Supermicro – a total IT solution manufacturer for AI, cloud, storage and 5G/Edge – is expanding its AI and HPC rack delivery capacity and advanced liquid cooling solutions.
Worldwide, Supermicro’s full rack scale delivery capacity is growing from several state-of-the-art integration facilities in the US, Taiwan, Netherlands and Malaysia. Future manufacturing expansion and locations are actively being considered to scale to the increasing demand for Supermicro’s rack scale AI and HPC solution portfolio.
“With our global footprint, we now can deliver 5,000 racks per month to support substantial orders for fully integrated, liquid cooled racks, requiring up to 100kW per rack,” said Charles Liang, President and CEO, Supermicro. “We anticipate that up to 20% of new data centres will adopt liquid cooling solutions as CPUs and GPUs continue to heat up.
“Our leading rack scale solutions are in great demand with the development of AI technologies, an increasing part of data centres worldwide. Full rack scale and liquid cooling solutions should be considered early in the design and implementation process, which results in reduced delivery times to meet the urgent implementation requirements for AI and hyperscale data centres.”
Supermicro maintains an extensive inventory of ‘Golden SKUs’ to meet fast delivery times for global deployments. Large CSPs and enterprise data centres running the latest Generative AI applications will quickly benefit from reduced delivery times worldwide. Supermicro’s broad range of servers from data centres to the Edge (IoT) can be seamlessly integrated, resulting in increased adoption and more engaged customers.
With the recent announcement of the MGX product line – and the NVIDIA GH200 Grace Hopper Superchip and the NVIDIA Grace CPU Superchip – Supermicro continues to expand AI-optimised servers to the industry.
Combined with the existing product line incorporating the LLM-optimized NVIDIA HGX 8-GPU solutions and NVIDIA L40S and L4 offerings, together with Intel Data Center MAX GPUs, Intel Gaudi2, and the AMD Instinct MI series GPUs, Supermicro can address the entire range of AI training and AI inferencing applications.
The Supermicro All-Flash storage servers with NVMe E1.S and E3.S storage systems accelerate data access for various AI training applications, resulting in faster execution times. For HPC applications, the Supermicro SuperBlade, with GPUs, reduces the execution time for high-end simulations with reduced power consumption.
Liquid cooling, when integrated into a data centre, can reduce the PUE by up to 50% compared to existing industry averages. Reducing the power footprint and the resulting lower PUE in a data centre significantly lowers operating expenditures when running generative AI or HPC simulations.
With rack scale integration and deployment services from Supermicro, customers can start with proven reference designs for rapid installation while considering clients’ unique business objectives. Clients can then work collaboratively with Supermicro-qualified experts to design optimised solutions for specific workloads.
Upon delivery, the racks only need to be connected to power, networking and the liquid cooling infrastructure, underscoring its seamless plug-and-play methodology. Supermicro is committed to delivering full data centre IT solutions, including on-site delivery, deployment, integration and benchmarking to achieve optimal operational efficiency.
Click below to share this article