Reduction

A primitive to compute reduction operation on data tensor using min, max, mul, sum, mean and norm_lp operations. More...

Classes
struct	dnnl::reduction
	Reduction. More...
struct	dnnl_reduction_desc_t
	A descriptor of reduction operation. More...

Functions
dnnl_status_t DNNL_API	dnnl_reduction_desc_init (dnnl_reduction_desc_t *desc, dnnl_alg_kind_t alg_kind, const dnnl_memory_desc_t *src_desc, const dnnl_memory_desc_t *dst_desc, float p, float eps)
	Initializes a descriptor for a reduction primitive. More...

Detailed Description

A primitive to compute reduction operation on data tensor using min, max, mul, sum, mean and norm_lp operations.

See also

Reduction in developer guide

Function Documentation

dnnl_reduction_desc_init()

dnnl_status_t DNNL_API dnnl_reduction_desc_init	(	dnnl_reduction_desc_t *	desc,
		dnnl_alg_kind_t	alg_kind,
		const dnnl_memory_desc_t *	src_desc,
		const dnnl_memory_desc_t *	dst_desc,
		float	p,
		float	eps
	)

Initializes a descriptor for a reduction primitive.

Note

Destination memory descriptor is allowed to be initialized with dnnl_format_tag_any or with format_kind set to dnnl_format_kind_any.

Parameters

desc	Output descriptor for a reduction primitive.
alg_kind	reduction algorithm kind. Possible values: dnnl_reduction_max, dnnl_reduction_min, dnnl_reduction_sum, dnnl_reduction_mul, dnnl_reduction_mean, dnnl_reduction_norm_lp_max, dnnl_reduction_norm_lp_sum, dnnl_reduction_norm_lp_power_p_max, dnnl_reduction_norm_lp_power_p_sum.
p	Algorithm specific parameter.
eps	Algorithm specific parameter.
src_desc	Source memory descriptor.
dst_desc	Destination memory descriptor.

Returns

dnnl_success on success and a status describing the error otherwise.