commit | efc47b8c72a6de830837dfd90cebb96a2ccc2ce3 | [log] [tgz] |
---|---|---|
author | Marat Dukhan <maratek@google.com> | Mon Nov 18 09:25:38 2019 -0800 |
committer | XNNPACK Team <xnnpack-github-robot@google.com> | Mon Nov 18 09:26:10 2019 -0800 |
tree | 9be5efade034787625d109a7525bd7aaca945970 | |
parent | 1b0922923a7333ebb8671cc2829241b58c9b394b [diff] |
Unify operator implementations filenames and tests - Always include layout in operator name - Standardize layout names - Prepare for greater variability in supported layouts - Merge testers for different layouts of the same operator PiperOrigin-RevId: 281084963
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 and 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.