quda::blas::MultiReduceFunctor< NXZ, ReduceType, Float2, FloatN > Struct Template Reference

Inheritance diagram for quda::blas::MultiReduceFunctor< NXZ, ReduceType, Float2, FloatN >:

Public Member Functions
virtual __device__ __host__ void	pre ()
	pre-computation routine called before the "M-loop" More...
virtual __device__ __host__ __host__ void	operator() (ReduceType &sum, FloatN &x, FloatN &y, FloatN &z, FloatN &w, const int i, const int j)=0
	where the reduction is usually computed and any auxiliary operations More...
virtual __device__ __host__ void	post (ReduceType &sum)
	post-computation routine called after the "M-loop" More...

Detailed Description

template<int NXZ, typename ReduceType, typename Float2, typename FloatN>
struct quda::blas::MultiReduceFunctor< NXZ, ReduceType, Float2, FloatN >

Base class from which all reduction functors should derive.

Definition at line 140 of file multi_reduce_core.cuh.

Member Function Documentation

operator()()

template<int NXZ, typename ReduceType , typename Float2 , typename FloatN >

virtual __device__ __host__ __host__ void quda::blas::MultiReduceFunctor< NXZ, ReduceType, Float2, FloatN >::operator() ( ReduceType &  sum, FloatN &  x, FloatN &  y, FloatN &  z, FloatN &  w, const int  i, const int  j  )

pure virtual

where the reduction is usually computed and any auxiliary operations

Implemented in quda::blas::CdotCopy< NXZ, ReduceType, Float2, FloatN >, quda::blas::Cdot< NXZ, ReduceType, Float2, FloatN >, and quda::blas::Dot< NXZ, ReduceType, Float2, FloatN >.

post()

template<int NXZ, typename ReduceType , typename Float2 , typename FloatN >

virtual __device__ __host__ void quda::blas::MultiReduceFunctor< NXZ, ReduceType, Float2, FloatN >::post ( ReduceType &  sum )

inlinevirtual

post-computation routine called after the "M-loop"

Definition at line 151 of file multi_reduce_core.cuh.

pre()

template<int NXZ, typename ReduceType , typename Float2 , typename FloatN >

virtual __device__ __host__ void quda::blas::MultiReduceFunctor< NXZ, ReduceType, Float2, FloatN >::pre ( )

inlinevirtual

pre-computation routine called before the "M-loop"

Definition at line 143 of file multi_reduce_core.cuh.

References quda::sum().

Here is the call graph for this function:

---

The documentation for this struct was generated from the following file:

• include/kernels/multi_reduce_core.cuh