Scaling the New Bar for Latency in Financial Networks

By Brian Quigley

August 9, 2010

The bar for what qualifies as a fast connection or “low latency” networking has always been higher in finance than in other areas of corporate networking. It’s never been quite this high, however.

The increased use of innovative algorithmic-trading strategies has levied unprecedented pressure on financial firms to seek out and remove any possible delays that could threaten the successful execution of automated buy and sell orders. Significant time and resources are spent to achieve even modest, incremental improvements in latency at every point in the ecosystem of processes and systems that undergird algorithmic trading.

Managers of financial networks have found that the process of transporting data from one building to another is a common source of those delays. The fiber optic links between stock exchanges, alternative trading systems, colocation providers and information feeds all introduce additional latency into the system. Once, those amounts were deemed negligible — even in financial networking. Today, they are simply unacceptable.

Contemporary Trading’s Latency Intolerance

High-frequency trading (HFT) and other forms of algorithmic trading have emerged since the late 1990s. In all of them, a computer model has a predefined set of rules that automates the process of buying and selling. The computer receives various inputs from throughout the world (market data on price and volume, labor statistics, employment information, for example). The data is parsed and monitored in real time, and automated buy/sell decisions are executed according to how the model interprets the incoming intelligence.

Since the first trade to the market gets the best price, the delivery of a buy or sell order must be as fast as possible. Just a little more than a year ago, firms were concentrating on removing milliseconds from their network; today, a mere 250 nanoseconds make a difference.

The solution is not a matter of contacting the local phone company and deploying its most current high-bandwidth connection to the buildings that house an exchange. Even adopting the leading-edge, highest-speed model of router or multicore processor computer blades might not successfully address the financial world’s hypersensitivity to latency.

Traditionally, a firm has sought to improve its algorithimic trading processes by focusing first on the computer model itself. A lot of mathematicians have invested a lot of hours into tweaking the models that predict how the world is going to behave. Next, firms have sought to boost efficiency by optimizing the servers that process information against models, as well as the switches connecting those servers. More and more frequently, firms often locate or colocate clusters of computers in the financial exchanges themselves to root out proximity delays. Today, a firm’s various building-to-building transport connections are attracting attention from IT staffs.

It’s an entire ecosystem that must be optimized to wring as much latency as possible from algorithmic trading, and many financial firms now seek to take greater control over all of it.

From Buy to Build

Historically, when a financial firm required a connection between two buildings, it procured service from a phone company by ordering a circuit at a monthly fee, and the system would run through the phone company’s network, which typically would have some routing functionality for linking the two locations. Two key things have changed in the last few years.

One, algorithmic trading has crystallized scrutiny on the latency created every time traffic must pass through a router or take an indirect path to a central office. (It’s easy enough to quantify the sum of these delays; any member of the IT staff can look up the impact on the router.) Two, a combination of advances in optical technology that are specifically designed to eliminate latency, plus the lower costs and expanded availability of dark fiber, have enhanced a financial firm’s business case for building a dedicated infrastructure.

The performance gains are in the orders of magnitude — from 120 microseconds of latency for a carrier-provided service between buildings to 40 microseconds in a privately operated, optimized infrastructure. Service reliability can be enhanced with 24-by-7 monitoring predicated on the knowledge that 30 minutes of downtime to a financial firm can mean millions of dollars in lost revenue. The firm becomes more flexible to react and scale for new opportunities, as circuits can be turned up as needed. And it gains a path to continued innovation when partnering with vendors who understand the firm’s low-latency requirements and are under the gun to roll out enhancements to continually shave delays.

These developments have financial network managers asking, “Who can I partner with to sell me dark fiber, and what is the path that the fiber will take?” The ramifications of the answers are far-reaching. Financial firms must ensure that they are not sinking their money in a dark fiber route that snakes jaggedly under roads and up and down manholes, given the fact that eight inches of fiber can translate into a nanosecond of delay.

The next question is, “What is the latency of that path?” That answer demands an understanding of how optical transport works.

Getting into the Glass

There are four common optical networking functions where managers of financial networks often can realize game-changing efficiencies in latency budgets. When traffic beams across glass fiber, it encounters equipment that performs amplification, color conversion, dispersion compensation and regeneration. Each of these Wavelength Division Multiplexing (WDM) functions can be absolutely necessary to successfully carry out transport depending on the specific network environment, but each certainly also will inject some delay into the process. How much delay is something that financial managers must quantify and control if they are to squeeze every drop of latency from their end-to-end infrastructures.

