Deep Neural Network Library (DNNL)  1.1.3
Performance library for Deep Learning
Modules
Primitive operations

Modules

 Common primitive operations
 
 Attributes
 An extension for controlling primitive behavior.
 
 Memory
 A primitive to describe and store data.
 
 Reorder
 A primitive to copy data between memory formats.
 
 Concat
 A primitive to concatenate data by arbitrary dimension.
 
 Sum
 A primitive to sum data.
 
 Binary
 A primitive to perform tensor operations over two tensors.
 
 Convolution
 The convolution primitive computes a forward, backward, or weight update for a batched convolution operation on 1D, 2D, or 3D spatial data with bias.
 
 Deconvolution
 A primitive to compute deconvolution using different algorithms.
 
 Shuffle
 A primitive to shuffle data along the axis.
 
 Eltwise
 A primitive to compute element-wise operations such as parametric rectifier linear unit (ReLU).
 
 Softmax
 A primitive to perform softmax.
 
 Pooling
 A primitive to perform max or average pooling.
 
 LRN
 A primitive to perform local response normalization (LRN) across or within channels.
 
 Batch Normalization
 A primitive to perform batch normalization.
 
 Layer Normalization
 A primitive to perform layer normalization.
 
 Inner product
 A primitive to compute an inner product.
 
 RNN
 A primitive to compute the common recurrent layer.
 

Detailed Description