Taskflow  3.2.0-Master-Branch
Loading...
Searching...
No Matches
reduce.hpp File Reference

cuda reduce algorithms include file More...

Go to the source code of this file.

Namespaces

namespace  tf
 taskflow namespace
 

Functions

template<typename P , typename T >
unsigned tf::cuda_reduce_buffer_size (unsigned count)
 queries the buffer size in bytes needed to call reduce kernels
 
template<typename P , typename I , typename T , typename O >
void tf::cuda_reduce (P &&p, I first, I last, T *res, O op, void *buf)
 performs asynchronous parallel reduction over a range of items
 
template<typename P , typename I , typename T , typename O >
void tf::cuda_uninitialized_reduce (P &&p, I first, I last, T *res, O op, void *buf)
 performs asynchronous parallel reduction over a range of items without an initial value
 
template<typename P , typename I , typename T , typename O , typename U >
void tf::cuda_transform_reduce (P &&p, I first, I last, T *res, O bop, U uop, void *buf)
 performs asynchronous parallel reduction over a range of transformed items without an initial value
 
template<typename P , typename I , typename T , typename O , typename U >
void tf::cuda_transform_uninitialized_reduce (P &&p, I first, I last, T *res, O bop, U uop, void *buf)
 performs asynchronous parallel reduction over a range of transformed items with an initial value
 

Detailed Description

cuda reduce algorithms include file