Int. J. of Big Data Intelligence   »   2014 Vol.1, No.4

 

 

Title: Total exchange routing on hierarchical dual-nets

 

Authors: Yamin Li; Wanming Chu

 

Addresses:
Hosei University, Tokyo 184-8584, Japan
University of Aizu, Aizu-Wakamatsu 965-8580, Japan

 

Abstract: The hierarchical dual-net (HDN) is a newly proposed interconnection network for building extra large scale supercomputers. The HDN is constructed based on a symmetric product graph (called base network), such as three-dimensional torus and n-dimensional hypercubes. A k-level hierarchical dual-net, HDN(B, k, S), is obtained by applying k-time dual constructions on the base network B. S defines a supernode set that adjusts the scale of the system. The node degree of HDN(B, k, S) is d0 + k, where d0 is the node degree of the base network. The HDN is node and edge symmetric and can contain huge number of nodes with small node-degree and short diameter. The total exchange, or all-to-all personalised communication, is one of the most dense communication patterns and is at the heart of numerous applications and programming models in parallel computing. In this paper, we show that the total exchange routing can be done on HDN efficiently and extra large scale HDNs can be implemented easily.

 

Keywords: interconnection networks; total exchange routing; hierarchical dual nets; HDN; supercomputers; all-to-all personalised communication.

 

DOI: 10.1504/IJBDI.2014.066958

 

Int. J. of Big Data Intelligence, 2014 Vol.1, No.4, pp.230 - 243

 

Submission date: 18 Mar 2014
Date of acceptance: 30 Jun 2014
Available online: 18 Jan 2015

 

 

Editors Full text accessAccess for SubscribersPurchase this articleComment on this article