compute_histogram.hpp File Reference

#include "shambase/exception.hpp"
#include "shambase/overloaded.hpp"
#include "shambase/string.hpp"
#include "shamalgs/ImplVariant.hpp"
#include "shambackends/Device.hpp"
#include "shambackends/DeviceBuffer.hpp"
#include "shambackends/DeviceScheduler.hpp"
#include "shambackends/kernel_call.hpp"
#include "shamcomm/logs.hpp"
#include <shambackends/sycl.hpp>
#include <optional>
#include <stdexcept>
#include <tuple>
#include <utility>
#include <vector>

Include dependency graph for compute_histogram.hpp:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Classes
struct	shamalgs::primitives::impl::Reference
	CPU reference implementation, computed on a host copy of the buffers. More...
struct	shamalgs::primitives::impl::NaiveGpu
	Portable GPU kernel, one work-item per bin. More...
struct	shamalgs::primitives::impl::GpuTeamFetching
	GPU kernel using a team-local cache to coalesce input reads. More...
struct	shamalgs::primitives::impl::GpuOversubscribe
	GPU kernel oversubscribing a work-group per bin, reducing locally. More...

Namespaces
namespace	shamalgs
	namespace to contain everything implemented by shamalgs
namespace	shamalgs::primitives
	namespace for primitive algorithm (e.g. sort, scan, reductions, ...)
namespace	shamalgs::primitives::impl
	namespace to control implementation behavior

Functions
std::vector< std::string >	shamalgs::primitives::impl::get_default_impl_list_compute_histogram ()
	Get list of available compute_histogram implementations.
std::string	shamalgs::primitives::impl::get_current_impl_compute_histogram ()
	Get the current implementation for compute_histogram.
bool	shamalgs::primitives::impl::is_impl_set_compute_histogram ()
	Check if an implementation has been selected for compute_histogram.
void	shamalgs::primitives::impl::set_impl_compute_histogram (const std::string &impl)
	Set the implementation for compute_histogram.
void	shamalgs::primitives::impl::autoselect_impl_compute_histogram (const sham::DeviceScheduler_ptr &dev_sched)
	Select the default implementation for compute_histogram.
template<class T, class Tbins, class... Targs, class Tfunctor>
void	shamalgs::primitives::impl::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	shamalgs::primitives::impl::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	shamalgs::primitives::impl::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	shamalgs::primitives::impl::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)
template<class T, class Tbins, class... Targs, class Tfunctor>
sham::DeviceBuffer< T >	shamalgs::primitives::compute_histogram (const sham::DeviceScheduler_ptr &dev_sched, const sham::DeviceBuffer< Tbins > &bin_edge_inf, const sham::DeviceBuffer< Tbins > &bin_edge_sup, size_t element_count, Tfunctor &&functor, const sham::DeviceBuffer< Targs > &...input_data)
template<class T>
sham::DeviceBuffer< T >	shamalgs::primitives::compute_histogram_basic (const sham::DeviceScheduler_ptr &dev_sched, const sham::DeviceBuffer< T > &bin_edge_inf, const sham::DeviceBuffer< T > &bin_edge_sup, const sham::DeviceBuffer< T > &positions)

Variables
shamalgs::ImplVariantGlobal< Reference, NaiveGpu, GpuTeamFetching, GpuOversubscribe >	shamalgs::primitives::impl::compute_histogram_impl

Detailed Description

Author

Timothée David–Cléris (tim.s.nosp@m.hamr.nosp@m.ock@p.nosp@m.roto.nosp@m.n.me)

Definition in file compute_histogram.hpp.