe ( Addr  addr ) const

inline

Definition at line 171 of file shader.hh.

References _scratchApe, addr, ApertureRegister::base, and ApertureRegister::limit.

ldsApe()

const ApertureRegister& Shader::ldsApe ( ) const

inline

Definition at line 143 of file shader.hh.

References _ldsApe.

mmap()

Addr Shader::mmap

(

int

length

)

Definition at line 102 of file shader.cc.

References Process::allocateMem(), DPRINTF, ThreadContext::getProcessPtr(), gpuTc, length, Process::memState, Process::mmapGrowsDown(), ArmISA::PageBytes, and roundUp().

notifyCuSleep()

void Shader::notifyCuSleep

(

)

Definition at line 591 of file shader.cc.

References _activeCus, _lastInactiveTick, cuList, curTick(), panic_if, and shaderActiveTicks.

Referenced by ComputeUnit::exec().

prepareFlush()

void Shader::prepareFlush

(

GPUDynInstPtr

gpuDynInst

)

dispatcher/shader arranges flush requests to the CUs

Definition at line 222 of file shader.cc.

References _dispatcher, cuList, GPUDispatcher::getOutstandingWbs(), and GPUDispatcher::updateWbCounter().

Referenced by Gcn3ISA::Inst_SOPP__S_ENDPGM::execute().

prepareInvalidate()

void Shader::prepareInvalidate

(

HSAQueueEntry *

task

)

Definition at line 194 of file shader.cc.

References _dispatcher, cuList, HSAQueueEntry::dispatchId(), HSAQueueEntry::isInvStarted(), n_cu, HSAQueueEntry::outstandingInvs(), and GPUDispatcher::updateInvCounter().

Referenced by GPUDispatcher::exec().

processTimingPacket()

bool Shader::processTimingPacket

(

PacketPtr

pkt

)

ReadMem() [1/2]

void Shader::ReadMem	(	uint64_t	address,
		void *	ptr,
		uint32_t	sz,
		int	cu_id
	)

Definition at line 468 of file shader.cc.

References AccessMem(), and MemCmd::ReadReq.

ReadMem() [2/2]

void Shader::ReadMem	(	uint64_t	address,
		void *	ptr,
		uint32_t	sz,
		int	cu_id,
		bool	suppress_func_errors
	)

Definition at line 474 of file shader.cc.

References AccessMem(), and MemCmd::ReadReq.

registerCU()

void Shader::registerCU ( int  cu_id, ComputeUnit *  compute_unit  )

inline

Definition at line 291 of file shader.hh.

References cuList.

regStats()

void Shader::regStats ( )

virtual

Callback to set stat parameters.

This callback is typically used for complex stats (e.g., distributions) that need parameters in addition to a name and a description. Stat names and descriptions should typically be set from the constructor usingo from the constructor using the ADD_STAT macro.

Reimplemented from Stats::Group.

Definition at line 278 of file shader.cc.

References allLatencyDist, cacheBlockRoundTrip, ccprintf(), coalsrLineAddresses, cuList, Stats::DataWrap< Derived, InfoProxyType >::desc(), Stats::DataWrap< Derived, InfoProxyType >::flags(), gmEnqueueLatency, gmToCompleteLatency, Stats::VectorBase< Derived, Stor >::init(), Stats::Distribution::init(), initToCoalesceLatency, loadLatencyDist, SimObject::name(), Stats::DataWrap< Derived, InfoProxyType >::name(), Stats::oneline, Stats::pdf, Stats::Group::regStats(), rubyNetworkLatency, shaderActiveTicks, storeLatencyDist, vectorInstDstOperand, and vectorInstSrcOperand.

sampleInstRoundTrip()

void Shader::sampleInstRoundTrip

(

std::vector< Tick >

roundTripTime

)

Definition at line 542 of file shader.cc.

References gmEnqueueLatency, gmToCompleteLatency, initToCoalesceLatency, InstMemoryHopMax, rubyNetworkLatency, Stats::DistBase< Derived, Stor >::sample(), ArmISA::t1, ArmISA::t2, ArmISA::t3, ArmISA::t4, and ArmISA::t5.

Referenced by GlobalMemPipeline::exec().

sampleLineRoundTrip()

void Shader::sampleLineRoundTrip

(

const std::map< Addr, std::vector< Tick >> &

roundTripTime

)

Definition at line 562 of file shader.cc.

References cacheBlockRoundTrip, coalsrLineAddresses, and Stats::DistBase< Derived, Stor >::sample().

Referenced by GlobalMemPipeline::exec().

sampleLoad()

void Shader::sampleLoad

(

const Tick

accessTime

)

Definition at line 535 of file shader.cc.

References allLatencyDist, loadLatencyDist, and Stats::DistBase< Derived, Stor >::sample().

