Inheritance diagram for quda::CopyGauge< FloatOut, FloatIn, length, Arg >:

Collaboration diagram for quda::CopyGauge< FloatOut, FloatIn, length, Arg >:

[legend]

Public Member Functions
	CopyGauge (Arg &arg, const GaugeField &out, const GaugeField &in, QudaFieldLocation location)

void	set_ghost (int is_ghost_)

virtual	~CopyGauge ()

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

bool	advanceTuneParam (TuneParam &param) const

Private Member Functions inherited from quda::TunableVectorYZ
	TunableVectorYZ (unsigned int vector_length_y, unsigned int vector_length_z)

bool	advanceBlockDim (TuneParam &param) const

void	initTuneParam (TuneParam &param) const

void	defaultTuneParam (TuneParam &param) const

void	resizeVector (int y, int z) const

void	resizeStep (int y, int z) const

Private Member Functions inherited from quda::TunableVectorY
	TunableVectorY (unsigned int vector_length_y)

void	resizeVector (int y) const

void	resizeStep (int y) 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

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

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
Arg	arg

int	size

const GaugeField &	meta

QudaFieldLocation	location

bool	is_ghost

Private Attributes inherited from quda::TunableVectorY
unsigned int	vector_length_y

unsigned int	step_y

bool	tune_block_x

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

CUresult	jitify_error

Detailed Description

template<typename FloatOut, typename FloatIn, int length, typename Arg>
class quda::CopyGauge< FloatOut, FloatIn, length, Arg >

Definition at line 11 of file copy_gauge_helper.cuh.

Constructor & Destructor Documentation

◆ CopyGauge()

template<typename FloatOut, typename FloatIn, int length, typename Arg>

quda::CopyGauge< FloatOut, FloatIn, length, Arg >::CopyGauge	(	Arg &	arg,
		const GaugeField &	out,
		const GaugeField &	in,
		QudaFieldLocation	location
	)

inline

Definition at line 31 of file copy_gauge_helper.cuh.

References quda::LatticeField::AuxString(), and quda::compile_type_str().

Here is the call graph for this function:

◆ ~CopyGauge()

template<typename FloatOut, typename FloatIn, int length, typename Arg>

virtual quda::CopyGauge< FloatOut, FloatIn, length, Arg >::~CopyGauge ( )

inlinevirtual

Definition at line 80 of file copy_gauge_helper.cuh.

Member Function Documentation

◆ advanceTuneParam()

template<typename FloatOut, typename FloatIn, int length, typename Arg>

bool quda::CopyGauge< FloatOut, FloatIn, length, Arg >::advanceTuneParam ( TuneParam & param ) const

inlineprivatevirtual

Reimplemented from quda::Tunable.

Definition at line 25 of file copy_gauge_helper.cuh.

References quda::Tunable::advanceTuneParam(), and QUDA_CUDA_FIELD_LOCATION.

Here is the call graph for this function:

◆ apply()

template<typename FloatOut, typename FloatIn, int length, typename Arg>

void quda::CopyGauge< FloatOut, FloatIn, length, Arg >::apply ( const cudaStream_t & stream )

inlinevirtual

Implements quda::Tunable.

Definition at line 82 of file copy_gauge_helper.cuh.

References quda::arg(), quda::TuneParam::block, errorQuda, getTuning(), getVerbosity(), quda::TuneParam::grid, length, QUDA_CPU_FIELD_LOCATION, QUDA_CUDA_FIELD_LOCATION, quda::TuneParam::shared_bytes, and quda::tuneLaunch().

Referenced by quda::copyGauge(), and quda::copyMom().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ bytes()

template<typename FloatOut, typename FloatIn, int length, typename Arg>

long long quda::CopyGauge< FloatOut, FloatIn, length, Arg >::bytes ( ) const

inlinevirtual

Reimplemented from quda::Tunable.

Definition at line 118 of file copy_gauge_helper.cuh.

◆ flops()

template<typename FloatOut, typename FloatIn, int length, typename Arg>

long long quda::CopyGauge< FloatOut, FloatIn, length, Arg >::flops ( ) const

inlinevirtual

Implements quda::Tunable.

Definition at line 117 of file copy_gauge_helper.cuh.

◆ minThreads()

template<typename FloatOut, typename FloatIn, int length, typename Arg>

unsigned int quda::CopyGauge< FloatOut, FloatIn, length, Arg >::minThreads ( ) const

inlineprivatevirtual

Reimplemented from quda::Tunable.

