commit | 810171ddd29de6e621268f3f1383752efde47f0d | [log] [tgz] |
---|---|---|
author | Frank Barchard <fbarchard@google.com> | Thu Oct 10 10:34:51 2019 -0700 |
committer | XNNPACK Team <xnnpack-github-robot@google.com> | Thu Oct 10 10:35:18 2019 -0700 |
tree | 5082b0887ab197a5ad113265076d16d5c89bf50d | |
parent | 21be34fc1f57b894aa494af9458481b9747c9d64 [diff] |
Enable assembly by default. For init.c the flag is not set but the code enables assembly if the flag is not set. For the benchmarks, the code expects the flag to be set and will not enable assembly by default. Changing the build file allows the default for benchmarks to be assembly enabled. PiperOrigin-RevId: 273988816
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. However, unlike QNNPACK, XNNPACK focuses entirely on floating-point operators, and its API is no longer compatible with QNNPACK.