Inheritance diagram for quda::blas::axpyCGNorm2< ReduceType, Float2, FloatN >:

Collaboration diagram for quda::blas::axpyCGNorm2< ReduceType, Float2, FloatN >:

Public Member Functions
	axpyCGNorm2 (const Float2 &a, const Float2 &b)

__device__ __host__ void	operator() (ReduceType &sum, FloatN &x, FloatN &y, FloatN &z, FloatN &w, FloatN &v)
	where the reduction is usually computed and any auxiliary operations More...

Public Member Functions inherited from quda::blas::ReduceFunctor< ReduceType, Float2, FloatN >
virtual __device__ __host__ void	pre ()
	pre-computation routine called before the "M-loop" More...

virtual __device__ __host__ void	post (ReduceType &sum)
	post-computation routine called after the "M-loop" More...

Static Public Member Functions
static int	streams ()

static int	flops ()
	total number of input and output streams More...

Public Attributes
Float2	a

Detailed Description

template<typename ReduceType, typename Float2, typename FloatN>
struct quda::blas::axpyCGNorm2< ReduceType, Float2, FloatN >

Specialized kernel for the modified CG norm computation for computing beta. Computes y = y + a*x and returns norm(y) and dot(y, delta(y)) where delta(y) is the difference between the input and out y vector.

Definition at line 640 of file reduce_quda.cu.

Constructor & Destructor Documentation

◆ axpyCGNorm2()

template<typename ReduceType , typename Float2 , typename FloatN >

quda::blas::axpyCGNorm2< ReduceType, Float2, FloatN >::axpyCGNorm2	(	const Float2 &	a,
		const Float2 &	b
	)

inline

Definition at line 642 of file reduce_quda.cu.

Member Function Documentation

◆ flops()

template<typename ReduceType , typename Float2 , typename FloatN >

static int quda::blas::axpyCGNorm2< ReduceType, Float2, FloatN >::flops ( )

inlinestatic

total number of input and output streams

Definition at line 651 of file reduce_quda.cu.

◆ operator()()

template<typename ReduceType , typename Float2 , typename FloatN >

__device__ __host__ void quda::blas::axpyCGNorm2< ReduceType, Float2, FloatN >::operator()	(	ReduceType &	sum,
		FloatN &	x,
		FloatN &	y,
		FloatN &	z,
		FloatN &	w,
		FloatN &	v
	)