Edgecore Networks, a global leader in open networking solutions, unveiled its new AI server AGS8200, a cutting-edge, high-performance GPU-based server tailored to meet the demands of AI (Artificial Intelligence) and ML (Machine Learning) applications. The AGS8200 is ideal for training large language models, automation, object classification and recognition use cases. The Edgecore AI server offers unrivaled performance and scalability.
The system is designed with eight Intel® Habana® Gaudi® 2 processors and dual 4th Gen Xeon® Scalable Sapphire-Rapids processors. The Gaudi® 2 processor integrates 96GB HBM2E memory and 24 NICs of 100Gbps RoCEv2 RDMA. The 24 x 100Gbps NICs offer all-to-all connectivity and scale-out internally and externally for training, fine-tuning, and other DL processing.
Each Gaudi® 2 processor has 21 x 100Gbps non-blocking, all-to-all connectivity to other Gaudi® 2 processors within the server, allowing training across all eight Intel® Gaudi® 2 processors without requiring an external Ethernet switch.
Each AGS8200 supports 6 QSFP-DD ports for scale-out. The 400Gbps ports can be connected to 400Gbps switches, or 800Gbps switches via breakout cables, in racks and clusters of Intel® Gaudi® 2-based nodes.
A well-designed AI data center is comprised of AI servers, high-capacity switches, transceivers, and cables, none of which are dispensable. Meanwhile, Edgecore total AI solutions are optimized for high performance and efficiency, excelling in heavy loading environments. Edgecore presents its state-of-the-art 800G Ethernet switching solution tailored for AI/ML — the 800G AI data center networking switches AIS800 series. The switch ports are equipped with Tomahawk 5, facilitating the advancement of a converged data center infrastructure, featuring 64 ports of 800GbE for switching and routing. Edgecore embraces open architecture, proactively involving different projects, then delivers complete, flexible, and future-ready solutions for your AI/ML connectivity needs.
Key Features of the AGS8200:
- Powerful Performance of AI Capabilities
Powered by the Intel® Gaudi® 2 AI accelerator, the AGS8200 is suitable for LLM (Large Language Models) training and inferencing, allowing customers to efficiently harness the power of AI.
- Energy Efficient and Cost-Effective
Leveraging a cutting-edge 7 nm process, Intel® Gaudi® 2 processors excel in heat dissipation. Teamed up with Edgecore’s ingenious design, the AGS8200 not only delivers enhanced performance but also prioritizes energy efficiency. The Intel® Gaudi® 2 is finely tuned for AI/ML usage, offering substantial cost benefits. - Open and AI-Optimized Architecture
At Edgecore, we embrace open and AI-optimized switch hardware and software, then engage in projects or communities such as OCP, TIP, and SONiC. Our proactive involvement in collaborative projects ensures that we deliver complete, flexible, and future-ready solutions for your AI/ML connectivity needs.
Source: BusinessWire