Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/nihui/ncnn-small-board
ncnn benchmark on various single board computers
https://github.com/nihui/ncnn-small-board
arm jetson mips ncnn neural-network risc-v rockchip sbc single-board-computer
Last synced: about 3 hours ago
JSON representation
ncnn benchmark on various single board computers
- Host: GitHub
- URL: https://github.com/nihui/ncnn-small-board
- Owner: nihui
- Created: 2022-01-16T03:05:48.000Z (over 2 years ago)
- Default Branch: master
- Last Pushed: 2023-10-19T11:51:32.000Z (12 months ago)
- Last Synced: 2023-10-19T12:45:53.879Z (12 months ago)
- Topics: arm, jetson, mips, ncnn, neural-network, risc-v, rockchip, sbc, single-board-computer
- Homepage:
- Size: 1.17 MB
- Stars: 128
- Watchers: 10
- Forks: 8
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# ncnn 小板子
ncnn is a high-performance neural network inference framework.
See https://github.com/Tencent/ncnn for more info about ncnn.
* The benchmark score is the inference time, **less is better**.
* Runs on all cpu big cores or vulkan, and fp16 arithmetic is enabled if supported.
* Table contents are ordered by mobilenet.
* rpi5b data from https://github.com/Tencent/ncnn/pull/5058
| small-board | image | spec | squeezenet | mobilenet | shufflenet |
| ---------------------- | --------------------------------- | ----------------------------------------------------------------- | ---------- | --------- | ---------- |
| NVIDIA Jetson AGX Orin |  | Ampere 1.3GHz x 2048
Tensor Core x 64 | 2.13 | 2.03 | 2.57 |
| NVIDIA Jetson AGX Orin |  | A78AE 2.2GHz x 12 | 3.50 | 3.49 | 5.08 |
| Radxa Rock5B |  | RK3588
A76 2.4GHz x 4
A55 1.8GHz x 4 | 3.65 | 5.41 | 3.37 |
| Orange Pi 5 |  | RK3588S
A76 2.4GHz x 4
A55 1.8GHz x 4 | 3.83 | 5.75 | 3.57 |
| ZYSJ RK3588 | | ARM Mali-G610 | 7.09 | 9.16 | 5.88 |
| ZYSJ RK3588 | | RK3588
A76 2.4GHz x 4
A55 1.8GHz x 4 | 7.57 | 11.01 | 7.95 |
| Raspberry Pi 5B | | BCM2712
A76 2.4GHz x 4 | 8.56 | 11.32 | 4.56 |
| M4N DOCK |  | AX650
A55 1.7Ghz x 8 | 10.61 | 11.86 | 10.64 |
| NVIDIA Jetson Nano |  | Maxwell 921MHz x 128 | 9.03 | 15.39 | 10.61 |
| Khadas VIM4 |  | ARM Mali-G52
800MHz x MP8(8EE) | 12.77 | 20.17 | 12.81 |
| Unisoc Tiger T710 |  | Unisoc Tiger T710
A75 1.82GHz x 4
A55 1.82GHz x 4 | 16.25 | 20.31 | 10.59 |
| Radxa Rock3A |  | RK3568
A55 2.0GHz x 4 | 23.20 | 30.78 | 19.49 |
| Khadas VIM3 |  | ARM Mali-G52
800MHz x MP4(6EE) | 19.54 | 31.62 | 17.91 |
| Panther X2 | | RK3566
A55 1.8GHz x 4 | 25.91 | 33.17 | 21.81 |
| NanoPi M4 |  | ARM Mali-T864 | 24.57 | 35.86 | 33.90 |
| Radxa RockPi X |  | Intel HD Graphics (Cherry Trail) 500 MHz | 29.91 | 36.41 | 24.54 |
| Khadas VIM4 |  | A311D2
A73 2.2GHz x 4
A53 2.0GHz x 2 | 24.27 | 37.65 | 19.79 |
