| commit | efc184ac20ea128e43164e627e94afc61f237a2e | [log] [tgz] |
|---|---|---|
| author | Marat Dukhan <maratek@google.com> | Thu Feb 13 09:47:01 2020 -0800 |
| committer | XNNPACK Team <xnnpack-github-robot@google.com> | Thu Feb 13 09:47:53 2020 -0800 |
| tree | b748798f321674422e0a244a077c9b826bb38624 | |
| parent | b00004dc2fda70bb3e0df59be3a390c5a2fada47 [diff] |
Properly set XNN_ENABLE_ASSEMBLY macro in CMake builds - Expose XNNPACK_ENABLE_ASSEMBLY CMake option - Define XNN_ENABLE_ASSEMBLY macro - Ensure assembly-implemented micro-kernels are checked in unit tests and benchmarks PiperOrigin-RevId: 294936208
XNNPACK is a highly optimized library of floating-point neural network inference operators for ARM, WebAssembly, and x86 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 three generations of MobileNet models and three generations of Pixel phones.
| Model | Pixel, ms | Pixel 2, ms | Pixel 3a, ms |
|---|---|---|---|
| MobileNet v1 1.0X | 81 | 89 | 88 |
| MobileNet v2 1.0X | 48 | 55 | 54 |
| MobileNet v3 Large | 40 | 44 | 44 |
| MobileNet v3 Small | 12 | 14 | 14 |
The following table presents multi-threaded (using as many threads as there are big cores) performance of XNNPACK library on three generations of MobileNet models and three generations of Pixel phones.
| Model | Pixel, ms | Pixel 2, ms | Pixel 3a, ms |
|---|---|---|---|
| MobileNet v1 1.0X | 45 | 27 | 46 |
| MobileNet v2 1.0X | 28 | 18 | 28 |
| MobileNet v3 Large | 23 | 16 | 24 |
| MobileNet v3 Small | 7 | 6 | 8 |
Benchmarked on January 9, 2020 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.
The table below presents multi-threaded performance of XNNPACK library on three generations of MobileNet models and three generations of Raspberry Pi boards.
| Model | RPi 2 (BCM2836), ms | RPi 3+ (BCM2837B0), ms | RPi 4 (BCM2711), ms |
|---|---|---|---|
| MobileNet v1 1.0X | 378 | 115 | 75 |
| MobileNet v2 1.0X | 216 | 79 | 44 |
| MobileNet v3 Large | 178 | 67 | 41 |
| MobileNet v3 Small | 56 | 23 | 14 |
Benchmarked on February 12, 2020 with end2end-bench --benchmark_min_time=5 on a Raspbian Buster build with CMake (./scripts/build-local.sh) 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.