Functions
__global__ void	accumulate_kernel (float x, int n, int groups, float sum)

void	activate_and_mult (float a1, float a2, size_t size, ACTIVATION a, float *dst)

__global__ void	activate_and_mult_kernel (float a1, float a2, size_t size, ACTIVATION a, float *dst)

void	adam_gpu (int n, float x, float m, float *v, float B1, float B2, float rate, float eps, int t)

__global__ void	adam_kernel (int N, float x, float m, float *v, float B1, float B2, float rate, float eps, int t)

void	adam_update_gpu (float w, float d, float m, float v, float B1, float B2, float eps, float decay, float rate, int n, int batch, int t)

void	add_3_arrays_activate (float a1, float a2, float a3, size_t size, ACTIVATION a, float dst)

__global__ void	add_3_arrays_activate_kernel (float a1, float a2, float a3, size_t size, ACTIVATION a, float dst)

void	add_bias_gpu (float output, float biases, int batch, int filters, int spatial)

__global__ void	add_bias_kernel (float output, float biases, int batch, int filters, int spatial, int current_size)

__global__ void	axpy_kernel (int N, float ALPHA, float X, int OFFX, int INCX, float Y, int OFFY, int INCY)

void	axpy_ongpu (int N, float ALPHA, float X, int INCX, float Y, int INCY)

void	axpy_ongpu_offset (int N, float ALPHA, float X, int OFFX, int INCX, float Y, int OFFY, int INCY)

void	backward_bias_gpu (float bias_updates, float delta, int batch, int n, int size)

__global__ void	backward_bias_kernel (float bias_updates, float delta, int batch, int n, int size)

void	backward_implicit_gpu (int batch, int nweights, float weight_updates_gpu, float delta_gpu)

__global__ void	backward_implicit_kernel (int size, int batch, int nweights, float weight_updates_gpu, float delta_gpu)

void	backward_sam_gpu (float in_w_h_c_delta, int size, int channel_size, float in_scales_c, float out_from_delta, float in_from_output, float *out_state_delta)

__global__ void	backward_sam_kernel (float in_w_h_c_delta, int size, int channel_size, float in_scales_c, float out_from_delta, float in_from_output, float *out_state_delta)

void	backward_scale_channels_gpu (float in_w_h_c_delta, int size, int channel_size, int batch_size, int scale_wh, float in_scales_c, float out_from_delta, float in_from_output, float *out_state_delta)

__global__ void	backward_scale_channels_kernel (float in_w_h_c_delta, int size, int channel_size, int batch_size, int scale_wh, float in_scales_c, float out_from_delta, float in_from_output, float *out_state_delta)

void	backward_scale_gpu (float x_norm, float delta, int batch, int n, int size, float *scale_updates)

__global__ void	backward_scale_kernel (float x_norm, float delta, int batch, int n, int size, float *scale_updates)

void	backward_shortcut_multilayer_gpu (int src_outputs, int batch, int n, int outputs_of_layers_gpu, float layers_delta_gpu, float delta_out, float delta_in, float weights_gpu, float weight_updates_gpu, int nweights, float in, float **layers_output_gpu, WEIGHTS_NORMALIZATION_T weights_normalization)

__global__ void	backward_shortcut_multilayer_kernel (int size, int src_outputs, int batch, int n, int outputs_of_layers_gpu, float layers_delta_gpu, float delta_out, float delta_in, float weights_gpu, float weight_updates_gpu, int nweights, float in, float **layers_output_gpu, WEIGHTS_NORMALIZATION_T weights_normalization)

void	compare_2_arrays_gpu (float one, float two, int size)

__global__ void	compare_2_arrays_kernel (float one, float two, int size)

__global__ void	const_kernel (int N, float ALPHA, float *X, int INCX)

void	const_ongpu (int N, float ALPHA, float *X, int INCX)

__global__ void	constrain_kernel (int N, float ALPHA, float *X, int INCX)

__global__ void	constrain_min_max_kernel (int N, float MIN, float MAX, float *X, int INCX)

void	constrain_min_max_ongpu (int N, float MIN, float MAX, float *X, int INCX)

void	constrain_ongpu (int N, float ALPHA, float *X, int INCX)

__global__ void	constrain_weight_updates_kernel (int N, float coef, float weights_gpu, float weight_updates_gpu)

void	constrain_weight_updates_ongpu (int N, float coef, float weights_gpu, float weight_updates_gpu)

void	coord_conv_gpu (float *dst, int size, int w, int h, int chan, int b, int type)

__global__ void	coord_conv_kernel (float *dst, int w, int h, int chan, int batch, int type)

__global__ void	copy_kernel (int N, float X, int OFFX, int INCX, float Y, int OFFY, int INCY)

void	copy_ongpu (int N, float X, int INCX, float Y, int INCY)

void	copy_ongpu_offset (int N, float X, int OFFX, int INCX, float Y, int OFFY, int INCY)

void	expand_array_gpu (const float src_gpu, float dst_gpu, int size, int groups)

__global__ void	expand_array_kernel (const float src_gpu, float dst_gpu, int current_size, int groups)

void	fast_mean_delta_gpu (float delta, float variance, int batch, int filters, int spatial, float *mean_delta)

__global__ void	fast_mean_delta_kernel (float delta, float variance, int batch, int filters, int spatial, float *mean_delta)

void	fast_mean_gpu (float x, int batch, int filters, int spatial, float mean)

__global__ void	fast_mean_kernel (float x, int batch, int filters, int spatial, float mean)

void	fast_v_cbn_gpu (const float x, float mean, int batch, int filters, int spatial, int minibatch_index, int max_minibatch_index, float m_avg, float v_avg, float variance, const float alpha, float rolling_mean_gpu, float *rolling_variance_gpu, int inverse_variance, float epsilon)

__global__ void	fast_v_cbn_kernel (const float x, float mean, int batch, int filters, int spatial, int minibatch_index, int max_minibatch_index, float m_avg, float v_avg, float variance, const float alpha, float rolling_mean_gpu, float *rolling_variance_gpu, int inverse_variance, float epsilon)

void	fast_variance_delta_gpu (float x, float delta, float mean, float variance, int batch, int filters, int spatial, float *variance_delta)

__global__ void	fast_variance_delta_kernel (float x, float delta, float mean, float variance, int batch, int filters, int spatial, float *variance_delta)

void	fast_variance_gpu (float x, float mean, int batch, int filters, int spatial, float *variance)

__global__ void	fast_variance_kernel (float x, float mean, int batch, int filters, int spatial, float *variance)

__global__ void	fill_kernel (int N, float ALPHA, float *X, int INCX)

void	fill_ongpu (int N, float ALPHA, float *X, int INCX)

void	fix_nan_and_inf (float *input, size_t size)

__global__ void	fix_nan_and_inf_kernel (float *input, size_t size)

__global__ void	flatten_kernel (int N, float x, int spatial, int layers, int batch, int forward, float out)

void	flatten_ongpu (float x, int spatial, int layers, int batch, int forward, float out)

void	forward_implicit_gpu (int batch, int nweights, float weight_gpu, float output_gpu)

