template<typename InputT,
int BLOCK_DIM_X,
int ITEMS_PER_THREAD,
BlockLoadAlgorithm ALGORITHM = BLOCK_LOAD_DIRECT,
int BLOCK_DIM_Y = 1,
int BLOCK_DIM_Z = 1,
int PTX_ARCH = CUB_PTX_ARCH>
template<
int DUMMY>
struct cub::BlockLoad< InputT, BLOCK_DIM_X, ITEMS_PER_THREAD, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, PTX_ARCH >::LoadInternal< BLOCK_LOAD_TRANSPOSE, DUMMY >
BLOCK_LOAD_TRANSPOSE specialization of load helper
Definition at line 805 of file block_load.cuh.
|
__device__ __forceinline__ | LoadInternal (TempStorage &temp_storage, int linear_tid) |
| Constructor.
|
|
template<typename InputIteratorT > |
__device__ __forceinline__ void | Load (InputIteratorT block_itr, InputT(&items)[ITEMS_PER_THREAD]) |
| Load a linear segment of items from memory.
|
|
template<typename InputIteratorT > |
__device__ __forceinline__ void | Load (InputIteratorT block_itr, InputT(&items)[ITEMS_PER_THREAD], int valid_items) |
| Load a linear segment of items from memory, guarded by range.
|
|
template<typename InputIteratorT , typename DefaultT > |
__device__ __forceinline__ void | Load (InputIteratorT block_itr, InputT(&items)[ITEMS_PER_THREAD], int valid_items, DefaultT oob_default) |
| Load a linear segment of items from memory, guarded by range, with a fall-back assignment of out-of-bound elements.
|
|