Inheritance diagram for quda::Pack< Float, nColor, spin_project >:

Collaboration diagram for quda::Pack< Float, nColor, spin_project >:

[legend]

Public Member Functions
	Pack (void *ghost[], const ColorSpinorField &in, MemoryLocation location, int nFace, bool dagger, int parity, double a, double b, double c)

virtual	~Pack ()

template<typename T , typename Arg >
void	launch (T *f, const TuneParam &tp, Arg &arg, const cudaStream_t &stream)

void	apply (const cudaStream_t &stream)

bool	tuneSharedBytes () const

void	initTuneParam (TuneParam &param) const

void	defaultTuneParam (TuneParam &param) const

TuneKey	tuneKey () const

int	tuningIter () const

long long	flops () const

long long	bytes () const

Protected Member Functions
bool	tuneGridDim () const

unsigned int	maxGridSize () const

unsigned int	minGridSize () const

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

bool	tuneAuxDim () const

unsigned int	minThreads () const

void	fillAux ()

Protected Attributes
void **	ghost

const ColorSpinorField &	in

MemoryLocation	location

const int	nFace

const bool	dagger

const int	parity

const int	nParity

int	threads

const double	a

const double	b

const double	c

int	twist

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

bool	advanceBlockDim (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

virtual unsigned int	sharedBytesPerThread () const

virtual unsigned int	sharedBytesPerBlock (const TuneParam &param) const

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

virtual	~Tunable ()

virtual void	preTune ()

virtual void	postTune ()

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

virtual std::string	perfString (float time) const

virtual bool	advanceTuneParam (TuneParam &param) const

void	checkLaunchParam (TuneParam &param)

CUresult	jitifyError () const

CUresult &	jitifyError ()

virtual bool	advanceGridDim (TuneParam &param) const

virtual unsigned int	maxBlockSize (const TuneParam &param) const

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 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 Float, int nColor, bool spin_project>
class quda::Pack< Float, nColor, spin_project >

Definition at line 45 of file dslash_pack2.cu.

Constructor & Destructor Documentation

◆ Pack()

template<typename Float, int nColor, bool spin_project>

quda::Pack< Float, nColor, spin_project >::Pack	(	void *	ghost[],
		const ColorSpinorField &	in,
		MemoryLocation	location,
		int	nFace,
		bool	dagger,
		int	parity,
		double	a,
		double	b,
		double	c
	)

inline

Definition at line 164 of file dslash_pack2.cu.

References quda::commDim, quda::Pack< Float, nColor, spin_project >::fillAux(), quda::ColorSpinorField::getDslashConstant(), quda::getKernelPackT(), and quda::DslashConstant::ghostFaceCB.

Here is the call graph for this function:

◆ ~Pack()

template<typename Float, int nColor, bool spin_project>

virtual quda::Pack< Float, nColor, spin_project >::~Pack ( )

inlinevirtual

Definition at line 189 of file dslash_pack2.cu.

Member Function Documentation

◆ apply()

template<typename Float, int nColor, bool spin_project>

void quda::Pack< Float, nColor, spin_project >::apply ( const cudaStream_t & stream )

inlinevirtual

Implements quda::Tunable.

Definition at line 202 of file dslash_pack2.cu.

References quda::arg(), quda::TuneParam::aux, errorQuda, getTuning(), getVerbosity(), quda::TuneParam::grid, quda::Host, quda::Pack< Float, nColor, spin_project >::launch(), quda::ColorSpinorField::Nspin(), quda::ColorSpinorField::PCType(), QUDA_4D_PC, QUDA_5D_PC, and quda::tuneLaunch().

Referenced by quda::PackGhost().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ bytes()

template<typename Float, int nColor, bool spin_project>

long long quda::Pack< Float, nColor, spin_project >::bytes ( ) const

inlinevirtual

Reimplemented from quda::Tunable.

Definition at line 331 of file dslash_pack2.cu.

References quda::ColorSpinorField::getDslashConstant(), quda::DslashConstant::Ls, nColor, quda::ColorSpinorField::Nspin(), QUDA_HALF_PRECISION, QUDA_QUARTER_PRECISION, and quda::Pack< Float, nColor, spin_project >::threads.

Here is the call graph for this function:

◆ defaultTuneParam()

template<typename Float, int nColor, bool spin_project>

void quda::Pack< Float, nColor, spin_project >::defaultTuneParam ( TuneParam & param ) const

inlinevirtual

sets default values for when tuning is disabled

Reimplemented from quda::TunableVectorYZ.

Definition at line 309 of file dslash_pack2.cu.

References quda::TunableVectorYZ::defaultTuneParam(), quda::TuneParam::grid, quda::Host, quda::Tunable::maxDynamicSharedBytesPerBlock(), quda::Pack< Float, nColor, spin_project >::minGridSize(), and quda::TuneParam::shared_bytes.

