EC-A3399C
Six-core AI Embedded Computer
Based on AIO-3399C (AI version) high-performance open-source platform, industrial-grade metal case and fan-off design
configured, with high-efficiency cooling ability, complete interface, strong applicability and computing power and
ultrahigh performance. It can be applicable to high-performance edge computing to accelerate in-depth learning
computation and AI algorithm. It can be rapidly applied in the field of mobile edge computing, smart home, face
recognition, etc.
Six-core 64 bit High-performance Core
ARM Cortex-A72 architecture and six-core 64-bit high-performance processor carried, frequency 1.8GHz reached, integrated
quad-core Mali-T860 GPU, H.265 HEVC, VP9 H.264 encoding and 4K HDR supported, with strong ability of hard decoding as
high as 4K.
Ultrahigh Performance
Onboard AI embedded neural network processor NPU, with 28000 parallel neural calculation cores, on-chip parallel and
in-situ computation supported, with a peak performance reaching up to 5.6 Tops and 2.8 Tops computing performance, with
an efficiency energy-consumption ratio reaching up to 9.3 Tops/W. It has strong computing power. In the meantime,
extremely low energy consumption is also maintained, making it extremely advantageous in the application of edge
computing of terminal device.
Unique AI Architecture
Dedicated MPE matrix engine and APiM (AI processing in Memory) framework for AI adopted, local parallel AI computation
integrated with storage and calculation. one-time upgrade network preload with no need for instructions, bus, and
external DDR cache. This configuration improves the processing speed hugely and lowers processing energy consumption a
lot compared with processors built in traditional architecture approaches.
Supporting Model Training Tool
Complete easy-to-use model-training tool PLAI (People Learn AI) based on PyTorch is offered. It can be developed on
Windows 10 and Ubuntu 16.04 system, and user-defined network model is added easier, greatly lowering the technical
threshold of using AI.
Provide Network Training Model
Three kinds of network training model sample including GNet1, GNet18 and GNetfc based on VGG are supported.
Subsequently, network samples will be continuously added, contributing to easy test of a large amount of in-depth
learning application on device.
Configuring Metal Case
High-quality metal case and fanless design configured, heat-conducting aluminum alloy structure, high-efficiency
cooling, 60℃high-temperature aging, stable operation for 7x24 hours, various installation ways contributing to its
embedding into various smart devices more convenient.
Rich External Interfaces
HDMI2.0, LAN, Type-C, USB3.0, RS485, RS232 and other interfaces owned to make it possible to be widely applied in
various industries
Specification
| Specification |
| CPU |
RK3399, Dual-core（Cortex-A72）+ Quad-core（Cortex-A53），frequency up to 1.8 GHz
|
| GPU |
Quad-core ARM Mali-T860
Support OpenGL ES 1.1/2.0 /3.0, OpenVG1.1, OpenCL, Directx11
|
| NPU |
SPR2801S, Adopt MPE and APiM unique AI architecture
Computing performance up to 2.8Tops and 9.3Tops/W energy efficiency
|
| DDR |
2GB / 4GB dual-channel LP DDR4
|
| Storage |
8GB -128GB High-speed eMMC、TF Card Slot
|
| Network |
RJ45 interface Gigabit Ethernet
On-board WIFI/BT module, support 2.4GHz/5GHz dual-band WiFi，802.11a/b/g/n/ac protocol
Support Bluetooth 4.1（support BLE）
Mini PCIe（Used to expand 3G/4G modules, use with Micro SIM card slot）
|
| Multimedia |
Support 4K VP9 and 4K 10bits H265/H264 video decoding, up to 60fps
1080P Multi-format video decoding(VC-1, MPEG-1/2/4, VP8)
1080P video decoding, support H.264，VP8 formats
Video post processor: deinterlacing, denoising, edge/ detail/ color optimization
|
| Display |
Dual VOP: support 4096X2160 and 2560X1600 resolution
HDMI2.0 support 4K 60Hz display, support HDCP 1.4/2.2
Support eDP 1.3(4 line, 10.8Gbps), can directly drive multiple resolutions LCD screen which with eDP interface
Support dual 6/8 bit LVDS interface, up to 24-bit 1920×1200 resolution
Support Rec.2020 and Rec.709 color gamut conversion
1 x DP 1.2 (DisplayPort) , support 4K@60 fps output
|
| Interface |
Dual ISP pixel processing capability up to 13MPix/s, support simultaneous input of two-way camera data
Support USB3.0 HOST and Type-C
ADC x 1, SPI / GPIO, LED×2, I²C×1, Gravity sensor×1(Scalable)
|
| SD Card |
Support SD Card
|
| RTC |
Support RTC real-time clock
|
| On/Off |
Support timer switch
|
| Audio |
PHONE x 1, LINE-IN x 1, LINE-OUT x 1, Microphone (left and right channel)
|
| USB |
Type-C(OTG), USB3.0 x 1, USB2.0 x 4(interface x 2, socket x 2)
|
| Button |
Power Button(Button×1, socket×1), Recover Button(Button×1, socket×1)
|
| Serial port |
RS232×1, RS485×1, Debug serial port×1, on-board 2-way TTL
|
| IR |
With a one-way infrared receiver, support infrared remote control
|
| Power Supply |
DC 12V-2A(DC5.5 × 2.1mm), Support for external connection( Power socket×1)
Can power by POE+（802.3 AT, Output Power 30W) Ethernet
|
| System |
Support Android\Linux\Ubuntu system
|
| Framework |
Support PyTorch , Caffe framework, follow-up support TensorFlow
|
| Tools |
PLAI model training tool(Support for GNet1, GNet18 and GNetfc network models which based on VGG)
|
| Power Parameter |
| Type |
Min |
Typical |
Max |
| Operating Voltage |
6v |
12v |
24v |
| Operating Current |
500mA |
1A |
2A |
| Environmental Parameter |
| Type |
Mix |
Typical |
Max |
| Operating Temperature |
-20 ℃ |
25 ℃ |
60 ℃ |
| Storage Temperature |
-40 ℃ |
25 ℃ |
125 ℃ |
| Appearance Structure |
| Specification
|
| Size |
160 x 94 x 26 mm |
EC-A3399C
Six-core Mini Embedded
Computer
Based on the AIO-3399C high-performance open-source platform, equipped with industrial case and
efficient fanless
cooling system, high-temperature resistance, 7X24 stable work, and with rich interfaces for high
applicability. It can
directly drive mainstream 5~100 inch displays and easily embedded into various intelligent products.
