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", stated 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 organisations 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.

"Computing requirements on Wall Street are growing exponentially as algorithms and models become more complex and tap much larger data sets. Star-P 2.5 for Financial Services accelerates the productivity of financial analysts by bridging the gap between interactive desktops and the computational muscle of HPCs", stated Ilya Mirman, ISC's vice president of marketing. "Analysts can focus on delivering the most accurate, comprehensive intelligence without delays or constraints, responding to market conditions more effectively."