Distributed Parallel Computing using Navigational Programming: Orchestrating Computations Around Data

L. Pan, L.F. Bic, M.B. Dillencourt, J.J. Huseynov, and M.K. Lai (USA)


Navigational Programming, distributed parallel computing (DPC), message passing (MP), distributed shared memory (DSM), shared variable (SV) programming, Cholesky fac torization


Message Passing (MP) and Distributed Shared Memory (DSM) are the two most common approaches to program ming on distributed memory systems. MP is difficult to use, while DSM is not scalable. Performance scalabil ity and ease of programming can be achieved at the same time by using “shared variable programming” and follow ing the principle of “computation locus following data,” which is embodied in our Navigational Programming ap proach. The implementation of a real-world algorithm, par allel Cholesky factorization, presented in this paper sup ports our claim that Navigational Programming is better suited for general purpose distributed programming than either MP or DSM.

Important Links:

Go Back