commit | 2dbdc2fa7d5d13e9472b2e4b819975c0fbd55975 | [log] [tgz] |
---|---|---|
author | Marat Dukhan <maratek@google.com> | Tue Oct 08 16:36:23 2019 -0700 |
committer | XNNPACK Team <xnnpack-github-robot@google.com> | Tue Oct 08 16:36:44 2019 -0700 |
tree | ab7118c5b988a555180ca3ad938716a4d6d86c0d | |
parent | afbca9ad87f3f295157794eeb6bbaf762722d4dc [diff] |
CMake build configurations PiperOrigin-RevId: 273632973
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.