Supermicro introduces new systems to its X14 servers

The new selection of workload-optimised servers addresses the needs of modern data centres, enterprises, and service providers. Joining the efficiency-optimised X14 servers leveraging the Xeon 6700 Series Processors with e-cores launched in June 2024, the additions bring maximum compute density and power to the Supermicro X14 lineup to create the industry's broadest range of optimised servers supporting a wide variety of workloads from demanding AI, HPC, media, and virtualisation to energy-efficient Edge, scale-out Cloud-native, and microservices applications.

"Supermicro X14 systems have been completely re-engineered to support the latest technologies including next-generation CPUs, GPUs, highest bandwidth and lowest latency with MRDIMMs, PCIe 5.0, and EDSFF E1.S and E3.S storage," said Charles Liang, President and CEO of Supermicro. "Not only can we now offer more than 15 families, but we can also use these designs to create customised solutions with complete rack integration services and our in-house developed liquid cooling solutions."

Approved customers can obtain early access to complete, full-production systems via Supermicro's Early Ship Programme or for remote testing with Supermicro JumpStart.

These new Supermicro X14 systems feature completely re-designed architectures, including all-new 10U and multi-node form factors that support next-generation GPUs and higher CPU core densities, updated memory slot configurations with 12 memory channels per CPU and new MRDIMMs, which provide up to 37% better memory bandwidth compared to DDR5 DIMMs.

The new Supermicro X14 family comprises a number of new systems – several of which are completely new architectures – in three distinct, workload-specific categories:

• GPU-optimised platforms designed for pure performance and enhanced thermal capacity to support the latest technology and highest-wattage GPUs. System architectures are built from the ground up for large-scale AI training, LLMs, generative AI, 3D media, and virtualisation applications.
• High compute-density multi-nodes including all-new FlexTwin, SuperBlade, and GrandTwin, which leverage resources such as shared power and cooling to increase efficiency, as well as direct-to-chip liquid cooling on specific models to maximise density without compromising on performance.
• Market-proven Supermicro Hyper rackmounts combine single or dual socket architectures with flexible I/O and storage configurations in traditional form factors to help enterprises and data centres scale up and out as their workloads evolve.

Supermicro's new max-performance X14 systems support the new Intel Xeon 6900 series processors with P-cores, while X14 efficiency-optimised systems support the Intel Xeon 6700 series processors with e-cores, which launched in June 2024. These systems will also offer socket compatibility with the upcoming Intel Xeon 6900 series processors with e-cores and Intel Xeon 6700 series processors with P-cores in Q1'25 to provide an additional dimension of flexibility when optimising systems for either performance-per-core or performance-per-watt.

"For the first time, Intel is offering two distinct, workload-optimised families of Xeon processors in the same generation, each designed to deliver specific performance and efficiency profiles that can shorten time-to-results, revolutionise compute, power, and rack density, maximising ROI for modern data centres," said Ryan Tabrah, VP and GM of Xeon Products at Intel. "With the new additions, Supermicro will be able to provide their customers with even more choice with the introduction of these new performance optimised CPUs for AI and compute-intensive workloads."

When configured with Intel Xeon 6900 series processors with P-cores, Supermicro systems support new FP16 instructions on the built-in Intel AMX accelerator to further enhance AI workload performance. These systems include 12 memory channels per CPU with support for both DDR5-6400 and MRDIMMs up to 8800MT/s, CXL 2.0, and feature more extensive support for high-density, industry-standard EDSFF E1.S and E3.S NVMe drives.

Supermicro liquid cooling solutions

Complementing this expanded X14 product portfolio are Supermicro's rack-scale integration and liquid cooling capabilities. With a global manufacturing capacity, extensive rack-scale integration and testing facilities, and a comprehensive suite of management software solutions, Supermicro designs, builds, tests, validates, and delivers complete data centre solutions at any scale in a matter of weeks.

Supermicro offers a complete in-house developed liquid cooling solution including cold plates for CPUs, GPUs, memory, cooling distribution units, cooling distribution manifolds, hoses, connectors, and cooling towers. Liquid cooling is easily included in rack-level integrations to increase system efficiency, reduce instances of thermal throttling, and lowers both the TCO and Total Cost to the Environment (TCE) of data centre deployments.