__global__ void	forward_implicit_kernel (int size, int batch, int nweights, float weight_gpu, float output_gpu)

__device__ float	grad_lrelu (float src)

__device__ float	grad_relu (float src)

void	gradient_centralization_gpu (int w, int h, int c, int f, float *in)

__global__ void	gradient_centralization_kernel (int filters, int f_size, float *in)

void	input_shortcut_gpu (float in, int batch, int w1, int h1, int c1, float add, int w2, int h2, int c2, float *out)

__global__ void	input_shortcut_kernel (float in, int size, int minw, int minh, int minc, int stride, int sample, int batch, int w1, int h1, int c1, float add, int w2, int h2, int c2, float *out)

__global__ void	inverse_variance_kernel (int size, float src, float dst, float epsilon)

void	inverse_variance_ongpu (int size, float src, float dst, float epsilon)

int	is_nan_or_inf (float *input, size_t size)

__global__ void	is_nan_or_inf_kernel (float input, size_t size, int pinned_return)

void	l2_gpu (int n, float pred, float truth, float delta, float error)

__global__ void	l2_kernel (int n, float pred, float truth, float delta, float error)

__device__ float	lrelu (float src)

void	mask_gpu_new_api (int N, float X, float mask_num, float mask, float val)

__global__ void	mask_kernel (int n, float x, float mask_num, float mask)

__global__ void	mask_kernel_new_api (int n, float x, float mask_num, float mask, float val)

void	mask_ongpu (int N, float X, float mask_num, float mask)

void	mean_array_gpu (float src, int size, float alpha, float avg)

__global__ void	mean_array_kernel (float src, int size, float alpha, float avg)

void	mean_delta_gpu (float delta, float variance, int batch, int filters, int spatial, float *mean_delta)

__global__ void	mean_delta_kernel (float delta, float variance, int batch, int filters, int spatial, float *mean_delta)

void	mean_gpu (float x, int batch, int filters, int spatial, float mean)

__global__ void	mean_kernel (float x, int batch, int filters, int spatial, float mean)

void	memcpy_ongpu (void dst, void src, int size_bytes)

__global__ void	mul_kernel (int N, float X, int INCX, float Y, int INCY)

void	mul_ongpu (int N, float X, int INCX, float Y, int INCY)

void	mult_add_into_gpu (int num, float a, float b, float *c)

__global__ void	mult_add_into_kernel (int n, float a, float b, float *c)

void	mult_inverse_array_gpu (const float src_gpu, float dst_gpu, int size, float eps, float divider, float clip, float abs_add)

__global__ void	mult_inverse_array_kernel (const float src_gpu, float dst_gpu, int size, const float eps, float divider, const float clip, const float abs_add)

void	normalize_delta_gpu (float x, float mean, float variance, float mean_delta, float variance_delta, int batch, int filters, int spatial, float delta)

__global__ void	normalize_delta_kernel (int N, float x, float mean, float variance, float mean_delta, float variance_delta, int batch, int filters, int spatial, float delta)

void	normalize_gpu (float x, float mean, float *variance, int batch, int filters, int spatial)

__global__ void	normalize_kernel (int N, float x, float mean, float *variance, int batch, int filters, int spatial)

void	normalize_scale_bias_gpu (float x, float mean, float variance, float scales, float *biases, int batch, int filters, int spatial, int inverse_variance, float epsilon)

__global__ void	normalize_scale_bias_kernel (int N, float x, float mean, float variance, float scales, float *biases, int batch, int filters, int spatial, int inverse_variance, float epsilon)

void	P_constrastive_f_det_gpu (int labels, unsigned int feature_size, float temperature, contrastive_params contrast_p, const int contrast_p_size)

__global__ void	P_constrastive_f_det_kernel (int labels, unsigned int feature_size, float temperature, contrastive_params contrast_p, const int contrast_p_size)

__global__ void	pow_kernel (int N, float ALPHA, float X, int INCX, float Y, int INCY)

void	pow_ongpu (int N, float ALPHA, float X, int INCX, float Y, int INCY)

void	reduce_and_expand_array_gpu (const float src_gpu, float dst_gpu, int size, int groups)

__global__ void	reduce_and_expand_array_kernel (const float src_gpu, float dst_gpu, int current_size, int groups)

__device__ float	relu (float src)

__global__ void	reorg_kernel (int N, float x, int w, int h, int c, int batch, int stride, int forward, float out)

void	reorg_ongpu (float x, int w, int h, int c, int batch, int stride, int forward, float out)

void	reset_nan_and_inf (float *input, size_t size)

__global__ void	reset_nan_and_inf_kernel (float *input, size_t size)

void	rotate_weights_gpu (const float src_weight_gpu, float weight_deform_gpu, int nweights, int n, int size, int reverse)

__global__ void	rotate_weights_kernel (const float src_weight_gpu, float weight_deform_gpu, int nweights, int n, int kernel_size, int reverse)

void	sam_gpu (float in_w_h_c, int size, int channel_size, float scales_c, float *out)

__global__ void	sam_kernel (float in_w_h_c, int size, int channel_size, float scales_c, float *out)

__global__ void	scal_add_kernel (int N, float ALPHA, float BETA, float *X, int INCX)

void	scal_add_ongpu (int N, float ALPHA, float BETA, float *X, int INCX)

__global__ void	scal_kernel (int N, float ALPHA, float *X, int INCX)

void	scal_ongpu (int N, float ALPHA, float *X, int INCX)

void	scale_bias_gpu (float output, float scale, int batch, int filters, int spatial)

__global__ void	scale_bias_kernel (float output, float scale, int batch, int filters, int spatial, int current_size)

void	scale_channels_gpu (float in_w_h_c, int size, int channel_size, int batch_size, int scale_wh, float scales_c, float *out)

__global__ void	scale_channels_kernel (float in_w_h_c, int size, int channel_size, int batch_size, int scale_wh, float scales_c, float *out)

void	shortcut_gpu (int batch, int w1, int h1, int c1, float add, int w2, int h2, int c2, float out)

__global__ void	shortcut_kernel (int size, int minw, int minh, int minc, int stride, int sample, int batch, int w1, int h1, int c1, float add, int w2, int h2, int c2, float out)

void	shortcut_multilayer_gpu (int src_outputs, int batch, int n, int outputs_of_layers_gpu, float layers_output_gpu, float out, float in, float weights_gpu, int nweights, WEIGHTS_NORMALIZATION_T weights_normalization)

__global__ void	shortcut_multilayer_kernel (int size, int src_outputs, int batch, int n, int outputs_of_layers_gpu, float layers_output_gpu, float out, float in, float weights_gpu, int nweights, WEIGHTS_NORMALIZATION_T weights_normalization)

