commit	b64f61731fce8d5c62ea4cc8ed975d08700ffde1	[log] [tgz]
author	Marat Dukhan <maratek@google.com>	Sat May 16 00:23:12 2020 -0700
committer	XNNPACK Team <xnnpack-github-robot@google.com>	Sat May 16 00:23:50 2020 -0700
tree	bfb96c2a0d43a71375744bd510a669d11c4a99d5
parent	ae89be61b1d258f801f3723b634ad3c42b4fcfd3 [diff]

tree: bfb96c2a0d43a71375744bd510a669d11c4a99d5

README.md

XNNPACK

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.

Supported Architectures

ARM64 on Android, Linux, and iOS (including WatchOS and tvOS)
ARMv7 (with NEON) on Android, Linux, and iOS (including WatchOS)
WebAssembly MVP
WebAssembly SIMD (experimental)
x86 and x86-64 (up to AVX512) on Android, Linux, macOS, and iOS simulator

Operator Coverage

XNNPACK implements the following neural network operators:

2D Convolution (including grouped and depthwise)
2D Deconvolution (AKA Transposed Convolution)
2D Average Pooling
2D Max Pooling
2D ArgMax Pooling (Max Pooling + indices)
2D Unpooling
2D Bilinear Resize
Add (including broadcasting, two inputs only)
Subtract (including broadcasting)
Divide (including broadcasting)
Maximum (including broadcasting)
Minimum (including broadcasting)
Multiply (including broadcasting)
Global Average Pooling
Channel Shuffle
Fully Connected
Clamp (includes ReLU and ReLU6)
HardSwish
Sigmoid
Softmax
PReLU

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.

Performance

Mobile phones

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.

Raspberry Pi

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	341	115	75
MobileNet v2 1.0X	197	79	44
MobileNet v3 Large	165	67	41
MobileNet v3 Small	53	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.

Publications

Marat Dukhan "The Indirect Convolution Algorithm". Presented on Efficient Deep Learning for Compute Vision (ECV) 2019 workshop (slides, paper on ArXiv).
Erich Elsen, Marat Dukhan, Trevor Gale, Karen Simonyan "Fast Sparse ConvNets". Paper on ArXiv, pre-trained sparse models.
Marat Dukhan, Artsiom Ablavatski "The Two-Pass Softmax Algorithm". Paper on ArXiv.
Yury Pisarchyk, Juhyun Lee "Efficient Memory Management for Deep Neural Net Inference". Paper on ArXiv.

Ecosystem

Machine Learning Frameworks

TensorFlow.js WebAssembly backend.
MediaPipe for Web.
TensorFlow Lite through the XNNPACK delegate.
PyTorch.

Acknowledgements

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.