Supermicro, a global vendor of compute, storage and networking technologies, has announced deployment of its disaggregated MicroBlade servers at one of the world’s highest density and energy efficient data centers. The Silicon Valley Fortune 100 data center has a calculated Power Usage Effectiveness (PUE) of 1.06.
A “technology-leading” Fortune 100 company has deployed over 30,000 Supermicro MicroBlade servers at its Silicon Valley data center premises – a facility with a Power Use Effectiveness (PUE) of 1.06, to support the company’s growing compute needs.
The Supermicro MicroBlade system represents an entirely new type of computing platform. It is a flexible extreme-density 3U or 6U all-in-one total system that features 14 or 28 hot-swappable MicroBlade Server blades.
The Supermicro MicroBlade server solution has 280 Intel Xeon processor-servers per rack. According to Supermicro, it would achieve 45 percent to-65 percent CAPEX savings per refresh cycle with a disaggregated rack scale design.
“With 280 Intel Xeon processor-servers in a 9-foot rack, and up to 86 percent improvement in system cooling efficiency, the MicroBlade system is a game changer,” said Charles Liang, President and CEO of Supermicro. “Leveraging our Silicon Valley based engineering team and global service capabilities, Supermicro collaborated closely with the company’s IT department and delivered a solution from design concept to optimally tuned, high-quality product with full supply chain and large-scale delivery support in five weeks. With our new MicroBlade and SuperBlade servers, we have changed the game of blade architecture to make blades the lowest in initial acquisition cost for our customers, not just the best in terms of computation, power efficiency, cable-less design, and TCO.”
The Supermicro MicroBlade disaggregated architecture unlocks the interdependence between the major server subsystems enabling the independent upgrade of CPU+Memory, I/O, Storage and, Power/Cooling. Now each component can be refreshed on-time to maximize Moore’s Law improvements in performance and efficiency versus waiting for a single monolithic server refresh cycle.
“A disaggregated server architecture enables the independent upgrades of the compute modules without replacing the rest of the enclosure including networking, storage, fans and power supplies, which refresh at a slower rate,” said Shesha Krishnapura, Intel Fellow and Intel IT CTO. “By disaggregating CPU and memory, each resource can be refreshed independently allowing data centers to reduce refresh cycle costs. When viewed over a three to five year refresh cycle, an Intel Rack Scale Design disaggregated server architecture will deliver, on-average, higher-performing and more-efficient servers at lower costs than traditional rip-and-replace models by allowing data centers to independently optimize adoption of new and improved technologies.”
The MicroBlade server would provide a good building block for a rack-scale design data center solution. The networking across all server blades is aggregated into just two ports for uplink through an integrated switch, eliminating the need for Top-of-Rack (ToR) switches and complex cabling. With “up to 99% cabling reduction” for the MicroBlade system, airflow is significantly improved, says Supermicro, which in turn would reduce the load on the cooling fans, resulting in even lower OPEX. Cooling fan power efficiency improvement is achieved by sharing four cooling fans and integrated power modules across all 14 MicroBlade server blades.
The MicroBlade server enclosure is configured with a Chassis Management Module for unified management and redundant 2,000 Watt Titanium Level certified digital power supplies for high energy efficiency. Supermicro MicroBlade is shipped with industry standard IPMI 2.0 and Redfish API designed to lower management overhead in large scale data centers. The MicroBladeb server also supports DP Intel Xeon E5-2600 v4/v3 processors (MBI-6128R-T2/T2X blade server part numbers).