#include <cuda.h>
#include <cuda_runtime.h>
#include <cuda_runtime_api.h>
#include <iostream>
#include <unsupported/Eigen/CXX11/src/Tensor/TensorGpuHipCudaDefines.h>
Go to the source code of this file.
|
void | ei_test_init_gpu () |
|
template<typename Kernel , typename Input , typename Output > |
void | run_and_compare_to_gpu (const Kernel &ker, int n, const Input &in, Output &out) |
|
template<typename Kernel , typename Input , typename Output > |
void | run_on_cpu (const Kernel &ker, int n, const Input &in, Output &out) |
|
template<typename Kernel , typename Input , typename Output > |
void | run_on_gpu (const Kernel &ker, int n, const Input &in, Output &out) |
|
template<typename Kernel , typename Input , typename Output > |
__global__ EIGEN_HIP_LAUNCH_BOUNDS_1024 void | run_on_gpu_meta_kernel (const Kernel ker, int n, const Input *in, Output *out) |
|
◆ EIGEN_USE_GPU
◆ ei_test_init_gpu()
void ei_test_init_gpu |
( |
| ) |
|
◆ run_and_compare_to_gpu()
template<typename Kernel , typename Input , typename Output >
void run_and_compare_to_gpu |
( |
const Kernel & |
ker, |
|
|
int |
n, |
|
|
const Input & |
in, |
|
|
Output & |
out |
|
) |
| |
◆ run_on_cpu()
template<typename Kernel , typename Input , typename Output >
void run_on_cpu |
( |
const Kernel & |
ker, |
|
|
int |
n, |
|
|
const Input & |
in, |
|
|
Output & |
out |
|
) |
| |
◆ run_on_gpu()
template<typename Kernel , typename Input , typename Output >
void run_on_gpu |
( |
const Kernel & |
ker, |
|
|
int |
n, |
|
|
const Input & |
in, |
|
|
Output & |
out |
|
) |
| |
◆ run_on_gpu_meta_kernel()
template<typename Kernel , typename Input , typename Output >
◆ blockDim
◆ blockIdx
◆ threadIdx