IBM-flavored event (stream) processing running on an IBM Blue Gene supercomputer said to handle data at 21 times the speed of OPRA.
IBM unveiled a prototype of an automated options trading system. During the project, scientists at IBM Research collaborated with TD Securities to achieve a 21 times performance improvement on the volume of data consumed by financial trading systems.
Through the combination of IBM's InfoSphere Streams — software technology from IBM Research — and IBM's Blue Gene/P supercomputer, the IBM Research team created a stream processing system suited to meet and surpass the demands of the financial services industry. By enabling rapid, intelligent analysis of live streaming data from a practically unlimited number of sources, IBM says it delivered low latency that surpasses the performance of traditional trading systems.
According to the Financial Information Forum, the combined options and equities traffic has exploded, doubling in size every year since 2003. The challenge to ingest, analyze and automatically act upon millions of messages every second is the difference between success and failure for automated trading systems. IBM says the use of its stream computing architecture and Blue Gene allowed for significant enhancements to real-time messaging and analytical capabilities while offering a simplified, energy-efficient underlying infrastructure.
The collaboration with TD Securities is part of IBM's First-Of-A-Kind program (FOAK), which engages IBM's scientists with the company's clients to explore how emerging technologies could solve real world business problems. In this collaboration, IBM Research scientists worked with TD Securities to create a tailored, unique system through applying advanced and emerging technologies and new approaches.
"TD Securities could potentially use the new system to analyze and act on information before their competitors can finish ingesting and analyzing, effectively blinding the competition to its actions," said Nagui Halim, chief scientist of the Stream Computing Project at IBM. "We're not talking about 20 percent faster here. We're talking about 20 times faster," he added.
In testing, the system was found to be capable of handling data at 21 times the speed of Options Price Reporting Authority (OPRA), the world's single largest market data feed, while maintaining ultra low end-to-end latencies.
No comments:
Post a Comment