Eltwise

A primitive to perform elementwise operations such as the rectifier linear unit (ReLU). More...

Classes
struct	dnnl::eltwise_forward
	Elementwise unary operation forward propagation primitive. More...
struct	dnnl::eltwise_backward
	Elementwise unary operation backward propagation primitive. More...
struct	dnnl_eltwise_desc_t
	A descriptor of a element-wise operation. More...

Functions
dnnl_status_t DNNL_API	dnnl_eltwise_forward_desc_init (dnnl_eltwise_desc_t *eltwise_desc, dnnl_prop_kind_t prop_kind, dnnl_alg_kind_t alg_kind, const dnnl_memory_desc_t *data_desc, float alpha, float beta)
	Initializes a descriptor for eltwise forward propagation primitive. More...
dnnl_status_t DNNL_API	dnnl_eltwise_backward_desc_init (dnnl_eltwise_desc_t *eltwise_desc, dnnl_alg_kind_t alg_kind, const dnnl_memory_desc_t *diff_data_desc, const dnnl_memory_desc_t *data_desc, float alpha, float beta)
	Initializes a descriptor for eltwise backward propagation primitive. More...

Detailed Description

A primitive to perform elementwise operations such as the rectifier linear unit (ReLU).

Both forward and backward propagation primitives support in-place operation; that is, src and dst can refer to the same memory for forward propagation, and diff_dst and diff_src can refer to the same memory for backward propagation.

Warning

Because the original source data is required for backward propagation, in-place forward propagation is not generally supported in the training mode. However, for algorithms supporting destination as input memory, dst can be used for the backward propagation, which makes it possible to get performance benefit even in the training mode.

See also

Eltwise in developer guide

Function Documentation

dnnl_eltwise_forward_desc_init()

dnnl_status_t DNNL_API dnnl_eltwise_forward_desc_init	(	dnnl_eltwise_desc_t *	eltwise_desc,
		dnnl_prop_kind_t	prop_kind,
		dnnl_alg_kind_t	alg_kind,
		const dnnl_memory_desc_t *	data_desc,
		float	alpha,
		float	beta
	)

Initializes a descriptor for eltwise forward propagation primitive.

Parameters

eltwise_desc	Output descriptor for an eltwise primitive.
prop_kind	Propagation kind. Possible values are dnnl_forward_training and dnnl_forward_inference.
alg_kind	Elementwise algorithm kind.
data_desc	Source and destination memory descriptor.
alpha	The alpha parameter for the elementwise operation. Specific meaning depends on the algorithm.
beta	The beta parameter for the elementwise operation. Specific meaning depends on the algorithm.

Returns

dnnl_success on success and a status describing the error otherwise.

Examples:

cnn_inference_f32.c, cpu_cnn_training_f32.c, and cross_engine_reorder.c.

dnnl_eltwise_backward_desc_init()

dnnl_status_t DNNL_API dnnl_eltwise_backward_desc_init	(	dnnl_eltwise_desc_t *	eltwise_desc,
		dnnl_alg_kind_t	alg_kind,
		const dnnl_memory_desc_t *	diff_data_desc,
		const dnnl_memory_desc_t *	data_desc,
		float	alpha,
		float	beta
	)

Initializes a descriptor for eltwise backward propagation primitive.

Parameters

eltwise_desc	Output descriptor for an eltwise primitive.
alg_kind	Elementwise algorithm kind.
diff_data_desc	Diff source and diff destination memory descriptors.
data_desc	Source and destination memory descriptor.
alpha	The alpha parameter for the elementwise operation. Specific meaning depends on the algorithm.
beta	The beta parameter for the elementwise operation. Specific meaning depends on the algorithm.

Returns

dnnl_success on success and a status describing the error otherwise.

Examples:

cpu_cnn_training_f32.c.