commit	af388617e5e2ea4c2b57ffcae97d18c724e740f5	[log] [tgz]
author	Android Build Role Account android-build-prod <android-build-team-robot@google.com>	Sat Feb 22 03:31:06 2020 +0000
committer	Android Build Role Account android-build-prod <android-build-team-robot@google.com>	Sat Feb 22 03:31:06 2020 +0000
tree	420706bf142f6bffdeab33d1ba81791db2787b99
parent	320e4c03d4a35b359ecb0712e96a1e8a6477640d [diff]
parent	488c2c0c7bafe7f41d09cc5b30238b46dabc8a96 [diff]

tree: 420706bf142f6bffdeab33d1ba81791db2787b99

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 MediaPipe, TensorFlow Lite, and TensorFlow.js.

Supported Architectures

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

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	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.

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	380	115	76
MobileNet v2 1.0X	217	80	45
MobileNet v3 Large	180	67	41
MobileNet v3 Small	57	23	15

Benchmarked on January 9, 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.

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.