The leading knowledge platform for the financial technology industry
The leading knowledge platform for the financial technology industry

A-Team Insight Blogs

Q&A: John Lockwood of Algo-Logic Systems on Reducing Time-to-Market for FPGA Apps

While the debate on whether to leverage FPGAs versus travel the Intel CPU roadmap for cutting-edge performance continues, there seems to be a common view that developing for FPGAs can be challenging. Looking to overcome that challenge is Algo-Logic Systems, with pre-built functionality for automated trading functions. spoke to the company’s founder and CEO John Lockwood to find out more on its mission and products.

Q: How did Algo-Logic Systems get started and what is its mission?

A: Algo-Logic Systems was founded in 2009. The core competency of the company, as the name implies, is to put algorithms into logic. Specifically, the company builds networked applications that run in Field Programmable Gate Array (FPGA) devices.

Throughout my career as an electrical engineer, tenured professor, and serial entrepreneur, I have developed multiple FPGA platforms and dozens of applications for FPGAs. It was hard work. Starting a new project on a proprietary platform requires years of effort by a team of engineers before the first packet can be processed. As a consulting Associate Professor at Stanford University between 2007 and 2009, I managed a research program focused on deployment of an open platform called the NetFPGA. Once the beta program grew to have 1,021 cards deployed, there was a need by non-engineers to have customised algorithms developed, which could run on this and other open platforms without a long time-to-market.

Consequently, Algo-Logic Systems was founded to service these commercial customers that needed hardware-accelerated networking applications implemented quickly in FPGA logic. Over the years, our team has accumulated a wealth of experience in building configurable, customisable FPGA circuits that power trading systems, exchanges, network switches, and high performance computing embedded real-time measurement devices.

The mission of Algo-Logic Systems is to extend its leadership as the world-class design centre by providing pre-built libraries that further reduce time-to-market. Algo-Logic provides deterministic, ultra-low-latency FPGA accelerated applications, products and solutions to our valued customers for accelerated finance applications, data centre switching, and real-time measurement.

Q: What products do you sell, and what do they do?

A: Algo-Logic Systems has three main categories of low-latency networking product-line segments, namely: 1) Accelerated Finance, 2) Packet Processing and 3) Embedded Hardware. In the Accelerated Finance space, Algo-Logic sells low latency libraries of pre-built financial trading accelerators, FPGA hardware platforms, plus FPGA design services. We provide complete solutions to end-customers that need to implement high frequency trading applications. Our low-latency libraries contain protocol parsers that handle order processing for all U.S. markets (e.g. NYSE ARCA, Nasdaq OUCH, FIX, XPRS, BOE) plus world markets (e.g. native trading gateways for LSE and TSE). Moreover, we have implemented complete hardware-accelerated FPGA applications for compliance risk-checks, market-data filtering, trading strategy customisation, feed processing, customised risk management, and order routing.

Q: Typically what level of latency do your products add, and at what segment of the market are you targeting with them?

A: We target the financial services segment inside the entire ‘tick-to-trade’ ecosystem that seeks a quantitative competitive edge by processing orders with the least possible latency. Our customised hardware-accelerated circuits can parse stock market orders in just 70 nanoseconds. Our risk dashboard applications records market exposure and position calculations based on the FIX protocol for in just 200 ns. Our complete tick-to-trade processing times are below 500 ns.

Algo-Logic System’s high performance and ultra- low-latency financial products and solutions are specifically designed for use by financial institutions, HFT firms, exchanges/ECNs, banks, hedge funds, prop-shops, broker/dealers and market-makers who are seeking to hyper-accelerate their proprietary financial applications.

Q: You recently became a partner of Solarflare Communications and its Application Onload offering. Can you describe what you will jointly offer?

A: Solarflare’s Application On-load Engine (AOE) Partner Network was created to bring together industry-leading application developers as well as FPGA design services, tools vendors, and intellectual property (IP) core providers together to serve as solutions providers. As a member, we collaborate with Solarflare to leverage their AOE platform to provide hardware accelerated next generation network applications and solutions to the financial industry. Along the same lines, we plan to target mutual end-customers by participating in relevant joint marketing programs to support their conferences, trade-shows and sales campaigns.

Q: Solarflare’s AOE uses an Altera FPGA, whereas your NetFPGA card is based on Xilinx. Has that presented any development challenges?

A: Algo-Logic Systems core libraries are designed so that they can synthesise on multiple platforms and devices. We already have products that run on Xilinx, Altera and Tabula devices. Moreover, we fully support most major platform providers including, HiTech Global, Terasic, and SolarFlare. BittWare and others vendors appear on our platform qualification and validation roadmap.

Yes, it is difficult to support multiple FPGA devices and Platform vendors. The company has invested in putting in place a very experienced and talented FPGA engineering team that works very closely with our fellow vendor counterparts here in Silicon Valley on a daily basis so that most development related issues are quickly resolved before they become a challenge.

Q: The market for ultra-low-latency offerings is quite limited – fewer firms are engaging in the latency arms race – so how is Algo-Logic going to grow?

A: There is indeed a latency arms race in the finance industry with a goal to achieve zero latency. Luckily, there is no end to reaching absolute zero – it can never be achieved. But every few years, we can provide another order of magnitude lower latency by optimising our algorithms and using even faster FPGA devices. Therefore, we are confident that Algo-Logic Systems is well positioned to continue to grow as the recognised leader in the ‘Accelerated Financial Industry’ to deliver new FPGA applications, products, and solutions with the shortest time-to-market.

Over time, we anticipate that all traders, banks, and exchanges will use FPGAs because they are the only viable means to win the low-latency race. No other technology can match the performance of parallel hardware customised to implement an algorithm in logic. FPGAs provide deterministic delay with no jitter because the processing operations are choreographed to compute using a minimal number of clock cycles.

The universe of low-latency offerings expands every day.

Algo-Logic’s hardware-accelerated protocol parsing library has grown to support all of the major worldwide markets. We also have expanding business with leading hedge funds and traders that ask us to map their increasingly complex trading algorithms into low latency logic so as to maximise their competitive edge.

Related content


Recorded Webinar: Approaches to migrating market data to the cloud to drive agility in trading operations

Market data in the cloud is an attractive proposition in terms of reducing the cost of on premise servers and storage, and moving into a more agile and flexible data delivery environment. It is also well suited to working from home, the fall-back of many financial institutions during lockdowns caused by the coronavirus pandemic. But...


The Composable Enterprise and Desktop Integration

By James Wooster, COO, Glue42. The starting point for this piece was a statistic buried within a report on the UK Contact Centre market[1]. It stated, on page 138, that across all industries, including Capital Markets, the cost of users navigating themselves within and between applications was estimated to be in excess of £4.3 billion...


TradingTech Summit Virtual

Trading Tech Summit (TTS) Virtual will look at how trading technology operations can capitalise on recent disruption and leverage technology to find efficiencies in the new normal environment. The crisis has highlighted that the future is digital and cloud based, and the ability to innovate faster and at scale has become critical. As we move into recovery and ‘business as usual’, what changes and technology innovations should the industry adopt to simplify operations and to support speed, agility and flexibility in trading operations.


Entity Data Management Handbook

Following on from the success of our Regulatory Data Handbook, A-Team Group is pleased to introduce its new Entity Data Management Handbook which is available for free download. This Handbook is the ultimate guide to all things entity data: Why Entity Data is important A full review of Legal Entity Identifiers (LEIs) Where they came...