| commit | e2142e7e74f03eef359e31df2c5429dd7a6be04c | [log] [tgz] |
|---|---|---|
| author | XNNPACK Team <xnnpack-github-robot@google.com> | Thu Oct 31 10:57:14 2019 -0700 |
| committer | XNNPACK Team <xnnpack-github-robot@google.com> | Thu Oct 31 10:57:14 2019 -0700 |
| tree | 04819ea181c3f679b846d5d8fb662d6026b06fef | |
| parent | 63ba2ed105d9256340d104077eda0f27bcbce992 [diff] | |
| parent | 791d01da82cecbc259eb396a19822f8f6a8b8219 [diff] |
Merge pull request #103 from Maratyszcza:master PiperOrigin-RevId: 277757316
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.
The table below presents single-threaded performance of XNNPACK library on two generations of MobileNet models and three generations of Pixel phones.
| Model | Pixel, ms | Pixel 2, ms | Pixel 3a, ms |
|---|---|---|---|
| MobileNet v1 1.0X | 81 | 93 | 88 |
| MobileNet v2 1.0X | 48 | 58 | 54 |
Benchmarked on October 9, 2019 with end2end_bench --benchmark_min_time=5 on an Android/ARM64 build (bazel build -c opt --config android_arm64 :end2end_bench) and neural network models with randomized weights and inputs.
XNNPACK is a based on QNNPACK library. Unlike QNNPACK, XNNPACK focuses entirely on floating-point operators, and its API is no longer compatible with QNNPACK.