EdgeCom70-C154
EdgeCom70-C154 Series AI Computing CardEdgeCom70-C154 Series AI Computing Card
Front
Performance Features
Supports INT8 peak computing performance of 154 TOPS
Supports FP16/BF16 peak computing performance of 76.8 TOPS
Supports mixedprecision computing
Hardware decoding for 154channel HD video @25fps
Hardware encoding for 58channel HD video @25fps
Decoding resolution for video and image up to 8K
Compatible with various servers
Overview
The EdgeCom70-C154 Series AI Computing Card is designed for cloud AI applications. It supports large model inference and efficiently adapts to mainstream AI algorithms for audio/video review, transcoding, structuring, behavior analysis and other AI applications, empowering internet, smart city, smart transportation, smart energy, smart finance, smart telecom, and smart industry.
Technical Parameters
| Main Processor | |
|---|---|
| CPU | 48-core A53, 338,560 DMIPS, 2.3GHz |
| AI Computing Power | |
| INT8 | 154 TOPS |
| FP16 / BF16 | 76.8 TFLOPS |
| FP32 | 9.6 TFLOPS |
| Video/Image Codec | |
| Video Decoding | H.264 & H.265: 1080P @3840fps |
| Video Decoding Resolution | 8K / 4K / 1080P / 720P / D1 / CIF |
| Video Encoding | H.264 & H.265: 1080P @1440fps |
| Video Encoding Resolution | 4K / 1080P / 720P / D1 / CIF |
| Image Codec | JPEG: 1920 images/s @1080P (interleave off) |
| Image Codec Max Resolution | 32768 * 32768 |
| Memory & Storage | |
| Memory | 96GB LPDDR4x 1024bit 328GB/s |
| Software Features | |
| Deep Learning Frameworks | TensorFlow / PyTorch / Paddle / Caffe / ONNX / MXNet / DarkNet |
| Supported OS | Ubuntu / CentOS / Debian / UOS / Kylin |
| Supported Host CPUs | Compatible with Intel, AMD, Phytium, Hygon, Sunway, Loongson and other CPUs |
| Mechanical | |
| Dimensions | Full-height, full-length, single-width |
| Electrical | |
| Wattage | 150W |
| Operating Environment | |
| Operating Temperature | 0℃ ~ 55℃ |
| Storage Temperature | 0℃ ~ 55℃ |
| Relative Humidity | 5% ~ 95% (non-condensing) |
| Standards and Certifications | |
| System Certification | ISO9001, ISO14001, ISO22163(IRIS) |
Resources
Ordering Information
| Model | Description |
|---|---|
| EdgeCom70-C154 | AI computing card, 154 TOPS, 9.6 TFLOPS AI computing power |