Referenced by GlobalMemPipeline::exec().

sampleStore()

void Shader::sampleStore

(

const Tick

accessTime

)

Definition at line 525 of file shader.cc.

References allLatencyDist, Stats::DistBase< Derived, Stor >::sample(), and storeLatencyDist.

Referenced by GlobalMemPipeline::exec().

ScheduleAdd()

void Shader::ScheduleAdd	(	int *	val,
		Tick	when,
		int	x
	)

Definition at line 431 of file shader.cc.

References curTick(), DPRINTF, EventManager::reschedule(), sa_n, sa_val, sa_when, sa_x, Event::scheduled(), tickEvent, X86ISA::val, Event::when(), and RiscvISA::x.

Referenced by LocalMemPipeline::exec(), GlobalMemPipeline::exec(), and ScalarMemPipeline::exec().

scratchApe()

const ApertureRegister& Shader::scratchApe ( ) const

inline

Definition at line 149 of file shader.hh.

References _scratchApe.

updateContext()

void Shader::updateContext

(

int

cid

)

Definition at line 150 of file shader.cc.

References cpuPointer, BaseCPU::getContext(), and gpuTc.

Referenced by GPUDispatcher::exec().

WriteMem() [1/2]

void Shader::WriteMem	(	uint64_t	address,
		void *	ptr,
		uint32_t	sz,
		int	cu_id
	)

Definition at line 482 of file shader.cc.

References AccessMem(), and MemCmd::WriteReq.

WriteMem() [2/2]

void Shader::WriteMem	(	uint64_t	address,
		void *	ptr,
		uint32_t	sz,
		int	cu_id,
		bool	suppress_func_errors
	)

Definition at line 488 of file shader.cc.

References AccessMem(), and MemCmd::WriteReq.

Member Data Documentation

_activeCus

int Shader::_activeCus

private

Definition at line 96 of file shader.hh.

Referenced by dispatchWorkgroups(), and notifyCuSleep().

_dispatcher

GPUDispatcher& Shader::_dispatcher

Definition at line 250 of file shader.hh.

Referenced by dispatcher(), prepareFlush(), and prepareInvalidate().

_gpuVmApe

ApertureRegister Shader::_gpuVmApe

private

Definition at line 90 of file shader.hh.

Referenced by gpuVmApe(), and isGpuVmApe().

_lastInactiveTick

Tick Shader::_lastInactiveTick

private

Definition at line 99 of file shader.hh.

Referenced by dispatchWorkgroups(), and notifyCuSleep().

_ldsApe

ApertureRegister Shader::_ldsApe

private

Definition at line 91 of file shader.hh.

Referenced by isLdsApe(), and ldsApe().

_scratchApe

ApertureRegister Shader::_scratchApe

private

Definition at line 92 of file shader.hh.

Referenced by getScratchBase(), isScratchApe(), and scratchApe().

allLatencyDist

Stats::Distribution Shader::allLatencyDist

private

Definition at line 102 of file shader.hh.

Referenced by regStats(), sampleLoad(), and sampleStore().

cacheBlockRoundTrip

Stats::Distribution* Shader::cacheBlockRoundTrip

private

Definition at line 119 of file shader.hh.

Referenced by regStats(), and sampleLineRoundTrip().

coalsrLineAddresses

Stats::Distribution Shader::coalsrLineAddresses

private

Definition at line 118 of file shader.hh.

Referenced by regStats(), and sampleLineRoundTrip().

coissue_return

int Shader::coissue_return

Definition at line 222 of file shader.hh.

Referenced by LocalMemPipeline::exec(), GlobalMemPipeline::exec(), and ScalarMemPipeline::exec().

cpuPointer

BaseCPU* Shader::cpuPointer

Definition at line 134 of file shader.hh.

Referenced by init(), and updateContext().

cpuThread

SimpleThread* Shader::cpuThread

Definition at line 132 of file shader.hh.

cuList

std::vector<ComputeUnit*> Shader::cuList

Definition at line 247 of file shader.hh.

Referenced by AccessMem(), dispatchWorkgroups(), doFunctionalAccess(), functionalTLBAccess(), notifyCuSleep(), prepareFlush(), prepareInvalidate(), registerCU(), regStats(), and ~Shader().

globalMemSize

int Shader::globalMemSize

Definition at line 231 of file shader.hh.

Referenced by GlobalMemPipeline::init().

gmEnqueueLatency

Stats::Distribution Shader::gmEnqueueLatency

private

Definition at line 112 of file shader.hh.

Referenced by regStats(), and sampleInstRoundTrip().

gmToCompleteLatency

Stats::Distribution Shader::gmToCompleteLatency

private

Definition at line 113 of file shader.hh.

