block_reduce.cuh File Reference

#include "specializations/block_reduce_raking.cuh"
#include "specializations/block_reduce_raking_commutative_only.cuh"
#include "specializations/block_reduce_warp_reductions.cuh"
#include "../config.cuh"
#include "../util_ptx.cuh"
#include "../util_type.cuh"
#include "../thread/thread_operators.cuh"

Classes
class	cub::BlockReduce< T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, PTX_ARCH >
	The BlockReduce class provides collective methods for computing a parallel reduction of items partitioned across a CUDA thread block. . More...
struct	cub::BlockReduce< T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, PTX_ARCH >::TempStorage
	The operations exposed by BlockReduce 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...

Namespaces
	cub

Enumerations
enum	cub::BlockReduceAlgorithm { cub::BLOCK_REDUCE_RAKING_COMMUTATIVE_ONLY, cub::BLOCK_REDUCE_RAKING, cub::BLOCK_REDUCE_WARP_REDUCTIONS }

Detailed Description

The cub::BlockReduce class provides collective methods for computing a parallel reduction of items partitioned across a CUDA thread block.