Here is the call graph for this function:

◆ fillAux()

template<typename Float, int nColor, bool spin_project>

void quda::Pack< Float, nColor, spin_project >::fillAux ( )

inlineprotected

Definition at line 125 of file dslash_pack2.cu.

References quda::Tunable::aux, quda::LatticeField::AuxString(), comm_dim_topology_string(), comm_peer2peer_enabled_global(), quda::commDim, quda::Device, errorQuda, quda::getKernelPackT(), quda::Host, quda::ColorSpinorField::Nspin(), quda::ColorSpinorField::PCType(), QUDA_5D_PC, and quda::Remote.

Referenced by quda::Pack< Float, nColor, spin_project >::Pack().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ flops()

template<typename Float, int nColor, bool spin_project>

long long quda::Pack< Float, nColor, spin_project >::flops ( ) const

inlinevirtual

Implements quda::Tunable.

Definition at line 325 of file dslash_pack2.cu.

References quda::ColorSpinorField::getDslashConstant(), quda::DslashConstant::Ls, nColor, quda::ColorSpinorField::Nspin(), and quda::Pack< Float, nColor, spin_project >::threads.

Here is the call graph for this function:

◆ gridStep()

template<typename Float, int nColor, bool spin_project>

int quda::Pack< Float, nColor, spin_project >::gridStep ( ) const

inlineprotectedvirtual

gridStep sets the step size when iterating the grid size in advanceGridDim.

Returns: Grid step size

Reimplemented from quda::Tunable.

Definition at line 104 of file dslash_pack2.cu.

References quda::commDim, quda::Tunable::gridStep(), quda::Host, and quda::ColorSpinorField::Ndim().

Here is the call graph for this function:

◆ initTuneParam()

template<typename Float, int nColor, bool spin_project>

void quda::Pack< Float, nColor, spin_project >::initTuneParam ( TuneParam & param ) const

inlinevirtual

Reimplemented from quda::TunableVectorYZ.

Definition at line 297 of file dslash_pack2.cu.

References quda::TuneParam::grid, quda::Host, quda::TunableVectorYZ::initTuneParam(), quda::Tunable::maxDynamicSharedBytesPerBlock(), quda::Pack< Float, nColor, spin_project >::minGridSize(), and quda::TuneParam::shared_bytes.

Here is the call graph for this function:

◆ launch()

template<typename Float, int nColor, bool spin_project>

template<typename T , typename Arg >

void quda::Pack< Float, nColor, spin_project >::launch	(	T *	f,
		const TuneParam &	tp,
		Arg &	arg,
		const cudaStream_t &	stream
	)

inline

Definition at line 192 of file dslash_pack2.cu.

References quda::TuneParam::block, deviceProp, quda::TuneParam::grid, quda::qudaLaunchKernel(), quda::Tunable::setMaxDynamicSharedBytesPerBlock(), and quda::TuneParam::shared_bytes.

Referenced by quda::Pack< Float, nColor, spin_project >::apply().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ maxGridSize()

template<typename Float, int nColor, bool spin_project>

unsigned int quda::Pack< Float, nColor, spin_project >::maxGridSize ( ) const

inlineprotectedvirtual

Reimplemented from quda::Tunable.

Definition at line 64 of file dslash_pack2.cu.

References quda::commDim, quda::Host, quda::Tunable::maxGridSize(), and quda::ColorSpinorField::Ndim().

Here is the call graph for this function:

◆ minGridSize()

template<typename Float, int nColor, bool spin_project>

unsigned int quda::Pack< Float, nColor, spin_project >::minGridSize ( ) const

inlineprotectedvirtual

Reimplemented from quda::Tunable.

Definition at line 84 of file dslash_pack2.cu.

References quda::commDim, quda::Host, quda::Tunable::minGridSize(), and quda::ColorSpinorField::Ndim().

Referenced by quda::Pack< Float, nColor, spin_project >::defaultTuneParam(), and quda::Pack< Float, nColor, spin_project >::initTuneParam().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ minThreads()

template<typename Float, int nColor, bool spin_project>

unsigned int quda::Pack< Float, nColor, spin_project >::minThreads ( ) const

inlineprotectedvirtual

Reimplemented from quda::Tunable.

Definition at line 123 of file dslash_pack2.cu.

References quda::Pack< Float, nColor, spin_project >::threads.

◆ tuneAuxDim()

template<typename Float, int nColor, bool spin_project>

bool quda::Pack< Float, nColor, spin_project >::tuneAuxDim ( ) const

inlineprotectedvirtual

Reimplemented from quda::Tunable.

Definition at line 122 of file dslash_pack2.cu.

◆ tuneGridDim()

template<typename Float, int nColor, bool spin_project>

bool quda::Pack< Float, nColor, spin_project >::tuneGridDim ( ) const

inlineprotectedvirtual

Reimplemented from quda::Tunable.

Definition at line 62 of file dslash_pack2.cu.

