Path: utzoo!attcan!utgpu!jarvis.csri.toronto.edu!mailrus!cs.utexas.edu!swrinde!zaphod.mps.ohio-state.edu!sol.ctr.columbia.edu!emory!hubcap!pase
From: pase@orville.nas.nasa.gov (Douglas M. Pase)
Newsgroups: comp.parallel
Subject: Re: scalability of n-cubes, meshes
Keywords: Ncube, scalability, 3D mesh
Message-ID: <7429@hubcap.clemson.edu>
Date: 14 Dec 89 15:46:02 GMT
Sender: fpst@hubcap.clemson.edu
Lines: 15
Approved: parallel@hubcap.clemson.edu

In <7341@hubcap.clemson.edu> kbreinho%ug@cs.utah.edu (Keith Breinholt) writes:
-[...] A hexagon has 6 sides.  A cube has 6 sides.  If I can produce 6 sets
-of connections to neighboring processors in a 2D plane I have effectively
-produced a 3D connection scheme in a 2D plane.

Hexagons and 3-d cubes are in fact planar figures, but 3-d meshes are not.
Yes you can lay out the processors in 2-d, but the mesh connections will
require more than one layer.  The physical distance between nearest neighbors
can also be quite large in a big 3-d mesh, though I gather not as large as
for the same sized n-cube.
Dr. Douglas M. Pase				Computer Sciences Corporation
95 Sierra Vista Ave				NAS MS 258-6
Mountain View, CA  94043			NASA Ames Research Center
(415) 940-1197					Moffett Field, CA  94035
pase@orville.nas.nasa.gov			(415) 694-6394