  • Amplification — Optical networks frequently rely on Erbium Doped Fiber Amplifiers (EDFAs) to boost a traffic signal and offset the weakening that occurs across an optical span. Latency in the microseconds is the not-uncommon impact of the conventionally, widely deployed EDFA architectures. Consequently, financial networks supporting algorithmic trading must instead utilize emergent amplifiers optimized to yield lower latency.
     
  • Color conversion — In WDM optical networking, traffic is “transponded” — or, converted to a color of light — for delivery of a signal across a pair of glass fiber. Similarly, multiple colors of light are aggregated across a single fiber; multiple 10 Gbit/s services, for example, are “muxponded” into a single pair of fibers. Again, a financial network’s transponding and muxponding functions must be optimized for low-latency transport because conventional techniques such as Optical Channel Data Unit (ODU) encapsulation and thin film filters introduce too much delay.
     
  • Dispersion compensation — One of the ways that a traffic signal can degrade over the span of an optical link is “chromatic dispersion.” This is a phenomenon in which a signal effectively smears into a spectrum of hues, and it’s particularly common for data travelling at high speed. Installing kilometers of dispersion compensating fiber (DCF) has provided a remedy in some optical networks, but it’s not a wise approach in infrastructures supporting algorithmic trading. Latencies are too great. Optimized methods, like Fiber Bragg gratings, offer a low-latency alternative for counteracting chromatic dispersion.
     
  • Regeneration — Another method for preventing signal degradation over the course of a glass fiber connection is regeneration. Low-latency approaches to the function can help managers of financial networks claim significant efficiencies, because commonly deployed methods of regeneration produce considerable delay.

Conclusion

Contemporary finance is a race between markets. Firms are concerned with nanoseconds of latency in the processes and the systems that underlie algorithmic trading. Shaving eight inches of fiber equates to a one-nanosecond lead. Every element in a firm’s strategy is being evaluated for improvements, and optical fiber transport is targeted as a prime area for optimization.

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

Musk’s Latest Startup Eyes Brain-Computer Links

April 21, 2017

Elon Musk, the auto and space entrepreneur and severe critic of artificial intelligence, is forming a new venture that reportedly will seek to develop an interface between the human brain and computers. Read more…

By George Leopold

MIT Mathematician Spins Up 220,000-Core Google Compute Cluster

April 21, 2017

On Thursday, Google announced that MIT math professor and computational number theorist Andrew V. Sutherland had set a record for the largest Google Compute Engine (GCE) job. Sutherland ran the massive mathematics workload on 220,000 GCE cores using preemptible virtual machine instances. Read more…

By Tiffany Trader

Nvidia P100 Shows 1.3-2.3x Speedup Over K80 GPU on Financial Apps

April 20, 2017

When it comes to the true performance of the latest silicon, every end user knows that the best processor is the one that works best for their application. Read more…

By Tiffany Trader

Quantum Adds Global Smarts to StorNext File System

April 20, 2017

Companies that use Quantum’s StorNext platform to store massive amounts of data this week got a glimpse of new storage capabilities that should make it easier to access their data horde from anywhere in the world. Read more…

By Alex Woodie

HPE Extreme Performance Solutions

HPC-Driven Weather Simulations Improving Forecasting Capabilities

In September of 1938, a massive hurricane traversed the Atlantic Ocean and made landfall in New England. Due to inadequate and incorrect forecasting, the storm struck farther north and with greater intensity than had been predicted, leaving residents and authorities with virtually no warning or time to properly prepare. Read more…

Scaling an HPC Career in Nepal Can Be a Steep Climb

April 20, 2017

Umesh Upadhyaya works as an IT Associate at the International Centre for Integrated Mountain Development (ICIMOD) in Nepal, which supports the country’s one and only HPC facility. He is directly involved in an initiative that focuses on climate change and atmosphere modeling Read more…

By Nages Sieslack

Hyperion (IDC) Paints a Bullish Picture of HPC Future

April 20, 2017

Hyperion Research – formerly IDC’s HPC group – yesterday painted a fascinating and complicated portrait of the HPC community’s health and prospects at the HPC User Forum held in Albuquerque, NM. HPC sales are up and growing ($22 billion, all HPC segments, 2016). Read more…

