block_load.cuh File Reference

#include <iterator>
#include <type_traits>
#include "../block/block_exchange.cuh"
#include "../iterator/cache_modified_input_iterator.cuh"
#include "../config.cuh"
#include "../util_ptx.cuh"
#include "../util_type.cuh"

Classes
class	cub::BlockLoad< InputT, BLOCK_DIM_X, ITEMS_PER_THREAD, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, PTX_ARCH >
	The BlockLoad class provides collective data movement methods for loading a linear segment of items from memory into a blocked arrangement across a CUDA thread block. . More...
struct	cub::BlockLoad< InputT, BLOCK_DIM_X, ITEMS_PER_THREAD, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, PTX_ARCH >::LoadInternal< BLOCK_LOAD_TRANSPOSE, DUMMY >::_TempStorage
	Shared memory storage layout type. More...
struct	cub::BlockLoad< InputT, BLOCK_DIM_X, ITEMS_PER_THREAD, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, PTX_ARCH >::LoadInternal< BLOCK_LOAD_TRANSPOSE, DUMMY >::TempStorage
	Alias wrapper allowing storage to be unioned. More...
struct	cub::BlockLoad< InputT, BLOCK_DIM_X, ITEMS_PER_THREAD, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, PTX_ARCH >::LoadInternal< BLOCK_LOAD_WARP_TRANSPOSE, DUMMY >::_TempStorage
	Shared memory storage layout type. More...
struct	cub::BlockLoad< InputT, BLOCK_DIM_X, ITEMS_PER_THREAD, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, PTX_ARCH >::LoadInternal< BLOCK_LOAD_WARP_TRANSPOSE, DUMMY >::TempStorage
	Alias wrapper allowing storage to be unioned. More...
struct	cub::BlockLoad< InputT, BLOCK_DIM_X, ITEMS_PER_THREAD, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, PTX_ARCH >::LoadInternal< BLOCK_LOAD_WARP_TRANSPOSE_TIMESLICED, DUMMY >::_TempStorage
	Shared memory storage layout type. More...
struct	cub::BlockLoad< InputT, BLOCK_DIM_X, ITEMS_PER_THREAD, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, PTX_ARCH >::LoadInternal< BLOCK_LOAD_WARP_TRANSPOSE_TIMESLICED, DUMMY >::TempStorage
	Alias wrapper allowing storage to be unioned. More...
struct	cub::BlockLoad< InputT, BLOCK_DIM_X, ITEMS_PER_THREAD, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, PTX_ARCH >::TempStorage
	The operations exposed by BlockLoad require a temporary memory allocation of this nested type for thread communication. This opaque storage can be allocated directly using the __shared__ keyword. Alternatively, it can be aliased to externally allocated memory (shared or global) or union'd with other storage allocation types to facilitate memory reuse. More...
struct	cub::BlockLoadType< Policy, It, T >

Namespaces
	cub

Enumerations
enum	cub::BlockLoadAlgorithm {   cub::BLOCK_LOAD_DIRECT, cub::BLOCK_LOAD_STRIPED, cub::BLOCK_LOAD_VECTORIZE, cub::BLOCK_LOAD_TRANSPOSE,   cub::BLOCK_LOAD_WARP_TRANSPOSE, cub::BLOCK_LOAD_WARP_TRANSPOSE_TIMESLICED }
	cub::BlockLoadAlgorithm enumerates alternative algorithms for cub::BlockLoad to read a linear segment of data from memory into a blocked arrangement across a CUDA thread block. More...

Functions
Blocked arrangement I/O (direct)
template<typename InputT , int ITEMS_PER_THREAD, typename InputIteratorT >
__device__ __forceinline__ void	cub::LoadDirectBlocked (int linear_tid, InputIteratorT block_itr, InputT(&items)[ITEMS_PER_THREAD])
	Load a linear segment of items into a blocked arrangement across the thread block. More...
template<typename InputT , int ITEMS_PER_THREAD, typename InputIteratorT >
__device__ __forceinline__ void	cub::LoadDirectBlocked (int linear_tid, InputIteratorT block_itr, InputT(&items)[ITEMS_PER_THREAD], int valid_items)
	Load a linear segment of items into a blocked arrangement across the thread block, guarded by range. More...
template<typename InputT , typename DefaultT , int ITEMS_PER_THREAD, typename InputIteratorT >
__device__ __forceinline__ void	cub::LoadDirectBlocked (int linear_tid, InputIteratorT block_itr, InputT(&items)[ITEMS_PER_THREAD], int valid_items, DefaultT oob_default)
	Load a linear segment of items into a blocked arrangement across the thread block, guarded by range, with a fall-back assignment of out-of-bound elements.. More...
template<typename T , int ITEMS_PER_THREAD>
__device__ __forceinline__ void	cub::LoadDirectBlockedVectorized (int linear_tid, T *block_ptr, T(&items)[ITEMS_PER_THREAD])
	Load a linear segment of items into a blocked arrangement across the thread block. More...
Striped arrangement I/O (direct)
template<int BLOCK_THREADS, typename InputT , int ITEMS_PER_THREAD, typename InputIteratorT >
__device__ __forceinline__ void	cub::LoadDirectStriped (int linear_tid, InputIteratorT block_itr, InputT(&items)[ITEMS_PER_THREAD])
	Load a linear segment of items into a striped arrangement across the thread block. More...
template<int BLOCK_THREADS, typename InputT , int ITEMS_PER_THREAD, typename InputIteratorT >
__device__ __forceinline__ void	cub::LoadDirectStriped (int linear_tid, InputIteratorT block_itr, InputT(&items)[ITEMS_PER_THREAD], int valid_items)
	Load a linear segment of items into a striped arrangement across the thread block, guarded by range. More...
template<int BLOCK_THREADS, typename InputT , typename DefaultT , int ITEMS_PER_THREAD, typename InputIteratorT >
__device__ __forceinline__ void	cub::LoadDirectStriped (int linear_tid, InputIteratorT block_itr, InputT(&items)[ITEMS_PER_THREAD], int valid_items, DefaultT oob_default)
	Load a linear segment of items into a striped arrangement across the thread block, guarded by range, with a fall-back assignment of out-of-bound elements. More...
Warp-striped arrangement I/O (direct)
template<typename InputT , int ITEMS_PER_THREAD, typename InputIteratorT >
__device__ __forceinline__ void	cub::LoadDirectWarpStriped (int linear_tid, InputIteratorT block_itr, InputT(&items)[ITEMS_PER_THREAD])
	Load a linear segment of items into a warp-striped arrangement across the thread block. More...
template<typename InputT , int ITEMS_PER_THREAD, typename InputIteratorT >
__device__ __forceinline__ void	cub::LoadDirectWarpStriped (int linear_tid, InputIteratorT block_itr, InputT(&items)[ITEMS_PER_THREAD], int valid_items)
	Load a linear segment of items into a warp-striped arrangement across the thread block, guarded by range. More...
template<typename InputT , typename DefaultT , int ITEMS_PER_THREAD, typename InputIteratorT >
__device__ __forceinline__ void	cub::LoadDirectWarpStriped (int linear_tid, InputIteratorT block_itr, InputT(&items)[ITEMS_PER_THREAD], int valid_items, DefaultT oob_default)
	Load a linear segment of items into a warp-striped arrangement across the thread block, guarded by range, with a fall-back assignment of out-of-bound elements. More...

Detailed Description

Operations for reading linear tiles of data into the CUDA thread block.