|
CUB
|
#include <iterator>#include "block_exchange.cuh"#include "../util_ptx.cuh"#include "../util_macro.cuh"#include "../util_type.cuh"#include "../util_namespace.cuh"Go to the source code of this file.
Namespaces | |
| cub | |
| Optional outer namespace(s) | |
Enumerations | |
| enum | cub::BlockLoadAlgorithm { cub::BLOCK_LOAD_DIRECT, cub::BLOCK_LOAD_VECTORIZE, cub::BLOCK_LOAD_TRANSPOSE, cub::BLOCK_LOAD_WARP_TRANSPOSE } |
| 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 T , int ITEMS_PER_THREAD, typename InputIterator > | |
| __device__ __forceinline__ void | cub::LoadDirectBlocked (int linear_tid, InputIterator block_itr, T(&items)[ITEMS_PER_THREAD]) |
| Load a linear segment of items into a blocked arrangement across the thread block. More... | |
| template<typename T , int ITEMS_PER_THREAD, typename InputIterator > | |
| __device__ __forceinline__ void | cub::LoadDirectBlocked (int linear_tid, InputIterator block_itr, T(&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 T , int ITEMS_PER_THREAD, typename InputIterator > | |
| __device__ __forceinline__ void | cub::LoadDirectBlocked (int linear_tid, InputIterator block_itr, T(&items)[ITEMS_PER_THREAD], int valid_items, T 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 T , int ITEMS_PER_THREAD, typename InputIterator > | |
| __device__ __forceinline__ void | cub::LoadDirectStriped (int linear_tid, InputIterator block_itr, T(&items)[ITEMS_PER_THREAD]) |
| Load a linear segment of items into a striped arrangement across the thread block. More... | |
| template<int BLOCK_THREADS, typename T , int ITEMS_PER_THREAD, typename InputIterator > | |
| __device__ __forceinline__ void | cub::LoadDirectStriped (int linear_tid, InputIterator block_itr, T(&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 T , int ITEMS_PER_THREAD, typename InputIterator > | |
| __device__ __forceinline__ void | cub::LoadDirectStriped (int linear_tid, InputIterator block_itr, T(&items)[ITEMS_PER_THREAD], int valid_items, T 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 T , int ITEMS_PER_THREAD, typename InputIterator > | |
| __device__ __forceinline__ void | cub::LoadDirectWarpStriped (int linear_tid, InputIterator block_itr, T(&items)[ITEMS_PER_THREAD]) |
| Load a linear segment of items into a warp-striped arrangement across the thread block. More... | |
| template<typename T , int ITEMS_PER_THREAD, typename InputIterator > | |
| __device__ __forceinline__ void | cub::LoadDirectWarpStriped (int linear_tid, InputIterator block_itr, T(&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 T , int ITEMS_PER_THREAD, typename InputIterator > | |
| __device__ __forceinline__ void | cub::LoadDirectWarpStriped (int linear_tid, InputIterator block_itr, T(&items)[ITEMS_PER_THREAD], int valid_items, T 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... | |
Operations for reading linear tiles of data into the CUDA thread block.
Definition in file block_load.cuh.
1.8.4