• Home
Name Date Size #Lines LOC

..--

bench/03-May-2024-40,39334,727

cmake/03-May-2024-169141

eval/03-May-2024-19,59717,904

include/03-May-2024-2,9782,000

models/03-May-2024-42,52239,825

scripts/03-May-2024-8,8346,498

src/03-May-2024-1,720,6891,393,191

test/03-May-2024-1,532,6101,418,410

third_party/03-May-2024-1,008925

tools/03-May-2024-11,2609,801

.bazelrcD03-May-20241.4 KiB5642

.clang-formatD03-May-2024521 1817

.gitignoreD03-May-2024491 3633

Android.bpD03-May-2024432.9 KiB9,6119,441

BUILD.bazelD03-May-2024522.2 KiB13,20712,652

CMakeLists.txtD03-May-2024430.8 KiB9,0798,692

CONTRIBUTING.mdD03-May-20241.1 KiB2920

LICENSED03-May-20241.5 KiB3224

METADATAD03-May-2024737 2019

MODULE_LICENSE_BSDD03-May-20240

OWNERSD03-May-2024219 1211

README.mdD03-May-20246.9 KiB12195

TEST_MAPPINGD03-May-20243.8 KiB211210

WORKSPACED03-May-20243.2 KiB9278

build_defs.bzlD03-May-202418.1 KiB471440

emscripten.bzlD03-May-20241.2 KiB4136

preamble.js.ldsD03-May-2024393 108

README.md

1# XNNPACK
2
3XNNPACK 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](https://www.tensorflow.org/lite), [TensorFlow.js](https://www.tensorflow.org/js), [PyTorch](https://pytorch.org/), and [MediaPipe](https://mediapipe.dev).
4
5## Supported Architectures
6
7- ARM64 on Android, Linux, macOS, and iOS (including WatchOS and tvOS)
8- ARMv7 (with NEON) on Android
9- ARMv6 (with VFPv2) on Linux
10- x86 and x86-64 (up to AVX512) on Windows, Linux, macOS, Android, and iOS simulator
11- WebAssembly MVP
12- WebAssembly SIMD
13- RISC-V (RV32GV and RV64GC)
14
15## Operator Coverage
16
17XNNPACK implements the following neural network operators:
18
19- 2D Convolution (including grouped and depthwise)
20- 2D Deconvolution (AKA Transposed Convolution)
21- 2D Average Pooling
22- 2D Max Pooling
23- 2D ArgMax Pooling (Max Pooling + indices)
24- 2D Unpooling
25- 2D Bilinear Resize
26- 2D Depth-to-Space (AKA Pixel Shuffle)
27- Add (including broadcasting, two inputs only)
28- Subtract (including broadcasting)
29- Divide (including broadcasting)
30- Maximum (including broadcasting)
31- Minimum (including broadcasting)
32- Multiply (including broadcasting)
33- Squared Difference (including broadcasting)
34- Global Average Pooling
35- Channel Shuffle
36- Fully Connected
37- Abs (absolute value)
38- Bankers' Rounding (rounding to nearest, ties to even)
39- Ceiling (rounding to integer above)
40- Clamp (includes ReLU and ReLU6)
41- Convert (includes fixed-point and half-precision quantization and
42  dequantization)
43- Copy
44- ELU
45- Floor (rounding to integer below)
46- HardSwish
47- Leaky ReLU
48- Negate
49- Sigmoid
50- Softmax
51- Square
52- Truncation (rounding to integer towards zero)
53- PReLU
54
55All operators in XNNPACK support NHWC layout, but additionally allow custom stride along the **C**hannel 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.
56
57## Performance
58
59### Mobile phones
60
61The table below presents **single-threaded** performance of XNNPACK library on three generations of MobileNet models and three generations of Pixel phones.
62
63| Model                   | Pixel, ms | Pixel 2, ms | Pixel 3a, ms |
64| ----------------------- | :-------: | :---------: | :----------: |
65| FP32 MobileNet v1 1.0X  |    82     |      86     |      88      |
66| FP32 MobileNet v2 1.0X  |    49     |      53     |      55      |
67| FP32 MobileNet v3 Large |    39     |      42     |      44      |
68| FP32 MobileNet v3 Small |    12     |      14     |      14      |
69
70The 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.
71
72| Model                   | Pixel, ms | Pixel 2, ms | Pixel 3a, ms |
73| ----------------------- | :-------: | :---------: | :----------: |
