stapl::skeletons::skeletons_impl::reduce_to_pow_two< Op, Span > Struct Template Reference

This class abstracts the semantics of a reduce to power-of-two skeleton by exposing only the necessary information in its representation. More...

Public Member Functions
	reduce_to_pow_two (Op const &op)
Op	get_op (void) const

Public Types
using	skeleton_tag_type = tags::reduce_to_pow_two
using	base_type = decltype(skeletons::elem< Span >(skeletons::reduce_to_pow_two_pd(std::declval< Op >())))

Detailed Description

template<typename Op, typename Span>
struct stapl::skeletons::skeletons_impl::reduce_to_pow_two< Op, Span >

This class abstracts the semantics of a reduce to power-of-two skeleton by exposing only the necessary information in its representation.

A reduce_to_pow_two skeleton converts the input to its closest power-of-two size by combining input elements using the operation provided.

This abstraction not only makes the reconstruction of a reduce_to_pow_two skeleton easier, but also provides access to the underlying operation in the reduce skeleton. Furthermore, it reduces the symbol size for a reduce_to_pow_two skeleton, hence, reducing the total compilation time.

Template Parameters

Op	the operation to be used while reducing the input.
Span	the iteration space for the elements.

---

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

• functional/reduce_to_pow_two.hpp