Definition at line 23 of file copy_gauge_helper.cuh.

References quda::size.

◆ set_ghost()

template<typename FloatOut, typename FloatIn, int length, typename Arg>

void quda::CopyGauge< FloatOut, FloatIn, length, Arg >::set_ghost ( int is_ghost_ )

inline

Definition at line 61 of file copy_gauge_helper.cuh.

References errorQuda, quda::GaugeField::Geometry(), length, quda::gauge::Ncolor(), and quda::LatticeField::Ndim().

Referenced by quda::copyGauge().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ sharedBytesPerBlock()

template<typename FloatOut, typename FloatIn, int length, typename Arg>

unsigned int quda::CopyGauge< FloatOut, FloatIn, length, Arg >::sharedBytesPerBlock ( const TuneParam & param ) const

inlineprivatevirtual

Reimplemented from quda::TunableVectorY.

Definition at line 20 of file copy_gauge_helper.cuh.

◆ sharedBytesPerThread()

template<typename FloatOut, typename FloatIn, int length, typename Arg>

unsigned int quda::CopyGauge< FloatOut, FloatIn, length, Arg >::sharedBytesPerThread ( ) const

inlineprivatevirtual

Reimplemented from quda::TunableVectorY.

Definition at line 19 of file copy_gauge_helper.cuh.

◆ tuneGridDim()

template<typename FloatOut, typename FloatIn, int length, typename Arg>

bool quda::CopyGauge< FloatOut, FloatIn, length, Arg >::tuneGridDim ( ) const

inlineprivatevirtual

Reimplemented from quda::Tunable.

Definition at line 22 of file copy_gauge_helper.cuh.

◆ tuneKey()

template<typename FloatOut, typename FloatIn, int length, typename Arg>

TuneKey quda::CopyGauge< FloatOut, FloatIn, length, Arg >::tuneKey ( ) const

inlinevirtual

Implements quda::Tunable.

Definition at line 110 of file copy_gauge_helper.cuh.

References quda::TuneKey::aux_n, and quda::LatticeField::VolString().

Here is the call graph for this function:

Member Data Documentation

◆ arg

template<typename FloatOut, typename FloatIn, int length, typename Arg>

Arg quda::CopyGauge< FloatOut, FloatIn, length, Arg >::arg

private

Definition at line 12 of file copy_gauge_helper.cuh.

◆ is_ghost

template<typename FloatOut, typename FloatIn, int length, typename Arg>

bool quda::CopyGauge< FloatOut, FloatIn, length, Arg >::is_ghost

private

Definition at line 16 of file copy_gauge_helper.cuh.

◆ location

template<typename FloatOut, typename FloatIn, int length, typename Arg>

QudaFieldLocation quda::CopyGauge< FloatOut, FloatIn, length, Arg >::location

private

Definition at line 15 of file copy_gauge_helper.cuh.

◆ meta

template<typename FloatOut, typename FloatIn, int length, typename Arg>

const GaugeField& quda::CopyGauge< FloatOut, FloatIn, length, Arg >::meta

private

Definition at line 14 of file copy_gauge_helper.cuh.

◆ size

template<typename FloatOut, typename FloatIn, int length, typename Arg>

int quda::CopyGauge< FloatOut, FloatIn, length, Arg >::size

private

Definition at line 13 of file copy_gauge_helper.cuh.

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

lib/copy_gauge_helper.cuh

Public Member Functions

Private Member Functions

Private Attributes

Detailed Description

template<typename FloatOut, typename FloatIn, int length, typename Arg> class quda::CopyGauge< FloatOut, FloatIn, length, Arg >

Constructor & Destructor Documentation

◆ CopyGauge()

◆ ~CopyGauge()

Member Function Documentation

◆ advanceTuneParam()

◆ apply()

◆ bytes()

◆ flops()

◆ minThreads()

◆ set_ghost()

◆ sharedBytesPerBlock()

◆ sharedBytesPerThread()

◆ tuneGridDim()

◆ tuneKey()

Member Data Documentation

◆ arg

◆ is_ghost

◆ location

◆ meta

◆ size

template<typename FloatOut, typename FloatIn, int length, typename Arg>
class quda::CopyGauge< FloatOut, FloatIn, length, Arg >