ryan/libdpf
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Document the new DPF surfaces in one command set, and test the field, half-tree, and multipoint edges.

Browse source 
Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Ryan Henry 2026-09-24 23:18:10 -06:00
parent 0d8a5a8131
commit 0dff6df8ed
250 changed files with 12199 additions and 1981 deletions
Download patch file Download diff file Expand all files Collapse all files

16
include/dpf/parallel_bit_iterable_helpers.hpp
View file

@ -1,7 +1,6 @@
/// @file dpf/parallel_bit_iterable_helpers.hpp
/// @author Christopher Jiang <christopher.jiang@ucalgary.ca>
/// @brief
/// @details
/// @brief Loads and masks used by the parallel bit iterators.
/// @copyright Copyright (c) 2019-2024 Ryan Henry and [others](@ref authors)
/// @license Released under a GNU General Public v2.0 (GPLv2) license;
/// see [LICENSE.md](@ref license) for details.
@ -28,8 +27,13 @@ namespace dpf
namespace
{
/// Unaligned 256-bit load of `words_per_vec` words starting at `offset`.
/// Words past `nwords` are zero so a short batch does not read off the end.
/// @brief Unaligned 256-bit load of `words_per_vec` words starting at `offset`.
/// @details Words past `nwords` are zero so a short batch does not read off the end.
/// @tparam Word word
/// @param words the `words`
/// @param nwords the number of words
/// @param offset the public offset
/// @return Unaligned 256-bit load of `words_per_vec` words starting at `offset`
template <typename Word>
HEDLEY_ALWAYS_INLINE
HEDLEY_NO_THROW
@ -56,6 +60,7 @@ template <std::size_t batch_size_log_2, typename ChildT>
struct parallel_bit_iterable_helper;
/// @brief for batch_size in 1..4
/// @tparam ChildT CRTP derived type
template <typename ChildT>
struct parallel_bit_iterable_helper<2, ChildT>
{
@ -88,6 +93,7 @@ HEDLEY_PRAGMA(GCC diagnostic pop)
}; // struct parallel_bit_iterable_helper<2>
/// @brief for batch_size in 5..8
/// @tparam ChildT CRTP derived type
template <typename ChildT>
struct parallel_bit_iterable_helper<3, ChildT>
{
@ -135,6 +141,7 @@ HEDLEY_PRAGMA(GCC diagnostic pop)
}; // struct parallel_bit_iterable_helper<3>
/// @brief for batch_size in 9..16
/// @tparam ChildT CRTP derived type
template <typename ChildT>
struct parallel_bit_iterable_helper<4, ChildT>
{
@ -203,6 +210,7 @@ HEDLEY_PRAGMA(GCC diagnostic pop)
}; // struct parallel_bit_iterable_helper<4>
/// @brief for batch_size in 17..32
/// @tparam ChildT CRTP derived type
template <typename ChildT>
struct parallel_bit_iterable_helper<5, ChildT>
{