Powerful Six-core Processor
Equipped with ARM Cortex-A72 architecture, six-core 64-bit high-performance processor,
frequency up to 1.8GHz. Its
processing performance is improved by 100%, faster and more powerful than Cortex-A57.
Powerful Hardware Decoding
Compatible with dual LVDS, EDP, HDMI, DP1.2 and other display output interfaces,
supports dual-screen identical
display/dual-screen differential display, H.265 HEVC, VP9 and H.264 encoding, 4K HDR, maximum supports
for 4K hardware
decoding. It can directly drive mainstream 5~100 inch displays.
Embed Into Industrial Equipment
Compact and space-saving design supports multiple installation modes; Compatible with RS232, RS485
and onboard two-way
TTL, allowing connecting to various industrial equipment. The performance is stable and reliable.
Efficient Fanless Cooling Design
Adopts fanless aluminum alloy structure for cooling, greatly improving heat dissipation
and reducing noise, supports
60°C high-temperature aging, 7x24 stable work.
Open SDK
Open SDK, tutorials, technical materials and development tools to make development
easier and more convenient.
Rich Interfaces
With HDMI2.0、LAN、Type-C、USB3.0、RS485、RS232 and other interfaces.
Specification
|
Specification |
| CPU |
RK3399, Dual-core(Cortex-A72)+ Quad-core(Cortex-A53), frequency up to 1.8 GHz
|
| GPU |
Quad-core ARM Mali-T860
Support OpenGL ES 1.1/2.0 /3.0, OpenVG1.1, OpenCL, Directx11
|
| DDR |
2GB/4GB LPDDR4
|
| Storage |
High-Speed eMMC, TF Card Slot
|
| Network |
Gigabit Ethernet (RJ45 interface )
On-board WIFI/BT module, support 2.4GHz / 5GHz dual-band WiFi, 802.11a/b/g/n/ac
protocol
Support Bluetooth 4.1
Mini PCIe (Used to expand 3G/4G modules, use with Micro SIM card slot)
|
| Multimedia |
Support 4K VP9 and 4K 10bits H265/H264 video decoding, up to 60fps
1080P Multi-format video decoding (VC-1，MPEG-1/2/4，VP8)
1080P video encoding，Support H.264，VP8 formats
Video post processor: deinterlacing, denoising, edge/ detail/ color optimization
|
| Display |
HDMI2.0 support 4K 60Hz display, support HDCP 1.4/2.2
Support DisplayPort 1.2 (4 lines, up to 4K 60Hz)
Dual VOP: Support 4096X2160 and 2560X1600
Support dual-screen identical display/dual-screen differential display
Scalable: eDP 1.3(4 lines10.8Gbps), Dual LVDS (6/8 bit, up to 24-bit 1920×1200
resolution)
Support single channel MIPI DSI, up to 1920x1080 resolution (customized interface)
|
| Other |
Support USB3.0 HOST and Type-C interface
ADC×1, SPI / GPIO, Controllable LED×2, I²C×1, Gravity sensor×1(Scalable)
|
| Audio |
1xPHONE，2xSPEAKER(L/R)，1xLINE-IN，1xLINE-OUT
|
| USB |
Type-C（OTG），1 x USB3.0，4 x USB2.0(Interface x 2, socket x 2)
|
| Key |
Power (Key x 1, socket x 1), Recover(Key x 1, socket x 1)
|
| Serial port |
RS232×1, RS485×1, Debug serial port×1, Onboard 2-way TTL
|
| IR |
With a one-way infrared receiver, Support infrared remote control
|
| OS |
Support Android, Linux, Ubuntu System
|
| Power |
DC 12V-2A（DC5.5 × 2.1mm）
|
|
Power
Parameter |
| Type |
Min |
Typical |
Max |
| Operating Voltage |
6v |
12v |
24v |
| Operating Current |
500mA |
1A |
2A |
|
Environmental
Parameter |
| Type |
Min |
Typical |
Max |
| Operating
Temperature |
-20 ℃ |
25 ℃ |
60 ℃ |
| Storage Temperature |
-40 ℃ |
25 ℃ |
125 ℃ |
|
Appearance
Structure |
| Type
|
Specification |
| Size |
160 x 94 x 26 mm |
| Specification |
AL6063 aluminum profile |
