Opportunities and challenges in porting a parallel code from a tightly-coupled system to the distributed EU Grid, enabling Grids for E-sciencE

Any large scale computation, either in the science or arts, requires high performance computing (HPC) facilities. This computational environment may change over time. Thus the source code of a computation needs to be ported. The change in the computational architecture or system can make the porting of code between various HPC facilities challenging. This chapter introduces an example of an engineering application which runs on a HPC facility and the porting from a local computing facility to Enabling Grids for E-sciencE (EGEE) is described in detail. The computational architecture of Enabling Grids for E-sciencE is introduced as it made our code porting very challenging, and the discussion presented is directly applicable to EGEE users. The final solution to the code poring problem is proposed, and its performance is examined. The solution to this problem be generally faced in the other large scale computation and so is applicable to users of other HPC facilities. This chapter gives a hint to those who have difficulties in applications with heavy data Input/Output (I/O) under the computational environment whose weak point is the data I/O.