Skip to main content

FPGA Matrix Architecture

When deterministic latency is critical, the goal is to avoid the bottlenecks inherent to CPU-based implementations and to maximize the use of FPGA’s even though the data is coming from multiple markets. Designed for time-sensitive trading strategies such as Market Making, Statistical Arbitrage or Algorithmic Trading, the NovaSparks platform adopts a pure FPGA architecture engineered to unleash the highest speed and enable trading firms to maximize the returns on their strategies.

This pure FPGA approach uses an expandable matrix of FPGA nodes that are linked with raw binary interconnections.

In addition, to avoid bottlenecks that can occur with other system resources, each FPGA node comes with its own set of Inputs/Outputs and memories. This modular matrix allows the system to grow proportionally across multiple market feeds.

As a result, all functions of the market data parsing, book building, filtering and distribution can be done in hardware without bottlenecks, irrespective of the number of feeds received, of the rate of data or the number of downstream consumers.

Key Advantages

When in need for optimized speed, it is important to consider the complete set of functions required to receive, manage and distribute data coming from multiple markets.
A pure FPGA design that utilizes a modular FPGA approach to scale capacity, can maintain nanosecond speeds even during market microbursts regardless of the number of market data feeds to be processed.
The resiliency nature of the pure FPGA approach is amplified/magnified when multiple market feeds are consolidated within the FPGA Matrix.
Software feed handlers can still be used to manage low data volume markets before consolidation in the FPGA matrix.

Introducing NovaTick a new paradigm for pure FPGA feed handlers

Learn more

Got a question? Get in touch

Contact us