tag | d17b364b7ca917cf5fcf8a3c336b051901f83af0 | |
---|---|---|
tagger | The Android Open Source Project <initial-contribution@android.com> | Mon Aug 08 14:27:44 2022 -0700 |
object | 8f8ffbb9d2bd3229b58f7570f9912f320b612c6c |
Android 12.1.0 release 25
commit | 8f8ffbb9d2bd3229b58f7570f9912f320b612c6c | [log] [tgz] |
---|---|---|
author | Haibo Huang <hhb@google.com> | Wed Mar 24 00:57:10 2021 +0000 |
committer | Automerger Merge Worker <android-build-automerger-merge-worker@system.gserviceaccount.com> | Wed Mar 24 00:57:10 2021 +0000 |
tree | 620677917f38b4015358dac80d83b3a760d9b25f | |
parent | 7f2c83e1f02630b74bd248d36fd7647af0c1bb53 [diff] | |
parent | b245f8db75b62fbc5a27bbe8e584994bfcef2566 [diff] |
Merge "Update Android.bp following XNNPACK rebase" am: 4df0b5067f am: 944fcf1709 am: b245f8db75 Original change: https://android-review.googlesource.com/c/platform/external/XNNPACK/+/1650467 Change-Id: Iad5949abf39afa658782f3581fd0ad35ac95f151
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 TensorFlow Lite, TensorFlow.js, PyTorch, and MediaPipe.
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 | 82 | 86 | 88 |
MobileNet v2 1.0X | 49 | 53 | 55 |
MobileNet v3 Large | 39 | 42 | 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 | 43 | 27 | 46 |
MobileNet v2 1.0X | 26 | 18 | 28 |
MobileNet v3 Large | 22 | 16 | 24 |
MobileNet v3 Small | 7 | 6 | 8 |
Benchmarked on March 27, 2020 with end2end_bench --benchmark_min_time=5
on an Android/ARM64 build with Android NDK r21 (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 Zero W (BCM2835), ms | RPi 2 (BCM2836), ms | RPi 3+ (BCM2837B0), ms | RPi 4 (BCM2711), ms |
---|---|---|---|---|
MobileNet v1 1.0X | 4004 | 337 | 116 | 72 |
MobileNet v2 1.0X | 2011 | 195 | 83 | 41 |
MobileNet v3 Large | 1694 | 163 | 70 | 38 |
MobileNet v3 Small | 482 | 52 | 23 | 13 |
Benchmarked on May 22, 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. Over time its codebase diverged a lot, and XNNPACK API is no longer compatible with QNNPACK.