| NVIDIA Jetson Nano |  | A57 1.43GHz x 4 | 28.55 | 40.25 | 19.44 |
| Khadas VIM3 |  | A311D
A73 2.2GHz x 4
A53 1.8GHz x 2 | 30.98 | 42.57 | 21.62 |
| Lichee Pi 4A |  | T-Head TH1520
RV64GCV 2.0GHz x 4 | 42.29 | 47.73 | 120.13 |
| NanoPi Fire3 |  | S5P6818
A53 1.4GHz x 8 | 41.81 | 52.33 | 33.54 |
| Debix Model A |  | i.MX8M Plus
A53 1.6GHz x 4 | 40.15 | 54.01 | 29.33 |
| Odroid XU4 |  | Exynos 5422
A15 2GHz x 4
A7 1.3GHz x 4 | 35.73 | 54.17 | 25.75 |
| Tinker Board S R2.0 |  | ARM Mali-T764 | 41.48 | 60.28 | 55.87 |
| Radxa Zero |  | S905Y2
A53 1.8GHz x 4 | 46.82 | 60.49 | 35.18 |
| Raspberry Pi 4B |  | BCM2711B0
A72 1.5GHz x 4 | 46.28 | 60.74 | 32.91 |
| NanoPi M4 |  | RK3399
A72 1.8GHz x 2
A53 1.5GHz x 4 | 43.73 | 64.28 | 27.43 |
| BeagleBone AI 64 |  | TDA4VM
A72 2.0GHz x 2 | 42.23 | 65.78 | 29.97 |
| NanoPi K2 |  | S905
A53 1.5GHz x 4 | 56.96 | 75.25 | 38.70 |
| Radxa RockPi X |  | Atom x5-Z8350
x86-64 1.92 GHz x 4 | 50.22 | 80.12 | 37.96 |
| Tinker Board S R2.0 |  | RK3288CGW
A17 1.8GHz x 4 | 52.86 | 82.19 | 38.17 |
| NanoPi R2S |  | RK3328
A53 1.3GHz x 4 | 62.20 | 82.88 | 52.34 |
| EAIDK 310 |  | RK3228H
A53 1.3GHz x 4 | 61.87 | 83.88 | 45.83 |
| Radxa Zero |  | ARM Mali-G31 850 MHz x 2 | 57.95 | 98.62 | 51.71 |
| Raspberry Pi 3B+ |  | BCM2837B0
A53 1.4GHz x 4 | 84.74 | 107.84 | 58.38 |
| Banana Pi M3 |  | AllWinner A83T
A7 1.8GHz x 8 | 88.35 | 109.72 | 80.91 |
| MangoPI MQ-Quad |  | AllWinner H616
A53 1.5GHz x 4 | 99.60 | 129.70 | 66.90 |
| Raspberry Pi Zero 2W |  | BCM2710A1
A53 1.0GHz x 4 | 119.52 | 162.60 | 72.72 |
| EASY EAI Nano |  | RV1126
A7 1.5GHz x 4 | 105.16 | 163.82 | 68.79 |
| Radxa RockPi S |  | RK3308
A35 1.3GHz x 4 | 142.02 | 214.56 | 102.44 |
| StarFive VisionFive V2 |  | SiFive’s U74
RV64GFC 1.5GHz x 4 | 150.07 | 256.21 | 91.14 |
| RVB-ICE |  | T-Head C910
RV64GC 1.2GHz x 2 | 161.10 | 274.39 | 118.61 |
| Loongson Pie Lite |  | Loongson 2K1000
GS264 1.0GHz x 2 | 185.28 | 276.03 | 124.39 |
| Ingenic X2000 | | Ingenic X2000
XBurst2 1.2GHz x 2 | 175.99 | 282.25 | 118.4 |
| Raspberry Pi 2B |  | BCM2836
A7 900MHz x 4 | 179.50 | 296.97 | 132.49 |
| Banana Pi M2 Zero 2 |  | AllWinner H2+
A7 1.2GHz x 4 | 218.73 | 303.92 | 138.43 |
| Raspberry Pi 4B |  | Broadcom VideoCore VI | 286.71 | 365.04 | 162.14 |
| PICO-PI-IMX7 |  | i.MX7D
A7 1.0GHz x 2 | 220.10 | 366.92 | 137.02 |
| Microphase Z7-Lite |  | XC7Z020CLG400
A9 766MHz x 2 | 389.18 | 623.71 | 212.20 |
| MangoPI MQ-Pro |  | D1 C906
RV64GCV 1GHz x 1 | 385.21 | 691.47 | 487.67 |
| NeZha D1 |  | D1 C906
RV64GCV 1GHz x 1 | 396.18 | 727.97 | 495.87 |
| StarFive VisionFive V1 |  | SiFive’s U74
RV64GFC 1.5GHz x 2 | 609.41 | 993.87 | 358.98 |
| Raspberry Pi B+ |  | ARM1176JZF-S
700MHz x 1 | 4285.24 | 7684.05 | 2102.22 |