Google Git
Sign in
android / platform / external / XNNPACK / 523448a22
commit523448a22ef8c61a618cc0f3d02700c995efcd1d[log] [tgz]
authorMarat Dukhan <maratek@google.com>Tue Oct 08 16:58:53 2019 -0700
committerXNNPACK Team <xnnpack-github-robot@google.com>Tue Oct 08 16:59:15 2019 -0700
tree33039fe65b765722008978e0ce9cb9cfd7f8fa43
parent2dbdc2fa7d5d13e9472b2e4b819975c0fbd55975 [diff]
Add .gitignore file

PiperOrigin-RevId: 273637007
1 file changed
tree: 33039fe65b765722008978e0ce9cb9cfd7f8fa43
  1. bench/
  2. cmake/
  3. include/
  4. models/
  5. scripts/
  6. src/
  7. test/
  8. third_party/
  9. tools/
  10. .bazelrc
  11. .gitignore
  12. BUILD
  13. build_defs.bzl
  14. CMakeLists.txt
  15. CONTRIBUTING.md
  16. emscripten.bzl
  17. LICENSE
  18. preamble.js.lds
  19. README.md
  20. WORKSPACE
README.md

XNNPACK

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.

Supported Architectures

  • ARM64 on Android and Linux
  • ARM on Android
  • WebAssembly MVP
  • WebAssembly SIMD (experimental)
  • x86 and x86-64 (up to SSE2 only) on Android, Linux, and macOS

Operator Coverage

XNNPACK implements the following neural network operators:

  • 2D Convolution (including grouped and depthwise)
  • 2D Deconvolution (AKA Transposed Convolution)
  • 2D Average Pooling
  • 2D Max Pooling
  • 2D ArgMax Pooling (Max Pooling + indices)
  • 2D Unpooling
  • Add (tensors of same shape)
  • Global Average Pooling
  • Channel Shuffle
  • Fully Connected
  • Clamp (includes ReLU and ReLU6)
  • HardSwish
  • PReLU

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.

Publications

Acknowledgements

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.