Intel(R) Math Kernel Library for Deep Neural Networks (Intel(R) MKL-DNN)  0.21.0
Performance library for Deep Learning
Public Attributes | List of all members
mkldnn_blocking_desc_t Struct Reference

Generic description of blocked data layout for most memory formats. More...

#include <mkldnn_types.h>

Public Attributes

mkldnn_dims_t block_dims
 Block size for each of the dimensions. More...
 
mkldnn_strides_t strides [2]
 strides[0]: stride between the first elements of adjacent blocks. More...
 
mkldnn_dims_t padding_dims
 Size of the data including padding in each dimension. More...
 
mkldnn_dims_t offset_padding_to_data
 Per-dimension offset from the padding to actual data, the top-level tensor with offsets applied must lie within the padding area. More...
 
ptrdiff_t offset_padding
 Offset from memory origin to the current block, non-zero only in a description of a memory sub-block. More...
 

Detailed Description

Generic description of blocked data layout for most memory formats.

See also
Understanding Memory Formats

Member Data Documentation

◆ block_dims

mkldnn_dims_t mkldnn_blocking_desc_t::block_dims

Block size for each of the dimensions.

◆ strides

mkldnn_strides_t mkldnn_blocking_desc_t::strides[2]

strides[0]: stride between the first elements of adjacent blocks.


strides[1]: strides between elements in the same block.

◆ padding_dims

mkldnn_dims_t mkldnn_blocking_desc_t::padding_dims

Size of the data including padding in each dimension.

◆ offset_padding_to_data

mkldnn_dims_t mkldnn_blocking_desc_t::offset_padding_to_data

Per-dimension offset from the padding to actual data, the top-level tensor with offsets applied must lie within the padding area.

◆ offset_padding

ptrdiff_t mkldnn_blocking_desc_t::offset_padding

Offset from memory origin to the current block, non-zero only in a description of a memory sub-block.


The documentation for this struct was generated from the following file: