A distributed block approach to solving near-block-diagonal systems with an application to a large macroeconometric model

This paper illustrates some benefits of small-scale distributed processing in solving near-block-diagonal systems. We review the theoretical advantages of distributed block algorithms and apply such an algorithm to solve a large nonlinear macroeconometric model. For our application, on a four-processor UNIX server, the algorithm achieves a speedup factor of more than 6 over the standard algorithm on a single processor. A speedup factor of about 2 is due to the added efficiency of the block algorithm on a single processor, and the remaining factor of 3 results from distributing the work over four processors.The views in this paper are solely the responsibility of the authors and should not be interpreted as reflecting the views of the Board of Governors of the Federal Reserve System or other members of its staff. We would like to thank Ray Board, Neil Ericsson, Mico Loretan, and an anonymous referee for helpful comments.