Inheritance diagram for quda::KSForceComplete< Float, Oprod, Gauge, Mom >:

Collaboration diagram for quda::KSForceComplete< Float, Oprod, Gauge, Mom >:

[legend]

Public Member Functions
	KSForceComplete (KSForceArg< Oprod, Gauge, Mom > &arg, const GaugeField &meta, QudaFieldLocation location)

virtual	~KSForceComplete ()

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	tuneSharedBytes () 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	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
KSForceArg< Oprod, Gauge, Mom >	arg

const GaugeField &	meta

const QudaFieldLocation	location

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

CUresult	jitify_error

Detailed Description

template<typename Float, typename Oprod, typename Gauge, typename Mom>
class quda::KSForceComplete< Float, Oprod, Gauge, Mom >

Definition at line 101 of file ks_force_quda.cu.

Constructor & Destructor Documentation

◆ KSForceComplete()

template<typename Float, typename Oprod, typename Gauge, typename Mom>

quda::KSForceComplete< Float, Oprod, Gauge, Mom >::KSForceComplete	(	KSForceArg< Oprod, Gauge, Mom > &	arg,
		const GaugeField &	meta,
		QudaFieldLocation	location
	)

inline

Definition at line 116 of file ks_force_quda.cu.

References quda::KSForceArg< Oprod, Gauge, Mom >::mom.

◆ ~KSForceComplete()

template<typename Float, typename Oprod, typename Gauge, typename Mom>

virtual quda::KSForceComplete< Float, Oprod, Gauge, Mom >::~KSForceComplete ( )

inlinevirtual

Definition at line 121 of file ks_force_quda.cu.

Member Function Documentation

◆ apply()

template<typename Float, typename Oprod, typename Gauge, typename Mom>

void quda::KSForceComplete< Float, Oprod, Gauge, Mom >::apply ( const cudaStream_t & stream )

inlinevirtual

Implements quda::Tunable.

Definition at line 123 of file ks_force_quda.cu.

References quda::arg(), QUDA_CUDA_FIELD_LOCATION, and quda::KSForceArg< Oprod, Gauge, Mom >::threads.

Referenced by quda::completeKSForce().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ bytes()

template<typename Float, typename Oprod, typename Gauge, typename Mom>

long long quda::KSForceComplete< Float, Oprod, Gauge, Mom >::bytes ( ) const

inlinevirtual

Reimplemented from quda::Tunable.

Definition at line 137 of file ks_force_quda.cu.

◆ flops()

template<typename Float, typename Oprod, typename Gauge, typename Mom>

long long quda::KSForceComplete< Float, Oprod, Gauge, Mom >::flops ( ) const

inlinevirtual

Implements quda::Tunable.

Definition at line 136 of file ks_force_quda.cu.

References quda::KSForceArg< Oprod, Gauge, Mom >::X.

Referenced by quda::completeKSForce().

Here is the caller graph for this function:

◆ minThreads()

template<typename Float, typename Oprod, typename Gauge, typename Mom>

unsigned int quda::KSForceComplete< Float, Oprod, Gauge, Mom >::minThreads ( ) const

inlineprivatevirtual

Reimplemented from quda::Tunable.

Definition at line 113 of file ks_force_quda.cu.

References quda::KSForceArg< Oprod, Gauge, Mom >::threads.

◆ sharedBytesPerBlock()

template<typename Float, typename Oprod, typename Gauge, typename Mom>

unsigned int quda::KSForceComplete< Float, Oprod, Gauge, Mom >::sharedBytesPerBlock ( const TuneParam & param ) const

inlineprivatevirtual

Implements quda::Tunable.

Definition at line 109 of file ks_force_quda.cu.

◆ sharedBytesPerThread()

template<typename Float, typename Oprod, typename Gauge, typename Mom>

unsigned int quda::KSForceComplete< Float, Oprod, Gauge, Mom >::sharedBytesPerThread ( ) const

inlineprivatevirtual

Implements quda::Tunable.

Definition at line 108 of file ks_force_quda.cu.

◆ tuneGridDim()

template<typename Float, typename Oprod, typename Gauge, typename Mom>

bool quda::KSForceComplete< Float, Oprod, Gauge, Mom >::tuneGridDim ( ) const

inlineprivatevirtual

Reimplemented from quda::Tunable.

Definition at line 112 of file ks_force_quda.cu.

◆ tuneKey()

template<typename Float, typename Oprod, typename Gauge, typename Mom>

TuneKey quda::KSForceComplete< Float, Oprod, Gauge, Mom >::tuneKey ( ) const

inlinevirtual

Implements quda::Tunable.

Definition at line 134 of file ks_force_quda.cu.

References quda::LatticeField::VolString().

Here is the call graph for this function:

◆ tuneSharedBytes()

template<typename Float, typename Oprod, typename Gauge, typename Mom>

bool quda::KSForceComplete< Float, Oprod, Gauge, Mom >::tuneSharedBytes ( ) const

inlineprivatevirtual

Reimplemented from quda::Tunable.

Definition at line 111 of file ks_force_quda.cu.

Member Data Documentation

◆ arg

template<typename Float, typename Oprod, typename Gauge, typename Mom>

KSForceArg<Oprod, Gauge, Mom> quda::KSForceComplete< Float, Oprod, Gauge, Mom >::arg

private

Definition at line 103 of file ks_force_quda.cu.

◆ location

template<typename Float, typename Oprod, typename Gauge, typename Mom>

const QudaFieldLocation quda::KSForceComplete< Float, Oprod, Gauge, Mom >::location

private

Definition at line 105 of file ks_force_quda.cu.

◆ meta

template<typename Float, typename Oprod, typename Gauge, typename Mom>

const GaugeField& quda::KSForceComplete< Float, Oprod, Gauge, Mom >::meta

private

Definition at line 104 of file ks_force_quda.cu.

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

lib/ks_force_quda.cu

Public Member Functions

Private Member Functions

Private Attributes

Detailed Description

template<typename Float, typename Oprod, typename Gauge, typename Mom> class quda::KSForceComplete< Float, Oprod, Gauge, Mom >

Constructor & Destructor Documentation

◆ KSForceComplete()

◆ ~KSForceComplete()

Member Function Documentation

◆ apply()

◆ bytes()

◆ flops()

◆ minThreads()

◆ sharedBytesPerBlock()

◆ sharedBytesPerThread()

◆ tuneGridDim()

◆ tuneKey()

◆ tuneSharedBytes()

Member Data Documentation

◆ arg

◆ location

◆ meta

template<typename Float, typename Oprod, typename Gauge, typename Mom>
class quda::KSForceComplete< Float, Oprod, Gauge, Mom >