To have a better experience, please upgrade your IE browser.upgrade
If you need help, please click here:
Atlas 300I Inference Card
Powered by the Ascend 310 AI processor, the Atlas 300I inference card (model: 3000/3010) unlocks superior AI inference performance. A single card provides up to 88 TOPS INT8 computing power and supports 80-channel real-time HD video analytics, making it an ideal option for intelligent scenarios such as smart city, transportation, and finance.
A single card provides 88 TOPS INT8 computing power and supports 80-channel HD video real-time analytics (1080p 25 FPS), providing powerful support for edge inference
Supports JPEG and video hardware codecs, improving image and video application performance
Supports large-capacity and high-bandwidth memory for feature matching scenarios, reducing application latency
For traffic violation investigation and vehicle tracking in applications such as license plate recognition, vehicle big data analytics, and track analysis.
For automatic recognition and structurization of financial documents, financial statements, cards, and insurance claims; support for service handling on mobile phones.
|Parameters||Atlas 300I Inference Card
|Form Factor||Half-height half-length PCIe standard card|
|AI Processor||Ascend 310|
|AI Computing Power||88 TOPS INT8|
|Memory||LPDDR4X, 32 GB, total bandwidth 204.8 GB/s|
|Encoding/ Decoding||• 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||PCIe x16 Gen3.0|
|Power Consumption||Maximum: 67 W|
|Operating Temperature||0°C to 55°C (32°F to +131°F)|
|Dimensions (W x D)||169.5 mm x 68.9 mm (6.67 in. x 2.71 in.)|