Parallel decomposition of combinatorial optimization problems using electro-optical vector by matrix multiplication architecture

Dan E. Tamir, Natan T. Shaked, Wilhelmus J. Geerts, Shlomi Dolev

Research output: Contribution to journalArticlepeer-review

5 Scopus citations

Abstract

A new state space representation for a class of combinatorial optimization problems, related to minimal Hamiltonian cycles, enables efficient implementation of exhaustive search for the minimal cycle in optimization problems with a relatively small number of vertices and heuristic search for problems with large number of vertices. This paper surveys structures for representing Hamiltonian cycles, the use of these structures in heuristic optimization techniques, and efficient mapping of these structures along with respective operators to a newly proposed electrooptical vector by matrix multiplication (VMM) architecture. Record keeping mechanisms are used to improve solution quality and execution time of these heuristics using the VMM. Finally, the utility of a low-power VMM based implementation is evaluated.

Original languageEnglish
Pages (from-to)633-655
Number of pages23
JournalJournal of Supercomputing
Volume62
Issue number2
DOIs
StatePublished - 1 Nov 2012

Keywords

  • Combinatorial optimization
  • Hamiltonian cycles
  • Heuristic search
  • Optical super computing
  • Parallel processing
  • The traveling salesman problem

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Information Systems
  • Hardware and Architecture

Fingerprint

Dive into the research topics of 'Parallel decomposition of combinatorial optimization problems using electro-optical vector by matrix multiplication architecture'. Together they form a unique fingerprint.

Cite this