QUDA
1.0.0
|
Public Member Functions | |
TwistClover (Arg &arg, const ColorSpinorField &meta) | |
virtual | ~TwistClover () |
void | apply (const cudaStream_t &stream) |
TuneKey | tuneKey () const |
void | preTune () |
void | postTune () |
![]() | |
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 |
![]() | |
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 () |
Protected Member Functions | |
long long | flops () const |
long long | bytes () const |
bool | tuneGridDim () const |
unsigned int | minThreads () const |
![]() | |
virtual unsigned int | sharedBytesPerThread () const |
virtual unsigned int | sharedBytesPerBlock (const TuneParam ¶m) 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 |
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,...) |
Protected Attributes | |
Arg & | arg |
const ColorSpinorField & | 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 725 of file dslash_quda.cu.
|
inline |
Definition at line 743 of file dslash_quda.cu.
References quda::LatticeField::AuxString().
|
inlinevirtual |
Definition at line 748 of file dslash_quda.cu.
|
inlinevirtual |
Implements quda::Tunable.
Definition at line 750 of file dslash_quda.cu.
References quda::arg(), quda::TuneParam::block, getTuning(), getVerbosity(), quda::TuneParam::grid, quda::LatticeField::Location(), QUDA_CPU_FIELD_LOCATION, quda::TuneParam::shared_bytes, and quda::tuneLaunch().
Referenced by quda::ApplyTwistClover().
|
inlineprotectedvirtual |
Reimplemented from quda::Tunable.
Definition at line 733 of file dslash_quda.cu.
References quda::Arg< real, Ns, Nc, order >::nParity, QUDA_TWIST_GAMMA5_INVERSE, and quda::Arg< real, Ns, Nc, order >::volumeCB.
|
inlineprotectedvirtual |
Implements quda::Tunable.
Definition at line 732 of file dslash_quda.cu.
References quda::Arg< real, Ns, Nc, order >::nParity, and quda::Arg< real, Ns, Nc, order >::volumeCB.
|
inlineprotectedvirtual |
Reimplemented from quda::Tunable.
Definition at line 740 of file dslash_quda.cu.
References quda::Arg< real, Ns, Nc, order >::volumeCB.
|
inlinevirtual |
Reimplemented from quda::Tunable.
Definition at line 764 of file dslash_quda.cu.
|
inlinevirtual |
Reimplemented from quda::Tunable.
Definition at line 763 of file dslash_quda.cu.
|
inlineprotectedvirtual |
Reimplemented from quda::Tunable.
Definition at line 739 of file dslash_quda.cu.
|
inlinevirtual |
Implements quda::Tunable.
Definition at line 762 of file dslash_quda.cu.
References quda::LatticeField::VolString().
|
protected |
Definition at line 728 of file dslash_quda.cu.
|
protected |
Definition at line 729 of file dslash_quda.cu.