quda::TunableVectorY Class Reference

#include <tune_quda.h>

Inheritance 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) const
void	resizeStep (int y) const
Public Member Functions inherited from quda::Tunable
	Tunable ()
virtual	~Tunable ()
virtual TuneKey	tuneKey () const =0
virtual void	apply (const qudaStream_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)
CUresult	jitifyError () const
CUresult &	jitifyError ()

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 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
	Returns the maximum number of simultaneously resident blocks per SM. We can directly query this of CUDA 11, but previously this needed to be hand coded. More...
unsigned int	maxDynamicSharedBytesPerBlock () const
	Returns the maximum dynamic shared memory per block. 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,...)
bool	tuned ()
	Whether the present instance has already been tuned or not. More...

Protected Attributes
unsigned int	vector_length_y
unsigned int	step_y
bool	tune_block_x
Protected Attributes inherited from quda::Tunable
char	aux [TuneKey::aux_n]
CUresult	jitify_error

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 462 of file tune_quda.h.

Constructor & Destructor Documentation

TunableVectorY()

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

inline

Definition at line 473 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 476 of file tune_quda.h.

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 510 of file tune_quda.h.

initTuneParam()

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

inlinevirtual

Reimplemented from quda::Tunable.

Reimplemented in quda::TunableVectorYZ.

Definition at line 502 of file tune_quda.h.

resizeStep()

void quda::TunableVectorY::resizeStep ( int  y ) const

inline

Definition at line 518 of file tune_quda.h.

resizeVector()

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

inline

Definition at line 517 of file tune_quda.h.

sharedBytesPerBlock()

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

inlineprotectedvirtual

Implements quda::Tunable.

Definition at line 466 of file tune_quda.h.

sharedBytesPerThread()

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

inlineprotectedvirtual

Implements quda::Tunable.

Definition at line 465 of file tune_quda.h.

Member Data Documentation

step_y

unsigned int quda::TunableVectorY::step_y

mutableprotected

Definition at line 469 of file tune_quda.h.

tune_block_x

bool quda::TunableVectorY::tune_block_x

protected

Definition at line 470 of file tune_quda.h.

vector_length_y

unsigned int quda::TunableVectorY::vector_length_y

mutableprotected

Definition at line 468 of file tune_quda.h.

---

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

• quda/include/tune_quda.h