__global__ void	shortcut_singlelayer_simple_kernel (int size, int src_outputs, int batch, int n, int outputs_of_layers_gpu, float layers_output_gpu, float out, float in, float weights_gpu, int nweights, WEIGHTS_NORMALIZATION_T weights_normalization)

__global__ void	simple_copy_kernel (int size, float src, float dst)

void	simple_copy_ongpu (int size, float src, float dst)

__global__ void	simple_input_shortcut_kernel (float in, int size, float add, float *out)

void	smooth_l1_gpu (int n, float pred, float truth, float delta, float error)

__global__ void	smooth_l1_kernel (int n, float pred, float truth, float delta, float error)

void	smooth_rotate_weights_gpu (const float src_weight_gpu, float weight_deform_gpu, int nweights, int n, int size, int angle, int reverse)

__global__ void	smooth_rotate_weights_kernel (const float src_weight_gpu, float weight_deform_gpu, int nweights, int n, int kernel_size, int angle, int reverse)

__device__ void	softmax_device (int n, float input, float temp, float output)

__device__ void	softmax_device_new_api (float input, int n, float temp, int stride, float output)

void	softmax_gpu (float input, int n, int offset, int groups, float temp, float output)

void	softmax_gpu_new_api (float input, int n, int batch, int batch_offset, int groups, int group_offset, int stride, float temp, float output)

__global__ void	softmax_kernel (int n, int offset, int batch, float input, float temp, float output)

__global__ void	softmax_kernel_new_api (float input, int n, int batch, int batch_offset, int groups, int group_offset, int stride, float temp, float output)

void	softmax_tree_gpu (float input, int spatial, int batch, int stride, float temp, float output, Darknet::Tree hier)

__global__ void	softmax_tree_kernel (float input, int spatial, int batch, int stride, float temp, float output, int groups, int group_size, int group_offset)

void	softmax_x_ent_gpu (int n, float pred, float truth, float delta, float error)

__global__ void	softmax_x_ent_kernel (int n, float pred, float truth, float delta, float error)

void	stretch_sway_flip_weights_gpu (const float src_weight_gpu, float weight_deform_gpu, int nweights, int n, int size, int angle, int reverse)

__global__ void	stretch_sway_flip_weights_kernel (const float src_weight_gpu, float weight_deform_gpu, int nweights, int n, int kernel_size, float angle, int reverse)

void	stretch_weights_gpu (const float src_weight_gpu, float weight_deform_gpu, int nweights, int n, int size, float scale, int reverse)

__global__ void	stretch_weights_kernel (const float src_weight_gpu, float weight_deform_gpu, int nweights, int n, int kernel_size, float scale, int reverse)

void	sum_of_mults (float a1, float a2, float b1, float b2, size_t size, float *dst)

__global__ void	sum_of_mults_kernel (float a1, float a2, float b1, float b2, size_t size, float *dst)

__global__ void	supp_kernel (int N, float ALPHA, float *X, int INCX)

void	supp_ongpu (int N, float ALPHA, float *X, int INCX)

void	sway_and_flip_weights_gpu (const float src_weight_gpu, float weight_deform_gpu, int nweights, int n, int size, int angle, int reverse)

__global__ void	sway_and_flip_weights_kernel (const float src_weight_gpu, float weight_deform_gpu, int nweights, int n, int kernel_size, int angle, int reverse)

void	upsample_gpu (float in, int w, int h, int c, int batch, int stride, int forward, float scale, float out)

__global__ void	upsample_kernel (size_t N, float x, int w, int h, int c, int batch, int stride, int forward, float scale, float out)

__global__ void	variance_delta_kernel (float x, float delta, float mean, float variance, int batch, int filters, int spatial, float *variance_delta)

void	variance_gpu (float x, float mean, int batch, int filters, int spatial, float *variance)

__global__ void	variance_kernel (float x, float mean, int batch, int filters, int spatial, float *variance)

__inline__ __device__ float	warpAllReduceSum (float val)

void	weighted_delta_gpu (float a, float b, float s, float da, float db, float ds, int num, float *dc)

__global__ void	weighted_delta_kernel (int n, float a, float b, float s, float da, float db, float ds, float *dc)

void	weighted_sum_gpu (float a, float b, float s, int num, float c)

__global__ void	weighted_sum_kernel (int n, float a, float b, float s, float c)

Function Documentation

◆ accumulate_kernel()

__global__ void accumulate_kernel	(	float *	x,
		int	n,
		int	groups,
		float *	sum
	)

◆ activate_and_mult()

void activate_and_mult	(	float *	a1,
		float *	a2,
		size_t	size,
		ACTIVATION	a,
		float *	dst
	)

Here is the call graph for this function:

◆ activate_and_mult_kernel()

__global__ void activate_and_mult_kernel	(	float *	a1,
		float *	a2,
		size_t	size,
		ACTIVATION	a,
		float *	dst
	)

Here is the caller graph for this function:

◆ adam_gpu()

void adam_gpu	(	int	n,
		float *	x,
		float *	m,
		float *	v,
		float	B1,
		float	B2,
		float	rate,
		float	eps,
		int	t
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ adam_kernel()

__global__ void adam_kernel	(	int	N,
		float *	x,
		float *	m,
		float *	v,
		float	B1,
		float	B2,
		float	rate,
		float	eps,
		int	t
	)

Here is the caller graph for this function:

◆ adam_update_gpu()

void adam_update_gpu	(	float *	w,
		float *	d,
		float *	m,
		float *	v,
		float	B1,
		float	B2,
		float	eps,
		float	decay,
		float	rate,
		int	n,
		int	batch,
		int	t
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ add_3_arrays_activate()

void add_3_arrays_activate	(	float *	a1,
		float *	a2,
		float *	a3,
		size_t	size,
		ACTIVATION	a,
		float *	dst
	)

Here is the call graph for this function:

◆ add_3_arrays_activate_kernel()

__global__ void add_3_arrays_activate_kernel	(	float *	a1,
		float *	a2,
		float *	a3,
		size_t	size,
		ACTIVATION	a,
		float *	dst
	)

Here is the caller graph for this function:

◆ add_bias_gpu()

void add_bias_gpu	(	float *	output,
		float *	biases,
		int	batch,
		int	filters,
		int	spatial
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ add_bias_kernel()

__global__ void add_bias_kernel	(	float *	output,
		float *	biases,
		int	batch,
		int	filters,
		int	spatial,
		int	current_size
	)

Here is the caller graph for this function:

◆ axpy_kernel()

__global__ void axpy_kernel	(	int	N,
		float	ALPHA,
		float *	X,
		int	OFFX,
		int	INCX,
		float *	Y,
		int	OFFY,
		int	INCY
	)

Here is the caller graph for this function:

◆ axpy_ongpu()

void axpy_ongpu	(	int	N,
		float	ALPHA,
		float *	X,
		int	INCX,
		float *	Y,
		int	INCY
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ axpy_ongpu_offset()

void axpy_ongpu_offset	(	int	N,
		float	ALPHA,
		float *	X,
		int	OFFX,
		int	INCX,
		float *	Y,
		int	OFFY,
		int	INCY
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ backward_bias_gpu()

void backward_bias_gpu	(	float *	bias_updates,
		float *	delta,
		int	batch,
		int	n,
		int	size
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ backward_bias_kernel()

