transform_reduce.h File Reference

QUDA reimplementation of thrust::transform_reduce as well as wrappers also implementing thrust::reduce. More...

#include <typeinfo>
#include <reduce_helper.h>
#include <uint_to_char.h>
#include <tune_quda.h>

Go to the source code of this file.

Classes
struct	quda::plus< T >
struct	quda::maximum< T >
struct	quda::minimum< T >
struct	quda::identity< T >
struct	quda::TransformReduceArg< reduce_t, T, count_t, transformer, reducer >
class	quda::TransformReduce< reduce_t, T, I, transformer, reducer >

Namespaces
	quda

Functions
template<typename Arg >
void	quda::transform_reduce (Arg &arg)
template<typename Arg >
	quda::__launch_bounds__ (Arg::block_size) __global__ void transform_reduce_kernel(Arg arg)
template<typename reduce_t , typename T , typename I , typename transformer , typename reducer >
void	quda::transform_reduce (QudaFieldLocation location, std::vector< reduce_t > &result, const std::vector< T * > &v, I n_items, transformer h, reduce_t init, reducer r)
	QUDA implementation providing thrust::transform_reduce like functionality. Improves upon thrust's implementation since a single kernel is used which writes the result directly to host memory, and is a batched implementation. More...
template<typename reduce_t , typename T , typename I , typename transformer , typename reducer >
reduce_t	quda::transform_reduce (QudaFieldLocation location, const T *v, I n_items, transformer h, reduce_t init, reducer r)
	QUDA implementation providing thrust::transform_reduce like functionality. Improves upon thrust's implementation since a single kernel is used which writes the result directly to host memory. More...
template<typename reduce_t , typename T , typename I , typename transformer , typename reducer >
void	quda::reduce (QudaFieldLocation location, std::vector< reduce_t > &result, const std::vector< T * > &v, I n_items, reduce_t init, reducer r)
	QUDA implementation providing thrust::reduce like functionality. Improves upon thrust's implementation since a single kernel is used which writes the result directly to host memory, and is a batched implementation. More...
template<typename reduce_t , typename T , typename I , typename reducer >
reduce_t	quda::reduce (QudaFieldLocation location, const T *v, I n_items, reduce_t init, reducer r)
	QUDA implementation providing thrust::reduce like functionality. Improves upon thrust's implementation since a single kernel is used which writes the result directly to host memory. More...

Detailed Description

QUDA reimplementation of thrust::transform_reduce as well as wrappers also implementing thrust::reduce.

Definition in file transform_reduce.h.