Elsevier

Parallel Computing

Volume 23, Issue 10, October 1997, Pages 1429-1460
Parallel Computing

Regular paper
Task assignment in Cayley interconnection topologies

https://doi.org/10.1016/S0167-8191(97)89285-XGet rights and content

Abstract

Based on the Cayley graph framework for the generation and evaluation of multiprocessor interconnection topologies, an application dependent task mapping problem is addressed. We start with interconnection topologies considered attractive from a graph theoretical point of view. Given such a topology together with an application dependent task communication profile, the problem addressed in this paper is to find an optimal task-to-processor assignment. Such a mapping yields for the given interconnection topology and the given profile a minimal expected communication path length and therefore a minimal number of data transfer steps between the physical processing elements of a multiprocessor machine. At first, the Cayley graph approach is briefly outlined. We demonstrate the potential of Cayley graphs for a systematic generation framework aiming at node-symmetric interconnection topologies for a given number of processing elements each equipped with a constant number of communication channels. Cayley graphs found most attractive within a large set of generated graphs are compared to prominent interconnection topologies like, for example, hypercubes. Later on, it is shown that the problem of the optimal task-to-processor assignment, being a special case of the well-known quadratic assignment problem, is still NP-hard. Consequently, any practically relevant mapping algorithm can be expected to produce at best near-optimal solutions for reasonable problem sizes beyond approximately 10 nodes. We present two fundamentally different mapping approaches, namely a straightforward greedy mapping and a more sophisticated algorithm using simulated annealing techniques as known from artificial intelligence applications. For both approaches, we elaborate on their relative performance as well as, where feasible, on the question of suboptimality.

References (35)

  • S. Bhatia et al.

    Shortest paths in orthogonal graphs

  • L.N. Bhuyan et al.

    Generalized hypercube and hyperbus structures for a computer network

    IEEE Transactions on Computers

    (1984)
  • L.N. Bhuyan

    Interconnection networks for parallel and distributed processing

    IEEE Computer

    (1987)
  • R.E. Burkard et al.

    The asymptotic behavior of quadratic sum assignment problems

    Zeitschrift für Operations Research

    (1983)
  • L. Campbell et al.

    Small diameter symmetric networks from linear groups

    IEEE Transactions on Computers

    (1992)
  • J. Chakrapani et al.

    Mapping tasks to processors to minimize communication time in a multiprocessor system

  • M.J. Dinneen et al.

    New results for the degree/diameter problem

    Networks

    (1994)
  • Cited by (5)

    • Sorting on graphs by adjacent swaps using permutation groups

      2016, Computer Science Review
      Citation Excerpt :

      Permutation Sorting for Ring Topology [18,21] Cayley graphs [3,19,20] play an important role in both mathematics (e.g. combinatorics [33,34], group theory [35,36], etc.) and computer science (e.g. interconnection network design [3,19,20], data center design [37,38], distributed systems [39,40], multi-agent systems [18,41], etc.). In Section 3 we used the diameters of several kinds of Cayley graphs to find upper bounds of the minimum number of adjacent swaps needed to sort objects on graphs with line, star, complete, and ring topologies.

    • Scalable rank-mapping algorithm for an icosahedral grid system on the massive parallel computer with a 3-D torus network

      2014, Parallel Computing
      Citation Excerpt :

      For several decades, many researchers have tackled the rank-mapping problem in order to efficiently execute application on parallel computer. ( e.g. [13–21] and the references cited therein). In graph theory, the rank-mapping problem is interpreted as the problem of embedding a source graph that represents a communication network into a destination graph that represents a node network.

    • Task swapping networks in distributed systems

      2013, International Journal of Computer Mathematics
    View full text