Inheritance diagram for quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >:

Collaboration diagram for quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >:

Public Member Functions
	CopyCuda (Output &Y, Input &X, int length, int nParity)

virtual	~CopyCuda ()

TuneKey	tuneKey () const

void	apply (const cudaStream_t &stream)

void	preTune ()

void	postTune ()

void	initTuneParam (TuneParam &param) const

void	defaultTuneParam (TuneParam &param) const

long long	flops () const

long long	bytes () const

int	tuningIter () const

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

virtual	~Tunable ()

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 ()

Private Member Functions
unsigned int	sharedBytesPerThread () const

unsigned int	sharedBytesPerBlock (const TuneParam &param) const

virtual bool	advanceSharedBytes (TuneParam &param) const

Private Attributes
Input &	X

Output &	Y

const int	length

const int	nParity

Additional Inherited Members
Protected Member Functions inherited from quda::Tunable
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

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	advanceAux (TuneParam &param) const

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

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

CUresult	jitify_error

Detailed Description

template<typename FloatN, int N, typename Output, typename Input>
class quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >

Definition at line 46 of file copy_quda.cu.

Constructor & Destructor Documentation

◆ CopyCuda()

template<typename FloatN , int N, typename Output , typename Input >

quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::CopyCuda	(	Output &	Y,
		Input &	X,
		int	length,
		int	nParity
	)

inline

Definition at line 68 of file copy_quda.cu.

◆ ~CopyCuda()

template<typename FloatN , int N, typename Output , typename Input >

virtual quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::~CopyCuda ( )

inlinevirtual

Definition at line 70 of file copy_quda.cu.

Member Function Documentation

◆ advanceSharedBytes()

template<typename FloatN , int N, typename Output , typename Input >

virtual bool quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::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 57 of file copy_quda.cu.

References quda::Tunable::advanceBlockDim(), quda::TuneParam::block, quda::TuneParam::shared_bytes, quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::sharedBytesPerBlock(), and quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::sharedBytesPerThread().

Here is the call graph for this function:

◆ apply()

template<typename FloatN , int N, typename Output , typename Input >

void quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::apply ( const cudaStream_t & stream )

inlinevirtual

Implements quda::Tunable.

Definition at line 76 of file copy_quda.cu.

References quda::TuneParam::block, getTuning(), getVerbosity(), quda::TuneParam::grid, quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::length, quda::TuneParam::shared_bytes, quda::tuneLaunch(), quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::X, and quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::Y.

Here is the call graph for this function:

◆ bytes()

template<typename FloatN , int N, typename Output , typename Input >

long long quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::bytes ( ) const

inlinevirtual

Reimplemented from quda::Tunable.

Definition at line 95 of file copy_quda.cu.

References quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::nParity, QUDA_HALF_PRECISION, and QUDA_QUARTER_PRECISION.

◆ defaultTuneParam()

template<typename FloatN , int N, typename Output , typename Input >

void quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::defaultTuneParam ( TuneParam & param ) const

inlinevirtual

sets default values for when tuning is disabled

Reimplemented from quda::Tunable.

Definition at line 89 of file copy_quda.cu.

References quda::Tunable::defaultTuneParam(), quda::TuneParam::grid, and quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::nParity.

Here is the call graph for this function:

◆ flops()

template<typename FloatN , int N, typename Output , typename Input >

long long quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::flops ( ) const

inlinevirtual

Implements quda::Tunable.

Definition at line 94 of file copy_quda.cu.

◆ initTuneParam()

template<typename FloatN , int N, typename Output , typename Input >

void quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::initTuneParam ( TuneParam & param ) const

inlinevirtual

Reimplemented from quda::Tunable.

Definition at line 84 of file copy_quda.cu.

References quda::TuneParam::grid, quda::Tunable::initTuneParam(), and quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::nParity.

Here is the call graph for this function:

◆ postTune()

template<typename FloatN , int N, typename Output , typename Input >

void quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::postTune ( )

inlinevirtual

Reimplemented from quda::Tunable.

Definition at line 82 of file copy_quda.cu.

◆ preTune()

template<typename FloatN , int N, typename Output , typename Input >

void quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::preTune ( )

inlinevirtual

Reimplemented from quda::Tunable.

Definition at line 81 of file copy_quda.cu.

◆ sharedBytesPerBlock()

template<typename FloatN , int N, typename Output , typename Input >

unsigned int quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::sharedBytesPerBlock ( const TuneParam & param ) const

inlineprivatevirtual

Implements quda::Tunable.

Definition at line 55 of file copy_quda.cu.

Referenced by quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::advanceSharedBytes().

Here is the caller graph for this function:

◆ sharedBytesPerThread()

template<typename FloatN , int N, typename Output , typename Input >

unsigned int quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::sharedBytesPerThread ( ) const

inlineprivatevirtual

Implements quda::Tunable.

Definition at line 54 of file copy_quda.cu.

Referenced by quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::advanceSharedBytes().

Here is the caller graph for this function:

◆ tuneKey()

template<typename FloatN , int N, typename Output , typename Input >

TuneKey quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::tuneKey ( ) const

inlinevirtual

Implements quda::Tunable.

Definition at line 72 of file copy_quda.cu.

References quda::blas::copy_ns::blasStrings.

◆ tuningIter()

template<typename FloatN , int N, typename Output , typename Input >

int quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::tuningIter ( ) const

inlinevirtual

Reimplemented from quda::Tunable.

Definition at line 102 of file copy_quda.cu.

Member Data Documentation

◆ length

template<typename FloatN , int N, typename Output , typename Input >

const int quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::length

private

Definition at line 51 of file copy_quda.cu.

Referenced by quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::apply().

◆ nParity

template<typename FloatN , int N, typename Output , typename Input >

const int quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::nParity

private

Definition at line 52 of file copy_quda.cu.

Referenced by quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::bytes(), quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::defaultTuneParam(), and quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::initTuneParam().

◆ X

template<typename FloatN , int N, typename Output , typename Input >

Input& quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::X

private

Definition at line 49 of file copy_quda.cu.

Referenced by quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::apply().

◆ Y

template<typename FloatN , int N, typename Output , typename Input >

Output& quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::Y

private

Definition at line 50 of file copy_quda.cu.

Referenced by quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >::apply().

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

lib/copy_quda.cu

Public Member Functions

Private Member Functions

Private Attributes

Additional Inherited Members

Detailed Description

template<typename FloatN, int N, typename Output, typename Input> class quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >

Constructor & Destructor Documentation

◆ CopyCuda()

◆ ~CopyCuda()

Member Function Documentation

◆ advanceSharedBytes()

◆ apply()

◆ bytes()

◆ defaultTuneParam()

◆ flops()

◆ initTuneParam()

◆ postTune()

◆ preTune()

◆ sharedBytesPerBlock()

◆ sharedBytesPerThread()

◆ tuneKey()

◆ tuningIter()

Member Data Documentation

◆ length

◆ nParity

◆ X

◆ Y

template<typename FloatN, int N, typename Output, typename Input>
class quda::blas::copy_ns::CopyCuda< FloatN, N, Output, Input >