New Supermicro max-performance X14 systems featuring Intel Xeon 6900 series processors with P-cores include:

• GPU-optimised – the highest performance Supermicro X14 systems designed for large-scale AI training, large language models (LLMs), generative AI and HPC, and supporting eight of the latest-generation SXM5 and SXM6 GPUs. These systems are available in air-cooled or liquid-cooled configurations.
• PCIe GPU – designed for maximum GPU flexibility, supporting up to 10 double-width PCIe 5.0 accelerator cards in a thermally-optimised 5U chassis. These servers are ideal for AI inferencing, media, collaborative design, simulation, cloud gaming, and virtualisation workloads.
• Intel Gaudi 3 AI Accelerators – Supermicro also plans to deliver the industry's first AI server based on the Intel Gaudi 3 accelerator hosted by Intel Xeon 6 processors. The system is expected to increase efficiency and lower the cost of large-scale AI model training and AI inferencing. The system features eight Intel Gaudi 3 accelerators on an OAM universal baseboard, six integrated OSFP ports for cost-effective scale-out networking, and an open platform designed to use a community-based, open-source software stack, requiring no software licensing costs.
• SuperBlade – Supermicro's X14 6U high-performance, density-optimised, and energy-efficient SuperBlade maximises rack density, with up to 100 servers and 200 GPUs per rack. Optimised for AI, HPC, and other compute-intensive workloads, each node features air cooling or direct-to-chip liquid cooling to maximise efficiency and achieve the lowest PUE with the best TCO, as well as connectivity up to four integrated Ethernet switches with 100G uplinks and front I/O supporting a range of flexible networking options up to 400G InfiniBand or 400G Ethernet per node.
• FlexTwin – the new Supermicro X14 FlexTwin architecture is purpose-built for HPC, cost-efficient, and designed to provide maximum compute power and density in a multi-node configuration with up to 24,576 performance cores in a 48U rack. Optimised for HPC and other compute-intensive workloads, each node features direct-to-chip liquid cooling only to maximise efficiency and reduce instances of CPU thermal throttling, as well as HPC low latency front and rear I/O supporting a range of flexible networking options up to 400G per node.
• Hyper – X14 Hyper is Supermicro's flagship rackmount platform designed to deliver the highest performance for demanding AI, HPC, and enterprise applications, with single or dual socket configurations supporting double-width PCIe GPUs for maximum workload acceleration. Both air cooling and direct-to-chip liquid cooling models are available to facilitate the support of top-bin CPUs without thermal limitations and reduce data centre cooling costs while also increasing efficiency.

Also, now shipping are Supermicro's X14 efficiency-optimised systems featuring Intel Xeon 6700 series processors with e-cores:

• SuperBlade – Supermicro's high-performance, density-optimised, and energy-efficient multi-node platform optimised for AI, Data Analytics, HPC, Cloud, and Enterprise workloads. Available as a 6U enclosure with 10 or five nodes, or an 8U enclosure with 20 or 10 nodes, one rack can feature up to 34,560 Xeon compute cores.
• Hyper – flagship performance rackmount servers designed for scale-out cloud workloads, with storage & I/O flexibility that provides a custom fit for a wide range of application needs.
• CloudDC – all-in-one platform for cloud data centres, based on the OCP Data Centre Modular Hardware System (DC-MHS) with flexible I/O and storage configurations and dual AIOM slots (PCIe 5.0; OCP 3.0 compliant) for maximum data throughput.
• Petascale storage – all-flash storage density and performance with EDSFF E1.S and E3.S drives, allowing unprecedented capacity and performance in a 1U or 2U chassis.
• WIO – offers flexible I/O configurations in a cost-effective architecture to enable optimisation of acceleration, storage, and networking alternatives to accelerate performance, increase efficiency and find the perfect fit for specific enterprise applications.
• BigTwin – 2U 2-Node or 2U 4-Node platform providing superior density, performance, and serviceability with dual processors per node and hot-swappable tool-less design. These systems are ideal for cloud, storage, and media workloads with new models, including E3.S drive support for superior density and throughput.
• GrandTwin – Purpose-built for single-processor performance and memory density, featuring front (cold aisle) hot-swappable nodes and front or rear I/O for easier serviceability. Now available with E1.S drives for better storage density and throughput.
• Hyper-E – delivers the power and flexibility of our flagship Hyper family optimised for deployment in edge environments. Edge-friendly features include a short-depth chassis and front I/O, making Hyper-E suitable for edge data centres and telco cabinets. These short-depth systems support up to three high-performance GPU or FPGA cards.
• Edge/Telco – high-density processing power in compact form factors optimised for telco cabinet and Edge data centre installation. Optional DC power configurations and enhanced operating temperatures up to 55°C (131°F).