GIGABYTE Announces New Liquid-Cooled Solutions for NVIDIA HGX H200 to Achieve Higher Energy Efficiency in Supercomputing Clusters

September 5, 2024 – Giga Computing, a subsidiary of GIGABYTE and an industry leader in generative AI servers and advanced cooling technologies, today announced new flagship GIGABYTE G593 series servers supporting direct liquid cooling (DLC) technology to advance green data centers using the NVIDIA HGX™ H200 system. As DLC technology is becoming a necessity for many data centers, GIGABYTE continues to increase its product portfolio with new DLC solutions for GPU and CPU technologies, with the cold plates made by CoolIT Systems.

G593-ZD1-LAX3: AMD EPYC™ 9004 processors
G593-SD1-LAX3: 5th Gen Intel^® Xeon^® processors

G593 Series – Tailored Cooling
The GPU-centric G593 series is custom engineered to house an 8-GPU baseboard, and its design has foresight for both air and liquid cooling. The compact 5U chassis leads the industry with its readily scalable nature, fitting up to 64 GPUs in a single rack and supporting 100kW of IT hardware. This helps to consolidate the IT hardware, and in turn, decrease the data center footprint. The G593 series servers for DLC were developed in response to the rising customer demand for greater energy efficiency. Liquids have a higher thermal conductivity than air, so they can rapidly and effectively remove heat from hot components to maintain lower operating temperatures. By relying on water and heat exchangers, the overall energy consumption of the data center is reduced.

“We offer a great AI scaling GIGABYTE solution using the NVIDIA HGX™ H200 system,” said Vincent Wang, VP of Sales at Giga Computing. “Due to the complexity of enterprise data centers, there is a need to ensure the infrastructure can handle the computational demand and complexity of AI, ML, and data science models. This increasing complexity necessitates greater optimization. We can develop and invest in scalable AI infrastructure. And we can cover all aspects of AI data center infrastructure services from deployment to software stack using the NVIDIA AI Enterprise software platform.”

“Powered by NVIDIA technologies, the GIGABYTE G593 series servers integrate direct liquid-cooling systems to improve energy efficiency and performance scalability, helping set a new standard for performance for complex AI applications,” said Kaustubh Sanghani, vice president of GPU product management at NVIDIA.

GIGABYTE has now released both air-cooled and DLC versions of its G593 series for both the NVIDIA HGX™ H200 and NVIDIA HGX™ H100 platforms. For rack-scale deployment of all these mentioned NVIDIA HGX™ platforms, GIGABYTE has already introduced GIGAPOD to enable a complete supercluster with 256x NVIDIA H100 Tensor Core GPUs. For DLC servers, this solution is composed of five racks with four of them populated with eight G593 servers each. For air cooling, a nine-rack solution can house the same 32 G593 servers. Excellent interconnectivity is achieved using NVIDIA^® NVLink^® and NVIDIA^® NVSwitch™, and systems are also paired with NVIDIA Quantum-2 InfiniBand networking to interconnect between nodes in the cluster. This solution includes NVIDIA AI Enterprise, an end-to-end cloud-native platform that accelerates the development and deployment of generative AI applications. A complete cluster can be used to tackle large-scale model training, scientific simulations, and more.

Discover all the G593 servers for NVIDIA HGX™ architecture.