| commit | 9d056a4f254ef0016ef37b92310d876a50d60839 | [log] [tgz] |
|---|---|---|
| author | Marat Dukhan <maratek@google.com> | Thu Oct 03 12:13:35 2019 -0700 |
| committer | XNNPACK Team <xnnpack-github-robot@google.com> | Thu Oct 03 12:14:02 2019 -0700 |
| tree | 35636b9c949772d784c7b754ab92fa66290f7b87 | |
| parent | 3bcea2bc5bac7e029a30c2d578c1359cefac0b4d [diff] |
Compatibility with TF.js WAsm build - Use the same Emscripten toolchain identifier as TF.js - Set :XNNPACK visibility to public PiperOrigin-RevId: 272713655
XNNPACK is a highly optimized library of floating-point neural network inference operators for ARM, WebAssembly, and x86 (SSE2 level) platforms. XNNPACK is not intended for direct use by deep learning practitioners researchers; instead it provides low-level performance primitives for accelerating high-level machine learning frameworks, such as MediaPipe, TensorFlow Lite, and TensorFlow.js.
XNNPACK implements the following neural network operators:
All operators in XNNPACK support NHWC layout, but additionally allow custom stride along the Channel dimension. Thus, operators can consume a subset of channels in the input tensor, and produce a subset of channels in the output tensor, providing a zero-cost Channel Split and Channel Concatenation operations.
XNNPACK is a based on QNNPACK library. However, unlike QNNPACK, XNNPACK focuses entirely on floating-point operators, and its API is no longer compatible with QNNPACK.