QUDA
1.0.0
|
Public Member Functions | |
GaugeOvrImpSTOUT (Arg &arg, const GaugeField &meta) | |
virtual | ~GaugeOvrImpSTOUT () |
void | apply (const cudaStream_t &stream) |
TuneKey | tuneKey () const |
void | preTune () |
void | postTune () |
long long | flops () const |
long long | bytes () const |
Private Member Functions | |
bool | tuneGridDim () const |
unsigned int | minThreads () const |
![]() | |
TunableVectorYZ (unsigned int vector_length_y, unsigned int vector_length_z) | |
bool | advanceBlockDim (TuneParam ¶m) const |
void | initTuneParam (TuneParam ¶m) const |
void | defaultTuneParam (TuneParam ¶m) const |
void | resizeVector (int y, int z) const |
void | resizeStep (int y, int z) const |
![]() | |
TunableVectorY (unsigned int vector_length_y) | |
void | resizeVector (int y) const |
void | resizeStep (int y) const |
virtual unsigned int | sharedBytesPerThread () const |
virtual unsigned int | sharedBytesPerBlock (const TuneParam ¶m) const |
![]() | |
Tunable () | |
virtual | ~Tunable () |
virtual int | tuningIter () const |
virtual std::string | paramString (const TuneParam ¶m) const |
virtual std::string | perfString (float time) const |
virtual bool | advanceTuneParam (TuneParam ¶m) const |
void | checkLaunchParam (TuneParam ¶m) |
CUresult | jitifyError () const |
CUresult & | jitifyError () |
virtual bool | tuneAuxDim () const |
virtual bool | tuneSharedBytes () const |
virtual bool | advanceGridDim (TuneParam ¶m) const |
virtual unsigned int | maxBlockSize (const TuneParam ¶m) 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 ¶m) 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 ¶m) const |
virtual bool | advanceAux (TuneParam ¶m) const |
int | writeAuxString (const char *format,...) |
Private Attributes | |
Arg & | arg |
const GaugeField & | meta |
![]() | |
unsigned int | vector_length_y |
unsigned int | step_y |
bool | tune_block_x |
![]() | |
char | aux [TuneKey::aux_n] |
CUresult | jitify_error |
Definition at line 160 of file gauge_stout.cu.
|
inline |
Definition at line 171 of file gauge_stout.cu.
|
inlinevirtual |
Definition at line 172 of file gauge_stout.cu.
|
inlinevirtual |
Implements quda::Tunable.
Definition at line 174 of file gauge_stout.cu.
References quda::arg(), quda::TuneParam::block, errorQuda, getTuning(), getVerbosity(), quda::TuneParam::grid, quda::LatticeField::Location(), QUDA_CUDA_FIELD_LOCATION, quda::TuneParam::shared_bytes, and quda::tuneLaunch().
|
inlinevirtual |
Reimplemented from quda::Tunable.
Definition at line 204 of file gauge_stout.cu.
|
inlinevirtual |
Implements quda::Tunable.
Definition at line 203 of file gauge_stout.cu.
|
inlineprivatevirtual |
Reimplemented from quda::Tunable.
Definition at line 167 of file gauge_stout.cu.
|
inlinevirtual |
Reimplemented from quda::Tunable.
Definition at line 201 of file gauge_stout.cu.
|
inlinevirtual |
Reimplemented from quda::Tunable.
Definition at line 200 of file gauge_stout.cu.
|
inlineprivatevirtual |
Reimplemented from quda::Tunable.
Definition at line 166 of file gauge_stout.cu.
|
inlinevirtual |
Implements quda::Tunable.
Definition at line 193 of file gauge_stout.cu.
References quda::LatticeField::VolString().
|
private |
Definition at line 162 of file gauge_stout.cu.
|
private |
Definition at line 163 of file gauge_stout.cu.