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::QudaMemCopy Class Reference
Inheritance diagram for quda::QudaMemCopy:
Inheritance graph
[legend]
Collaboration diagram for quda::QudaMemCopy:
Collaboration graph
[legend]

Public Member Functions

 QudaMemCopy (void *dst, const void *src, size_t count, cudaMemcpyKind kind, bool async, const char *func, const char *file, const char *line)
 
virtual ~QudaMemCopy ()
 
void apply (const cudaStream_t &stream)
 
bool advanceTuneParam (TuneParam &param) const
 
TuneKey tuneKey () const
 
long long flops () const
 
long long bytes () const
 
- Public 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
 
void checkLaunchParam (TuneParam &param)
 
CUresult jitifyError () const
 
CUresult & jitifyError ()
 

Private Member Functions

unsigned int sharedBytesPerThread () const
 
unsigned int sharedBytesPerBlock (const TuneParam &param) const
 

Private Attributes

void * dst
 
const void * src
 
const size_t count
 
const cudaMemcpyKind kind
 
const bool async
 
const char * name
 

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 advanceSharedBytes (TuneParam &param) const
 
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

Definition at line 29 of file quda_cuda_api.cpp.

Constructor & Destructor Documentation

◆ QudaMemCopy()

quda::QudaMemCopy::QudaMemCopy ( void *  dst,
const void *  src,
size_t  count,
cudaMemcpyKind  kind,
bool  async,
const char *  func,
const char *  file,
const char *  line 
)
inline

Definition at line 42 of file quda_cuda_api.cpp.

References quda::Tunable::aux, and errorQuda.

◆ ~QudaMemCopy()

virtual quda::QudaMemCopy::~QudaMemCopy ( )
inlinevirtual

Definition at line 72 of file quda_cuda_api.cpp.

Member Function Documentation

◆ advanceTuneParam()

bool quda::QudaMemCopy::advanceTuneParam ( TuneParam param) const
inlinevirtual

Reimplemented from quda::Tunable.

Definition at line 112 of file quda_cuda_api.cpp.

◆ apply()

void quda::QudaMemCopy::apply ( const cudaStream_t &  stream)
inlinevirtual

Implements quda::Tunable.

Definition at line 74 of file quda_cuda_api.cpp.

References errorQuda, getTuning(), getVerbosity(), PROFILE, quda::QUDA_PROFILE_MEMCPY_D2D_ASYNC, quda::QUDA_PROFILE_MEMCPY_D2H_ASYNC, quda::QUDA_PROFILE_MEMCPY_H2D_ASYNC, and quda::tuneLaunch().

Referenced by quda::qudaMemcpy_(), and quda::qudaMemcpyAsync_().

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

◆ bytes()

long long quda::QudaMemCopy::bytes ( ) const
inlinevirtual

Reimplemented from quda::Tunable.

Definition at line 122 of file quda_cuda_api.cpp.

References count.

◆ flops()

long long quda::QudaMemCopy::flops ( ) const
inlinevirtual

Implements quda::Tunable.

Definition at line 121 of file quda_cuda_api.cpp.

◆ sharedBytesPerBlock()

unsigned int quda::QudaMemCopy::sharedBytesPerBlock ( const TuneParam param) const
inlineprivatevirtual

Implements quda::Tunable.

Definition at line 39 of file quda_cuda_api.cpp.

◆ sharedBytesPerThread()

unsigned int quda::QudaMemCopy::sharedBytesPerThread ( ) const
inlineprivatevirtual

Implements quda::Tunable.

Definition at line 38 of file quda_cuda_api.cpp.

◆ tuneKey()

TuneKey quda::QudaMemCopy::tuneKey ( ) const
inlinevirtual

Implements quda::Tunable.

Definition at line 114 of file quda_cuda_api.cpp.

References quda::Tunable::aux, and quda::u64toa().

Here is the call graph for this function:

Member Data Documentation

◆ async

const bool quda::QudaMemCopy::async
private

Definition at line 35 of file quda_cuda_api.cpp.

◆ count

const size_t quda::QudaMemCopy::count
private

Definition at line 33 of file quda_cuda_api.cpp.

Referenced by bytes().

◆ dst

void* quda::QudaMemCopy::dst
private

Definition at line 31 of file quda_cuda_api.cpp.

Referenced by quda::qudaMemcpy2DAsync_().

◆ kind

const cudaMemcpyKind quda::QudaMemCopy::kind
private

Definition at line 34 of file quda_cuda_api.cpp.

◆ name

const char* quda::QudaMemCopy::name
private

Definition at line 36 of file quda_cuda_api.cpp.

◆ src

const void* quda::QudaMemCopy::src
private

Definition at line 32 of file quda_cuda_api.cpp.


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