QUDA  1.0.0
All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros
Public Member Functions | Private Member Functions | Private Attributes | List of all members
quda::CopySpinorEx< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder, Basis, extend > Class Template Reference
Inheritance diagram for quda::CopySpinorEx< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder, Basis, extend >:
Inheritance graph
[legend]
Collaboration diagram for quda::CopySpinorEx< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder, Basis, extend >:
Collaboration graph
[legend]

Public Member Functions

 CopySpinorEx (CopySpinorExArg< OutOrder, InOrder, Basis > &arg, const ColorSpinorField &meta, QudaFieldLocation location)
 
virtual ~CopySpinorEx ()
 
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 advanceSharedBytes (TuneParam &param) 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 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,...)
 

Private Attributes

CopySpinorExArg< OutOrder, InOrder, Basis > arg
 
const ColorSpinorFieldmeta
 
QudaFieldLocation location
 
- Private Attributes inherited from quda::Tunable
char aux [TuneKey::aux_n]
 
CUresult jitify_error
 

Detailed Description

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder, typename Basis, bool extend>
class quda::CopySpinorEx< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder, Basis, extend >

Definition at line 228 of file extended_color_spinor_utilities.cu.

Constructor & Destructor Documentation

◆ CopySpinorEx()

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder, typename Basis, bool extend>
quda::CopySpinorEx< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder, Basis, extend >::CopySpinorEx ( CopySpinorExArg< OutOrder, InOrder, Basis > &  arg,
const ColorSpinorField meta,
QudaFieldLocation  location 
)
inline

◆ ~CopySpinorEx()

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder, typename Basis, bool extend>
virtual quda::CopySpinorEx< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder, Basis, extend >::~CopySpinorEx ( )
inlinevirtual

Definition at line 246 of file extended_color_spinor_utilities.cu.

Member Function Documentation

◆ advanceSharedBytes()

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder, typename Basis, bool extend>
bool quda::CopySpinorEx< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder, Basis, extend >::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 237 of file extended_color_spinor_utilities.cu.

◆ apply()

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder, typename Basis, bool extend>
void quda::CopySpinorEx< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder, Basis, extend >::apply ( const cudaStream_t &  stream)
inlinevirtual

Implements quda::Tunable.

Definition at line 248 of file extended_color_spinor_utilities.cu.

References quda::arg(), quda::TuneParam::block, getTuning(), getVerbosity(), quda::TuneParam::grid, QUDA_CPU_FIELD_LOCATION, QUDA_CUDA_FIELD_LOCATION, quda::TuneParam::shared_bytes, and quda::tuneLaunch().

Referenced by quda::copySpinorEx().

Here is the call graph for this function:
Here is the caller graph for this function:

◆ bytes()

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder, typename Basis, bool extend>
long long quda::CopySpinorEx< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder, Basis, extend >::bytes ( ) const
inlinevirtual

◆ flops()

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder, typename Basis, bool extend>
long long quda::CopySpinorEx< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder, Basis, extend >::flops ( ) const
inlinevirtual

Implements quda::Tunable.

Definition at line 261 of file extended_color_spinor_utilities.cu.

◆ minThreads()

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder, typename Basis, bool extend>
unsigned int quda::CopySpinorEx< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder, Basis, extend >::minThreads ( ) const
inlineprivatevirtual

◆ sharedBytesPerBlock()

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder, typename Basis, bool extend>
unsigned int quda::CopySpinorEx< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder, Basis, extend >::sharedBytesPerBlock ( const TuneParam param) const
inlineprivatevirtual

Implements quda::Tunable.

Definition at line 236 of file extended_color_spinor_utilities.cu.

◆ sharedBytesPerThread()

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder, typename Basis, bool extend>
unsigned int quda::CopySpinorEx< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder, Basis, extend >::sharedBytesPerThread ( ) const
inlineprivatevirtual

Implements quda::Tunable.

Definition at line 235 of file extended_color_spinor_utilities.cu.

◆ tuneGridDim()

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder, typename Basis, bool extend>
bool quda::CopySpinorEx< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder, Basis, extend >::tuneGridDim ( ) const
inlineprivatevirtual

Reimplemented from quda::Tunable.

Definition at line 238 of file extended_color_spinor_utilities.cu.

◆ tuneKey()

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder, typename Basis, bool extend>
TuneKey quda::CopySpinorEx< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder, Basis, extend >::tuneKey ( ) const
inlinevirtual

Implements quda::Tunable.

Definition at line 259 of file extended_color_spinor_utilities.cu.

References quda::LatticeField::VolString().

Here is the call graph for this function:

Member Data Documentation

◆ arg

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder, typename Basis, bool extend>
CopySpinorExArg<OutOrder,InOrder,Basis> quda::CopySpinorEx< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder, Basis, extend >::arg
private

Definition at line 230 of file extended_color_spinor_utilities.cu.

◆ location

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder, typename Basis, bool extend>
QudaFieldLocation quda::CopySpinorEx< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder, Basis, extend >::location
private

Definition at line 232 of file extended_color_spinor_utilities.cu.

◆ meta

template<typename FloatOut, typename FloatIn, int Ns, int Nc, typename OutOrder, typename InOrder, typename Basis, bool extend>
const ColorSpinorField& quda::CopySpinorEx< FloatOut, FloatIn, Ns, Nc, OutOrder, InOrder, Basis, extend >::meta
private

Definition at line 231 of file extended_color_spinor_utilities.cu.


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