Using Premia and Nsp for constructing a risk management benchmark for testing parallel architecture

摘要

Financial institutions have massive computations to carry out overnight, which are very CPU demanding.rnThe challenge is to price many different products on a cluster-like architecture. We have used the Premiarnsoftware to valuate the financial derivatives. In this work, we explain how Premia can be embedded intornNsp, a scientific software like MATLAB, to provide a powerful tool to valuate a whole portfolio. Finally, wernhave integrated an Message Passing Interface (MPI) toolbox into Nsp to enable the use of Premia to solverna bunch of pricing problems on a cluster. This unified framework can then be used to test different parallelrnarchitectures.