Arama
  • Atlas 200 AI Accelerator Module

  • Overview
  • Features
  • Specifications
  • Resources

Atlas 200 AI Accelerator Module (Model: 3000)

The Atlas 200 AI accelerator module (model: 3000) integrates the Ascend processor to implement image recognition and image classification on the device side. Atlas 200 is widely used in AI scenarios such as intelligent cameras, robots, and drones.

Ultimate performance

Ultimate performance

• Supporting real-time analysis of 20-channel HD videos (1080p 25FPS)

Ultra-low consumption

Ultra-low consumption

• Hibernation at milliwatts and wakeup in milliseconds, typical power consumption of 5.5 W, enabling edge AI applications

Specifications

Parameters Atlas 200 AI Accelerator Module
Model: 3000
AI Processor Ascend Processor
Memory LPDDR4X, 8 GB/4 GB, total bandwidth 51.2 GB/s
Encoding/ Decoding • H.264 hardware decoding, 16-channel 1080p 30 FPS (2-channel 3840 x 2160 @ 60 FPS)
• H.265 hardware decoding, 16-channel 1080p 30 FPS (2-channel 3840 x 2160 @ 60 FPS)
• H.264 hardware encoding, 1-channel 1080p 30 FPS
• H.265 hardware encoding, 1-channel 1080p 30 FPS
• JPEG decoding: 1080p 256 FPS; encoding: 1080p 64 FPS; maximum resolution: 8192 x 4320
• PNG decoding: 1080p 24 FPS; maximum resolution: 4096 x 2160
Port • PCIe x4 Gen3.0
• 1 USB 2.0/USB 3.0
• 1 RGMII
Serial Bus UART/I2C/SPI
Interface Specifications 144-pin BTB connector
Typical Power Consumption 4 GB: 5.5 W
8 GB: 8 W
Operating Temperature  -25°C to +80°C (-13°F to +176°F)
Weight 30 g
Dimensions (H x W x D) 8.5 mm x 52.6 mm x 38.5 mm (0.33 in. x 2.07 in. x 1.52 in.)

TOP