Inheritance diagram for quda::CopySpinor< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder >:

Collaboration diagram for quda::CopySpinor< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder >:

[legend]

Public Member Functions
	CopySpinor (OutOrder &out, const InOrder &in, const ColorSpinorField &meta, QudaFieldLocation location)

virtual	~CopySpinor ()

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	advanceSharedBytes (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)

virtual bool	tuneAuxDim () const

virtual bool	tuneSharedBytes () const

virtual bool	advanceGridDim (TuneParam &param) const

virtual unsigned int	maxBlockSize () const

virtual unsigned int	maxGridSize () const

virtual unsigned int	minGridSize () const

virtual int	blockStep () const

virtual int	blockMin () const

virtual bool	advanceBlockDim (TuneParam &param) const

unsigned int	maxBlocksPerSM () const
	For 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 9.0 (Technical Specifications per Compute Capability) More...

virtual bool	advanceAux (TuneParam &param) const

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

Private Attributes
const InOrder &	in

OutOrder &	out

const ColorSpinorField &	meta

QudaFieldLocation	location

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

Detailed Description

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder>
class quda::CopySpinor< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder >

Definition at line 46 of file copy_color_spinor_mg.cuh.

Constructor & Destructor Documentation

◆ CopySpinor()

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder>

quda::CopySpinor< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder >::CopySpinor	(	OutOrder &	out,
		const InOrder &	in,
		const ColorSpinorField &	meta,
		QudaFieldLocation	location
	)

inline

Definition at line 61 of file copy_color_spinor_mg.cuh.

◆ ~CopySpinor()

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder>

virtual quda::CopySpinor< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder >::~CopySpinor ( )

inlinevirtual

Definition at line 63 of file copy_color_spinor_mg.cuh.

Member Function Documentation

◆ advanceSharedBytes()

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder>

bool quda::CopySpinor< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder >::advanceSharedBytes ( TuneParam & param ) const

inlineprivatevirtual

The goal here is to throttle the number of thread blocks per SM by over-allocating shared memory (in order to improve L2 utilization, etc.). We thus request the smallest amount of dynamic shared memory that guarantees throttling to a given number of blocks, in order to allow some extra leeway.

Reimplemented from quda::Tunable.

Definition at line 56 of file copy_color_spinor_mg.cuh.

◆ apply()

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder>

void quda::CopySpinor< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder >::apply ( const cudaStream_t & stream )

inlinevirtual

Implements quda::Tunable.

Definition at line 65 of file copy_color_spinor_mg.cuh.

References quda::TuneParam::block, getTuning(), getVerbosity(), quda::TuneParam::grid, in, out, QUDA_CPU_FIELD_LOCATION, quda::TuneParam::shared_bytes, quda::stream, quda::tuneLaunch(), and quda::ColorSpinorField::VolumeCB().

Here is the call graph for this function:

◆ bytes()

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder>

long long quda::CopySpinor< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder >::bytes ( ) const

inlinevirtual

Reimplemented from quda::Tunable.

Definition at line 79 of file copy_color_spinor_mg.cuh.

References in, and out.

◆ flops()

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder>

long long quda::CopySpinor< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder >::flops ( ) const

inlinevirtual

Implements quda::Tunable.

Definition at line 78 of file copy_color_spinor_mg.cuh.

◆ minThreads()

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder>

unsigned int quda::CopySpinor< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder >::minThreads ( ) const

inlineprivatevirtual

Reimplemented from quda::Tunable.

Definition at line 58 of file copy_color_spinor_mg.cuh.

References quda::ColorSpinorField::VolumeCB().

Here is the call graph for this function:

◆ sharedBytesPerBlock()

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder>

unsigned int quda::CopySpinor< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder >::sharedBytesPerBlock ( const TuneParam & param ) const

inlineprivatevirtual

Implements quda::Tunable.

Definition at line 55 of file copy_color_spinor_mg.cuh.

◆ sharedBytesPerThread()

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder>

unsigned int quda::CopySpinor< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder >::sharedBytesPerThread ( ) const

inlineprivatevirtual

Implements quda::Tunable.

Definition at line 53 of file copy_color_spinor_mg.cuh.

◆ tuneGridDim()

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder>

bool quda::CopySpinor< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder >::tuneGridDim ( ) const

inlineprivatevirtual

Reimplemented from quda::Tunable.

Definition at line 57 of file copy_color_spinor_mg.cuh.

◆ tuneKey()

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder>

TuneKey quda::CopySpinor< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder >::tuneKey ( ) const

inlinevirtual

Implements quda::Tunable.

Definition at line 76 of file copy_color_spinor_mg.cuh.

References quda::ColorSpinorField::AuxString(), and quda::LatticeField::VolString().

Here is the call graph for this function:

Member Data Documentation

◆ in

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder>

const InOrder& quda::CopySpinor< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder >::in

private

Definition at line 47 of file copy_color_spinor_mg.cuh.

◆ location

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder>

QudaFieldLocation quda::CopySpinor< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder >::location

private

Definition at line 50 of file copy_color_spinor_mg.cuh.

◆ meta

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder>

const ColorSpinorField& quda::CopySpinor< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder >::meta

private

Definition at line 49 of file copy_color_spinor_mg.cuh.

◆ out

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder>

OutOrder& quda::CopySpinor< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder >::out

private

Definition at line 48 of file copy_color_spinor_mg.cuh.

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

lib/copy_color_spinor_mg.cuh

Public Member Functions

Private Member Functions

Private Attributes

Detailed Description

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder> class quda::CopySpinor< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder >

Constructor & Destructor Documentation

◆ CopySpinor()

◆ ~CopySpinor()

Member Function Documentation

◆ advanceSharedBytes()

◆ apply()

◆ bytes()

◆ flops()

◆ minThreads()

◆ sharedBytesPerBlock()

◆ sharedBytesPerThread()

◆ tuneGridDim()

◆ tuneKey()

Member Data Documentation

◆ in

◆ location

◆ meta

◆ out

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder>
class quda::CopySpinor< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder >