About a-team Marketing Services
The knowledge platform for the financial technology industry
The knowledge platform for the financial technology industry

A-Team Insight Blogs

Arista Debuts Application Switch; Embeds FPGAs Into Network for Lowest Latency

Subscribe to our newsletter

Sun Microsystems might have coined the the slogan “The Network Is The Computer” but it is Arista Networks that is today delivering on the concept with its first Application Switch, which embeds FPGA processing into a switch so that business logic can really be run in the networking fabric itself with lowest-latency data access.

With both Sun and Arista sharing a founder in Andy Bechtolsheim, it’s perhaps not surprising that the company has taken an inevitable leap in network intelligence by allowing business logic to run natively on its switch, bringing applications as close to data traffic as is possible. For the financial markets, that means execution algorithms, pre-trade risk, market data ticker plants, and other low-latency applications that might be made available across a networked enterprise.

Specifically, Arista is introducing the 7124FX – a version of its 7124SX low-latency switch, which marries 24 x 10gE network ports with an Altera Stratix V FPGA chip, 8GB RAM, 50GB solid state disk, and options for precision timing (including an atomic clock) for clock synchronisation.

By embedding FPGA processing into a switch as opposed to a network interface card (NIC), which is now pretty commonplace, it’s possible to architect systems where low-latency services can access data from or be made accessible across an enterprise network, instead of to applications running on a single server. How trading systems architects will adopt these intelligent switches alongside equally intelligent NICs is yet to be seen, but one can expect reference designs to emerge that take advantage of the best of both approaches.

Arista is partnering with the likes of Exegy and NovaSparks to deliver integrated appliances, while it is also working with Impulse C and Enyx to provide development environments and building blocks for firms looking to implement their own code in the switch.

Availability of the 7124FX is slated for this summer, with pricing of around $50K for a model without an atomic clock, and $60K with one.

Subscribe to our newsletter

Related content

WEBINAR

Upcoming Webinar: Navigating the Build vs Buy Dilemma: Cloud Strategies for Accelerating Quantitative Research

Date: 20 May 2026 Time: 10:00am ET / 3:00pm London / 4:00pm CET Duration: 50 minutes For many quantitative trading firms and asset managers, building a self-provisioned historical market data environment remains one of the most time-consuming and resource-intensive steps in establishing a new research capability. Sourcing data, normalising symbologies, handling corporate actions and maintaining...

BLOG

Broadridge Deepens AI Push with Minority Investment in DeepSee to Transform Post-Trade Operations

Broadridge Financial Solutions has taken a minority stake in agentic AI specialist DeepSee and expanded its partnership to embed intelligent automation into post-trade workflows, marking a strategic advance in its data and AI roadmap for capital markets operations. Tom Carey, President of Broadridge Global Technology and Operations (GTO), will join DeepSee’s Board of Directors as...

EVENT

TEST Event page 1

Now in its 15th year the TradingTech Summit London brings together the European trading technology capital markets industry and examines the latest changes and innovations in trading technology and explores how technology is being deployed to create an edge in sell side and buy side capital markets financial institutions.

GUIDE

Evaluated Pricing

Valuations and pricing teams are facing a much higher degree of scrutiny from both the regulatory community and the investor community in the glare of the post-crisis data transparency spotlight. Fair value price transparency requirements and the gradual move towards a more harmonised accounting standards environment is set within the context of the whole debate...