Micro Server SE8-288

SOPHON micro server SE8 288-EA6-72 is a new edge computing product with high-performance, low-power consumption and small size. Equipped with the fourth-generation tensor processor BM1684X launched by SOPHGO, SE8 288-EA6-72 supports INT8/FP16/BF16/FP32 and mixed-precision inference. It can process up to 288 channels of HD video analysis at the same time. With 8-core/16-thread X86 CPU@2.8GHz as the host processor and web storage expansion supported, it is widely used in high concurrency scenarios such as public security, transportation, industrial parks, producing and warehousing, empowering thousands of industries with deep learning capabilities.

Features

Surging Performace
INT8/FP16/BF16/FP32 and mixed-precision inference supported, up to 288-channel HD video whole-process processing
Excellent Computing Performance
Equipped with 8-core/16-thread X86 CPU @ 2.8GHz. Support 288-channel full HD video hardware decoding and 108-channel encoding
High Computing Density
High-density integration and tight deployment, 9*BM1684X in a single device to reduce TCO
Easy Migration
Developer-friendly SOPHON SDK, supporting Caffe/TensorFlow/PyTorch/ MXNet/Paddle Lite and other mainstream deep learning frameworks
Strong Adaptability
Working temperature ranging from 0 ℃ to +40 ℃ with portable design
Rich Algorithms
Support algorithm migration of pedestrian/vehicle / non-vehicle / object recognition, video structurization, trajectory behavior analysis, etc.
Various Scenarios
Widely used in public security / traffic / industrial parks / producing / warehousing, etc. Flexible deployment in multiple fields and scenarios
Flexible Scalability
Multi-server cluster deployment, Ethernet connection, Unified management services and cloud deployment

Application Scenarios

Intelligent storage

Intelligent Public Security

Intelligent Governance

Safety production

Intelligent storage

Automatic monitoring of violations and abnormal events such as smoke and fire, material stacking, blockage of fire escapes, lack of safety signs in hazardous chemical warehouses, video obscuring, vehicle intrusion, item movement, personnel sleeping, smoking, dress code violations, intrusion in restricted areas, etc.

Intelligent Public Security

Full target Video Structuring including human, vehicle and face-recognition, behavior analysis, target capture, traffic event analysis. Widely used in counter-terrorism, anti-drug, security management, police case handling, intelligence command etc.

Intelligent Governance

City appearance, street order, municipal facilities, social events, outdoor advertising, urban firefighting, natural disaster-related monitor, alarm and closed-loop event disposal control

Safety production

Supervision of production safety in hazardous chemical enterprises, oil and gas sites, three-small sites, and construction sites

Specifications

Product Model

SE8 288-EA6-72

Processing Capacity

INT8/FP16/BF16/FP32 supported, up to 288-channel HD video whole-process processing

Video/JPEG Codec

Video Decoding

H.264 & H.265: 7200fps @1080P

Video Decoding Resolution

8K / 4K / 1080P / 720P / D1 / CIF

Video Encoding

H.264 & H.265: 2700fps @ 1080P

Video Encoding Resolution

4K / 1080P / 720P / D1 / CIF

JPEG Decoding

JPEG: 5400 pics/second @1080P

Deep Learning Co-processor

Processor

ARM A53 72-core @2.3GHz

Device Memory

DDR

144GB LPDDR4x

Host Processor

Processor

X86 2.8GHz 8-core/16-thread L3 16MB

Host Memory

DDR

2 x UDIMM DDR4-2666Mhz,2 x 32GB

Storage

Host Storage

1 x M.2 2280 NVME, 1TB

Device eMMC

576GB

Dimension

Width*Height*Depth

148mm(W)*140mm(H)*300mm(D)

Interface

RJ45

3 x 10/100/1000Mbps(1 x BMC)

Other

1 x RJ45 console, 1 x HDMI 1.4a, 4 x USB3.0

Power Supply

AC

1 x 500W gold power supply, 100-240V~, 7-3.5A, 60-50Hz

Working Temperature

Temperature Range

0°C ~ 40°C

Operation System

Linux

Ubuntu/Kylin

Deep Learning Framework

Models

PyTorch / ONNX / PaddlePaddle / TensorFlow / Caffe / MXNet / Darknet