__global__ void backward_bias_kernel	(	float *	bias_updates,
		float *	delta,
		int	batch,
		int	n,
		int	size
	)

Here is the caller graph for this function:

◆ backward_implicit_gpu()

void backward_implicit_gpu	(	int	batch,
		int	nweights,
		float *	weight_updates_gpu,
		float *	delta_gpu
	)

Here is the call graph for this function:

◆ backward_implicit_kernel()

__global__ void backward_implicit_kernel	(	int	size,
		int	batch,
		int	nweights,
		float *	weight_updates_gpu,
		float *	delta_gpu
	)

Here is the caller graph for this function:

◆ backward_sam_gpu()

void backward_sam_gpu	(	float *	in_w_h_c_delta,
		int	size,
		int	channel_size,
		float *	in_scales_c,
		float *	out_from_delta,
		float *	in_from_output,
		float *	out_state_delta
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ backward_sam_kernel()

__global__ void backward_sam_kernel	(	float *	in_w_h_c_delta,
		int	size,
		int	channel_size,
		float *	in_scales_c,
		float *	out_from_delta,
		float *	in_from_output,
		float *	out_state_delta
	)

Here is the caller graph for this function:

◆ backward_scale_channels_gpu()

void backward_scale_channels_gpu	(	float *	in_w_h_c_delta,
		int	size,
		int	channel_size,
		int	batch_size,
		int	scale_wh,
		float *	in_scales_c,
		float *	out_from_delta,
		float *	in_from_output,
		float *	out_state_delta
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ backward_scale_channels_kernel()

__global__ void backward_scale_channels_kernel	(	float *	in_w_h_c_delta,
		int	size,
		int	channel_size,
		int	batch_size,
		int	scale_wh,
		float *	in_scales_c,
		float *	out_from_delta,
		float *	in_from_output,
		float *	out_state_delta
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ backward_scale_gpu()

void backward_scale_gpu	(	float *	x_norm,
		float *	delta,
		int	batch,
		int	n,
		int	size,
		float *	scale_updates
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ backward_scale_kernel()

__global__ void backward_scale_kernel	(	float *	x_norm,
		float *	delta,
		int	batch,
		int	n,
		int	size,
		float *	scale_updates
	)

Here is the caller graph for this function:

◆ backward_shortcut_multilayer_gpu()

void backward_shortcut_multilayer_gpu	(	int	src_outputs,
		int	batch,
		int	n,
		int *	outputs_of_layers_gpu,
		float **	layers_delta_gpu,
		float *	delta_out,
		float *	delta_in,
		float *	weights_gpu,
		float *	weight_updates_gpu,
		int	nweights,
		float *	in,
		float **	layers_output_gpu,
		WEIGHTS_NORMALIZATION_T	weights_normalization
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ backward_shortcut_multilayer_kernel()

__global__ void backward_shortcut_multilayer_kernel	(	int	size,
		int	src_outputs,
		int	batch,
		int	n,
		int *	outputs_of_layers_gpu,
		float **	layers_delta_gpu,
		float *	delta_out,
		float *	delta_in,
		float *	weights_gpu,
		float *	weight_updates_gpu,
		int	nweights,
		float *	in,
		float **	layers_output_gpu,
		WEIGHTS_NORMALIZATION_T	weights_normalization
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ compare_2_arrays_gpu()

void compare_2_arrays_gpu	(	float *	one,
		float *	two,
		int	size
	)

Here is the call graph for this function:

◆ compare_2_arrays_kernel()

__global__ void compare_2_arrays_kernel	(	float *	one,
		float *	two,
		int	size
	)

Here is the caller graph for this function:

◆ const_kernel()

__global__ void const_kernel	(	int	N,
		float	ALPHA,
		float *	X,
		int	INCX
	)

Here is the caller graph for this function:

◆ const_ongpu()

void const_ongpu	(	int	N,
		float	ALPHA,
		float *	X,
		int	INCX
	)

Here is the call graph for this function:

◆ constrain_kernel()

__global__ void constrain_kernel	(	int	N,
		float	ALPHA,
		float *	X,
		int	INCX
	)

Here is the caller graph for this function:

◆ constrain_min_max_kernel()

__global__ void constrain_min_max_kernel	(	int	N,
		float	MIN,
		float	MAX,
		float *	X,
		int	INCX
	)

Here is the caller graph for this function:

◆ constrain_min_max_ongpu()

void constrain_min_max_ongpu	(	int	N,
		float	MIN,
		float	MAX,
		float *	X,
		int	INCX
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ constrain_ongpu()

void constrain_ongpu	(	int	N,
		float	ALPHA,
		float *	X,
		int	INCX
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ constrain_weight_updates_kernel()

__global__ void constrain_weight_updates_kernel	(	int	N,
		float	coef,
		float *	weights_gpu,
		float *	weight_updates_gpu
	)

Here is the caller graph for this function:

◆ constrain_weight_updates_ongpu()

void constrain_weight_updates_ongpu	(	int	N,
		float	coef,
		float *	weights_gpu,
		float *	weight_updates_gpu
	)

Here is the call graph for this function:

◆ coord_conv_gpu()

void coord_conv_gpu	(	float *	dst,
		int	size,
		int	w,
		int	h,
		int	chan,
		int	b,
		int	type
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ coord_conv_kernel()

__global__ void coord_conv_kernel	(	float *	dst,
		int	w,
		int	h,
		int	chan,
		int	batch,
		int	type
	)

Here is the caller graph for this function:

◆ copy_kernel()

__global__ void copy_kernel	(	int	N,
		float *	X,
		int	OFFX,
		int	INCX,
		float *	Y,
		int	OFFY,
		int	INCY
	)

Here is the caller graph for this function:

◆ copy_ongpu()

void copy_ongpu	(	int	N,
		float *	X,
		int	INCX,
		float *	Y,
		int	INCY
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ copy_ongpu_offset()

void copy_ongpu_offset	(	int	N,
		float *	X,
		int	OFFX,
		int	INCX,
		float *	Y,
		int	OFFY,
		int	INCY
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ expand_array_gpu()

void expand_array_gpu	(	const float *	src_gpu,
		float *	dst_gpu,
		int	size,
		int	groups
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ expand_array_kernel()

__global__ void expand_array_kernel	(	const float *	src_gpu,
		float *	dst_gpu,
		int	current_size,
		int	groups
	)

Here is the caller graph for this function:

◆ fast_mean_delta_gpu()

void fast_mean_delta_gpu	(	float *	delta,
		float *	variance,
		int	batch,
		int	filters,
		int	spatial,
		float *	mean_delta
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ fast_mean_delta_kernel()

