According to the company, these advanced liquid cooling technologies will help to reduce the lead time for a complete installation, increase performance, and result in lower operating expenses while significantly reducing the PUE of data centres.
Savings for a data centre are estimated to be 40% for power when using these liquid cooling solutions compared to an air-cooled data centre and, in addition, there’s up to an 86% reduction in direct cooling costs compared to existing data centres.
Commenting Charles Liang, president, and CEO of Supermicro, said, "Our innovative GPU servers that use our liquid cooling technology significantly lower the power requirements of data centres. With the amount of power required to enable today's rapidly evolving large scale AI models, optimising TCO and the Total Cost to Environment (TCE) is crucial to data centre operators. These GPU systems are designed from the ground up for rack scale integration with liquid cooling to provide superior performance, efficiency, and ease of deployments, allowing us to meet our customers' requirements with a short lead time."
AI-optimised racks using these latest product families, including the Intel and AMD server product lines, can be quickly delivered from standard engineering templates or easily customised based on the user's requirements. Rack scale integrated solutions give customers the ability to plug the racks in, connect to the network and become more productive sooner than managing the technology themselves.
The top-of-the-line liquid cooled GPU server contains dual Intel or AMD CPUs and eight or four interconnected NVIDIA HGX H100 Tensor Core GPUs. Both systems significantly surpass the previous generation of NVIDIA HGX GPU equipped systems, providing up to 30x performance and efficiency in today's large transformer models with faster GPU-GPU interconnect speed and PCIe 5.0 based networking and storage.
Supermicro's liquid cooling rack level solution includes a Coolant Distribution Unit (CDU) that provides up to 80kW of direct-to-chip (D2C) cooling for today's highest TDP CPUs and GPUs for a wide range of Supermicro servers. The redundant and hot-swappable power supply and liquid cooling pumps ensure that the servers are continuously cooled, even with a power supply or pump failure. The leak-proof connectors give customers the added confidence of uninterrupted liquid cooling for all systems.
Rack scale design and integration has become a vital service for systems suppliers. As AI and HPC have become an increasingly critical technology within organisations, configurations from the server level to the entire data centre must be optimised and configured for maximum performance. The Supermicro system and rack scale experts work closely with customers to explore the requirements and have the knowledge and manufacturing abilities to deliver significant numbers of racks to customers worldwide.
