 oneDNN API | |
  Primitives | Compute primitives |
  Common | Common operations to create, destroy and inspect primitives |
| Attributes | A container for parameters that extend primitives behavior |
| Reorder | A primitive to copy data between two memory objects |
| Concat | A primitive to concatenate data by arbitrary dimension |
| Sum | A primitive to sum multiple tensors |
| Binary | A primitive to perform tensor operations over two tensors |
| Convolution | A primitive to perform 1D, 2D or 3D convolution |
| Deconvolution | A primitive to perform 1D, 2D or 3D deconvolution |
| Shuffle | A primitive to shuffle tensor data along an axis |
| Eltwise | A primitive to perform elementwise operations such as the rectifier linear unit (ReLU) |
| Softmax | A primitive to perform softmax |
| LogSoftmax | A primitive to perform logsoftmax |
| 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 recurrent neural network layers |
| Matrix Multiplication | A primitive to perform matrix-matrix multiplication |
| Resampling | A primitive to compute resampling operation on 1D, 2D or 3D data tensor using Nearest Neighbor, or Linear (Bilinear, Trilinear) interpolation method |
| Reduction | A primitive to compute reduction operation on data tensor using min, max, mul, sum, mean and norm_lp operations |
 Dnnl_api_pooling_v2 | |
| Memory | A container that describes and stores data |
| Engine | An abstraction of a computational device: a CPU, a specific GPU card in the system, etc |
| Stream | An encapsulation of execution context tied to a particular engine |
| Primitive Cache | A set of functions that provide primitive cache control |
| Service | A set of functions that aid in oneDNN debugging and profiling |
| BLAS functions | A subset of Basic Linear Algebra (BLAS) functions that perform matrix-matrix multiplication |
| Utilities | Utility types and definitions |