__global__ void fast_mean_delta_kernel	(	float *	delta,
		float *	variance,
		int	batch,
		int	filters,
		int	spatial,
		float *	mean_delta
	)

Here is the caller graph for this function:

◆ fast_mean_gpu()

void fast_mean_gpu	(	float *	x,
		int	batch,
		int	filters,
		int	spatial,
		float *	mean
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ fast_mean_kernel()

__global__ void fast_mean_kernel	(	float *	x,
		int	batch,
		int	filters,
		int	spatial,
		float *	mean
	)

Here is the caller graph for this function:

◆ fast_v_cbn_gpu()

void fast_v_cbn_gpu	(	const float *	x,
		float *	mean,
		int	batch,
		int	filters,
		int	spatial,
		int	minibatch_index,
		int	max_minibatch_index,
		float *	m_avg,
		float *	v_avg,
		float *	variance,
		const float	alpha,
		float *	rolling_mean_gpu,
		float *	rolling_variance_gpu,
		int	inverse_variance,
		float	epsilon
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ fast_v_cbn_kernel()

__global__ void fast_v_cbn_kernel	(	const float *	x,
		float *	mean,
		int	batch,
		int	filters,
		int	spatial,
		int	minibatch_index,
		int	max_minibatch_index,
		float *	m_avg,
		float *	v_avg,
		float *	variance,
		const float	alpha,
		float *	rolling_mean_gpu,
		float *	rolling_variance_gpu,
		int	inverse_variance,
		float	epsilon
	)

Here is the caller graph for this function:

◆ fast_variance_delta_gpu()

void fast_variance_delta_gpu	(	float *	x,
		float *	delta,
		float *	mean,
		float *	variance,
		int	batch,
		int	filters,
		int	spatial,
		float *	variance_delta
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ fast_variance_delta_kernel()

__global__ void fast_variance_delta_kernel	(	float *	x,
		float *	delta,
		float *	mean,
		float *	variance,
		int	batch,
		int	filters,
		int	spatial,
		float *	variance_delta
	)

Here is the caller graph for this function:

◆ fast_variance_gpu()

void fast_variance_gpu	(	float *	x,
		float *	mean,
		int	batch,
		int	filters,
		int	spatial,
		float *	variance
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ fast_variance_kernel()

__global__ void fast_variance_kernel	(	float *	x,
		float *	mean,
		int	batch,
		int	filters,
		int	spatial,
		float *	variance
	)

Here is the caller graph for this function:

◆ fill_kernel()

__global__ void fill_kernel	(	int	N,
		float	ALPHA,
		float *	X,
		int	INCX
	)

Here is the caller graph for this function:

◆ fill_ongpu()

void fill_ongpu	(	int	N,
		float	ALPHA,
		float *	X,
		int	INCX
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ fix_nan_and_inf()

void fix_nan_and_inf	(	float *	input,
		size_t	size
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ fix_nan_and_inf_kernel()

__global__ void fix_nan_and_inf_kernel	(	float *	input,
		size_t	size
	)

Here is the caller graph for this function:

◆ flatten_kernel()

__global__ void flatten_kernel	(	int	N,
		float *	x,
		int	spatial,
		int	layers,
		int	batch,
		int	forward,
		float *	out
	)

Here is the caller graph for this function:

◆ flatten_ongpu()

void flatten_ongpu	(	float *	x,
		int	spatial,
		int	layers,
		int	batch,
		int	forward,
		float *	out
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ forward_implicit_gpu()

void forward_implicit_gpu	(	int	batch,
		int	nweights,
		float *	weight_gpu,
		float *	output_gpu
	)

Here is the call graph for this function:

◆ forward_implicit_kernel()

__global__ void forward_implicit_kernel	(	int	size,
		int	batch,
		int	nweights,
		float *	weight_gpu,
		float *	output_gpu
	)

Here is the caller graph for this function:

◆ grad_lrelu()

__device__ float grad_lrelu ( float src )

◆ grad_relu()

__device__ float grad_relu ( float src )

◆ gradient_centralization_gpu()

void gradient_centralization_gpu	(	int	w,
		int	h,
		int	c,
		int	f,
		float *	in
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ gradient_centralization_kernel()

__global__ void gradient_centralization_kernel	(	int	filters,
		int	f_size,
		float *	in
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ input_shortcut_gpu()

void input_shortcut_gpu	(	float *	in,
		int	batch,
		int	w1,
		int	h1,
		int	c1,
		float *	add,
		int	w2,
		int	h2,
		int	c2,
		float *	out
	)

Here is the call graph for this function:

◆ input_shortcut_kernel()

__global__ void input_shortcut_kernel	(	float *	in,
		int	size,
		int	minw,
		int	minh,
		int	minc,
		int	stride,
		int	sample,
		int	batch,
		int	w1,
		int	h1,
		int	c1,
		float *	add,
		int	w2,
		int	h2,
		int	c2,
		float *	out
	)

Here is the call graph for this function:

◆ inverse_variance_kernel()

__global__ void inverse_variance_kernel	(	int	size,
		float *	src,
		float *	dst,
		float	epsilon
	)

Here is the caller graph for this function:

◆ inverse_variance_ongpu()

void inverse_variance_ongpu	(	int	size,
		float *	src,
		float *	dst,
		float	epsilon
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ is_nan_or_inf()

int is_nan_or_inf	(	float *	input,
		size_t	size
	)

Here is the call graph for this function:

◆ is_nan_or_inf_kernel()

__global__ void is_nan_or_inf_kernel	(	float *	input,
		size_t	size,
		int *	pinned_return
	)

Here is the caller graph for this function:

◆ l2_gpu()

void l2_gpu	(	int	n,
		float *	pred,
		float *	truth,
		float *	delta,
		float *	error
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ l2_kernel()

__global__ void l2_kernel	(	int	n,
		float *	pred,
		float *	truth,
		float *	delta,
		float *	error
	)

Here is the caller graph for this function:

◆ lrelu()

__device__ float lrelu ( float src )

Here is the caller graph for this function:

◆ mask_gpu_new_api()

void mask_gpu_new_api	(	int	N,
		float *	X,
		float	mask_num,
		float *	mask,
		float	val
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ mask_kernel()

__global__ void mask_kernel	(	int	n,
		float *	x,
		float	mask_num,
		float *	mask
	)

Here is the caller graph for this function:

◆ mask_kernel_new_api()

__global__ void mask_kernel_new_api	(	int	n,
		float *	x,
		float	mask_num,
		float *	mask,
		float	val
	)

Here is the caller graph for this function:

◆ mask_ongpu()

void mask_ongpu	(	int	N,
		float *	X,
		float	mask_num,
		float *	mask
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ mean_array_gpu()

void mean_array_gpu	(	float *	src,
		int	size,
		float	alpha,
		float *	avg
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ mean_array_kernel()

__global__ void mean_array_kernel	(	float *	src,
		int	size,
		float	alpha,
		float *	avg
	)

Here is the caller graph for this function:

