|
| struct | Reference |
| | CPU reference implementation, computed on a host copy of the buffers. More...
|
| struct | NaiveGpu |
| | Portable GPU kernel, one work-item per bin. More...
|
| struct | GpuTeamFetching |
| | GPU kernel using a team-local cache to coalesce input reads. More...
|
| struct | GpuOversubscribe |
| | GPU kernel oversubscribing a work-group per bin, reducing locally. More...
|
| struct | Host |
| | Check all elements on host after copying the buffer back. More...
|
| struct | SumReduction |
| | Check all elements via a sum reduction on device. More...
|
| struct | AtomicEarlyExit |
| | Check all elements via a sum reduction on device. More...
|
| struct | Fallback |
| | Fallback USM reduction (portable, no group reduction support required). More...
|
| struct | StdScan |
| | std::exclusive_scan on a host copy of the buffer (portable fallback) More...
|
| struct | LocalInsertionSort |
| | Sort each segment locally with an insertion sort, one kernel work-item per segment. More...
|
| struct | MultiStdSort |
| | Copy back to host and sort each segment with std::sort, parallelized over OpenMP. More...
|
| struct | BitonicSort |
| | Bitonic sort, updated USM kernel (see bitonicSort_updated_usm.hpp). More...
|
| struct | StdSort |
| | Copy the buffers to host, std::sort the zipped key/value pairs, and copy back. More...
|
| struct | LsdRadixSortBasic |
| struct | BatcherOddEvenHostSerial |
| | Copy the buffers to host, sort with Batcher's odd-even merge sort, and copy back. More...
|
| struct | BatcherOddEven |
| | Copy the buffers to host, sort with Batcher's odd-even merge sort, and copy back. More...
|
|
| template<class T, class Tbins, class... Targs, class Tfunctor> |
| void | compute_histogram_reference (const sham::DeviceBuffer< Tbins > &bin_edge_inf, const sham::DeviceBuffer< Tbins > &bin_edge_sup, size_t nbins, size_t element_count, Tfunctor &&functor, sham::DeviceBuffer< T > &result, const sham::DeviceBuffer< Targs > &...input_data) |
| template<class T, class Tbins, class... Targs, class Tfunctor> |
| void | compute_histogram_naive_gpu (const sham::DeviceScheduler_ptr &dev_sched, const sham::DeviceBuffer< Tbins > &bin_edge_inf, const sham::DeviceBuffer< Tbins > &bin_edge_sup, size_t nbins, size_t element_count, Tfunctor &&functor, sham::DeviceBuffer< T > &result, const sham::DeviceBuffer< Targs > &...input_data) |
| template<class T, class Tbins, class... Targs, class Tfunctor> |
| void | compute_histogram_gpu_team_fetching (const sham::DeviceScheduler_ptr &dev_sched, const sham::DeviceBuffer< Tbins > &bin_edge_inf, const sham::DeviceBuffer< Tbins > &bin_edge_sup, size_t nbins, size_t element_count, Tfunctor &&functor, sham::DeviceBuffer< T > &result, const sham::DeviceBuffer< Targs > &...input_data) |
| template<class T, class Tbins, class... Targs, class Tfunctor> |
| void | compute_histogram_gpu_oversubscribe (const sham::DeviceScheduler_ptr &dev_sched, u32 group_size, const sham::DeviceBuffer< Tbins > &bin_edge_inf, const sham::DeviceBuffer< Tbins > &bin_edge_sup, size_t nbins, size_t element_count, Tfunctor &&functor, sham::DeviceBuffer< T > &result, const sham::DeviceBuffer< Targs > &...input_data) |
|
| SHAMALGS_REGISTER_IMPL (compute_histogram_impl_name, compute_histogram_impl) |
|
| SHAMALGS_REGISTER_IMPL (is_all_true_impl_name, is_all_true_impl) |
|
| SHAMALGS_REGISTER_IMPL (reduction_impl_name, reduction_impl) |
|
| SHAMALGS_REGISTER_IMPL (scan_exclusive_sum_in_place_impl_name, scan_exclusive_sum_in_place_impl) |
|
| SHAMALGS_REGISTER_IMPL (segmented_sort_in_place_impl_name, segmented_sort_in_place_impl) |
|
| SHAMALGS_REGISTER_IMPL (sort_by_key_pow2_len_impl_name, sort_by_key_pow2_len_impl) |
| template<class Tkey, class Tval> |
| void | sort_by_key_pow2_len_bitonic_dispatch (const sham::DeviceScheduler_ptr &sched, sham::DeviceBuffer< Tkey > &buf_key, sham::DeviceBuffer< Tval > &buf_values, u32 len, MaxStencilSize stencil_size) |
|
| SHAMALGS_REGISTER_IMPL (sort_by_keys_impl_name, sort_by_keys_impl) |
|
| ComputeHistogramImpl | compute_histogram_impl |
| | Implementation selector for compute_histogram (defined in compute_histogram.cpp).
|
| constexpr std::string_view | compute_histogram_impl_name = "compute_histogram" |
| | Registry name, shared by its registration and the dispatch site(s).
|
| constexpr std::string_view | is_all_true_impl_name = "is_all_true" |
| | Registry name, shared by its registration and the dispatch site(s).
|
| shamalgs::ImplVariantGlobal< Host, SumReduction, AtomicEarlyExit > | is_all_true_impl |
| constexpr std::string_view | reduction_impl_name = "reduction" |
| | Registry name, shared by its registration and the dispatch site(s).
|
| shamalgs::ImplVariantGlobal< Fallback > | reduction_impl |
| constexpr std::string_view | scan_exclusive_sum_in_place_impl_name = "scan_exclusive_sum_in_place" |
| | Registry name, shared by its registration and the dispatch site(s).
|
| shamalgs::ImplVariantGlobal< StdScan > | scan_exclusive_sum_in_place_impl |
| constexpr std::string_view | segmented_sort_in_place_impl_name = "segmented_sort_in_place" |
| | Registry name, shared by its registration and the dispatch site(s).
|
| shamalgs::ImplVariantGlobal< LocalInsertionSort, MultiStdSort > | segmented_sort_in_place_impl |
| constexpr std::string_view | sort_by_key_pow2_len_impl_name = "sort_by_key_pow2_len" |
| | Registry name, shared by its registration and the dispatch site(s).
|
| shamalgs::ImplVariantGlobal< BitonicSort, StdSort, LsdRadixSortBasic > | sort_by_key_pow2_len_impl |
| constexpr std::string_view | sort_by_keys_impl_name = "sort_by_keys" |
| | Registry name, shared by its registration and the dispatch site(s).
|
| shamalgs::ImplVariantGlobal< StdSort, BatcherOddEvenHostSerial, BatcherOddEven, LsdRadixSortBasic > | sort_by_keys_impl |
namespace to control implementation behavior