Dell has unveiled a new sever infrastructure range dubbed the PowerEdge MX, which the Texas-based tech giant describes as the “first modular server designed for… disaggregated data centre infrastructure, or kinetic infrastructure” amid a push to make data centre resources as readily available and flexible as cloud services
The PowerEdge MX range was designed without a so-called midplane and is intended to support multiple generations of technology releases (microprocessors, new storage types and new connectivity innovation) well into the future.
Dell uses the term “kinetic infrastructure” to refer to the ability to extend flexible configuration down to individual storage devices and, in the future, all the way to memory-centric devices like DRAM, storage class memory, GPUs, FPGAs.
The announcement this week (the line will be commercially available globally from September 12) comes after the company reported 41 percent year-on-year growth in its servers and networking division in the first quarter, with sales worth $4.6 billion.
“A Tiny Disaggregated Datacentre in a Box”
Its release comes as Dell continues to emphasise a push to “composability” and the MX – rather than having blades with compute, DRAM, and persistent storage slide into the front and the networking slides into the back, with servers connected by a midplane –eschews a midplane for 25 Gb/sec Ethernet switching.
As industry follower Timothy Prickett Morgan describes it on NextPlatform, “it is, in essence, a tiny disaggregated hyperscale datacenter in a box rather than a blade server as we know it, but it makes use of the modularity and form factor density of blade servers just the same.”
(Composable IT infrastructure abstracts compute, storage and networking resources from their physical locations, making them manageable through a web-based interface; the aim is to make data centre resources as readily available as cloud services).
In a release shared Tuesday, the newly public company said: “The PowerEdge MX is designed for the software-defined data center – able to support a combination of dense virtualization, software-defined storage, software-defined networking, artificial intelligence and big data projects.”
The company added that the range is “designed to support the latest low latency NVMe drives and native 25GbE connectivity, customers can tailor compute and storage configurations to their own requirements and benefit from shared pools of disaggregated resources to respond to changing needs as they happen. By creating on-the-fly hardware capacity, overprovisioning and stranded assets are reduced as performance and efficiency are optimised.”