Reduction operators

reduce()	generic batch reduction
reduce_add()	sum of each batch element
reduce_max()	max of the batch elements
reduce_min()	min of the batch elements
haddp()	horizontal sum across batches

---

template<class T, class A>
inline batch<T, A> haddp(batch<T, A> const *row) noexcept

Parallel horizontal addition: adds the scalars of each batch in the array pointed by row and store them in a returned batch.

Parameters:

row – an array of N batches

Returns:

the result of the reduction.

template<class T, class A, class F>
inline T reduce(F &&f, batch<T, A> const &x) noexcept

Generic reducer using only batch operations.

Parameters:

• f – reducing function, accepting batch ()(batch, batch)

• x – batch involved in the reduction

Returns:

the result of the reduction, as a scalar.

template<class T, class A>
inline T reduce_add(batch<T, A> const &x) noexcept

Adds all the scalars of the batch x.

Parameters:

x – batch involved in the reduction

Returns:

the result of the reduction.

template<class T, class A>
inline T reduce_max(batch<T, A> const &x) noexcept

Max of all the scalars of the batch x.

Parameters:

x – batch involved in the reduction

Returns:

the result of the reduction.

template<class T, class A>
inline T reduce_min(batch<T, A> const &x) noexcept

Min of all the scalars of the batch x.

Parameters:

x – batch involved in the reduction

Returns:

the result of the reduction.