QUDA v0.4.0
A library for QCD on GPUs
Public Member Functions
BlasCuda< FloatN, M, writeX, writeY, writeZ, writeW, InputX, InputY, InputZ, InputW, OutputX, OutputY, OutputZ, OutputW, Functor > Class Template Reference

#include <blas_core.h>

Inheritance diagram for BlasCuda< FloatN, M, writeX, writeY, writeZ, writeW, InputX, InputY, InputZ, InputW, OutputX, OutputY, OutputZ, OutputW, Functor >:

List of all members.

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

Detailed Description

template<typename FloatN, int M, int writeX, int writeY, int writeZ, int writeW, typename InputX, typename InputY, typename InputZ, typename InputW, typename OutputX, typename OutputY, typename OutputZ, typename OutputW, typename Functor>
class BlasCuda< FloatN, M, writeX, writeY, writeZ, writeW, InputX, InputY, InputZ, InputW, OutputX, OutputY, OutputZ, OutputW, Functor >

Definition at line 32 of file blas_core.h.


Constructor & Destructor Documentation

template<typename FloatN , int M, int writeX, int writeY, int writeZ, int writeW, typename InputX , typename InputY , typename InputZ , typename InputW , typename OutputX , typename OutputY , typename OutputZ , typename OutputW , typename Functor >
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.

template<typename FloatN , int M, int writeX, int writeY, int writeZ, int writeW, typename InputX , typename InputY , typename InputZ , typename InputW , typename OutputX , typename OutputY , typename OutputZ , typename OutputW , typename Functor >
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.


Member Function Documentation

template<typename FloatN , int M, int writeX, int writeY, int writeZ, int writeW, typename InputX , typename InputY , typename InputZ , typename InputW , typename OutputX , typename OutputY , typename OutputZ , typename OutputW , typename Functor >
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.

template<typename FloatN , int M, int writeX, int writeY, int writeZ, int writeW, typename InputX , typename InputY , typename InputZ , typename InputW , typename OutputX , typename OutputY , typename OutputZ , typename OutputW , typename Functor >
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.

template<typename FloatN , int M, int writeX, int writeY, int writeZ, int writeW, typename InputX , typename InputY , typename InputZ , typename InputW , typename OutputX , typename OutputY , typename OutputZ , typename OutputW , typename Functor >
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.

template<typename FloatN , int M, int writeX, int writeY, int writeZ, int writeW, typename InputX , typename InputY , typename InputZ , typename InputW , typename OutputX , typename OutputY , typename OutputZ , typename OutputW , typename Functor >
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.

template<typename FloatN , int M, int writeX, int writeY, int writeZ, int writeW, typename InputX , typename InputY , typename InputZ , typename InputW , typename OutputX , typename OutputY , typename OutputZ , typename OutputW , typename Functor >
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.

template<typename FloatN , int M, int writeX, int writeY, int writeZ, int writeW, typename InputX , typename InputY , typename InputZ , typename InputW , typename OutputX , typename OutputY , typename OutputZ , typename OutputW , typename Functor >
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.


The documentation for this class was generated from the following file:
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Defines