| commit | 1025ea33fe2149badcf87dbf06473f234713b05a | [log] [tgz] |
|---|---|---|
| author | Marat Dukhan <maratek@google.com> | Thu Nov 21 16:01:08 2019 -0800 |
| committer | XNNPACK Team <xnnpack-github-robot@google.com> | Thu Nov 21 16:02:06 2019 -0800 |
| tree | e8708f3ecede2ff5dbc69fa0b75091c5b10413ac | |
| parent | 496e735079df6c8639ac3738d8df2b87c370feff [diff] |
Enable AVX and FMA3 GEMM micro-kernels for non-mobile x86 PiperOrigin-RevId: 281853163
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.