By John Russell

Intel Open Sources All Lustre Work, Brent Gorda Exits

April 19, 2017

In a letter to the Lustre community posted on the Intel website, Vice President of Intel's Data Center Group Trish Damkroger writes that effective immediately the company will be contributing all Lustre development to the open source community. Damkroger also announced that Brent Gorda, General Manager, High Performance Data Division at Intel is leaving the company. Read more…

By Tiffany Trader

Facebook Open Sources Caffe2; Nvidia, Intel Rush to Optimize

April 18, 2017

From its F8 developer conference in San Jose, Calif., today, Facebook announced Caffe2, a new open-source, cross-platform framework for deep learning. Caffe2 is the successor to Caffe, the deep learning framework developed by Berkeley AI Research and community contributors. Read more…

By Tiffany Trader

Hyperion (IDC) Paints a Bullish Picture of HPC Future

April 20, 2017

Hyperion Research – formerly IDC’s HPC group – yesterday painted a fascinating and complicated portrait of the HPC community’s health and prospects at the HPC User Forum held in Albuquerque, NM. HPC sales are up and growing ($22 billion, all HPC segments, 2016). Read more…

By John Russell

Knights Landing Processor with Omni-Path Makes Cloud Debut

April 18, 2017

HPC cloud specialist Rescale is partnering with Intel and HPC resource provider R Systems to offer first-ever cloud access to Xeon Phi "Knights Landing" processors. The infrastructure is based on the 68-core Intel Knights Landing processor with integrated Omni-Path fabric (the 7250F Xeon Phi). Read more…

By Tiffany Trader

CERN openlab Explores New CPU/FPGA Processing Solutions

April 14, 2017

Through a CERN openlab project known as the ‘High-Throughput Computing Collaboration,’ researchers are investigating the use of various Intel technologies in data filtering and data acquisition systems. Read more…

By Linda Barney

DOE Supercomputer Achieves Record 45-Qubit Quantum Simulation

April 13, 2017

In order to simulate larger and larger quantum systems and usher in an age of “quantum supremacy,” researchers are stretching the limits of today’s most advanced supercomputers. Read more…

By Tiffany Trader

Penguin Takes a Run at the Big Cloud Providers

April 12, 2017

HPC specialist Penguin Computing recently re-ran benchmarks from a study of its larger brethren and says the results show its ‘public cloud’ – Penguin on Demand (POD) – is among the leaders in cost and performance. Read more…

By John Russell

Nvidia Responds to Google TPU Benchmarking

April 10, 2017

Nvidia highlights strengths of its newest GPU silicon in response to Google's report on the performance and energy advantages of its custom tensor processor. Read more…

By Tiffany Trader

HPC and the Colocation Datacenter – a Bridge Too Far?

April 7, 2017

A more standardised HPC platform approach is making the running of HPC projects within increasing financial reach. Read more…

By Clive Longbottom, Quocirca

Google Pulls Back the Covers on Its First Machine Learning Chip

April 6, 2017

This week Google released a report detailing the design and performance characteristics of the Tensor Processing Unit (TPU), its custom ASIC for the inference phase of neural networks (NN). Read more…

By Tiffany Trader

Google Pulls Back the Covers on Its First Machine Learning Chip

April 6, 2017

This week Google released a report detailing the design and performance characteristics of the Tensor Processing Unit (TPU), its custom ASIC for the inference phase of neural networks (NN). Read more…

By Tiffany Trader

Quantum Bits: D-Wave and VW; Google Quantum Lab; IBM Expands Access

March 21, 2017

For a technology that’s usually characterized as far off and in a distant galaxy, quantum computing has been steadily picking up steam. Read more…

By John Russell

Trump Budget Targets NIH, DOE, and EPA; No Mention of NSF

March 16, 2017

President Trump’s proposed U.S. fiscal 2018 budget issued today sharply cuts science spending while bolstering military spending as he promised during the campaign. Read more…

By John Russell

HPC Compiler Company PathScale Seeks Life Raft

March 23, 2017

HPCwire has learned that HPC compiler company PathScale has fallen on difficult times and is asking the community for help or actively seeking a buyer for its assets. Read more…