◆ mean_delta_gpu()

void mean_delta_gpu	(	float *	delta,
		float *	variance,
		int	batch,
		int	filters,
		int	spatial,
		float *	mean_delta
	)

Here is the call graph for this function:

◆ mean_delta_kernel()

__global__ void mean_delta_kernel	(	float *	delta,
		float *	variance,
		int	batch,
		int	filters,
		int	spatial,
		float *	mean_delta
	)

Here is the caller graph for this function:

◆ mean_gpu()

void mean_gpu	(	float *	x,
		int	batch,
		int	filters,
		int	spatial,
		float *	mean
	)

Here is the call graph for this function:

◆ mean_kernel()

__global__ void mean_kernel	(	float *	x,
		int	batch,
		int	filters,
		int	spatial,
		float *	mean
	)

Here is the caller graph for this function:

◆ memcpy_ongpu()

void memcpy_ongpu	(	void *	dst,
		void *	src,
		int	size_bytes
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ mul_kernel()

__global__ void mul_kernel	(	int	N,
		float *	X,
		int	INCX,
		float *	Y,
		int	INCY
	)

Here is the caller graph for this function:

◆ mul_ongpu()

void mul_ongpu	(	int	N,
		float *	X,
		int	INCX,
		float *	Y,
		int	INCY
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ mult_add_into_gpu()

void mult_add_into_gpu	(	int	num,
		float *	a,
		float *	b,
		float *	c
	)

Here is the call graph for this function:

◆ mult_add_into_kernel()

__global__ void mult_add_into_kernel	(	int	n,
		float *	a,
		float *	b,
		float *	c
	)

Here is the caller graph for this function:

◆ mult_inverse_array_gpu()

void mult_inverse_array_gpu	(	const float *	src_gpu,
		float *	dst_gpu,
		int	size,
		float	eps,
		float	divider,
		float	clip,
		float	abs_add
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ mult_inverse_array_kernel()

__global__ void mult_inverse_array_kernel	(	const float *	src_gpu,
		float *	dst_gpu,
		int	size,
		const float	eps,
		float	divider,
		const float	clip,
		const float	abs_add
	)

Here is the caller graph for this function:

◆ normalize_delta_gpu()

void normalize_delta_gpu	(	float *	x,
		float *	mean,
		float *	variance,
		float *	mean_delta,
		float *	variance_delta,
		int	batch,
		int	filters,
		int	spatial,
		float *	delta
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ normalize_delta_kernel()

__global__ void normalize_delta_kernel	(	int	N,
		float *	x,
		float *	mean,
		float *	variance,
		float *	mean_delta,
		float *	variance_delta,
		int	batch,
		int	filters,
		int	spatial,
		float *	delta
	)

Here is the caller graph for this function:

◆ normalize_gpu()

void normalize_gpu	(	float *	x,
		float *	mean,
		float *	variance,
		int	batch,
		int	filters,
		int	spatial
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ normalize_kernel()

__global__ void normalize_kernel	(	int	N,
		float *	x,
		float *	mean,
		float *	variance,
		int	batch,
		int	filters,
		int	spatial
	)

Here is the caller graph for this function:

◆ normalize_scale_bias_gpu()

void normalize_scale_bias_gpu	(	float *	x,
		float *	mean,
		float *	variance,
		float *	scales,
		float *	biases,
		int	batch,
		int	filters,
		int	spatial,
		int	inverse_variance,
		float	epsilon
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ normalize_scale_bias_kernel()

__global__ void normalize_scale_bias_kernel	(	int	N,
		float *	x,
		float *	mean,
		float *	variance,
		float *	scales,
		float *	biases,
		int	batch,
		int	filters,
		int	spatial,
		int	inverse_variance,
		float	epsilon
	)

Here is the caller graph for this function:

◆ P_constrastive_f_det_gpu()

void P_constrastive_f_det_gpu	(	int *	labels,
		unsigned int	feature_size,
		float	temperature,
		contrastive_params *	contrast_p,
		const int	contrast_p_size
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ P_constrastive_f_det_kernel()

__global__ void P_constrastive_f_det_kernel	(	int *	labels,
		unsigned int	feature_size,
		float	temperature,
		contrastive_params *	contrast_p,
		const int	contrast_p_size
	)

Here is the caller graph for this function:

◆ pow_kernel()

__global__ void pow_kernel	(	int	N,
		float	ALPHA,
		float *	X,
		int	INCX,
		float *	Y,
		int	INCY
	)

Here is the caller graph for this function:

◆ pow_ongpu()

void pow_ongpu	(	int	N,
		float	ALPHA,
		float *	X,
		int	INCX,
		float *	Y,
		int	INCY
	)

Here is the call graph for this function:

◆ reduce_and_expand_array_gpu()

void reduce_and_expand_array_gpu	(	const float *	src_gpu,
		float *	dst_gpu,
		int	size,
		int	groups
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ reduce_and_expand_array_kernel()

__global__ void reduce_and_expand_array_kernel	(	const float *	src_gpu,
		float *	dst_gpu,
		int	current_size,
		int	groups
	)

Here is the caller graph for this function:

◆ relu()

__device__ float relu ( float src )

◆ reorg_kernel()

__global__ void reorg_kernel	(	int	N,
		float *	x,
		int	w,
		int	h,
		int	c,
		int	batch,
		int	stride,
		int	forward,
		float *	out
	)

Here is the caller graph for this function:

◆ reorg_ongpu()

void reorg_ongpu	(	float *	x,
		int	w,
		int	h,
		int	c,
		int	batch,
		int	stride,
		int	forward,
		float *	out
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ reset_nan_and_inf()

void reset_nan_and_inf	(	float *	input,
		size_t	size
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ reset_nan_and_inf_kernel()

__global__ void reset_nan_and_inf_kernel	(	float *	input,
		size_t	size
	)

Here is the caller graph for this function:

◆ rotate_weights_gpu()

void rotate_weights_gpu	(	const float *	src_weight_gpu,
		float *	weight_deform_gpu,
		int	nweights,
		int	n,
		int	size,
		int	reverse
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ rotate_weights_kernel()

__global__ void rotate_weights_kernel	(	const float *	src_weight_gpu,
		float *	weight_deform_gpu,
		int	nweights,
		int	n,
		int	kernel_size,
		int	reverse
	)

Here is the caller graph for this function:

◆ sam_gpu()

void sam_gpu	(	float *	in_w_h_c,
		int	size,
		int	channel_size,
		float *	scales_c,
		float *	out
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ sam_kernel()

__global__ void sam_kernel	(	float *	in_w_h_c,
		int	size,
		int	channel_size,
		float *	scales_c,
		float *	out
	)

Here is the caller graph for this function:

◆ scal_add_kernel()

__global__ void scal_add_kernel	(	int	N,
		float	ALPHA,
		float	BETA,
		float *	X,
		int	INCX
	)

Here is the caller graph for this function:

