Monte Carlo methods are common practice in financial engineering for a wide variety of problems, one being option pricing. Large clusters of computers are used to run these calculations. Growing volumes and complexity of work that needs to be performed as well as strict requirements for fast responses makes for a pressing demand for high performance computing. We present a prototype implementation of an option pricer running on graphics cards. The prototype supports various exotic option types, quasi Monte Carlo and support for custom models for the evolution of stock prices. We conclude that graphics cards can outperform CPUs given certain conditions and for reasonable problem sizes we find a 12x improvement over sequential code when pricing options in a production system.
QC 20120410