QUDA
v1.1.0
A library for QCD on GPUs
|
#include <tune_quda.h>
Public Member Functions | |
TunableVectorY (unsigned int vector_length_y) | |
bool | advanceBlockDim (TuneParam ¶m) const |
void | initTuneParam (TuneParam ¶m) const |
void | defaultTuneParam (TuneParam ¶m) 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 ¶m) const |
virtual std::string | perfString (float time) const |
virtual bool | advanceTuneParam (TuneParam ¶m) const |
void | checkLaunchParam (TuneParam ¶m) |
CUresult | jitifyError () const |
CUresult & | jitifyError () |
Protected Member Functions | |
virtual unsigned int | sharedBytesPerThread () const |
virtual unsigned int | sharedBytesPerBlock (const TuneParam ¶m) 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 ¶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 |
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 ¶m) const |
virtual bool | advanceAux (TuneParam ¶m) 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 |
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.
|
inline |
Definition at line 473 of file tune_quda.h.
|
inlinevirtual |
Reimplemented from quda::Tunable.
Reimplemented in quda::TunableVectorYZ.
Definition at line 476 of file tune_quda.h.
|
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.
|
inlinevirtual |
Reimplemented from quda::Tunable.
Reimplemented in quda::TunableVectorYZ.
Definition at line 502 of file tune_quda.h.
|
inline |
Definition at line 518 of file tune_quda.h.
|
inline |
Definition at line 517 of file tune_quda.h.
|
inlineprotectedvirtual |
Implements quda::Tunable.
Definition at line 466 of file tune_quda.h.
|
inlineprotectedvirtual |
Implements quda::Tunable.
Definition at line 465 of file tune_quda.h.
|
mutableprotected |
Definition at line 469 of file tune_quda.h.
|
protected |
Definition at line 470 of file tune_quda.h.
|
mutableprotected |
Definition at line 468 of file tune_quda.h.