RK3588+12 GPU Edge Computing Server Design Solution, Supporting 120-Channel High-Definition Video

The high-density server is an edge computing product with high performance and high computing power. It is equipped with an intelligent visual deep learning processor BM1688, and 12 computing units are optional. It supports intelligent analysis of 192 high-definition videos (hardware decoding) and hardware encoding of 120 high-definition videos; it also supports multiple Ethernet ports, HDMI, USB, and storage expansion. It can flexibly respond to high-concurrency business scenarios such as public security, transportation, industrial parks, manufacturing, and warehousing, and is equipped with diverse algorithms to empower various industries with intelligence.

| Type | Key Parameters | |---|---| | Product Name | High-Density Server | | Product Model | XM3588-BM1688 | | AI Computing Power | 192 TOPS (INT8) peak computing power | | Encoding and Decoding Capability | Video Decoding: H.264 & H.265: 16x1080P@30fps, supports 8192x8192 / 8K / 4K / 1080P / 720P / D1 / CIFVideo Encoding: H.264 & H.265: 10x1080P@30fps, supports 8K / 4K / 1080P / 720P / D1 / CIF | | Number of Nodes | 12 computing nodes (up to 96 ARM cores) + 1 control node | | Processor | Computing Node: BM1688 Core (8x A53) 64-bit processor with a maximum clock speed of 1.6GHzControl Node: RK3588 octa-core (4x Cortex-A76 + 4x Cortex-A55) 64-bit processor, with a maximum clock speed of 2.4GHz | | Memory | 8GB LPDDR4 x 12 (per compute node), 32GB eMMC x 8 (per compute node), 2x 2.5-inch SATA 3.0 hard drives | | Network | 5x Gigabit Ethernet RJ45 network ports (1 control node port, 1 general-purpose network port), 2x SFP+, 4G/LTE/5G network (optional) | | Display | HDMI 2.0, 4K@60Hz (Main processor core board display) | | USB | 1x USB 3.0 HOST, 1x USB 2.0 HOST, 1x Type-C (for BMC unit debugging/testing) | | Fan | 5 high-speed cooling fans | | Power Supply | 300W AC power supply (input: 100V AC ~ 240V AC) | | Linux BMC | Integrated BMC management system, provides a web-based management interface, BMC management system can be further developed | | Deep Learning Frameworks | TensorFlow / PyTorch / Paddle / Caffe / ONNX / MXNet / DarkNet | | Dimensions and Specifications | Standard 1U rack-mounted server: 490mm x 390mm x 44.4mm | | Operating Temperature | 0°C - 50°C, Operating Humidity: 10% ~ 90% RH (non-condensing) |