This article presents a new high-level parallel computational model named BSF - Bulk Synchronous Farm. The BSF model extends the BSP model to deal with the compute-intensive iterative numerical methods executed on distributed-memory multiprocessor systems. The BSF model is based on the master-worker paradigm and the SPMD programming model. The BSF model makes it possible to predict the upper scalability bound of a BSF-program with great accuracy. The BSF model also provides equations for estimating the speedup and parallel efficiency of a BSF-program.
@article{arxiv.1710.10490,
title = {Analytical Estimation of the Scalability of Iterative Numerical Algorithms on Distributed Memory Multiprocessors},
author = {Leonid B. Sokolinsky},
journal= {arXiv preprint arXiv:1710.10490},
year = {2018}
}
Comments
Submitted to a special issue of Lobachevskii Journal of Mathematics on "Parallel Structure of Algorithms"