quda::TunableVectorY Class Reference

#include <tune_quda.h>

Inheritance diagram for quda::TunableVectorY:

Collaboration diagram for quda::TunableVectorY:

Public Member Functions
	TunableVectorY (unsigned int vector_length_y)
bool	advanceBlockDim (TuneParam &param) const
void	initTuneParam (TuneParam &param) const
void	defaultTuneParam (TuneParam &param) const
void	resizeVector (int y)
Public Member Functions inherited from quda::Tunable
	Tunable ()
virtual	~Tunable ()
virtual TuneKey	tuneKey () const =0
virtual void	apply (const cudaStream_t &stream)=0
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 bool	advanceTuneParam (TuneParam &param) const
void	checkLaunchParam (TuneParam &param)

Protected Member Functions
virtual unsigned int	sharedBytesPerThread () const
virtual unsigned int	sharedBytesPerBlock (const TuneParam &param) const
Protected Member Functions inherited from quda::Tunable
virtual long long	flops () const =0
virtual long long	bytes () const
virtual unsigned int	minThreads () const
virtual bool	tuneGridDim () const
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
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	advanceSharedBytes (TuneParam &param) const
virtual bool	advanceAux (TuneParam &param) const
int	writeAuxString (const char *format,...)

Protected Attributes
unsigned int	vector_length_y
Protected Attributes inherited from quda::Tunable
char	aux [TuneKey::aux_n]

Detailed Description

This derived class is for algorithms that deploy a vector of computations across the y dimension of both the threads block and grid. For example this could be parity in the y dimension and checkerboarded volume in x.

Definition at line 346 of file tune_quda.h.

Constructor & Destructor Documentation

TunableVectorY()

quda::TunableVectorY::TunableVectorY ( unsigned int  vector_length_y )

inline

Definition at line 355 of file tune_quda.h.

Member Function Documentation

advanceBlockDim()

bool quda::TunableVectorY::advanceBlockDim ( TuneParam &  param ) const

inlinevirtual

Reimplemented from quda::Tunable.

Reimplemented in quda::TunableVectorYZ.

Definition at line 357 of file tune_quda.h.

References quda::Tunable::advanceBlockDim(), deg_tm_dslash_cuda_gen::block(), deviceProp, param, ret, and vector_length_y.

Referenced by quda::TunableVectorYZ::advanceBlockDim().

Here is the call graph for this function:

Here is the caller graph for this function:

defaultTuneParam()

void quda::TunableVectorY::defaultTuneParam ( TuneParam &  param ) const

inlinevirtual

sets default values for when tuning is disabled

Reimplemented from quda::Tunable.

Reimplemented in quda::TunableVectorYZ.

Definition at line 390 of file tune_quda.h.

References quda::Tunable::defaultTuneParam(), param, and vector_length_y.

Referenced by quda::TunableVectorYZ::defaultTuneParam().

Here is the call graph for this function:

Here is the caller graph for this function:

initTuneParam()

void quda::TunableVectorY::initTuneParam ( TuneParam &  param ) const

inlinevirtual

Reimplemented from quda::Tunable.

Reimplemented in quda::TunableVectorYZ.

Definition at line 382 of file tune_quda.h.

References quda::Tunable::initTuneParam(), param, and vector_length_y.

Referenced by quda::TunableVectorYZ::initTuneParam().

Here is the call graph for this function:

Here is the caller graph for this function:

resizeVector()

void quda::TunableVectorY::resizeVector ( int  y )

inline

Definition at line 397 of file tune_quda.h.

References vector_length_y, and y.

Referenced by quda::TunableVectorYZ::resizeVector().

Here is the caller graph for this function:

sharedBytesPerBlock()

virtual unsigned int quda::TunableVectorY::sharedBytesPerBlock ( const TuneParam &  param ) const

inlineprotectedvirtual

Implements quda::Tunable.

Reimplemented in quda::CopyColorSpinor< FloatOut, FloatIn, 4, Nc, Arg >, quda::CopyGauge< FloatOut, FloatIn, length, OutOrder, InOrder, isGhost >, and quda::CopyColorSpinor< FloatOut, FloatIn, Ns, Nc, Arg >.

Definition at line 350 of file tune_quda.h.

sharedBytesPerThread()

virtual unsigned int quda::TunableVectorY::sharedBytesPerThread ( ) const

inlineprotectedvirtual

Implements quda::Tunable.

Reimplemented in quda::CopyColorSpinor< FloatOut, FloatIn, 4, Nc, Arg >, quda::CopyGauge< FloatOut, FloatIn, length, OutOrder, InOrder, isGhost >, and quda::CopyColorSpinor< FloatOut, FloatIn, Ns, Nc, Arg >.

Definition at line 349 of file tune_quda.h.

Member Data Documentation

vector_length_y

unsigned int quda::TunableVectorY::vector_length_y

protected

Definition at line 352 of file tune_quda.h.

Referenced by advanceBlockDim(), defaultTuneParam(), initTuneParam(), and resizeVector().

---

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

• include/tune_quda.h