Monte Carlo applications are widely perceived as computationally intensive but naturally parallel. Therefore, they can be effectively executed on the grid using the dynamic bag-of-work model.  We improve the efficiency of the subtask-scheduling scheme by using an N-out-of-M strategy, and develop a Monte Carlo-specific lightweight checkpoint technique, which leads to a performance improvement for Monte Carlo grid computing.  Also, we enhance the trustworthiness of Monte Carlo grid-computing applications by utilizing the statistical nature of Monte Carlo and by cryptographically validating intermediate results utilizing the random number generator already in use in the Monte Carlo application.  All these techniques lead to our implementation of a grid-computing infrastructure -- GCIMCA, which is based on Globus and the SPRNG (Scalable Parallel Random Number Generators) library.  GCIMCA intends to provide trustworthy grid-computing services for large-scale and high-performance distributed Monte Carlo computations.

One application for this grid-computing infrastructure is the implementation of the grid-based hybrid Molecular Dynamics (MD)/Brownian Dynamics (BD) algorithm for simulating the long-time, nonequilibrium dynamics of receptor-ligand interactions.  We expect to develop a "plug-drug" system based on the grid-based MD/BD simulation with the purpose of searching for good drug candidates among a field of many chemical agents.

This is joint work with Prof. Yaohang Li of North Carolina A&T Univeristy.