|
Intel(R) Math Kernel Library for Deep Neural Networks (Intel(R) MKL-DNN)
0.21.0
Performance library for Deep Learning
|
A primitive to concatenate data by arbitrary dimension. More...
Functions | |
| mkldnn_status_t MKLDNN_API | mkldnn_concat_primitive_desc_create (mkldnn_primitive_desc_t *concat_primitive_desc, const mkldnn_memory_desc_t *output_desc, int n, int concat_dimension, const_mkldnn_primitive_desc_t *input_pds) |
Creates out-of-place concat_primitive_desc for concatenation of n inputs by concat_dimension with resulting output_desc memory descriptor. More... | |
A primitive to concatenate data by arbitrary dimension.
| mkldnn_status_t MKLDNN_API mkldnn_concat_primitive_desc_create | ( | mkldnn_primitive_desc_t * | concat_primitive_desc, |
| const mkldnn_memory_desc_t * | output_desc, | ||
| int | n, | ||
| int | concat_dimension, | ||
| const_mkldnn_primitive_desc_t * | input_pds | ||
| ) |
Creates out-of-place concat_primitive_desc for concatenation of n inputs by concat_dimension with resulting output_desc memory descriptor.
output_desc can be NULL or specified with the mkldnn_any format – in this case, the appropriate memory format would be chosen automatically.
Order of inputs:
n - 1 (mkldnn_query_input_pd, n - 1)Order of outputs:
1.8.14