Last December Qualcomm announced plans to launch their Centriq 2400 series of platforms for data centres, demonstrating Apache Spark and Hadoop on Linux as well as a Java demo. They announced a 48 Core design based on ARM v8 and fabbed with on Samsung's 10nm process, which will compete against Intel's current offerings for the server room.
Today marks the official release of the Qualcomm Falkor CPU and Centriq 2400 series of products, as well as the existence of a partnership with Microsoft which may see these products offered to Azure customers. Microsoft has successfully configured a version of Windows Server to run on these new chips, which is rather big news for customers looking for low powered hosting solutions running a familiar OS. The Centriq 2400 family is compliant with Microsoft's Project Olympus architecture, used by the Open Compute Project Foundation to offer standardized building blocks upon which you can design a data centre from scratch or use as an expansion plan.
Enough of the background, we are here for the specifications of the new platform and what can be loaded onto a Centriq 2400. The reference motherboard supports SOCs of up to 48 cores, with both single and dual socket designs announced. Each SOC can support up to six channels of DDR4 in either single or dual channel configurations with a maximum of 768GB installed. Falkor will offer 32 lanes of PCIe 3.0, eight SATA ports and a GbE ethernet port as well as USB and a standard 50Gb/s NIC. NVMe is supported, one design offers 20 NVMe drives with a PCIe 16x slot but you can design the platform to match your requirements. Unfortunately they did not discuss performance during their call, nor any suggested usage scenarios. We expect to hear more about that during the 2017 Open Compute Platform US Summit, which starts today.
The submission of the design to Open Compute Project ensures a focus on compatibility and modularity and allows a wide variety of designs to be requested and networked together. If you have a need for HPC performance you can request a board with an HPC GPU such as a FirePro or Tesla, or even drop in your own optimized FPGA. Instead of opting for an impressive but expensive NVME storage solution, you can modify the design to accommodate 16 SATA HDDs for affordable storage.
Qualcomm have already announced Windows 10 support on their Snapdragon, but the fact that Microsoft are internally running Windows Server on an ARM v8 based processor is much more impressive. Intel and AMD have long held reign in the server room and have rightfully shrugged of the many times in which companies have announced ARM based servers which will offer more power efficient alternatives. Intel have made huge advances at creating low power chips for the server room; AMD's recently announced Naples shows their intentions to hold their market share as well.
If the submission to the OPC succeeds then we may see the first mainstream ARM based servers appear on the market. Even if the Windows Server instances remain internal to Microsoft, the Centriq series will support Red Hat, CentOS, Canonical and Ubuntu as well as both GCC and LLVM compilers.
(click to seriously embiggen)
ARM may finally have reached the server market after all these years and it will be interesting to see how they fare. AMD and Intel have both had to vastly reduce the power consumption of their chips and embrace a diametrically opposite design philosophy; instead of a small number of powerful chips, servers of the future will consist of arrays of less powerful chips working in tandem. ARM has had to do the opposite, they are the uncontested rulers of low powered chips but have had to change their designs to increase the processing capabilities of their chips in order to produce an effective product for the server room.
Could Qualcomm successful enter the server room; or will their ARMs not have the necessary reach?