Super Micro Computer, Inc. today announced that it is shipping high-performance X14 servers based on the Intel Xeon 6900 series processors (P-Core) in volume.

The server features a new architecture and upgraded technologies optimized for the most demanding high-performance workloads, including large-scale AI, cluster-scale HPC, as well as work environments that require massive amounts of GPUs, such as collaborative design and media distribution.

“Shipping in volume now, the X14 server delivers powerful features and enhanced performance to customers worldwide,” said Charles Liang, President and CEO of Supermicro. “This includes low latency, fast data transfer with maximum I/O expansion, up to 256 high-performance cores per system, 12 memory channels per CPU (with MRDIMM support), and high-performance EDSFF storage options.”

He said, "With our server building block solution design advantage, Supermicro's global capabilities to deliver solutions of all sizes and our unmatched proprietary liquid cooling solutions will lead the industry into a new era of high-performance computing."

Supermicro X14 servers offer a variety of form factors for performance-intensive workloads.The GPU-optimized platform supports the latest SXM and PCIe GPUs, with some models offering enhanced cooling capabilities and direct-to-chip (DTC) liquid cooling. The high-density compute multi-nodes offer the proven SuperBlade architecture, including high-density multi-nodes including the new FlexTwin and GrandTwin models.

These models utilize common components to increase efficiency and can be equipped with direct-to-chip liquid cooling for greater integration:

Additionally, the validated HyperRack mount combines single or dual-socket architecture with flexible I/O and storage configurations in traditional form factors, enabling enterprises and data centers to scale up and out as workloads grow.