If you need help, please click here:
Atlas 300I Inference Card
Powered by the Ascend 310 AI processor, the Atlas 300 AI Inference Card (model: 3000) unlocks ultimateAI inference performance. A single card provides up to 64 TOPS INT8 computing power and supports 64-channel realtime HD video analytics, making it an ideal option for intelligent scenarios such as the Smart City, transportation, and finance.
Provides 64 TOPS INT8 computing power and supports 64-channel real-time HD video analytics on a single card, unleashing powerful computing for edge inference.
Supports JPEG and video hardware encoding/decoding, improving the performance of image/video applications.
Reduces application latency with large memory capacity and high bandwidth, meeting memory requirements in feature-based scenarios.
For traffic violation investigation and vehicle tracking in applications such as license plate recognition, vehicle big data analytics, and track analysis.
For automatic identification and content of financial documents, financial statements, cards, and insurance claims; supports service processes on smartphones.
|Model||Atlas 300 AI Inference Card
|Form Factor||HHHL PCIe standard card|
|AI Chip||Ascend 310|
|AI Computing Power||64 TOPS INT8|
|Memory||32 GB LPDDR4X, total bandwidth 204.8 Gbit/s|
|Encoding/Decoding Capability||• H.264 hardware decoding, 64-channel 1080p 30 FPS (8-channel 3840 x 2160 @ 60 FPS)
• H.265 hardware decoding, 64-channel 1080p 30 FPS (8-channel 3840 x 2160 @ 60 FPS)
• H.264 hardware encoding, 4-channel 1080p 30 FPS
• H.265 hardware encoding, 4-channel 1080p 30 FPS
• JPEG decoding: 4-channel 1080p 256 FPS; encoding: 4-channel 1080p 64 FPS; maximum resolution: 8192 x 4320
• PNG decoding: 4-channel 1080p 48 FPS; maximum resolution: 4096 x 2160
|PCIe||16 PCIe 3.0|
|Power Consumption||Max. 67 W|
|Operating Temperature||0°C to 55°C (32°F to +131°F)|
|Dimensions||169.5 mm x 68.9 mm (6.67 in. x 2.71 in.)|