◆ tuneKey()

template<typename Float, int nColor, bool spin_project>

TuneKey quda::Pack< Float, nColor, spin_project >::tuneKey ( ) const

inlinevirtual

Implements quda::Tunable.

Definition at line 321 of file dslash_pack2.cu.

References quda::Tunable::aux, and quda::LatticeField::VolString().

Here is the call graph for this function:

◆ tuneSharedBytes()

template<typename Float, int nColor, bool spin_project>

bool quda::Pack< Float, nColor, spin_project >::tuneSharedBytes ( ) const

inlinevirtual

Reimplemented from quda::Tunable.

Definition at line 289 of file dslash_pack2.cu.

References quda::Tunable::maxDynamicSharedBytesPerBlock(), and quda::Tunable::maxSharedBytesPerBlock().

Here is the call graph for this function:

◆ tuningIter()

template<typename Float, int nColor, bool spin_project>

int quda::Pack< Float, nColor, spin_project >::tuningIter ( ) const

inlinevirtual

Reimplemented from quda::Tunable.

Definition at line 323 of file dslash_pack2.cu.

Member Data Documentation

◆ a

template<typename Float, int nColor, bool spin_project>

const double quda::Pack< Float, nColor, spin_project >::a

protected

Definition at line 57 of file dslash_pack2.cu.

Referenced by quda::PackGhost().

◆ b

template<typename Float, int nColor, bool spin_project>

const double quda::Pack< Float, nColor, spin_project >::b

protected

Definition at line 58 of file dslash_pack2.cu.

Referenced by quda::PackGhost().

◆ c

template<typename Float, int nColor, bool spin_project>

const double quda::Pack< Float, nColor, spin_project >::c

protected

Definition at line 59 of file dslash_pack2.cu.

Referenced by quda::PackGhost().

◆ dagger

template<typename Float, int nColor, bool spin_project>

const bool quda::Pack< Float, nColor, spin_project >::dagger

protected

Definition at line 53 of file dslash_pack2.cu.

Referenced by quda::PackGhost().

◆ ghost

template<typename Float, int nColor, bool spin_project>

void** quda::Pack< Float, nColor, spin_project >::ghost

protected

Definition at line 49 of file dslash_pack2.cu.

Referenced by quda::PackGhost().

◆ in

template<typename Float, int nColor, bool spin_project>

const ColorSpinorField& quda::Pack< Float, nColor, spin_project >::in

protected

Definition at line 50 of file dslash_pack2.cu.

Referenced by quda::PackGhost().

◆ location

template<typename Float, int nColor, bool spin_project>

MemoryLocation quda::Pack< Float, nColor, spin_project >::location

protected

Definition at line 51 of file dslash_pack2.cu.

Referenced by quda::PackGhost().

◆ nFace

template<typename Float, int nColor, bool spin_project>

const int quda::Pack< Float, nColor, spin_project >::nFace

protected

Definition at line 52 of file dslash_pack2.cu.

Referenced by quda::PackGhost().

◆ nParity

template<typename Float, int nColor, bool spin_project>

const int quda::Pack< Float, nColor, spin_project >::nParity

protected

Definition at line 55 of file dslash_pack2.cu.

◆ parity

template<typename Float, int nColor, bool spin_project>

const int quda::Pack< Float, nColor, spin_project >::parity

protected

Definition at line 54 of file dslash_pack2.cu.

Referenced by quda::PackGhost().

◆ threads

template<typename Float, int nColor, bool spin_project>

int quda::Pack< Float, nColor, spin_project >::threads

protected

Definition at line 56 of file dslash_pack2.cu.

Referenced by quda::Pack< Float, nColor, spin_project >::bytes(), quda::Pack< Float, nColor, spin_project >::flops(), and quda::Pack< Float, nColor, spin_project >::minThreads().

◆ twist

template<typename Float, int nColor, bool spin_project>

int quda::Pack< Float, nColor, spin_project >::twist

protected

Definition at line 60 of file dslash_pack2.cu.

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

lib/dslash_pack2.cu

Public Member Functions

Protected Member Functions

Protected Attributes

Additional Inherited Members

Detailed Description

template<typename Float, int nColor, bool spin_project> class quda::Pack< Float, nColor, spin_project >

Constructor & Destructor Documentation

◆ Pack()

◆ ~Pack()

Member Function Documentation

◆ apply()

◆ bytes()

◆ defaultTuneParam()

◆ fillAux()

◆ flops()

◆ gridStep()

◆ initTuneParam()

◆ launch()

◆ maxGridSize()

◆ minGridSize()

◆ minThreads()

◆ tuneAuxDim()

◆ tuneGridDim()

◆ tuneKey()

◆ tuneSharedBytes()

◆ tuningIter()

Member Data Documentation

◆ a

◆ b

◆ c

◆ dagger

◆ ghost

◆ in

◆ location

◆ nFace

◆ nParity

◆ parity

◆ threads

◆ twist

template<typename Float, int nColor, bool spin_project>
class quda::Pack< Float, nColor, spin_project >