CUB
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Groups
Classes | Namespaces | Enumerations
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 "../util_ptx.cuh"
#include "../util_type.cuh"
#include "../thread/thread_operators.cuh"
#include "../util_namespace.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.

reduce_logo.png
.
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
 Optional outer namespace(s)
 

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.