Single-board computer for AI applications, with Rockchip NPU and Arm big.LITTLE architecture, advanced power design and easy machine-learning model deployment
KEY POINTS
- Made for machine learning: Powered Rockchip neural processing unit (NPU) with hex-core Arm big.LITTLE A72+A53 architecture
- Stacked with connectivity: Rich I/O interface, including one MIPI-DSI, two MIPI-CSI, one 40-pin GPIO and a PCIe Mini expansion slot
- Stable power delivery: Flexible 12-19 V DC input, via either a DC jack or a 4-pin header, to provide up to 65 W
- Multiple OS support and dev tools: Both Linux and Android options supported, plus robust API and SDK for developers
TAIPEI, Taiwan, April 29, 2020 — ASUS today announced Tinker Edge R, a single-board computer (SBC) specially designed for AI applications. It uses a Rockchip RK3399Pro NPU, a machine-learning (ML) accelerator that speeds up processing efficiency, lowers power demands and makes it easier to build connected devices and intelligent applications.
With this integrated ML accelerator, Tinker Edge R can perform three tera-operations per second (3TOPS), using low power consumption.
It also features an optimized neural-network (NN) architecture, which means Tinker Edge R can support multiple ML frameworks and allow lots of common ML models to be compiled and run easily.
Advanced power design
Most SBC motherboards offer only a 15-watt (5V 3A) power design, which can cause device and system instability when there are multiple connected devices. Other SBCs have power designs that lower the performance of their I/O ports. Tinker Edge R has a special power design that, together with both a DC jack input and a 4-pin header, delivers up to 65 watts of power, enabling stable system operation and full I/O performance — even with multiple connected devices. Additionally, an exclusive power-protection design activates automatically if the supplied current and voltage change significantly, effectively protecting the board and all connected devices.
Rockchip RK3399Pro processor
With its powerful and modern hex-core Rockchip RK3399Pro processor powered by Arm
® big.LITTLE A72+A53 technology, Tinker Edge R offers a powerful solution for graphics, machine vision, video, audio, voice and safety-critical applications. Tinker Edge R features 4 GB of dual-channel LPDDR4 system memory, the 4th generation of low-power DDR DRAM technology, offering faster speeds and even lower power consumption for improved system performance and efficiency. It also boasts 2 GB of standalone memory for the NPU, delivering faster speeds, improved stability and high efficiency for ML inference.
Tinker Edge R also comes equipped with an onboard 16 GB eMMC and SD 3.0 interface that offers significantly faster read and write speeds for the operating system, applications and file storage.
More connectivity options for developers
Tinker Edge R features a rich I/O interface, including one MIPI-DSI connection for displays and touch screens, and two MIPI-CSI connections for compatible cameras to enable computer vision for applications such as depth measurement, smart-vending-machines and interactive advertising.
A developer-friendly design offers many carefully considered features to provide a superior experience for first-time builders and seasoned hobbyists alike. Programmable LEDs let developers develop custom lighting behaviors, such as system notifications and status indicators, and the color-coded GPIO header makes it easy to recognize respective pin headers.
Tinker Edge R also boasts a full-size HDMI port, USB Type-A, USB Type-C, gigabit LAN and WiFi and Bluetooth for internet and network connectivity as well as a mini PCI Express
® Mini slot for a 4G/LTE extension card.
Multiple OS support and machine-learning developer tools
Tinker OS is a great starting point for any project or build and offers operating system (OS) freedom. A Debian-based Linux distribution ensures a smooth and functional experience. Tinker Edge R also support the Android OS: this allows for an entirely different set of usage scenarios, ranging from running popular Android app, machine-learning (ML) inference and much more.
ASUS provides a robust API and SDK that enables users to deploy ML models to Tinker Edge R easily for applications such as image classification and object detection. It also supports model conversion from Caffe, TensorFlow, TensorFlow Lite, ONNX, Darknet and more.
NOTES TO EDITORS
Tinker Edge R Product Page: https://tinker-board.asus.com/prod_tinker-edge-r.html
ASUS Global Press Room: http://press.asus.com
ASUS Global Facebook: http://www.facebook.com/asus
ASUS Global Twitter: http://www.twitter.com/asus
| SPECIFICATIONS[1] |
| SoC |
RockchipRK3399Pro |
| CPU |
Dual-core Arm® Cortex®-A72 @ 1.8 GHz +
Quad-core Arm® Cortex®-A53 @ 1.4 GHz |
| GPU |
Arm® Mali™-T860 MP4 GPU @ 800 MHz |
| NN Processor |
Rockchip NPU |
| Memory |
Dual-CH LPDDR4 4GB (SYSTEM) + LPDDR3 2GB (NPU) |
| Storage |
16GB eMMC
1 x Micro SD (TF) card slot (push & pull) |
| Display |
1 x HDMI with CEC hardware ready
1 x Type-C (DP)
1 x 22-pin MIPI DSI (4 lane) |
| USB |
3 xUSB3.2 Gen1 Type-A ports
1 x USB3.2 Gen1 Type-C OTG port |
| Camera interface |
1 x 22-pin MIPI CSI-2 (4 lane)
1 x 22-pin MIPI CSI-2/DSI (4 lane) |
| Connectivity |
1 x RTL8211F-CGGbELAN
1 x 802.11 a/b/g/n/ac & Bluetooth 5.0(2T2R) |
| Expansions |
1 x Mini PCIe slot
(Full-Length, nano-SIM socket, for 4G/LTE) |
| Audio |
1 x 3.5mm audio jack (with Mic & plug-in detection) |
| Internal I/O |
1 x 40-pin header includes:
- up to 2 x SPI bus
- up to 2 x I2C bus
- up to 2 x UART
- up to 3 x PWM
- up to 1 x S/PDIF TX
- 2 x 5V power pins
- 2 x 3.3V power pins
- 8 x ground pins
1 x 2-pin Recovery header
1 x 2-pin Power-on header
1 x 2-pin Reset header
1 x 2-pin DC Fan header
1 x 2-pin RTC Battery header
1 x 2-pin NPU UART header |
| Non-operation temperature |
-40–85°C |
| Relative humidity |
0%–85% |
| Operating system support |
Debian 9 / Android 8.1 |
| Form factor |
Pico-ITX, 3.9" x 2.8" (100 × 72 mm) |
About ASUS
ASUS is a multinational company known for the world’s best motherboards, PCs, monitors, graphics cards and routers. Along with an expanding range of superior gaming, content-creation and AIoT solutions, ASUS leads the industry through cutting-edge design and innovations made to create the most ubiquitous, intelligent, heartfelt and joyful smart life for everyone. With a global workforce that includes more than 5,000 R&D professionals, ASUS is driven to become the world’s most admired innovative leading technology enterprise. Inspired by the
In Search of Incredible brand spirit, ASUS won more than 11 awards every day in 2019 and ranks as one of Forbes’ World’s Best Regarded Companies and Fortune’s World’s Most Admired Companies.
[1] Specifications, content and product availability are all subject to change without notice and may differ from country to country. Actual performance may vary depending on applications, usage, environment and other factors. Full specifications are available at http://www.asus.com
