Arista Unveils New Highly Scalable, Low Latency Switches

Arista Networks (NYSE:ANET) has introduced their 7130 Series systems, a new family of converged extremely low latency, highly programmable platforms suited for demanding in-network applications. The new switching solutions would help increase customer agility while reducing complexity, power, and costs by unifying several devices.

Integrating full-featured, programmable switching silicon from industry-leading partners with ultra low latency Layer 1 and highly scalable FPGAs on a single platform would allow financial market participants to construct multiple trading logic elements in highly scalable, low latency switching fabrics.

Two new variants have been added to the 7130 Series of low latency programmable switches, which combine full-featured L2/3 switching and open programmability with high performance L1 connection. They both run Arista EOS and interact with CloudVision, allowing them to handle Arista’s full portfolio of switching, routing, DANZ monitoring, and programmability.

Key features of Arista’s newly launched 7130 Series systems would include:

  • Reduces network latency in order to meet the growing demand for financial trading solutions
  • To improve application speed and decrease complexity, dynamically composes important FPGA, networking, and software applications into a single tier
  • Consolidates servers, networks, and FPGA devices to save space, energy, and money
  • Applications may be scaled out to serve more customers, venues, or data sources 

“Cboe is one of the world’s largest global market infrastructure providers and delivers leading-edge technology that powers markets and serves investors around the globe,” said Curt Schumacher, SVP Infrastructure at Cboe Global Markets. “As we continue to invest in our infrastructure to drive our ongoing expansion into new markets and regions globally, we expect Arista’s solutions will provide new ways to further enhance application performance and scale, without compromising on efficiency, in our business.”

Density and Latency Advantages

The 7130LBR Series is a 96-port system that combines the ultra-low latency Layer 1 X-Point with two high-performance FPGAs, Broadcom Jericho2 switching silicon, a powerful CPU, and precision timing hardware, allowing network, server, and custom FPGA applications to be consolidated into a highly compact form factor. The 7130LBR would decrease device and network hop count, cabling, power, and cost when compared to typical multi-box systems, while enabling orders of magnitude density and latency advantages through co-location of these key components.

Customers can mix and match Arista applications with their bespoke processing without resorting to slow connections to external devices thanks to dynamic reconfigurability, the robust features of Arista’s R series, a portfolio of 7130 FPGA applications from Arista and its partners, and a comprehensive FPGA Development Kit. Furthermore, two high-grade AMD/Xilinx FPGAs may be used together to accomplish complicated data processing activities, or they can be used in parallel to enable separate functionalities and live prestaging of new applications with smooth switch-over.

The 7130B Series combines a full-featured, high-radix Intel Tofino L2/3 switch with a high-density Layer 1 fabric. Hundreds of devices may be joined to give thousands of edge ports and hundreds of FPGAs with low latency by providing over 2.5x the Layer 1 connectivity of conventional solutions with 256 interfaces utilizing high-density QSFP-DD connections.

In addition, Arista’s advanced pipeline profiles for scalable address translation, tunneling, and load balancing are supported by the 7130B’s sophisticated P4 programmable packet processing, which allows for customized packet handling, filtering, and statistics, as well as Arista’s advanced pipeline profiles for scalable address translation, tunneling, and load balancing.

The 7130LBR and 7130B work together to provide a new level of composability, performance, and scale for high-performance FPGA-native applications in Financial Services, Network Monitoring, Government, and Broadcast.

Application Partnerships

These next-generation 7130 systems are compatible with Arista’s FPGA application portfolio, which includes financial solutions like MetaMux and ExchangeApp, as well as high-capacity traffic capture and pico-second precise timestamping with MetaWatch.

Integrated high-performance switching silicon would take advantage of EOS’s extensive capabilities, including the switching and routing suite, DANZ’s packet broker capabilities for network monitoring, and the Tofino packet processor’s P4 applications.

Arista’s EOS would offer a robust programming environment for developers, including a comprehensive API, FDK, and SDK, as well as complete support for AMD/Vitis Xilinx’s Unified Software Platform, Enyx’s nxFramework, and Intel’s P4 Studio for Tofino.

The next-generation 7130 family’s complete processing capabilities would make it a good fit for applications in banking, government, broadcast media, and beyond that presently need separate dedicated appliances or server-hosted processing modules.

Availability

For consistency in day-to-day operations, the new 7130 Series additions are completely integrated with Arista EOS and CloudVision. They come with a full FDK to aid in the creation of bespoke applications. Customer testing is underway, with wide availability expected in Q4 2022.

Executive Summary

Arista Networks has introduced their 7130 Series systems, a new family of converged extremely low latency, highly programmable platforms suited for demanding in-network applications.
The new switching solutions would help increase customer agility while reducing complexity, power, and costs by unifying several devices
Features of Arista’s 7130 Series
  • Reduces network latency to meet growing demand for financial trading solutions
  • Dynamic composes important FPGA, networking, and software applications into a single tier
  • Consolidates servers, networks, and FPGAs to save space, energy, and money
  • Applications may be scaled out to serve more customers, venues, or data sources
Density and Latency Advantages
  • The 7130LBR Series is a 96-port system that combines the ultra-low latency Layer 1 X-Point with two high-performance FPGAs, Broadcom Jericho2 switching silicon, a powerful CPU, and precision timing hardware, allowing network, server, and custom FPGA applications to be consolidated into a highly compact form factor.
  • Customers can mix and match Arista applications with their bespoke processing without resorting to slow connections to external devices thanks to dynamic reconfigurability.
Application Partnerships
  • These next-generation 7130 systems are compatible with Arista’s FPGA application portfolio, which includes financial solutions like MetaMux and ExchangeApp, as well as high-capacity traffic capture and pico-second precise timestamping with MetaWatch.
  • Integrated high-performance switching silicon would take advantage of EOS’s extensive capabilities.