Referenced by regStats(), and sampleInstRoundTrip().

gpuCmdProc

GPUCommandProcessor& Shader::gpuCmdProc

Definition at line 249 of file shader.hh.

gpuTc

ThreadContext* Shader::gpuTc

Definition at line 133 of file shader.hh.

Referenced by functionalTLBAccess(), init(), FetchUnit::initiateFetch(), mmap(), ComputeUnit::sendRequest(), ComputeUnit::sendScalarRequest(), and updateContext().

hsail_mode

hsail_mode_e Shader::hsail_mode

Definition at line 215 of file shader.hh.

Referenced by Wavefront::exec().

impl_kern_end_rel

int Shader::impl_kern_end_rel

Definition at line 220 of file shader.hh.

Referenced by Gcn3ISA::Inst_SOPP__S_ENDPGM::execute(), and ComputeUnit::injectGlobalMemFence().

impl_kern_launch_acq

int Shader::impl_kern_launch_acq

Definition at line 218 of file shader.hh.

Referenced by GPUDispatcher::exec().

initToCoalesceLatency

Stats::Distribution Shader::initToCoalesceLatency

private

Definition at line 110 of file shader.hh.

Referenced by regStats(), and sampleInstRoundTrip().

loadLatencyDist

Stats::Distribution Shader::loadLatencyDist

private

Definition at line 103 of file shader.hh.

Referenced by regStats(), and sampleLoad().

max_valu_insts

int64_t Shader::max_valu_insts

Definition at line 260 of file shader.hh.

Referenced by ComputeUnit::updateInstStats().

n_cu

int Shader::n_cu

Definition at line 226 of file shader.hh.

Referenced by dispatchWorkgroups(), prepareInvalidate(), and ~Shader().

n_wf

int Shader::n_wf

Definition at line 228 of file shader.hh.

Referenced by ComputeUnit::dispWorkgroup(), FetchUnit::exec(), ScoreboardCheckStage::exec(), ComputeUnit::hasDispResources(), FetchUnit::init(), ComputeUnit::isVectorAluIdle(), ComputeUnit::regStats(), ComputeUnit::releaseWFsFromBarrier(), Wavefront::setStatus(), and ComputeUnit::~ComputeUnit().

nextSchedCu

int Shader::nextSchedCu

Definition at line 234 of file shader.hh.

Referenced by dispatchWorkgroups().

rubyNetworkLatency

Stats::Distribution Shader::rubyNetworkLatency

private

Definition at line 111 of file shader.hh.

Referenced by regStats(), and sampleInstRoundTrip().

sa_n

uint32_t Shader::sa_n

Definition at line 237 of file shader.hh.

Referenced by execScheduledAdds(), and ScheduleAdd().

sa_val

std::vector<int*> Shader::sa_val

Definition at line 240 of file shader.hh.

Referenced by execScheduledAdds(), and ScheduleAdd().

sa_when

std::vector<uint64_t> Shader::sa_when

Definition at line 242 of file shader.hh.

Referenced by execScheduledAdds(), and ScheduleAdd().

sa_x

std::vector<int32_t> Shader::sa_x

Definition at line 244 of file shader.hh.

Referenced by execScheduledAdds(), and ScheduleAdd().

shaderActiveTicks

Stats::Scalar Shader::shaderActiveTicks

Statistics.

Definition at line 255 of file shader.hh.

Referenced by notifyCuSleep(), and regStats().

shHiddenPrivateBaseVmid

Addr Shader::shHiddenPrivateBaseVmid

private

Definition at line 93 of file shader.hh.

Referenced by getHiddenPrivateBase(), and initShHiddenPrivateBase().

storeLatencyDist

Stats::Distribution Shader::storeLatencyDist

private

Definition at line 104 of file shader.hh.

Referenced by regStats(), and sampleStore().

tickEvent

EventFunctionWrapper Shader::tickEvent

Definition at line 211 of file shader.hh.

Referenced by dispatchWorkgroups(), execScheduledAdds(), and ScheduleAdd().

timingSim

bool Shader::timingSim

Definition at line 214 of file shader.hh.

Referenced by FetchUnit::init(), and ComputeUnit::sendRequest().

total_valu_insts

int64_t Shader::total_valu_insts

Definition at line 261 of file shader.hh.

Referenced by ComputeUnit::updateInstStats().

trace_vgpr_all

int Shader::trace_vgpr_all

Definition at line 224 of file shader.hh.

vectorInstDstOperand

Stats::Vector Shader::vectorInstDstOperand

Definition at line 257 of file shader.hh.

Referenced by Wavefront::exec(), and regStats().

vectorInstSrcOperand

Stats::Vector Shader::vectorInstSrcOperand

Definition at line 256 of file shader.hh.

Referenced by Wavefront::exec(), and regStats().

---

The documentation for this class was generated from the following files:

• gpu-compute/shader.hh
• gpu-compute/shader.cc