◆ scal_add_ongpu()

void scal_add_ongpu	(	int	N,
		float	ALPHA,
		float	BETA,
		float *	X,
		int	INCX
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ scal_kernel()

__global__ void scal_kernel	(	int	N,
		float	ALPHA,
		float *	X,
		int	INCX
	)

Here is the caller graph for this function:

◆ scal_ongpu()

void scal_ongpu	(	int	N,
		float	ALPHA,
		float *	X,
		int	INCX
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ scale_bias_gpu()

void scale_bias_gpu	(	float *	output,
		float *	scale,
		int	batch,
		int	filters,
		int	spatial
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ scale_bias_kernel()

__global__ void scale_bias_kernel	(	float *	output,
		float *	scale,
		int	batch,
		int	filters,
		int	spatial,
		int	current_size
	)

Here is the caller graph for this function:

◆ scale_channels_gpu()

void scale_channels_gpu	(	float *	in_w_h_c,
		int	size,
		int	channel_size,
		int	batch_size,
		int	scale_wh,
		float *	scales_c,
		float *	out
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ scale_channels_kernel()

__global__ void scale_channels_kernel	(	float *	in_w_h_c,
		int	size,
		int	channel_size,
		int	batch_size,
		int	scale_wh,
		float *	scales_c,
		float *	out
	)

Here is the caller graph for this function:

◆ shortcut_gpu()

void shortcut_gpu	(	int	batch,
		int	w1,
		int	h1,
		int	c1,
		float *	add,
		int	w2,
		int	h2,
		int	c2,
		float *	out
	)

Here is the call graph for this function:

◆ shortcut_kernel()

__global__ void shortcut_kernel	(	int	size,
		int	minw,
		int	minh,
		int	minc,
		int	stride,
		int	sample,
		int	batch,
		int	w1,
		int	h1,
		int	c1,
		float *	add,
		int	w2,
		int	h2,
		int	c2,
		float *	out
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ shortcut_multilayer_gpu()

void shortcut_multilayer_gpu	(	int	src_outputs,
		int	batch,
		int	n,
		int *	outputs_of_layers_gpu,
		float **	layers_output_gpu,
		float *	out,
		float *	in,
		float *	weights_gpu,
		int	nweights,
		WEIGHTS_NORMALIZATION_T	weights_normalization
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ shortcut_multilayer_kernel()

__global__ void shortcut_multilayer_kernel	(	int	size,
		int	src_outputs,
		int	batch,
		int	n,
		int *	outputs_of_layers_gpu,
		float **	layers_output_gpu,
		float *	out,
		float *	in,
		float *	weights_gpu,
		int	nweights,
		WEIGHTS_NORMALIZATION_T	weights_normalization
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ shortcut_singlelayer_simple_kernel()

__global__ void shortcut_singlelayer_simple_kernel	(	int	size,
		int	src_outputs,
		int	batch,
		int	n,
		int *	outputs_of_layers_gpu,
		float **	layers_output_gpu,
		float *	out,
		float *	in,
		float *	weights_gpu,
		int	nweights,
		WEIGHTS_NORMALIZATION_T	weights_normalization
	)

Here is the caller graph for this function:

◆ simple_copy_kernel()

__global__ void simple_copy_kernel	(	int	size,
		float *	src,
		float *	dst
	)

Here is the caller graph for this function:

◆ simple_copy_ongpu()

void simple_copy_ongpu	(	int	size,
		float *	src,
		float *	dst
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ simple_input_shortcut_kernel()

__global__ void simple_input_shortcut_kernel	(	float *	in,
		int	size,
		float *	add,
		float *	out
	)

Here is the caller graph for this function:

◆ smooth_l1_gpu()

void smooth_l1_gpu	(	int	n,
		float *	pred,
		float *	truth,
		float *	delta,
		float *	error
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ smooth_l1_kernel()

__global__ void smooth_l1_kernel	(	int	n,
		float *	pred,
		float *	truth,
		float *	delta,
		float *	error
	)

Here is the caller graph for this function:

◆ smooth_rotate_weights_gpu()

void smooth_rotate_weights_gpu	(	const float *	src_weight_gpu,
		float *	weight_deform_gpu,
		int	nweights,
		int	n,
		int	size,
		int	angle,
		int	reverse
	)

Here is the call graph for this function:

◆ smooth_rotate_weights_kernel()

__global__ void smooth_rotate_weights_kernel	(	const float *	src_weight_gpu,
		float *	weight_deform_gpu,
		int	nweights,
		int	n,
		int	kernel_size,
		int	angle,
		int	reverse
	)

Here is the caller graph for this function:

◆ softmax_device()

__device__ void softmax_device	(	int	n,
		float *	input,
		float	temp,
		float *	output
	)

Here is the caller graph for this function:

◆ softmax_device_new_api()

__device__ void softmax_device_new_api	(	float *	input,
		int	n,
		float	temp,
		int	stride,
		float *	output
	)

Here is the caller graph for this function:

◆ softmax_gpu()

void softmax_gpu	(	float *	input,
		int	n,
		int	offset,
		int	groups,
		float	temp,
		float *	output
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ softmax_gpu_new_api()

void softmax_gpu_new_api	(	float *	input,
		int	n,
		int	batch,
		int	batch_offset,
		int	groups,
		int	group_offset,
		int	stride,
		float	temp,
		float *	output
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ softmax_kernel()

__global__ void softmax_kernel	(	int	n,
		int	offset,
		int	batch,
		float *	input,
		float	temp,
		float *	output
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ softmax_kernel_new_api()

__global__ void softmax_kernel_new_api	(	float *	input,
		int	n,
		int	batch,
		int	batch_offset,
		int	groups,
		int	group_offset,
		int	stride,
		float	temp,
		float *	output
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ softmax_tree_gpu()

void softmax_tree_gpu	(	float *	input,
		int	spatial,
		int	batch,
		int	stride,
		float	temp,
		float *	output,
		Darknet::Tree	hier
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ softmax_tree_kernel()

__global__ void softmax_tree_kernel	(	float *	input,
		int	spatial,
		int	batch,
		int	stride,
		float	temp,
		float *	output,
		int	groups,
		int *	group_size,
		int *	group_offset
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ softmax_x_ent_gpu()

void softmax_x_ent_gpu	(	int	n,
		float *	pred,
		float *	truth,
		float *	delta,
		float *	error
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ softmax_x_ent_kernel()

__global__ void softmax_x_ent_kernel	(	int	n,
		float *	pred,
		float *	truth,
		float *	delta,
		float *	error
	)

Here is the caller graph for this function:

◆ stretch_sway_flip_weights_gpu()

void stretch_sway_flip_weights_gpu	(	const float *	src_weight_gpu,
		float *	weight_deform_gpu,
		int	nweights,
		int	n,
		int	size,
		int	angle,
		int	reverse
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ stretch_sway_flip_weights_kernel()

__global__ void stretch_sway_flip_weights_kernel	(	const float *	src_weight_gpu,
		float *	weight_deform_gpu,
		int	nweights,
		int	n,
		int	kernel_size,
		float	angle,
		int	reverse
	)

