|
| caxpydotzy (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...
|
|
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...
|
|
template<typename ReduceType, typename Float2, typename FloatN>
struct quda::blas::caxpydotzy< ReduceType, Float2, FloatN >
double caxpyDotzyCuda(float a, float *x, float *y, float *z, n){} First performs the operation y[i] = a*x[i] + y[i] Second returns the dot product (z,y)
Definition at line 368 of file reduce_core.cuh.
template<typename ReduceType , typename Float2 , typename FloatN >
__device__ __host__ void quda::blas::caxpydotzy< ReduceType, Float2, FloatN >::operator() |
( |
ReduceType & |
sum, |
|
|
FloatN & |
x, |
|
|
FloatN & |
y, |
|
|
FloatN & |
z, |
|
|
FloatN & |
w, |
|
|
FloatN & |
v |
|
) |
| |
|
inlinevirtual |