By Tiffany Trader

Nvidia Responds to Google TPU Benchmarking

April 10, 2017

Nvidia highlights strengths of its newest GPU silicon in response to Google's report on the performance and energy advantages of its custom tensor processor. Read more…

By Tiffany Trader

For IBM/OpenPOWER: Success in 2017 = (Volume) Sales

January 11, 2017

To a large degree IBM and the OpenPOWER Foundation have done what they said they would – assembling a substantial and growing ecosystem and bringing Power-based products to market, all in about three years. Read more…

By John Russell

CPU-based Visualization Positions for Exascale Supercomputing

March 16, 2017

In this contributed perspective piece, Intel’s Jim Jeffers makes the case that CPU-based visualization is now widely adopted and as such is no longer a contrarian view, but is rather an exascale requirement. Read more…

By Jim Jeffers, Principal Engineer and Engineering Leader, Intel

TSUBAME3.0 Points to Future HPE Pascal-NVLink-OPA Server

February 17, 2017

Since our initial coverage of the TSUBAME3.0 supercomputer yesterday, more details have come to light on this innovative project. Of particular interest is a new board design for NVLink-equipped Pascal P100 GPUs that will create another entrant to the space currently occupied by Nvidia's DGX-1 system, IBM's "Minsky" platform and the Supermicro SuperServer (1028GQ-TXR). Read more…

By Tiffany Trader

Leading Solution Providers

Tokyo Tech’s TSUBAME3.0 Will Be First HPE-SGI Super

February 16, 2017

In a press event Friday afternoon local time in Japan, Tokyo Institute of Technology (Tokyo Tech) announced its plans for the TSUBAME3.0 supercomputer, which will be Japan’s “fastest AI supercomputer,” Read more…

By Tiffany Trader

IBM Wants to be “Red Hat” of Deep Learning

January 26, 2017

IBM today announced the addition of TensorFlow and Chainer deep learning frameworks to its PowerAI suite of deep learning tools, which already includes popular offerings such as Caffe, Theano, and Torch. Read more…

By John Russell

Is Liquid Cooling Ready to Go Mainstream?

February 13, 2017

Lost in the frenzy of SC16 was a substantial rise in the number of vendors showing server oriented liquid cooling technologies. Three decades ago liquid cooling was pretty much the exclusive realm of the Cray-2 and IBM mainframe class products. That’s changing. We are now seeing an emergence of x86 class server products with exotic plumbing technology ranging from Direct-to-Chip to servers and storage completely immersed in a dielectric fluid. Read more…

By Steve Campbell

BioTeam’s Berman Charts 2017 HPC Trends in Life Sciences

January 4, 2017

Twenty years ago high performance computing was nearly absent from life sciences. Today it’s used throughout life sciences and biomedical research. Genomics and the data deluge from modern lab instruments are the main drivers, but so is the longer-term desire to perform predictive simulation in support of Precision Medicine (PM). There’s even a specialized life sciences supercomputer, ‘Anton’ from D.E. Shaw Research, and the Pittsburgh Supercomputing Center is standing up its second Anton 2 and actively soliciting project proposals. There’s a lot going on. Read more…

By John Russell

HPC Startup Advances Auto-Parallelization’s Promise

January 23, 2017

The shift from single core to multicore hardware has made finding parallelism in codes more important than ever, but that hasn’t made the task of parallel programming any easier. Read more…

By Tiffany Trader

HPC Technique Propels Deep Learning at Scale

February 21, 2017

Researchers from Baidu’s Silicon Valley AI Lab (SVAIL) have adapted a well-known HPC communication technique to boost the speed and scale of their neural network training and now they are sharing their implementation with the larger deep learning community. Read more…

By Tiffany Trader

US Supercomputing Leaders Tackle the China Question

March 15, 2017

Joint DOE-NSA report responds to the increased global pressures impacting the competitiveness of U.S. supercomputing. Read more…

By Tiffany Trader

IDG to Be Bought by Chinese Investors; IDC to Spin Out HPC Group

January 19, 2017

US-based publishing and investment firm International Data Group, Inc. (IDG) will be acquired by a pair of Chinese investors, China Oceanwide Holdings Group Co., Ltd. Read more…

By Tiffany Trader

  • arrow
  • Click Here for More Headlines
  • arrow
Share This