FPGA acceleration of quasi-Monte Carlo in finance
Authors:
- 1 January 2008
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 1946147X,p. 335-340
Abstract
Today, quasi-Monte Carlo (QMC) methods are widely used in finance to price derivative securities. The QMC approach is popular because for many types of derivatives it yields an estimate of the price, to a given accuracy, faster than other competitive approaches, like Monte Carlo (MC) methods. The calculation of the large number of underlying asset pathways consumes a significant portion of the overall run-time and energy of modern QMC derivative pricing simulations. Therefore, we present an FPGA-based accelerator for the calculation of asset pathways suitable for use in the QMC pricing of several types of derivative securities. Although this implementation uses constructs (recursive algorithms and double-precision floating point) not normally associated with successful FPGA computing, we demonstrate performance in excess of 50times that of a 3 GHz multi-core processor.Keywords
This publication has 10 references indexed in Scilit:
- A hardware framework for the fast generation of multiple long-period random number streams2008
- FPGA-optimised high-quality uniform random number generators2008
- Floating point datapath synthesis for FPGAs2008
- A parameterizable floating-point logarithm operator for FPGAs2006
- Quasi-Monte Carlo Methods in Finance2005
- A Gaussian noise generator for hardware-based simulationsIEEE Transactions on Computers, 2004
- Monte Carlo Radiative Heat Transfer Simulation on a Reconfigurable Computer2004
- Valuation of mortgage-backed securities using Brownian bridges to reduce effective dimensionJournal of Computational Finance, 1997
- An economic method of computing LPτ-sequencesUSSR Computational Mathematics and Mathematical Physics, 1979
- Uniformly distributed sequences with an additional uniform propertyUSSR Computational Mathematics and Mathematical Physics, 1976