|
Intel(R) Math Kernel Library for Deep Neural Networks (Intel(R) MKL-DNN)
0.21.0
Performance library for Deep Learning
|
A primitive to sum data. More...
Functions | |
| mkldnn_status_t MKLDNN_API | mkldnn_sum_primitive_desc_create (mkldnn_primitive_desc_t *sum_primitive_desc, const mkldnn_memory_desc_t *output_desc, int n, const float *scales, const_mkldnn_primitive_desc_t *input_pds) |
Creates out-of-place sum_primitive_desc for sum of n inputs multiplied by scale with resulting output_desc memory descriptor. More... | |
A primitive to sum data.
| mkldnn_status_t MKLDNN_API mkldnn_sum_primitive_desc_create | ( | mkldnn_primitive_desc_t * | sum_primitive_desc, |
| const mkldnn_memory_desc_t * | output_desc, | ||
| int | n, | ||
| const float * | scales, | ||
| const_mkldnn_primitive_desc_t * | input_pds | ||
| ) |
Creates out-of-place sum_primitive_desc for sum of n inputs multiplied by scale 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