The Community for Technology Leaders
Green Image
<p>We demonstrate the feasibility of a distributed implementation of the Goldberg-Tarjan algorithm for finding the maximum flow in a network. Unlike other parallel implementations of this algorithm, where the network graph is partitioned among many processors, we partition the algorithm among processors arranged in a pipeline. The network graph data are distributed among the processors according to local requirements. The partitioned algorithm is implemented on six processors within a 15-processor pipelined message-passing multicomputer operating at 5 MHz. We used randomly generated networks with integer capacities as examples. Performance estimates based upon a six-processor pipelined implementation indicated a speedup between 3.8 and 5.9 over a single processor.</p>
Index Termspipeline processing; distributed algorithms; graph theory; network flow; multiple processor pipeline; maximum flow; Goldberg-Tarjan algorithm; parallel implementations; network graph; partitioned algorithm; six processors; message-passing multicomputer; performance estimates
A. Ng, P. Agrawal, "Computing Network Flow on a Multiple Processor Pipeline", IEEE Transactions on Parallel & Distributed Systems, vol. 5, no. , pp. 653-658, June 1994, doi:10.1109/71.285611
96 ms
(Ver 3.3 (11022016))