Inheritance diagram for quda::CopyGaugeEx< FloatOut, FloatIn, length, OutOrder, InOrder >:

Collaboration diagram for quda::CopyGaugeEx< FloatOut, FloatIn, length, OutOrder, InOrder >:

[legend]

Public Member Functions
	CopyGaugeEx (CopyGaugeExArg< OutOrder, InOrder > &arg, const GaugeField &meta, QudaFieldLocation location)

virtual	~CopyGaugeEx ()

void	apply (const cudaStream_t &stream)

TuneKey	tuneKey () const

long long	flops () const

long long	bytes () const

Private Member Functions
unsigned int	sharedBytesPerThread () const

unsigned int	sharedBytesPerBlock (const TuneParam &param) const

bool	tuneGridDim () const

unsigned int	minThreads () const

Private Member Functions inherited from quda::Tunable
	Tunable ()

virtual	~Tunable ()

virtual void	preTune ()

virtual void	postTune ()

virtual int	tuningIter () const

virtual std::string	paramString (const TuneParam &param) const

virtual std::string	perfString (float time) const

virtual void	initTuneParam (TuneParam &param) const

virtual void	defaultTuneParam (TuneParam &param) const

virtual bool	advanceTuneParam (TuneParam &param) const

void	checkLaunchParam (TuneParam &param)

CUresult	jitifyError () const

CUresult &	jitifyError ()

virtual bool	tuneAuxDim () const

virtual bool	tuneSharedBytes () const

virtual bool	advanceGridDim (TuneParam &param) const

virtual unsigned int	maxBlockSize (const TuneParam &param) const

virtual unsigned int	maxGridSize () const

virtual unsigned int	minGridSize () const

virtual int	gridStep () const
	gridStep sets the step size when iterating the grid size in advanceGridDim. More...

virtual int	blockStep () const

virtual int	blockMin () const

virtual void	resetBlockDim (TuneParam &param) const

virtual bool	advanceBlockDim (TuneParam &param) const

unsigned int	maxBlocksPerSM () const
	For some reason this can't be queried from the device properties, so here we set set this. Based on Table 14 of the CUDA Programming Guide 10.0 (Technical Specifications per Compute Capability) More...

template<typename F >
void	setMaxDynamicSharedBytesPerBlock (F *func) const
	Enable the maximum dynamic shared bytes for the kernel "func" (values given by maxDynamicSharedBytesPerBlock()). More...

unsigned int	maxDynamicSharedBytesPerBlock () const
	This can't be correctly queried in CUDA for all architectures so here we set set this. Based on Table 14 of the CUDA Programming Guide 10.0 (Technical Specifications per Compute Capability). More...

virtual unsigned int	maxSharedBytesPerBlock () const
	The maximum shared memory that a CUDA thread block can use in the autotuner. This isn't necessarily the same as maxDynamicSharedMemoryPerBlock since that may need explicit opt in to enable (by calling setMaxDynamicSharedBytes for the kernel in question). If the CUDA kernel in question does this opt in then this function can be overloaded to return maxDynamicSharedBytesPerBlock. More...

virtual bool	advanceSharedBytes (TuneParam &param) const

virtual bool	advanceAux (TuneParam &param) const

int	writeAuxString (const char *format,...)

Private Attributes
CopyGaugeExArg< OutOrder, InOrder >	arg

const GaugeField &	meta

QudaFieldLocation	location

Private Attributes inherited from quda::Tunable
char	aux [TuneKey::aux_n]

CUresult	jitify_error

Detailed Description

template<typename FloatOut, typename FloatIn, int length, typename OutOrder, typename InOrder>
class quda::CopyGaugeEx< FloatOut, FloatIn, length, OutOrder, InOrder >

Definition at line 111 of file copy_gauge_extended.cu.

Constructor & Destructor Documentation

◆ CopyGaugeEx()

template<typename FloatOut , typename FloatIn , int length, typename OutOrder , typename InOrder >

quda::CopyGaugeEx< FloatOut, FloatIn, length, OutOrder, InOrder >::CopyGaugeEx	(	CopyGaugeExArg< OutOrder, InOrder > &	arg,
		const GaugeField &	meta,
		QudaFieldLocation	location
	)

inline

Definition at line 124 of file copy_gauge_extended.cu.

References quda::CopyGaugeExArg< OutOrder, InOrder >::geometry, quda::CopyGaugeExArg< OutOrder, InOrder >::in, and quda::CopyGaugeExArg< OutOrder, InOrder >::out.

◆ ~CopyGaugeEx()

template<typename FloatOut , typename FloatIn , int length, typename OutOrder , typename InOrder >

virtual quda::CopyGaugeEx< FloatOut, FloatIn, length, OutOrder, InOrder >::~CopyGaugeEx ( )

inlinevirtual

Definition at line 128 of file copy_gauge_extended.cu.

Member Function Documentation

◆ apply()

template<typename FloatOut , typename FloatIn , int length, typename OutOrder , typename InOrder >

void quda::CopyGaugeEx< FloatOut, FloatIn, length, OutOrder, InOrder >::apply ( const cudaStream_t & stream )

inlinevirtual

Implements quda::Tunable.

Definition at line 130 of file copy_gauge_extended.cu.

