Exploiting the brownian bridge technique to improve longstaff-schwartz american option pricing on FPGA systems

Risk analysis and management is a very compute intensive task that needs to be performed on a regular (daily) basis. FPGAs have already shown acceleration potential in financial applications with high energy efficiency. In this paper, we present a novel way to price multi-dimensional American options (highly involved in risk management) targeting heterogeneous CPU/FPGA systems. We demonstrate how an architectural limitation of the Longstaff-Schwartz algorithm is solved by means of an algorithmic transformation employing the Brownian Bridge technique. Based on this, we present a new pricing system on FPGAs that achieves a 2x improvement in runtime compared to the state-of-the-art solution in the same technology, with a maximum resources overhead of 15%. On top of that, our proposed architecture is 1.8x more energy efficient than the same reference.