74| FP32 MobileNet v1 1.0X  |    43     |      27     |      46      |
75| FP32 MobileNet v2 1.0X  |    26     |      18     |      28      |
76| FP32 MobileNet v3 Large |    22     |      16     |      24      |
77| FP32 MobileNet v3 Small |     7     |       6     |       8      |
78
79Benchmarked 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.
80
81### Raspberry Pi
82
83The table below presents **multi-threaded** performance of XNNPACK library on three generations of MobileNet models and three generations of Raspberry Pi boards.
84
85| Model                   | RPi Zero W (BCM2835), ms | RPi 2 (BCM2836), ms | RPi 3+ (BCM2837B0), ms | RPi 4 (BCM2711), ms | RPi 4 (BCM2711, ARM64), ms |
86| ----------------------- | :----------------------: | :-----------------: | :--------------------: | :-----------------: | :------------------------: |
87| FP32 MobileNet v1 1.0X  |          3937            |         299         |          114           |          72         |             76             |
88| FP32 MobileNet v2 1.0X  |          1987            |         187         |           79           |          41         |             44             |
89| FP32 MobileNet v3 Large |          1658            |         158         |           67           |          38         |             41             |
90| FP32 MobileNet v3 Small |           487            |          50         |           23           |          13         |             14             |
91| INT8 MobileNet v1 1.0X  |          2598            |         169         |           61           |          29         |             24             |
92| INT8 MobileNet v2 1.0X  |          1487            |         109         |           40           |          20         |             17             |
93
94Benchmarked on Oct 15, 2021 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. INT8 inference was evaluated on per-channel quantization schema.
95
96## Publications
97
98- Marat Dukhan "The Indirect Convolution Algorithm". Presented on [Efficient Deep Learning for Compute Vision (ECV) 2019](https://sites.google.com/corp/view/ecv2019/) workshop ([slides](https://drive.google.com/file/d/1ZayB3By5ZxxQIRtN7UDq_JvPg1IYd3Ac/view), [paper on ArXiv](https://arxiv.org/abs/1907.02129)).
99- Erich Elsen, Marat Dukhan, Trevor Gale, Karen Simonyan "Fast Sparse ConvNets".
100  [Paper on ArXiv](https://arxiv.org/abs/1911.09723), [pre-trained sparse
101  models](https://github.com/google-research/google-research/tree/master/fastconvnets).
102- Marat Dukhan, Artsiom Ablavatski "The Two-Pass Softmax Algorithm".
103  [Paper on ArXiv](https://arxiv.org/abs/2001.04438).
104- Yury Pisarchyk, Juhyun Lee "Efficient Memory Management for Deep Neural Net Inference".
105  [Paper on ArXiv](https://arxiv.org/abs/2001.03288).
106
107## Ecosystem
108
109### Machine Learning Frameworks
110
111- [TensorFlow Lite](https://blog.tensorflow.org/2020/07/accelerating-tensorflow-lite-xnnpack-integration.html).
112- [TensorFlow.js WebAssembly backend](https://blog.tensorflow.org/2020/03/introducing-webassembly-backend-for-tensorflow-js.html).
113- [PyTorch Mobile](https://pytorch.org/mobile).
114- [MediaPipe for the Web](https://developers.googleblog.com/2020/01/mediapipe-on-web.html).
115- [Alibaba HALO (Heterogeneity-Aware Lowering and Optimization)](https://github.com/alibaba/heterogeneity-aware-lowering-and-optimization)
116- [Samsung ONE (On-device Neural Engine)](https://github.com/Samsung/ONE)
117
118## Acknowledgements
119
120XNNPACK is a based on [QNNPACK](https://github.com/pytorch/QNNPACK) library. Over time its codebase diverged a lot, and XNNPACK API is no longer compatible with QNNPACK.
121