The server specifications are based on Microsoft’s Project Olympus, the company’s next-generation, open source hyperscale cloud hardware design. Microsoft contributed the design to the Open Compute Project (OCP) last year. The Open Compute Project is a collaboration between multiple hardware and software vendors dedicated to promoting open source design in hardware and data center infrastructure.
Qualcomm said it has been working with Microsoft on ARM-based server enablement for several years and has an onsite engineering team embedded at Microsoft to collaboratively optimize the version of Windows Server designed for Qualcomm’s hardware.
In addition to its collaboration with Microsoft, Qualcomm also announced that it has formally joined the Open Compute Project Foundation.
Qualcomm said that its specifications pair its recently announced 10nm, 48-core server processor with new interfaces for memory, network and peripherals that will enable suppliers in the Open Compute Project community to access and design ARM-based servers for the most common cloud compute workloads.
The server design fits into a standard 1U server system, offering system vendors the flexibility to create innovative, configurable designs for compute-intensive data center workloads, according to Qualcomm. It can be paired with compute accelerators, multi-host NICs (network interface controllers) and leading-edge storage technologies, such as NVMe, to optimize performance for specific workloads.