Hypercubes and pyramids

Hypercube computers have recently become popular parallel computers for a variety of engineering and scientific computations. However, despite the fact that the characteristics which make them useful scientific processors also makes them efficient image processors, they have not yet been extensively used as image processing machines. This is partially due to the hardware characteristics of current hypercube computers, partially to the particular history of the groups which first built hypercubes, and partially to the fact that the image processing community did not initially realize some of the advantages of hypercubes. In this paper, their suitability for image processing will be put forth, showing that they can be viewed as competitors to, and collaborators with, mesh and pyramid computers, architectures which are often promoted as being ideal for image processing.

[1]  Trevor N. Mudge,et al.  Vision Algorithms for Hypercube Machines , 1987, J. Parallel Distributed Comput..

[2]  Russ Miller,et al.  Data Movement Techniques for the Pyramid Computer , 1987, SIAM J. Comput..

[3]  Theodore R. Bashkow,et al.  A large scale, homogeneous, fully distributed parallel machine, I , 1977, ISCA '77.

[4]  Jon S. Squire,et al.  Programming and design considerations of a highly parallel computer , 1963, AFIPS '63 (Spring).

[5]  Charles L. Seitz,et al.  The cosmic cube , 1985, CACM.

[6]  W. Daniel Hillis,et al.  The connection machine , 1985 .

[7]  John P. Hayes,et al.  Architecture of a Hypercube Supercomputer , 1986, ICPP.

[8]  Franco P. Preparata,et al.  The cube-connected-cycles: A versatile network for parallel computation , 1979, 20th Annual Symposium on Foundations of Computer Science (sfcs 1979).

[9]  Leslie G. Valiant,et al.  A Scheme for Fast Parallel Communication , 1982, SIAM J. Comput..