CUDA Templates for Linear Algebra Subroutines and Solvers
Classes | Namespaces
host_tensor.h File Reference

HostTensor contributes management for both host and device memory. More...

#include <vector>
#include "cutlass/cutlass.h"
#include "cutlass/matrix_traits.h"
#include "cutlass/tensor_ref.h"
#include "cutlass/tensor_view.h"
#include "device_memory.h"
Include dependency graph for host_tensor.h:
This graph shows which files directly or indirectly include this file:

Go to the source code of this file.


class  cutlass::HostTensor< Element_, Layout_ >
 Host tensor. More...



Detailed Description

HostTensor allocates host and device memory upon construction. Basic element-wise operations on host memory synchronize device memory automatically. Explicit copy operations provide abstractions for CUDA memcpy operations.

Call {host, device}_{data, ref, view}() for accessing host or device memory.

See cutlass/tensor_ref.h and cutlass/tensor_view.h for more details.