powered by TMCnet

Wire Speed

Wire Speed Feature

October 06, 2010

Xelerated Delivers Wire Speed by Design Architecture

By David Sims, TMCnet Contributing Editor

Xelerated (News - Alert) is a company working in providing processing technology for the networking industry, helping network equipment vendors build wire speed programmable carrier-class systems for prolonged product life times, streamlined R&D and accelerated time-to-market.

“Overall,” company officials say, “Xelerated provides tools that make fixed and mobile broadband networks faster and more efficient.”

The networking industry is currently undergoing a major shift with 10GE and soon 100GE interfaces enabling new systems that support significantly higher bandwidth, company officials say, adding that as fiber-based access and 3G move to 4G, “applications benefit from more bandwidth -- pushing network system vendors to develop equipment with much higher processing bandwidth and richer service densities.”

Xelerated officials are pitching their products and know-how as tools which, when coupled with “a rich ecosystem of partners, can unleash the full power of Carrier Ethernet.” Targeting metro Ethernet, unified fiber access, mobile backhaul and cloud computing systems, these data plane solutions can be customized to any vendor feature set.

At the heart of Xelerated's development efforts is a patented hardware technology for programmable packet processing, namely the Dataflow Architecture. It was designed, company officials say, to “empower the next wave of Carrier Ethernet infrastructure. The architecture is now offered in the third generation network processors and programmable Ethernet switches with industry leading performance and capabilities.”

The architecture is wire speed by design, where all packets are processed with a deterministic behavior and a guaranteed number of instructions and classification lookups per packet. The architecture handles any type of traffic, be it Ethernet, MPLS, IPv4 or IPv6. The result is “a deterministic packet processing architecture which translates to unique engineering advantages,” according to company officials:


The latest generation of chips scales to 100 Gbps and 150 mpps.

Simplified programming model makes programming efficient and reduces time-to-market.

Highest service densities and integration levels. In a single chip, the technology allows for Carrier Ethernet and IP/MPLS forwarding with off-chip access to full-Internet sized tables, metering and counting.

David Sims is a contributing editor for TMCnet. To read more of David’s articles, please visit his columnist page. He also blogs for TMCnet here.

Edited by Erin Monda