.rst .pdf

Contents

Reduction

Overview

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

// structs

struct dnnl_reduction_desc_t;
struct dnnl::reduction;

// global 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
    );

Detailed Documentation

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

Global 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.

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.

struct dnnl::resampling_forward::primitive_desc struct dnnl_reduction_desc_t