New Star-P for Financial Services brings supercomputing to Wall Street
First Published Monday, 10 September 2007 from Automated Trader : Algorithmic Trading News
Interactive Supercomputing has announced a new version of its Star-P software designed to make high performance computing (HPC) easier and more accessible to financial services organizations.
Peter Cotton, CEO of Julius Finance: "With Star-P, not only can we create accurate, realistic models and compute the answers we need quickly, we can continually experiment with new algorithms and models with real-time interactivity."
Star-P 2.5 for Financial Services enables analysts to work with their familiar desktop financial modeling tools while gaining quantum leaps in computational performance and programming productivity. They can do better forecasting, risk analysis and trading by creating more complex financial algorithms and working with much larger data sets than current desktop computers allow. And they can do it faster: Star-P's interactive environment allows continual feedback and refinement of algorithms and models, resulting in applications developed in days, not months or years.
Until now, banks, investment firms and insurance companies have had to live with the performance limitations of desktop systems, or engage teams of expert programmers to re-code their algorithms in C and MPI (message passing interface). Star-P 2.5 for Financial Services solves this problem by enabling users to code algorithms and models on their desktops using popular tools - like MATLAB®, Python, and R - but run them instantly and interactively on parallel HPCs. It eliminates the need to re-program the applications to run on parallel systems - which typically takes months to complete for large, complex problems.
Star-P 2.5 for Financial Services is designed to accelerate and improve decision making in applications such as portfolio optimization, financial derivatives valuation, credit fraud detection, hedge fund trading, Monte Carlo simulations and risk analysis. For example, Julius Finance develops next generation credit derivative models using MATLAB and Star-P. "Researchers have struggled to create a consistent mathematical framework for valuation, market risk and opportunities in corporate credit," said Peter Cotton, CEO of Julius Finance. "With Star-P, not only can we create accurate, realistic models and compute the answers we need quickly, we can continually experiment with new algorithms and models with real-time interactivity."
Star-P 2.5 for Financial Services features a number of performance improvements important to financial analysis, including task- and data-parallel processing, extensive plug-in tools and libraries, and scalability to terabyte size datasets across hundreds of processors.
Other enhancements include:
- A new Python client interface that lets users take advantage of Python-specific numerical libraries and functions. Python support is important to financial services due to the growing array of open source Python modules available for analysis. With Star-P, these Python modules can now be automatically parallelized, yielding significant productivity gains for users.
- More seamless integration with workload managers, such as PBS Pro, which is critical for fitting into the large, standardized computing infrastructures that most financial organizations employ.
- Performance profiling, which enables users to interactively explore their algorithms and models to fine-tune computational performance.
- Through its collocated install configuration, Star-P can also turn multi-processor workstations into parallel application development systems. Collocated install enables analysts to run the client and server on the same workstation. This allows them to develop models on multiple processors and refine them interactively; and then easily scale the models to bigger processor counts and data sets on larger servers and clusters.
- Interxion and euNetworks partner for co-location & connectivity
Anthony Foy, Group Managing Director, Interxion: "We collaborate with customers at all levels, and our agreement with euNetworks illustrates the immediate benefits this approach can bring.” Interxion the European operator of carrier-neutral data centres, and euNetworks the provider of data services, have announced a non-exclusive partnership to provide traders with turnkey pan-European colocation and low-latency access to key liquidity venues....continued
- Atrium Network offers connectivity to Pure Trading
Emmanuel Pellé, Executive Director, Atrium Network: “Pure Trading continues to attract new participants looking to trade securities listed on the Canadian Exchanges.” Atrium Network has announced that it is expanding further into the Canadian market with low latency connectivity to Pure Trading, a Toronto-based competitive alternative auction market system, aimed at attracting latency sensitive traders interested in Canadian exchange-listed securities....continued
- Caplin announces new version of Caplin Trader
Paul Caplin, CEO, Caplin: “Caplin Trader is already seen as the most effective way to create a highly differentiated single-dealer portal....continued
More Like This...
You can get news like this delivered directly to your email inbox as a real-time alert or as part of a daily/weekly summary.
Click here to set your preferences now!
