Self-healing in binomial graph networks

  • Authors:
  • Thara Angskun;George Bosilca;Jack Dongarra

  • Affiliations:
  • Department of Computer Science, The University of Tennessee, Knoxville;Department of Computer Science, The University of Tennessee, Knoxville;Department of Computer Science, The University of Tennessee, Knoxville and Computer Science and Mathematics Division, Oak Ridge National Laboratory and Computer Science and Mathematics Schools, Th ...

  • Venue:
  • OTM'07 Proceedings of the 2007 OTM Confederated international conference on On the move to meaningful internet systems - Volume Part II
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

The number of processors embedded in high performance computing platforms is growing daily to solve larger and more complex problems. However, as the number of components increases, so does the probability of failure. The logical network topologies must also support the fault-tolerant capability in such dynamic environments. This paper presents a self-healing mechanism to improve the fault-tolerant capability of a Binomial graph (BMG) network. The self-healing mechanism protects BMG from network bisection and helps maintain optimal routing even in failure circumstances. The experimental results show that self-healing with an adaptive method significantly reduces the overhead from reconstructing the networks.