References quda::arg(), quda::TuneParam::block, getTuning(), getVerbosity(), quda::TuneParam::grid, QUDA_CPU_FIELD_LOCATION, QUDA_CUDA_FIELD_LOCATION, quda::CopyGaugeExArg< OutOrder, InOrder >::regularToextended, quda::TuneParam::shared_bytes, and quda::tuneLaunch().

Here is the call graph for this function:

◆ bytes()

template<typename FloatOut , typename FloatIn , int length, typename OutOrder , typename InOrder >

long long quda::CopyGaugeEx< FloatOut, FloatIn, length, OutOrder, InOrder >::bytes ( ) const

inlinevirtual

Reimplemented from quda::Tunable.

Definition at line 149 of file copy_gauge_extended.cu.

References quda::CopyGaugeExArg< OutOrder, InOrder >::in, quda::CopyGaugeExArg< OutOrder, InOrder >::out, and quda::CopyGaugeExArg< OutOrder, InOrder >::volume.

◆ flops()

template<typename FloatOut , typename FloatIn , int length, typename OutOrder , typename InOrder >

long long quda::CopyGaugeEx< FloatOut, FloatIn, length, OutOrder, InOrder >::flops ( ) const

inlinevirtual

Implements quda::Tunable.

Definition at line 148 of file copy_gauge_extended.cu.

◆ minThreads()

template<typename FloatOut , typename FloatIn , int length, typename OutOrder , typename InOrder >

unsigned int quda::CopyGaugeEx< FloatOut, FloatIn, length, OutOrder, InOrder >::minThreads ( ) const

inlineprivatevirtual

Reimplemented from quda::Tunable.

Definition at line 121 of file copy_gauge_extended.cu.

References quda::CopyGaugeExArg< OutOrder, InOrder >::volume.

◆ sharedBytesPerBlock()

template<typename FloatOut , typename FloatIn , int length, typename OutOrder , typename InOrder >

unsigned int quda::CopyGaugeEx< FloatOut, FloatIn, length, OutOrder, InOrder >::sharedBytesPerBlock ( const TuneParam & param ) const

inlineprivatevirtual

Implements quda::Tunable.

Definition at line 118 of file copy_gauge_extended.cu.

◆ sharedBytesPerThread()

template<typename FloatOut , typename FloatIn , int length, typename OutOrder , typename InOrder >

unsigned int quda::CopyGaugeEx< FloatOut, FloatIn, length, OutOrder, InOrder >::sharedBytesPerThread ( ) const

inlineprivatevirtual

Implements quda::Tunable.

Definition at line 117 of file copy_gauge_extended.cu.

◆ tuneGridDim()

template<typename FloatOut , typename FloatIn , int length, typename OutOrder , typename InOrder >

bool quda::CopyGaugeEx< FloatOut, FloatIn, length, OutOrder, InOrder >::tuneGridDim ( ) const

inlineprivatevirtual

Reimplemented from quda::Tunable.

Definition at line 120 of file copy_gauge_extended.cu.

◆ tuneKey()

template<typename FloatOut , typename FloatIn , int length, typename OutOrder , typename InOrder >

TuneKey quda::CopyGaugeEx< FloatOut, FloatIn, length, OutOrder, InOrder >::tuneKey ( ) const

inlinevirtual

Implements quda::Tunable.

Definition at line 144 of file copy_gauge_extended.cu.

References quda::LatticeField::VolString().

Here is the call graph for this function:

Member Data Documentation

◆ arg

template<typename FloatOut , typename FloatIn , int length, typename OutOrder , typename InOrder >

CopyGaugeExArg<OutOrder,InOrder> quda::CopyGaugeEx< FloatOut, FloatIn, length, OutOrder, InOrder >::arg

private

Definition at line 112 of file copy_gauge_extended.cu.

◆ location

template<typename FloatOut , typename FloatIn , int length, typename OutOrder , typename InOrder >

QudaFieldLocation quda::CopyGaugeEx< FloatOut, FloatIn, length, OutOrder, InOrder >::location

private

Definition at line 114 of file copy_gauge_extended.cu.

◆ meta

template<typename FloatOut , typename FloatIn , int length, typename OutOrder , typename InOrder >

const GaugeField& quda::CopyGaugeEx< FloatOut, FloatIn, length, OutOrder, InOrder >::meta

private

Definition at line 113 of file copy_gauge_extended.cu.

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

lib/copy_gauge_extended.cu

Public Member Functions

Private Member Functions

Private Attributes

Detailed Description

template<typename FloatOut, typename FloatIn, int length, typename OutOrder, typename InOrder> class quda::CopyGaugeEx< FloatOut, FloatIn, length, OutOrder, InOrder >

Constructor & Destructor Documentation

◆ CopyGaugeEx()

◆ ~CopyGaugeEx()

Member Function Documentation

◆ apply()

◆ bytes()

◆ flops()

◆ minThreads()

◆ sharedBytesPerBlock()

◆ sharedBytesPerThread()

◆ tuneGridDim()

◆ tuneKey()

Member Data Documentation

◆ arg

◆ location

◆ meta

template<typename FloatOut, typename FloatIn, int length, typename OutOrder, typename InOrder>
class quda::CopyGaugeEx< FloatOut, FloatIn, length, OutOrder, InOrder >