Aquis Slashes 'Jitter' in Cloud Project
In a recent proof-of-concept with AWS and SGX, Aquis demonstrated significant jitter reduction.
Aquis Technologies, the software and technology arm of Aquis Exchange, last week announced a successful proof-of-concept (PoC) with Amazon Web Services (AWS) and Singapore Exchange (SGX), which it says demonstrates that complex exchange architecture can work as efficiently in the cloud as in physical datacenters when it comes to latency variation, or jitter.
When a major exchange moves its core matching engine to the cloud, challenges include ensuring the same low latency for the transfer of data as in an on-premise environment, as well as reducing jitter. Brokers’ smart order routers are tuned by, among other things, the latency profile of the venues they can trade on to try to get as much of the order filled at the best price possible due to regulations around best execution.
Being able to rely on a consistent latency profile is an important requirement. Adrian Ip, director of product management and technology sales at Aquis Exchange, says the higher the jitter range, the less a smart order router or a trading algorithm can rely on receiving confirmation within a set timeframe.
“Jitter is sort of the enemy of highly deterministic, high-frequency matching engines,” he says. “That is why we have a lot of very expensive physical hardware in datacenters today—first of all, to make it fast, but also to minimize jitter.”
In December 2019, AWS launched a multicast service in the cloud for its AWS Transit Gateway, a cloud router that allows the ushering of data between different AWS environments. When WatersTechnology spoke with AWS earlier this year, the firm confirmed working on a number of pilots for the new offering with some unnamed exchanges.
When the Aquis project with AWS first began in late spring this year, the range of jitter was 200 microseconds. “To have such a broad range of jitter was really quite troubling at first,” Ip says.
In contrast, with the Aquis Trading Protocol (ATP)—its own binary trading protocol—a matching engine would take 13 microseconds to respond to a message from the outside world, with a jitter range of just 1 microsecond.
Working closely with AWS, it was able to significantly lower the jitter range to 4 microseconds in the cloud for the PoC. Aquis had direct access to AWS’s transit gateway development team, Ip says, but declines to go into the specifics of how it achieved the reductions in jitter, describing it as “secret ingredients.”
“This is all using completely standard AWS infrastructure. We are not looking at bare metal, or any of the sort of fancy reserved hardware that underpins virtualized machines, or anything like that,” Ip says.
The latency achieved in the project is in the range of 100 to 200 microseconds, compared to 13 microseconds on-premise. So while the results may be an important step in exchanges’ bid to move to the cloud, when it comes to ultra-low latency trading environments, there is still more work to be done.
Further reading
Only users who have a paid subscription or are part of a corporate subscription are able to print or copy content.
To access these options, along with all other subscription benefits, please contact info@waterstechnology.com or view our subscription options here: http://subscriptions.waterstechnology.com/subscribe
You are currently unable to print this content. Please contact info@waterstechnology.com to find out more.
You are currently unable to copy this content. Please contact info@waterstechnology.com to find out more.
Copyright Infopro Digital Limited. All rights reserved.
As outlined in our terms and conditions, https://www.infopro-digital.com/terms-and-conditions/subscriptions/ (point 2.4), printing is limited to a single copy.
If you would like to purchase additional rights please email info@waterstechnology.com
Copyright Infopro Digital Limited. All rights reserved.
You may share this content using our article tools. As outlined in our terms and conditions, https://www.infopro-digital.com/terms-and-conditions/subscriptions/ (clause 2.4), an Authorised User may only make one copy of the materials for their own personal use. You must also comply with the restrictions in clause 2.5.
If you would like to purchase additional rights please email info@waterstechnology.com
More on Data Management
New working group to create open framework for managing rising market data costs
Substantive Research is putting together a working group of market data-consuming firms with the aim of crafting quantitative metrics for market data cost avoidance.
Off-channel messaging (and regulators) still a massive headache for banks
Waters Wrap: Anthony wonders why US regulators are waging a war using fines, while European regulators have chosen a less draconian path.
Back to basics: Data management woes continue for the buy side
Data management platform Fencore helps investment managers resolve symptoms of not having a central data layer.
‘Feature, not a bug’: Bloomberg makes the case for Figi
Bloomberg created the Figi identifier, but ceded all its rights to the Object Management Group 10 years ago. Here, Bloomberg’s Richard Robinson and Steve Meizanis write to dispel what they believe to be misconceptions about Figi and the FDTA.
SS&C builds data mesh to unite acquired platforms
The vendor is using GenAI and APIs as part of the ongoing project.
Aussie asset managers struggle to meet ‘bank-like’ collateral, margin obligations
New margin and collateral requirements imposed by UMR and its regulator, Apra, are forcing buy-side firms to find tools to help.
Where have all the exchange platform providers gone?
The IMD Wrap: Running an exchange is a profitable business. The margins on market data sales alone can be staggering. And since every exchange needs a reliable and efficient exchange technology stack, Max asks why more vendors aren’t diving into this space.
Reading the bones: Citi, BNY, Morgan Stanley invest in AI, alt data, & private markets
Investment arms at large US banks are taken with emerging technologies such as generative AI, alternative and unstructured data, and private markets as they look to partner with, acquire, and invest in leading startups.