Type of Document Dissertation Author Li, Yaohang URN etd-09222003-185420 Title A Grid Computing Infrastructure For Monte Carlo Applications Degree Doctor of Philosophy Department Computer Science, Department of Advisory Committee
Advisor Name Title Craig Nolder Committee Member David Whalley Committee Member Michael H. Peters Committee Member Michael Mascagni Committee Member Robert van Engelen Committee Member Xin Yuan Committee Member Keywords
- Monte Carlo Applications
- Grid Computing Infrastructure
Date of Defense 2003-08-02 Availability unrestricted AbstractMonte 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 gridcomputing infrastructure – GCIMCA (Grid-Computing Infrastructure for Monte Carlo
applications), 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.
We apply Monte Carlo applications to GCIMCA to show the capability of our techniques. These applications include the grid-based Monte Carlo integration and a “real-life” Monte Carlo application -- the grid-based hybrid Molecular Dynamics (MD)/Brownian Dynamics (BD) application for simulating the long-time, nonequilibrium
dynamics of receptor-ligand interactions. Our preliminary results show that our techniques and infrastructure can achieve significant speedup, efficiency, accuracy, and trustworthiness for grid-based Monte Carlo applications.
Filename Size Approximate Download Time (Hours:Minutes:Seconds)
28.8 Modem 56K Modem ISDN (64 Kb) ISDN (128 Kb) Higher-speed Access DissertationSubmit.pdf 1.50 Mb 00:06:56 00:03:34 00:03:07 00:01:33 00:00:08