mirror of
https://github.com/pjreddie/darknet.git
synced 2023-08-10 21:13:14 +03:00
Improve training performance - batch-norm using cuDNN.
This commit is contained in:
32
src/cuda.h
32
src/cuda.h
@ -19,19 +19,25 @@ extern int gpu_index;
|
||||
#include "cudnn.h"
|
||||
#endif
|
||||
|
||||
void check_error(cudaError_t status);
|
||||
cublasHandle_t blas_handle();
|
||||
float *cuda_make_array(float *x, size_t n);
|
||||
int *cuda_make_int_array(size_t n);
|
||||
void cuda_push_array(float *x_gpu, float *x, size_t n);
|
||||
void cuda_pull_array(float *x_gpu, float *x, size_t n);
|
||||
void cuda_set_device(int n);
|
||||
int cuda_get_device();
|
||||
void cuda_free(float *x_gpu);
|
||||
void cuda_random(float *x_gpu, size_t n);
|
||||
float cuda_compare(float *x_gpu, float *x, size_t n, char *s);
|
||||
dim3 cuda_gridsize(size_t n);
|
||||
cudaStream_t get_cuda_stream();
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
void check_error(cudaError_t status);
|
||||
cublasHandle_t blas_handle();
|
||||
float *cuda_make_array(float *x, size_t n);
|
||||
int *cuda_make_int_array(size_t n);
|
||||
void cuda_push_array(float *x_gpu, float *x, size_t n);
|
||||
void cuda_pull_array(float *x_gpu, float *x, size_t n);
|
||||
void cuda_set_device(int n);
|
||||
int cuda_get_device();
|
||||
void cuda_free(float *x_gpu);
|
||||
void cuda_random(float *x_gpu, size_t n);
|
||||
float cuda_compare(float *x_gpu, float *x, size_t n, char *s);
|
||||
dim3 cuda_gridsize(size_t n);
|
||||
cudaStream_t get_cuda_stream();
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
#endif
|
||||
|
||||
#ifdef CUDNN
|
||||
cudnnHandle_t cudnn_handle();
|
||||
|
Reference in New Issue
Block a user