col2im_kernels.cu File Reference

Macros
#define	CUDA_KERNEL_LOOP(i, n)

Functions
int	CAFFE_GET_BLOCKS (const int N)
void	col2im_gpu_ext (const float *data_col, const int channels, const int height, const int width, const int kernel_h, const int kernel_w, const int pad_h, const int pad_w, const int stride_h, const int stride_w, const int dilation_h, const int dilation_w, float *data_im)
__global__ void	col2im_gpu_kernel (const int n, const float *data_col, const int height, const int width, const int ksize, const int pad, const int stride, const int height_col, const int width_col, float *data_im)
__global__ void	col2im_gpu_kernel_ext (const int n, const float *data_col, const int height, const int width, const int channels, const int kernel_h, const int kernel_w, const int pad_h, const int pad_w, const int stride_h, const int stride_w, const int dilation_h, const int dilation_w, const int height_col, const int width_col, float *data_im)
void	col2im_ongpu (float *data_col, int channels, int height, int width, int ksize, int stride, int pad, float *data_im)

Variables
const int	CAFFE_CUDA_NUM_THREADS = 512

Macro Definition Documentation

CUDA_KERNEL_LOOP

#define CUDA_KERNEL_LOOP	(		i,
			n
	)

Value:

for (int i = blockIdx.x * blockDim.x + threadIdx.x; \
    i < (n); \
    i += blockDim.x * gridDim.x)

Function Documentation

CAFFE_GET_BLOCKS()

int CAFFE_GET_BLOCKS ( const int  N )

inline

Here is the caller graph for this function:

col2im_gpu_ext()

void col2im_gpu_ext	(	const float *	data_col,
		const int	channels,
		const int	height,
		const int	width,
		const int	kernel_h,
		const int	kernel_w,
		const int	pad_h,
		const int	pad_w,
		const int	stride_h,
		const int	stride_w,
		const int	dilation_h,
		const int	dilation_w,
		float *	data_im
	)

Here is the call graph for this function:

Here is the caller graph for this function:

col2im_gpu_kernel()

__global__ void col2im_gpu_kernel	(	const int	n,
		const float *	data_col,
		const int	height,
		const int	width,
		const int	ksize,
		const int	pad,
		const int	stride,
		const int	height_col,
		const int	width_col,
		float *	data_im
	)

Here is the caller graph for this function:

col2im_gpu_kernel_ext()

__global__ void col2im_gpu_kernel_ext	(	const int	n,
		const float *	data_col,
		const int	height,
		const int	width,
		const int	channels,
		const int	kernel_h,
		const int	kernel_w,
		const int	pad_h,
		const int	pad_w,
		const int	stride_h,
		const int	stride_w,
		const int	dilation_h,
		const int	dilation_w,
		const int	height_col,
		const int	width_col,
		float *	data_im
	)

Here is the caller graph for this function:

col2im_ongpu()

void col2im_ongpu	(	float *	data_col,
		int	channels,
		int	height,
		int	width,
		int	ksize,
		int	stride,
		int	pad,
		float *	data_im
	)

Here is the call graph for this function:

Variable Documentation

CAFFE_CUDA_NUM_THREADS

const int CAFFE_CUDA_NUM_THREADS = 512