QUDA v0.4.0
A library for QCD on GPUs
|
#include <blas_core.h>
Public Member Functions | |
BlasCuda (InputX &X, InputY &Y, InputZ &Z, InputW &W, Functor &f, OutputX &XX, OutputY &YY, OutputZ &ZZ, OutputW &WW, int length) | |
virtual | ~BlasCuda () |
TuneKey | tuneKey () const |
void | apply (const cudaStream_t &stream) |
void | preTune () |
void | postTune () |
long long | flops () const |
long long | bytes () const |
Definition at line 32 of file blas_core.h.
BlasCuda< FloatN, M, writeX, writeY, writeZ, writeW, InputX, InputY, InputZ, InputW, OutputX, OutputY, OutputZ, OutputW, Functor >::BlasCuda | ( | InputX & | X, |
InputY & | Y, | ||
InputZ & | Z, | ||
InputW & | W, | ||
Functor & | f, | ||
OutputX & | XX, | ||
OutputY & | YY, | ||
OutputZ & | ZZ, | ||
OutputW & | WW, | ||
int | length | ||
) | [inline] |
Definition at line 66 of file blas_core.h.
virtual BlasCuda< FloatN, M, writeX, writeY, writeZ, writeW, InputX, InputY, InputZ, InputW, OutputX, OutputY, OutputZ, OutputW, Functor >::~BlasCuda | ( | ) | [inline, virtual] |
Definition at line 70 of file blas_core.h.
void BlasCuda< FloatN, M, writeX, writeY, writeZ, writeW, InputX, InputY, InputZ, InputW, OutputX, OutputY, OutputZ, OutputW, Functor >::apply | ( | const cudaStream_t & | stream | ) | [inline, virtual] |
Implements Tunable.
Definition at line 82 of file blas_core.h.
long long BlasCuda< FloatN, M, writeX, writeY, writeZ, writeW, InputX, InputY, InputZ, InputW, OutputX, OutputY, OutputZ, OutputW, Functor >::bytes | ( | ) | const [inline, virtual] |
Reimplemented from Tunable.
Definition at line 108 of file blas_core.h.
long long BlasCuda< FloatN, M, writeX, writeY, writeZ, writeW, InputX, InputY, InputZ, InputW, OutputX, OutputY, OutputZ, OutputW, Functor >::flops | ( | ) | const [inline, virtual] |
Reimplemented from Tunable.
Definition at line 107 of file blas_core.h.
void BlasCuda< FloatN, M, writeX, writeY, writeZ, writeW, InputX, InputY, InputZ, InputW, OutputX, OutputY, OutputZ, OutputW, Functor >::postTune | ( | ) | [inline, virtual] |
Reimplemented from Tunable.
Definition at line 98 of file blas_core.h.
void BlasCuda< FloatN, M, writeX, writeY, writeZ, writeW, InputX, InputY, InputZ, InputW, OutputX, OutputY, OutputZ, OutputW, Functor >::preTune | ( | ) | [inline, virtual] |
Reimplemented from Tunable.
Definition at line 89 of file blas_core.h.
TuneKey BlasCuda< FloatN, M, writeX, writeY, writeZ, writeW, InputX, InputY, InputZ, InputW, OutputX, OutputY, OutputZ, OutputW, Functor >::tuneKey | ( | ) | const [inline, virtual] |
Implements Tunable.
Definition at line 72 of file blas_core.h.