Energy Efficient Acceleration and Evaluation of Financial Computations towards Real-Time Pricing

Modern financial markets are as vivid as never before. Asset prices - and therefore the prices of all related financial products - change within several milliseconds nowadays. However, not only due to the financial crisis in 2008, calculating fair and meaningful prices for these products is much more important than in the past. In order to obtain reliable prices, sophisticated simulation models have to be used. Pricing in these models in general has a very high computational complexity and can in many cases only be approximately done by using numerical methods. On the other hand, we all know that energy costs will become more and more significant in the future. The gap between the increasing computational complexity and the consumed energy can only be bridged by using more tailored computation engines, like dedicated hardware accelerators or application specific instruction set processors (ASIPs). In this paper we present a comprehensive methodology for the efficient design of optimal hardware accelerators and the evaluation thereof. We give two case studies: a new hardware random number generator for arbitrary distributions and a dedicated hardware accelerator for calculating European barrier option prices.

[1]  Wayne Luk,et al.  Credit Risk Modelling using Hardware Accelerated Monte-Carlo Simulation , 2008, 2008 16th International Symposium on Field-Programmable Custom Computing Machines.

[2]  Leif Andersen.  Efficient Simulation of the Heston Stochastic Volatility Model , 2007 .

[3]  F. Black,et al.  The Pricing of Options and Corporate Liabilities , 1973, Journal of Political Economy.

[4]  Paul Chow,et al.  FPGA acceleration of Monte-Carlo based credit derivative pricing , 2008, 2008 International Conference on Field Programmable Logic and Applications.

[5]  Norbert Wehn,et al.  A New Hardware Efficient Inversion Based Random Number Generator for Non-uniform Distributions , 2010, 2010 International Conference on Reconfigurable Computing and FPGAs.

[6]  Michael B. Giles,et al.  Multilevel Monte Carlo Path Simulation , 2008, Oper. Res..

[7]  D. Dijk,et al.  A comparison of biased simulation schemes for stochastic volatility models , 2008 .

[8]  R. Korn,et al.  Monte Carlo Methods and Models in Finance and Insurance , 2010 .

[9]  Tom VanCourt,et al.  FPGA acceleration of quasi-Monte Carlo in finance , 2008, 2008 International Conference on Field Programmable Logic and Applications.

[10]  Jin E. Zhang,et al.  Pricing S&P 500 index options with Heston's model , 2003, 2003 IEEE International Conference on Computational Intelligence for Financial Engineering, 2003. Proceedings..

[11]  A. Pelsser,et al.  UvA-DARE ( Digital Academic Repository ) Efficient , almost exact simulation of the Heston stochastic volatility model , 2008 .

[12]  S. Heston.  A Closed-Form Solution for Options with Stochastic Volatility with Applications to Bond and Currency Options , 1993 .

[13]  A. Bernemann,et al.  Pricing structured equity products on GPUs , 2010, 2010 IEEE Workshop on High Performance Computational Finance.

[14]  André Bernemann,et al.  Accelerating Exotic Option Pricing and Model Calibration Using GPUs , 2011 .