Xeon D-2100 Brings Data Processing to the Network Edge
Intel recently announced a new chipset called the Xeon D-2100 for enterprise and data centre customers who want to move computing to the network edge. In edge computing, data is processed on the device itself rather than being sent to the cloud. This avoids network congestion, offers considerable advantages in performance, specifically latency, and has been promoted by companies such as Apple for privacy purposes. It will be a vital component in uses ranging from artificial intelligence, 5G-connected cars, smart stadiums, and retail and medical solutions.
Intel’s new processor is a stand-alone system-on-chip, meaning everything is built into the chip including computing, network and storage components. It also consumes less power, which could be necessary to run an edge computing device without the benefit of a data centre power structure. Intel has tried to address space and power needs that are unique to computing at the edge.
According to the company, its Xeon D-2100 processor offers up to 1.6 times the computing performance, 2.9 times the network performance and up to 2.8 times the storage performance of Intel’s previous-generation D-1500 solution.
In the present day business scenario, data services need more computing and intelligence closer to consumer and commercial end-point devices that generate and act on the data, such as smartphones, Internet of things sensors and autonomous cars. By expanding the capabilities of the data centre outward to the network edge, solution providers can process more data closer to end-point devices. This in turn reduces application latency and opens up a whole new world of services.
Intel claims the D-2100 processor “allows service providers and enterprises to deliver the maximum amount of computing intelligence at the edge or Web tier while expending the least power”.
Users of the new processor, which include industry leaders Dell EMC, Ericsson, NEC and NetApp, can benefit from Intel’s unique breadth of product offerings in hardware and software, and its significant global ecosystem. Intel isn’t inherently strong in silicon at the edge because of its weakness in the mobile market, its decision to abandon Galileo, Joule and Edison development, as well as a slow start for its Quark microcontrollers.
However, Intel is proving that a “solutions and systems” approach is where the value lies. Its investments in artificial intelligence, vertical markets in the Internet of things, automotive and 5G combined with its strength in data centres are all serving to establish Intel as a player with capability from the cloud to the network edge. In this context, it doesn’t need to supply low-margin silicon for an array of edge devices to be successful. As CEO Brian Krzanich frequently points out, Intel is a data company. It’s shrewdly positioning itself to create value at every point where data is captured, processed, analysed and actioned.
Subscribe to our blog
Make sure you don't miss out on our fresh insights on topical news in the connected world
"*" indicates required fields