commit | bd4197199239443db168f1c6f40f494fa5b079b5 | [log] [tgz] |
---|---|---|
author | Frank Barchard <fbarchard@google.com> | Thu Oct 31 14:15:36 2019 -0700 |
committer | XNNPACK Team <xnnpack-github-robot@google.com> | Thu Oct 31 14:17:24 2019 -0700 |
tree | b150f1c49ac3fa4da29c417217674553a1625d2d | |
parent | 8e6e997f3e1735846972389ec71081fd4d27c75c [diff] |
A57 branch a version of A53 kernel The A53 kernel in its current form performs better than the derivative of A785 with prefetch removed. This new kernel is LD64 based with unroll and prefetch every 64 bytes. PiperOrigin-RevId: 277799014
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.