Authors: Halis Sak, Süleyman Özekici, Ilkay Boduroglu We discuss the use of parallel computing,in Asian option pricing and evaluate the efficiency of various algorithms. We only focus on ‘‘backward-starting fixed strike’’ Asian options that are continuously,averaged. We implement,a partial differential equation (PDE) approach that involves a single state variable to price the Asian option, and implement the same methodology,to price a standard,European,option to check for accuracy. A parabolic PDE is solved by using both explicit and Crank–Nicolson’s implicit finite-difference methods. In particular, we look for algorithms designed for implementing the computations,in massively parallel processors (MPP). We evaluate the performance,of the algorithms by comparing,the numerical,results with respect to accuracy,and wall-clock time of code,executions. Codes are executed,on a Linux PC cluster. 2006 Elsevier B.V. All rights reserved.
Keywords: Asian option pricing; Computational,finance; Parallel computing; Finite-difference methods