Here is the caller graph for this function:

◆ stretch_weights_gpu()

void stretch_weights_gpu	(	const float *	src_weight_gpu,
		float *	weight_deform_gpu,
		int	nweights,
		int	n,
		int	size,
		float	scale,
		int	reverse
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ stretch_weights_kernel()

__global__ void stretch_weights_kernel	(	const float *	src_weight_gpu,
		float *	weight_deform_gpu,
		int	nweights,
		int	n,
		int	kernel_size,
		float	scale,
		int	reverse
	)

Here is the caller graph for this function:

◆ sum_of_mults()

void sum_of_mults	(	float *	a1,
		float *	a2,
		float *	b1,
		float *	b2,
		size_t	size,
		float *	dst
	)

Here is the call graph for this function:

◆ sum_of_mults_kernel()

__global__ void sum_of_mults_kernel	(	float *	a1,
		float *	a2,
		float *	b1,
		float *	b2,
		size_t	size,
		float *	dst
	)

Here is the caller graph for this function:

◆ supp_kernel()

__global__ void supp_kernel	(	int	N,
		float	ALPHA,
		float *	X,
		int	INCX
	)

Here is the caller graph for this function:

◆ supp_ongpu()

void supp_ongpu	(	int	N,
		float	ALPHA,
		float *	X,
		int	INCX
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ sway_and_flip_weights_gpu()

void sway_and_flip_weights_gpu	(	const float *	src_weight_gpu,
		float *	weight_deform_gpu,
		int	nweights,
		int	n,
		int	size,
		int	angle,
		int	reverse
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ sway_and_flip_weights_kernel()

__global__ void sway_and_flip_weights_kernel	(	const float *	src_weight_gpu,
		float *	weight_deform_gpu,
		int	nweights,
		int	n,
		int	kernel_size,
		int	angle,
		int	reverse
	)

Here is the caller graph for this function:

◆ upsample_gpu()

void upsample_gpu	(	float *	in,
		int	w,
		int	h,
		int	c,
		int	batch,
		int	stride,
		int	forward,
		float	scale,
		float *	out
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ upsample_kernel()

__global__ void upsample_kernel	(	size_t	N,
		float *	x,
		int	w,
		int	h,
		int	c,
		int	batch,
		int	stride,
		int	forward,
		float	scale,
		float *	out
	)

Here is the caller graph for this function:

◆ variance_delta_kernel()

__global__ void variance_delta_kernel	(	float *	x,
		float *	delta,
		float *	mean,
		float *	variance,
		int	batch,
		int	filters,
		int	spatial,
		float *	variance_delta
	)

◆ variance_gpu()

void variance_gpu	(	float *	x,
		float *	mean,
		int	batch,
		int	filters,
		int	spatial,
		float *	variance
	)

Here is the call graph for this function:

◆ variance_kernel()

__global__ void variance_kernel	(	float *	x,
		float *	mean,
		int	batch,
		int	filters,
		int	spatial,
		float *	variance
	)

Here is the caller graph for this function:

◆ warpAllReduceSum()

__inline__ __device__ float warpAllReduceSum ( float val )

Here is the caller graph for this function:

◆ weighted_delta_gpu()

void weighted_delta_gpu	(	float *	a,
		float *	b,
		float *	s,
		float *	da,
		float *	db,
		float *	ds,
		int	num,
		float *	dc
	)

Here is the call graph for this function:

◆ weighted_delta_kernel()

__global__ void weighted_delta_kernel	(	int	n,
		float *	a,
		float *	b,
		float *	s,
		float *	da,
		float *	db,
		float *	ds,
		float *	dc
	)

Here is the caller graph for this function:

◆ weighted_sum_gpu()

void weighted_sum_gpu	(	float *	a,
		float *	b,
		float *	s,
		int	num,
		float *	c
	)

Here is the call graph for this function:

◆ weighted_sum_kernel()

__global__ void weighted_sum_kernel	(	int	n,
		float *	a,
		float *	b,
		float *	s,
		float *	c
	)

Here is the caller graph for this function:

Functions

Function Documentation

◆ accumulate_kernel()

◆ activate_and_mult()

◆ activate_and_mult_kernel()

◆ adam_gpu()

◆ adam_kernel()

◆ adam_update_gpu()

◆ add_3_arrays_activate()

◆ add_3_arrays_activate_kernel()

◆ add_bias_gpu()

◆ add_bias_kernel()

◆ axpy_kernel()

◆ axpy_ongpu()

◆ axpy_ongpu_offset()

◆ backward_bias_gpu()

◆ backward_bias_kernel()

◆ backward_implicit_gpu()

◆ backward_implicit_kernel()

◆ backward_sam_gpu()

◆ backward_sam_kernel()

◆ backward_scale_channels_gpu()

◆ backward_scale_channels_kernel()

◆ backward_scale_gpu()

◆ backward_scale_kernel()

◆ backward_shortcut_multilayer_gpu()

◆ backward_shortcut_multilayer_kernel()

◆ compare_2_arrays_gpu()

◆ compare_2_arrays_kernel()

◆ const_kernel()

◆ const_ongpu()

◆ constrain_kernel()

◆ constrain_min_max_kernel()

◆ constrain_min_max_ongpu()

◆ constrain_ongpu()

◆ constrain_weight_updates_kernel()

◆ constrain_weight_updates_ongpu()

◆ coord_conv_gpu()

◆ coord_conv_kernel()

◆ copy_kernel()

◆ copy_ongpu()

◆ copy_ongpu_offset()

◆ expand_array_gpu()

◆ expand_array_kernel()

◆ fast_mean_delta_gpu()

◆ fast_mean_delta_kernel()

◆ fast_mean_gpu()

◆ fast_mean_kernel()

◆ fast_v_cbn_gpu()

◆ fast_v_cbn_kernel()

◆ fast_variance_delta_gpu()

◆ fast_variance_delta_kernel()

◆ fast_variance_gpu()

◆ fast_variance_kernel()

◆ fill_kernel()

◆ fill_ongpu()

◆ fix_nan_and_inf()

◆ fix_nan_and_inf_kernel()

◆ flatten_kernel()

◆ flatten_ongpu()

◆ forward_implicit_gpu()

◆ forward_implicit_kernel()

◆ grad_lrelu()

◆ grad_relu()

◆ gradient_centralization_gpu()

◆ gradient_centralization_kernel()

◆ input_shortcut_gpu()

◆ input_shortcut_kernel()

◆ inverse_variance_kernel()

◆ inverse_variance_ongpu()

◆ is_nan_or_inf()

◆ is_nan_or_inf_kernel()

◆ l2_gpu()

◆ l2_kernel()

◆ lrelu()

◆ mask_gpu_new_api()

◆ mask_kernel()

◆ mask_kernel_new_api()

◆ mask_ongpu()

◆ mean_array_gpu()