An Experimental Analysis of Counting Networks

An Experimental Analysis of Counting Networks Eric N. Klein Costas Busch David R. Musser Counting networks are highly distributed data structures that provide low contention solu- tions to distributed coordination problems. Counting networks are structured with balancers interconnected in a networked fashion. We study experimentally (with simulations and real implementation) the performance of counting networks according to three criteria: (i) The way the balancers are distributed among the processors in the system, where we show that in most cases the best performance is to assign a connecting chain of balancers to each system node; (ii) The various sizes of counting networks, where we examine the tradeo®s between size and number of nodes in the system; (iii) The different kinds of counting networks, where we compare the bitonic, periodic, and BM counting networks where we ¯nd that for high loads the BM performs better than all the other networks. Department of Computer Science, Rensselaer Polytechnic Institute, Troy, NY cs-06-13

An Experimental Analysis of Counting Networks

Eric N. Klein

Costas Busch

David R. Musser

Counting networks are highly distributed data structures that provide low contention solu- tions to distributed coordination problems. Counting networks are structured with balancers interconnected in a networked fashion. We study experimentally (with simulations and real implementation) the performance of counting networks according to three criteria: (i) The way the balancers are distributed among the processors in the system, where we show that in most cases the best performance is to assign a connecting chain of balancers to each system node; (ii) The various sizes of counting networks, where we examine the tradeo®s between size and number of nodes in the system; (iii) The different kinds of counting networks, where we compare the bitonic, periodic, and BM counting networks where we ¯nd that for high loads the BM performs better than all the other networks.

Department of Computer Science, Rensselaer Polytechnic Institute, Troy, NY

cs-06-13