Intel(R) Math Kernel Library for Deep Neural Networks (Intel(R) MKL-DNN)
0.21.0
Performance library for Deep Learning
|
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... | |
Generic description of blocked data layout for most memory formats.
mkldnn_dims_t mkldnn_blocking_desc_t::block_dims |
Block size for each of the dimensions.
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.
mkldnn_dims_t mkldnn_blocking_desc_t::padding_dims |
Size of the data including padding in each dimension.
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.
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.