|
Intel(R) Math Kernel Library for Deep Neural Networks (Intel(R) MKL-DNN)
0.19.0
Performance library for Deep Learning
|
|
Intel(R) Math Kernel Library for Deep Neural Networks (Intel(R) MKL-DNN)
0.19.0
Performance library for Deep Learning
|
  mkldnn | |
   handle_traits | A class that provides the destructor for an Intel(R) MKL-DNN C handle |
| handle | A class for wrapping an Intel(R) MKL-DNN handle. It is used as the base class for primitive (mkldnn_primitive_t), engine (mkldnn_engine_t), and stream (mkldnn_stream_t) handles. An object of the mkldnn::handle class can be passed by value. This class enables wrapping: |
 primitive | Base class for all computational primitives |
| error | Intel(R) MKL-DNN exception class |
| post_ops | |
| primitive_attr | |
| engine | An execution engine |
| memory | Memory primitive that describes the data |
| reorder | |
| view | |
| concat | |
| sum | |
| primitive_desc | A base class for all primitive descriptors |
| convolution_forward | |
| convolution_backward_data | |
| convolution_backward_weights | |
| deconvolution_forward | |
| deconvolution_backward_data | |
| deconvolution_backward_weights | |
| lrn_forward | |
| lrn_backward | |
| pooling_forward | |
| pooling_backward | |
| eltwise_forward | |
| eltwise_backward | |
| softmax_forward | |
| softmax_backward | |
| batch_normalization_forward | |
| batch_normalization_backward | |
| inner_product_forward | |
| inner_product_backward_data | |
| inner_product_backward_weights | |
| rnn_cell | |
| rnn_forward | |
| rnn_backward | |
| shuffle_forward | |
| shuffle_backward | |
 stream | |
| mkldnn_batch_normalization_desc_t | A descriptor of a Batch Normalization operation |
| mkldnn_blocking_desc_t | Generic description of blocked data layout for most memory formats |
| mkldnn_convolution_desc_t | A descriptor of a convolution operation |
| mkldnn_eltwise_desc_t | A descriptor of a element-wise operation |
| mkldnn_engine | An opaque structure to describe an engine |
| mkldnn_inner_product_desc_t | A descriptor of an inner product operation |
| mkldnn_lrn_desc_t | A descriptor of a Local Response Normalization (LRN) operation |
| mkldnn_memory_desc_t | Memory descriptor |
| mkldnn_pooling_desc_t | A descriptor of a pooling operation |
| mkldnn_post_ops | An opaque structure for a chain of post operations |
| mkldnn_primitive | An opaque structure to describe a primitive |
| mkldnn_primitive_at_t | A wrapper structure to specify a particular output of a primitive |
| mkldnn_primitive_attr | An opaque structure for primitive descriptor attributes |
| mkldnn_primitive_desc | An opaque structure to describe a primitive descriptor |
| mkldnn_primitive_desc_iterator | An opaque structure to describe a primitive descriptor iterator |
| mkldnn_rnn_cell_desc_t | |
| mkldnn_rnn_desc_t | A descriptor for an RNN operation |
| mkldnn_rnn_packed_desc_t | Description of tensor of packed weights for rnn |
| mkldnn_shuffle_desc_t | A descriptor of a shuffle operation |
| mkldnn_softmax_desc_t | A descriptor of a Softmax operation |
| mkldnn_stream | An opaque structure to describe an execution stream |
| mkldnn_version_t | Intel(R) MKL-DNN Version type |
| mkldnn_wino_desc_t | Description of tensor of weights for winograd 2x3 convolution |
1.8.5
