AICore SG2300X
- AICore SG2300X
- Fogwise® AirBox
Products
The AICore SG2300X is a core board featuring the advanced SOPHON AI processor SG2300X for powerful performance. It can be equipped with up to 16GB of RAM and supports 128GB of eMMC storage. With an impressive 32TOPS INT8 computing power, it excels in a variety of tasks and fully supports mainstream deep learning frameworks.
With an open SDK and a comprehensive all-in-one AI development kit and user-friendly toolchain, you can easily deploy and migrate algorithms, simplifying the complex AI development process. This versatility spans the security, transportation, retail, and industrial sectors, opening up exciting possibilities for your projects.
The AICore SG2300X operates in SOC mode as well as in PCIe mode, i.e. the AICore SG2300X can be used as a PCIe slave device.
Photograph of sth.
Features
| Specification | AICore SG2300X |
|---|---|
| sizes | 55 mm × 60 mm |
| processing unit | SOPHON SG2300X SoC，octa-core Arm® Cortex®-A53 (ARMv8) @ 2.3GHz. |
| tensor processing unit | Tensor Processing Unit Computing Power: Up to 32TOPS (INT8), 16TFLOPS (FP16/BF16) and 2TFLOPS (FP32) Support for major deep learning frameworks including TensorFlow, Caffe, PyTorch, Paddle, ONNX, MXNet, Tengine and DarkNet. |
| memory | Supports 16GB LPDDR4X memory.option |
| storage | Supports 32GB, 64GB, and 128GB eMMC storage options Built-in 16MB of SPI flash memory Supports SDMMC interface with SD card for data storage and operating system booting. |
| multimedia | Supports decoding 32 channels of H.265/H.264 1080p@25fps video Fully process 32 channels of HD 1080p@25fps video, including decoding and AI analysis Supports encoding 12 channels of H.265/H.264 1080p@25fps video JPEG: 1080p@600fps, max. Support 32768 x 32768 Support video post-processing, including image CSC, resize, crop, fill, border, font, contrast and brightness adjustment. |
| connectivity | 2 built-in Gigabit Ethernet PHYs 1 PCIe3.0 X4 RC 1 PCIe3.0 X4 EP up to 3 UARTs up to 2 PWMs up to 3 I2Cs up to 32 GPIOs. |
| Board-to-Board Connectors | 144P 0.5mm Pitch B2B Connectors |
| operating temperature | -20°C to 60°C |
Chip block diagram
Products
Fogwise® AirBox is an embedded AI micro-server with arithmetic power up to 32TOPS@INT8, supports multiple precision (INT8, FP16/BF16, FP32), supports private GPT, text-to-image, and other mainstream AI model deployments, and is equipped with an aluminum alloy casing for deployment in harsh environments.
Characterization
| module | Fogwise® AirBox |
|---|---|
| sizes | 104 mm × 84 mm × 50.2 mm |
| processing unit | SOPHON SG2300X SoC，octa-core Arm® Cortex®-A53 (ARMv8) @ 2.3GHz |
| tensor processing unit | Tensor Processing Unit, computational power: up to 32TOPS (INT8), 16TFLOPS (FP16/BF16) and 2TFLOPS (FP32) Support for major deep learning frameworks including TensorFlow, Caffe, PyTorch, Paddle, ONNX, MXNet, Tengine and DarkNet. |
| memory | 16GB LPDDR4X |
| storage | 64GB eMMC 16MB SPI Flash High Speed SD Card Slot Available |
| multimedia | Supports decoding 32 channels of H.265/H.264 1080p@25fps video Fully handles 32 channels of HD 1080p@25fps video, including decoding and AI analytics Supports encoding 12 channels of H.265/H.264 1080p@25fps video JPEG: 1080p@600fps, max. Support 32768 x 32768 Support video post-processing, including image CSC, resize, crop, fill, border, font, contrast and brightness adjustment |
| interface | 2 Gigabit Ethernet ports (RJ45) 1 M.2 M-key slot for NVMe SSDs. |
| operating temperature | 0°C to 40°C |
| housings | Corrosion-resistant aluminum alloy housing |
| radiator | PWM speed control fan with custom heat sink |
Photograph of sth.
Chip block diagram
System block diagram
